From 34428dff3679f0c4c9b185ff8eccefd12a7f55f8 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Mon, 10 Feb 2020 09:04:15 +0200
Subject: igc: Add GSO partial support

Partial generic segmentation offload is a hybrid between TSO and GSO.
What is effectively does is take advantage of certain traits of TCP and
tunnels so that instead of having to rewrite the packet headers for each
segment only in the inner-most transport header and possible the outer-most
network header need to be updated.
This allows devices that do not support tunnel offload or tunnels
offloads with checksum to still make use of segmentation.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 69fa1ce1f927..46ab035c2032 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4727,6 +4727,16 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;
 
+#define IGC_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
+				  NETIF_F_GSO_GRE_CSUM | \
+				  NETIF_F_GSO_IPXIP4 | \
+				  NETIF_F_GSO_IPXIP6 | \
+				  NETIF_F_GSO_UDP_TUNNEL | \
+				  NETIF_F_GSO_UDP_TUNNEL_CSUM)
+
+	netdev->gso_partial_features = IGC_GSO_PARTIAL_FEATURES;
+	netdev->features |= NETIF_F_GSO_PARTIAL | IGC_GSO_PARTIAL_FEATURES;
+
 	/* setup the private structure */
 	err = igc_sw_init(adapter);
 	if (err)
-- 
cgit v1.2.3


From ec50a9d437f05dd76444a65fdd3cfbfad90ee9d6 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Fri, 14 Feb 2020 15:52:02 -0800
Subject: igc: Add support for taprio offloading

Adds support for translating taprio schedules into i225 cycles. This
will allow schedules to run in the hardware, making the schedules
enforcement more precise and saving CPU time.

Right now, the only simple schedules are allowed, complex schedules are
rejected. "simple" in this context are schedules that each HW queue is
opened and closed only once in each cycle.

Changing schedules is still not supported as well.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/Makefile      |   2 +-
 drivers/net/ethernet/intel/igc/igc.h         |   7 ++
 drivers/net/ethernet/intel/igc/igc_defines.h |  12 +++
 drivers/net/ethernet/intel/igc/igc_main.c    | 113 +++++++++++++++++++++
 drivers/net/ethernet/intel/igc/igc_regs.h    |  12 +++
 drivers/net/ethernet/intel/igc/igc_tsn.c     | 140 +++++++++++++++++++++++++++
 drivers/net/ethernet/intel/igc/igc_tsn.h     |   9 ++
 7 files changed, 294 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/intel/igc/igc_tsn.c
 create mode 100644 drivers/net/ethernet/intel/igc/igc_tsn.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index e3c164c12e10..3652f211f351 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -8,4 +8,4 @@
 obj-$(CONFIG_IGC) += igc.o
 
 igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
-igc_ethtool.o igc_ptp.o igc_dump.o
+igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index a1f845a2aa80..5e36822de5ec 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -70,6 +70,7 @@ extern char igc_driver_version[];
 #define IGC_FLAG_HAS_MSIX		BIT(13)
 #define IGC_FLAG_VLAN_PROMISC		BIT(15)
 #define IGC_FLAG_RX_LEGACY		BIT(16)
+#define IGC_FLAG_TSN_QBV_ENABLED	BIT(17)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
@@ -287,6 +288,9 @@ struct igc_ring {
 	u8 reg_idx;                     /* physical index of the ring */
 	bool launchtime_enable;		/* true if LaunchTime is enabled */
 
+	u32 start_time;
+	u32 end_time;
+
 	/* everything past this point are written often */
 	u16 next_to_clean;
 	u16 next_to_use;
@@ -421,6 +425,9 @@ struct igc_adapter {
 	u32 max_frame_size;
 	u32 min_frame_size;
 
+	ktime_t base_time;
+	ktime_t cycle_time;
+
 	/* OS defined structs */
 	struct pci_dev *pdev;
 	/* lock for statistics */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 4ddccccf42cc..2da5a9b012af 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -377,6 +377,11 @@
 #define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
 #define IGC_RXPBS_CFG_TS_EN	0x80000000 /* Timestamp in Rx buffer */
 
+#define IGC_TXPBSIZE_TSN	0x04145145 /* 5k bytes buffer for each queue */
+
+#define IGC_DTXMXPKTSZ_TSN	0x19 /* 1600 bytes of max TX DMA packet size */
+#define IGC_DTXMXPKTSZ_DEFAULT	0x98 /* 9728-byte Jumbo frames */
+
 /* Time Sync Interrupt Causes */
 #define IGC_TSICR_SYS_WRAP	BIT(0) /* SYSTIM Wrap around. */
 #define IGC_TSICR_TXTS		BIT(1) /* Transmit Timestamp. */
@@ -431,6 +436,13 @@
 #define IGC_TSYNCTXCTL_START_SYNC		0x80000000  /* initiate sync */
 #define IGC_TSYNCTXCTL_TXSYNSIG			0x00000020  /* Sample TX tstamp in PHY sop */
 
+/* Transmit Scheduling */
+#define IGC_TQAVCTRL_TRANSMIT_MODE_TSN	0x00000001
+#define IGC_TQAVCTRL_ENHANCED_QAV	0x00000008
+
+#define IGC_TXQCTL_STRICT_CYCLE		0x00000002
+#define IGC_TXQCTL_STRICT_END		0x00000004
+
 /* Receive Checksum Control */
 #define IGC_RXCSUM_CRCOFL	0x00000800   /* CRC32 offload enable */
 #define IGC_RXCSUM_PCSD		0x00002000   /* packet checksum disabled */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 46ab035c2032..12d672a6bc45 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -9,11 +9,13 @@
 #include <linux/udp.h>
 #include <linux/ip.h>
 #include <linux/pm_runtime.h>
+#include <net/pkt_sched.h>
 
 #include <net/ipv6.h>
 
 #include "igc.h"
 #include "igc_hw.h"
+#include "igc_tsn.h"
 
 #define DRV_VERSION	"0.0.1-k"
 #define DRV_SUMMARY	"Intel(R) 2.5G Ethernet Linux Driver"
@@ -106,6 +108,9 @@ void igc_reset(struct igc_adapter *adapter)
 	/* Re-enable PTP, where applicable. */
 	igc_ptp_reset(adapter);
 
+	/* Re-enable TSN offloading, where applicable. */
+	igc_tsn_offload_apply(adapter);
+
 	igc_get_phy_info(hw);
 }
 
@@ -4491,6 +4496,113 @@ static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	}
 }
 
+static bool validate_schedule(const struct tc_taprio_qopt_offload *qopt)
+{
+	int queue_uses[IGC_MAX_TX_QUEUES] = { };
+	size_t n;
+
+	if (qopt->cycle_time_extension)
+		return false;
+
+	for (n = 0; n < qopt->num_entries; n++) {
+		const struct tc_taprio_sched_entry *e;
+		int i;
+
+		e = &qopt->entries[n];
+
+		/* i225 only supports "global" frame preemption
+		 * settings.
+		 */
+		if (e->command != TC_TAPRIO_CMD_SET_GATES)
+			return false;
+
+		for (i = 0; i < IGC_MAX_TX_QUEUES; i++) {
+			if (e->gate_mask & BIT(i))
+				queue_uses[i]++;
+
+			if (queue_uses[i] > 1)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static int igc_save_qbv_schedule(struct igc_adapter *adapter,
+				 struct tc_taprio_qopt_offload *qopt)
+{
+	u32 start_time = 0, end_time = 0;
+	size_t n;
+
+	if (!qopt->enable) {
+		adapter->base_time = 0;
+		return 0;
+	}
+
+	if (adapter->base_time)
+		return -EALREADY;
+
+	if (!validate_schedule(qopt))
+		return -EINVAL;
+
+	adapter->cycle_time = qopt->cycle_time;
+	adapter->base_time = qopt->base_time;
+
+	/* FIXME: be a little smarter about cases when the gate for a
+	 * queue stays open for more than one entry.
+	 */
+	for (n = 0; n < qopt->num_entries; n++) {
+		struct tc_taprio_sched_entry *e = &qopt->entries[n];
+		int i;
+
+		end_time += e->interval;
+
+		for (i = 0; i < IGC_MAX_TX_QUEUES; i++) {
+			struct igc_ring *ring = adapter->tx_ring[i];
+
+			if (!(e->gate_mask & BIT(i)))
+				continue;
+
+			ring->start_time = start_time;
+			ring->end_time = end_time;
+		}
+
+		start_time += e->interval;
+	}
+
+	return 0;
+}
+
+static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter,
+					 struct tc_taprio_qopt_offload *qopt)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int err;
+
+	if (hw->mac.type != igc_i225)
+		return -EOPNOTSUPP;
+
+	err = igc_save_qbv_schedule(adapter, qopt);
+	if (err)
+		return err;
+
+	return igc_tsn_offload_apply(adapter);
+}
+
+static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			void *type_data)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return igc_tsn_enable_qbv_scheduling(adapter, type_data);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops igc_netdev_ops = {
 	.ndo_open		= igc_open,
 	.ndo_stop		= igc_close,
@@ -4503,6 +4615,7 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_set_features	= igc_set_features,
 	.ndo_features_check	= igc_features_check,
 	.ndo_do_ioctl		= igc_ioctl,
+	.ndo_setup_tc		= igc_setup_tc,
 };
 
 /* PCIe configuration access */
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index d4af53a80f11..6093cde2351c 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -231,6 +231,18 @@
 
 #define IGC_RXPBS	0x02404  /* Rx Packet Buffer Size - RW */
 
+/* Transmit Scheduling Registers */
+#define IGC_TQAVCTRL		0x3570
+#define IGC_TXQCTL(_n)		(0x3344 + 0x4 * (_n))
+#define IGC_BASET_L		0x3314
+#define IGC_BASET_H		0x3318
+#define IGC_QBVCYCLET		0x331C
+#define IGC_QBVCYCLET_S		0x3320
+
+#define IGC_STQT(_n)		(0x3324 + 0x4 * (_n))
+#define IGC_ENDQT(_n)		(0x3334 + 0x4 * (_n))
+#define IGC_DTXMXPKTSZ		0x355C
+
 /* System Time Registers */
 #define IGC_SYSTIML	0x0B600  /* System time register Low - RO */
 #define IGC_SYSTIMH	0x0B604  /* System time register High - RO */
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
new file mode 100644
index 000000000000..257fe970afe8
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2019 Intel Corporation */
+
+#include "igc.h"
+#include "igc_tsn.h"
+
+/* Returns the TSN specific registers to their default values after
+ * TSN offloading is disabled.
+ */
+static int igc_tsn_disable_offload(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 tqavctrl;
+	int i;
+
+	if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED))
+		return 0;
+
+	adapter->cycle_time = 0;
+
+	wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
+
+	tqavctrl = rd32(IGC_TQAVCTRL);
+	tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
+		      IGC_TQAVCTRL_ENHANCED_QAV);
+	wr32(IGC_TQAVCTRL, tqavctrl);
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		ring->start_time = 0;
+		ring->end_time = 0;
+		ring->launchtime_enable = false;
+
+		wr32(IGC_TXQCTL(i), 0);
+		wr32(IGC_STQT(i), 0);
+		wr32(IGC_ENDQT(i), NSEC_PER_SEC);
+	}
+
+	wr32(IGC_QBVCYCLET_S, NSEC_PER_SEC);
+	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
+
+	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
+
+	return 0;
+}
+
+static int igc_tsn_enable_offload(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 tqavctrl, baset_l, baset_h;
+	u32 sec, nsec, cycle;
+	ktime_t base_time, systim;
+	int i;
+
+	if (adapter->flags & IGC_FLAG_TSN_QBV_ENABLED)
+		return 0;
+
+	cycle = adapter->cycle_time;
+	base_time = adapter->base_time;
+
+	wr32(IGC_TSAUXC, 0);
+	wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
+	wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
+
+	tqavctrl = rd32(IGC_TQAVCTRL);
+	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
+	wr32(IGC_TQAVCTRL, tqavctrl);
+
+	wr32(IGC_QBVCYCLET_S, cycle);
+	wr32(IGC_QBVCYCLET, cycle);
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+		u32 txqctl = 0;
+
+		wr32(IGC_STQT(i), ring->start_time);
+		wr32(IGC_ENDQT(i), ring->end_time);
+
+		if (adapter->base_time) {
+			/* If we have a base_time we are in "taprio"
+			 * mode and we need to be strict about the
+			 * cycles: only transmit a packet if it can be
+			 * completed during that cycle.
+			 */
+			txqctl |= IGC_TXQCTL_STRICT_CYCLE |
+				IGC_TXQCTL_STRICT_END;
+		}
+
+		wr32(IGC_TXQCTL(i), txqctl);
+	}
+
+	nsec = rd32(IGC_SYSTIML);
+	sec = rd32(IGC_SYSTIMH);
+
+	systim = ktime_set(sec, nsec);
+
+	if (ktime_compare(systim, base_time) > 0) {
+		s64 n;
+
+		n = div64_s64(ktime_sub_ns(systim, base_time), cycle);
+		base_time = ktime_add_ns(base_time, (n + 1) * cycle);
+	}
+
+	baset_h = div_s64_rem(base_time, NSEC_PER_SEC, &baset_l);
+
+	wr32(IGC_BASET_H, baset_h);
+	wr32(IGC_BASET_L, baset_l);
+
+	adapter->flags |= IGC_FLAG_TSN_QBV_ENABLED;
+
+	return 0;
+}
+
+int igc_tsn_offload_apply(struct igc_adapter *adapter)
+{
+	bool is_any_enabled = adapter->base_time;
+
+	if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) && !is_any_enabled)
+		return 0;
+
+	if (!is_any_enabled) {
+		int err = igc_tsn_disable_offload(adapter);
+
+		if (err < 0)
+			return err;
+
+		/* The BASET registers aren't cleared when writing
+		 * into them, force a reset if the interface is
+		 * running.
+		 */
+		if (netif_running(adapter->netdev))
+			schedule_work(&adapter->reset_task);
+
+		return 0;
+	}
+
+	return igc_tsn_enable_offload(adapter);
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
new file mode 100644
index 000000000000..f76bc86ddccd
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2020 Intel Corporation */
+
+#ifndef _IGC_TSN_H_
+#define _IGC_TSN_H_
+
+int igc_tsn_offload_apply(struct igc_adapter *adapter);
+
+#endif /* _IGC_BASE_H */
-- 
cgit v1.2.3


From 82faa9b799500f9e002067c6d8cb027ab12acca4 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Fri, 14 Feb 2020 15:52:03 -0800
Subject: igc: Add support for ETF offloading

This adds support for ETF offloading for the i225 controller.

For i225, the LaunchTime feature is almost a subset of the Qbv
feature. The main change from the i210 is that the launchtime of each
packet is specified as an offset applied to the BASET register. BASET
is automatically incremented each cycle.

For i225, the approach chosen is to re-use most of the setup used for
taprio offloading. With a few changes:

 - The more or less obvious one is that when ETF is enabled, we should
 set add the expected launchtime to the (advanced) transmit
 descriptor;

 - The less obvious, is that when taprio offloading is not enabled, we
 add a dummy schedule (all queues are open all the time, with a cycle
 time of 1 second).

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h |  1 +
 drivers/net/ethernet/intel/igc/igc_main.c    | 70 ++++++++++++++++++++++++++--
 drivers/net/ethernet/intel/igc/igc_tsn.c     | 19 +++++++-
 3 files changed, 86 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 2da5a9b012af..1b0fd2ffd08d 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -440,6 +440,7 @@
 #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN	0x00000001
 #define IGC_TQAVCTRL_ENHANCED_QAV	0x00000008
 
+#define IGC_TXQCTL_QUEUE_MODE_LAUNCHT	0x00000001
 #define IGC_TXQCTL_STRICT_CYCLE		0x00000002
 #define IGC_TXQCTL_STRICT_END		0x00000004
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 12d672a6bc45..896b314035c9 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -869,6 +869,23 @@ static int igc_write_mc_addr_list(struct net_device *netdev)
 	return netdev_mc_count(netdev);
 }
 
+static __le32 igc_tx_launchtime(struct igc_adapter *adapter, ktime_t txtime)
+{
+	ktime_t cycle_time = adapter->cycle_time;
+	ktime_t base_time = adapter->base_time;
+	u32 launchtime;
+
+	/* FIXME: when using ETF together with taprio, we may have a
+	 * case where 'delta' is larger than the cycle_time, this may
+	 * cause problems if we don't read the current value of
+	 * IGC_BASET, as the value writen into the launchtime
+	 * descriptor field may be misinterpreted.
+	 */
+	div_s64_rem(ktime_sub_ns(txtime, base_time), cycle_time, &launchtime);
+
+	return cpu_to_le32(launchtime);
+}
+
 static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
 			    struct igc_tx_buffer *first,
 			    u32 vlan_macip_lens, u32 type_tucmd,
@@ -876,7 +893,6 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
 {
 	struct igc_adv_tx_context_desc *context_desc;
 	u16 i = tx_ring->next_to_use;
-	struct timespec64 ts;
 
 	context_desc = IGC_TX_CTXTDESC(tx_ring, i);
 
@@ -898,9 +914,12 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
 	 * should have been handled by the upper layers.
 	 */
 	if (tx_ring->launchtime_enable) {
-		ts = ktime_to_timespec64(first->skb->tstamp);
+		struct igc_adapter *adapter = netdev_priv(tx_ring->netdev);
+		ktime_t txtime = first->skb->tstamp;
+
 		first->skb->tstamp = ktime_set(0, 0);
-		context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32);
+		context_desc->launch_time = igc_tx_launchtime(adapter,
+							      txtime);
 	} else {
 		context_desc->launch_time = 0;
 	}
@@ -4496,6 +4515,32 @@ static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	}
 }
 
+static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
+				      bool enable)
+{
+	struct igc_ring *ring;
+	int i;
+
+	if (queue < 0 || queue >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+	ring->launchtime_enable = enable;
+
+	if (adapter->base_time)
+		return 0;
+
+	adapter->cycle_time = NSEC_PER_SEC;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		ring = adapter->tx_ring[i];
+		ring->start_time = 0;
+		ring->end_time = NSEC_PER_SEC;
+	}
+
+	return 0;
+}
+
 static bool validate_schedule(const struct tc_taprio_qopt_offload *qopt)
 {
 	int queue_uses[IGC_MAX_TX_QUEUES] = { };
@@ -4528,6 +4573,22 @@ static bool validate_schedule(const struct tc_taprio_qopt_offload *qopt)
 	return true;
 }
 
+static int igc_tsn_enable_launchtime(struct igc_adapter *adapter,
+				     struct tc_etf_qopt_offload *qopt)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int err;
+
+	if (hw->mac.type != igc_i225)
+		return -EOPNOTSUPP;
+
+	err = igc_save_launchtime_params(adapter, qopt->queue, qopt->enable);
+	if (err)
+		return err;
+
+	return igc_tsn_offload_apply(adapter);
+}
+
 static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 				 struct tc_taprio_qopt_offload *qopt)
 {
@@ -4598,6 +4659,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_QDISC_TAPRIO:
 		return igc_tsn_enable_qbv_scheduling(adapter, type_data);
 
+	case TC_SETUP_QDISC_ETF:
+		return igc_tsn_enable_launchtime(adapter, type_data);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 257fe970afe8..174103c4bea6 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -4,6 +4,20 @@
 #include "igc.h"
 #include "igc_tsn.h"
 
+static bool is_any_launchtime(struct igc_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		if (ring->launchtime_enable)
+			return true;
+	}
+
+	return false;
+}
+
 /* Returns the TSN specific registers to their default values after
  * TSN offloading is disabled.
  */
@@ -88,6 +102,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 				IGC_TXQCTL_STRICT_END;
 		}
 
+		if (ring->launchtime_enable)
+			txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT;
+
 		wr32(IGC_TXQCTL(i), txqctl);
 	}
 
@@ -115,7 +132,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 
 int igc_tsn_offload_apply(struct igc_adapter *adapter)
 {
-	bool is_any_enabled = adapter->base_time;
+	bool is_any_enabled = adapter->base_time || is_any_launchtime(adapter);
 
 	if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) && !is_any_enabled)
 		return 0;
-- 
cgit v1.2.3


From a34c7f5156654ebaf7eaace102938be7ff7036cb Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 19 Feb 2020 22:23:02 -0800
Subject: e1000: Distribute switch variables for initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Variables declared in a switch statement before any case statements
cannot be automatically initialized with compiler instrumentation (as
they are not part of any execution flow). With GCC's proposed automatic
stack variable initialization feature, this triggers a warning (and they
don't get initialized). Clang's automatic stack variable initialization
(via CONFIG_INIT_STACK_ALL=y) doesn't throw a warning, but it also
doesn't initialize such variables[1]. Note that these warnings (or silent
skipping) happen before the dead-store elimination optimization phase,
so even when the automatic initializations are later elided in favor of
direct initializations, the warnings remain.

To avoid these problems, move such variables into the "case" where
they're used or lift them up into the main function body.

drivers/net/ethernet/intel/e1000/e1000_main.c: In function ‘e1000_xmit_frame’:
drivers/net/ethernet/intel/e1000/e1000_main.c:3143:18: warning: statement will never be executed [-Wswitch-unreachable]
 3143 |     unsigned int pull_size;
      |                  ^~~~~~~~~

[1] https://bugs.llvm.org/show_bug.cgi?id=44916

Signed-off-by: Kees Cook <keescook@chromium.org>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index f7103356ef56..ac5146d53c4c 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3136,8 +3136,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		if (skb->data_len && hdr_len == len) {
 			switch (hw->mac_type) {
+			case e1000_82544: {
 				unsigned int pull_size;
-			case e1000_82544:
+
 				/* Make sure we have room to chop off 4 bytes,
 				 * and that the end alignment will work out to
 				 * this hardware's requirements
@@ -3158,6 +3159,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				}
 				len = skb_headlen(skb);
 				break;
+			}
 			default:
 				/* do nothing */
 				break;
-- 
cgit v1.2.3


From f1fd45598205b3eb52779f5d92b7df9d42fb755b Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 27 Feb 2020 18:57:23 +0200
Subject: igc: Remove unused MDIC_DEST mask

Formally Destination bit should be kept reserved to
support legacy drivers and ignore on write/read
operation
Not applicable for i225 parts

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 1b0fd2ffd08d..d6e07f81ca4c 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -510,7 +510,6 @@
 #define IGC_MDIC_READY		0x10000000
 #define IGC_MDIC_INT_EN		0x20000000
 #define IGC_MDIC_ERROR		0x40000000
-#define IGC_MDIC_DEST		0x80000000
 
 #define IGC_N0_QUEUE		-1
 
-- 
cgit v1.2.3


From 3d1ce3fa83917b19e150352c5a0f9c6324b2da9b Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 27 Feb 2020 19:19:12 +0200
Subject: igc: Remove unused CTRL_EXT_LINK_MODE_MASK

We support only copper mode
Not applicable for i225 parts

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index d6e07f81ca4c..40d6f557079b 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -44,9 +44,6 @@
 /* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */
 #define IGC_WUPM_BYTES	128
 
-/* Physical Func Reset Done Indication */
-#define IGC_CTRL_EXT_LINK_MODE_MASK	0x00C00000
-
 /* Loop limit on how long we wait for auto-negotiation to complete */
 #define COPPER_LINK_UP_LIMIT		10
 #define PHY_AUTO_NEG_LIMIT		45
-- 
cgit v1.2.3


From 89d35511f38da851c71c3ad9d2b8197ee34e0846 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Fri, 28 Feb 2020 02:25:15 +0200
Subject: igc: Remove forward declaration

Move igc_adapter and igc_ring structures up to avoid
forward declaration
It is not necessary to forward declare these structures

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 391 +++++++++++++++++------------------
 1 file changed, 194 insertions(+), 197 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5e36822de5ec..c7b0afd370d4 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -19,8 +19,200 @@
 /* forward declaration */
 void igc_set_ethtool_ops(struct net_device *);
 
-struct igc_adapter;
-struct igc_ring;
+/* Transmit and receive queues */
+#define IGC_MAX_RX_QUEUES		4
+#define IGC_MAX_TX_QUEUES		4
+
+#define MAX_Q_VECTORS			8
+#define MAX_STD_JUMBO_FRAME_SIZE	9216
+
+#define MAX_ETYPE_FILTER		(4 - 1)
+#define IGC_RETA_SIZE			128
+
+struct igc_tx_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 restart_queue;
+	u64 restart_queue2;
+};
+
+struct igc_rx_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 drops;
+	u64 csum_err;
+	u64 alloc_failed;
+};
+
+struct igc_rx_packet_stats {
+	u64 ipv4_packets;      /* IPv4 headers processed */
+	u64 ipv4e_packets;     /* IPv4E headers with extensions processed */
+	u64 ipv6_packets;      /* IPv6 headers processed */
+	u64 ipv6e_packets;     /* IPv6E headers with extensions processed */
+	u64 tcp_packets;       /* TCP headers processed */
+	u64 udp_packets;       /* UDP headers processed */
+	u64 sctp_packets;      /* SCTP headers processed */
+	u64 nfs_packets;       /* NFS headers processe */
+	u64 other_packets;
+};
+
+struct igc_ring_container {
+	struct igc_ring *ring;          /* pointer to linked list of rings */
+	unsigned int total_bytes;       /* total bytes processed this int */
+	unsigned int total_packets;     /* total packets processed this int */
+	u16 work_limit;                 /* total work allowed per interrupt */
+	u8 count;                       /* total number of rings in vector */
+	u8 itr;                         /* current ITR setting for ring */
+};
+
+struct igc_ring {
+	struct igc_q_vector *q_vector;  /* backlink to q_vector */
+	struct net_device *netdev;      /* back pointer to net_device */
+	struct device *dev;             /* device for dma mapping */
+	union {                         /* array of buffer info structs */
+		struct igc_tx_buffer *tx_buffer_info;
+		struct igc_rx_buffer *rx_buffer_info;
+	};
+	void *desc;                     /* descriptor ring memory */
+	unsigned long flags;            /* ring specific flags */
+	void __iomem *tail;             /* pointer to ring tail register */
+	dma_addr_t dma;                 /* phys address of the ring */
+	unsigned int size;              /* length of desc. ring in bytes */
+
+	u16 count;                      /* number of desc. in the ring */
+	u8 queue_index;                 /* logical index of the ring*/
+	u8 reg_idx;                     /* physical index of the ring */
+	bool launchtime_enable;         /* true if LaunchTime is enabled */
+
+	u32 start_time;
+	u32 end_time;
+
+	/* everything past this point are written often */
+	u16 next_to_clean;
+	u16 next_to_use;
+	u16 next_to_alloc;
+
+	union {
+		/* TX */
+		struct {
+			struct igc_tx_queue_stats tx_stats;
+			struct u64_stats_sync tx_syncp;
+			struct u64_stats_sync tx_syncp2;
+		};
+		/* RX */
+		struct {
+			struct igc_rx_queue_stats rx_stats;
+			struct igc_rx_packet_stats pkt_stats;
+			struct u64_stats_sync rx_syncp;
+			struct sk_buff *skb;
+		};
+	};
+} ____cacheline_internodealigned_in_smp;
+
+/* Board specific private data structure */
+struct igc_adapter {
+	struct net_device *netdev;
+
+	unsigned long state;
+	unsigned int flags;
+	unsigned int num_q_vectors;
+
+	struct msix_entry *msix_entries;
+
+	/* TX */
+	u16 tx_work_limit;
+	u32 tx_timeout_count;
+	int num_tx_queues;
+	struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES];
+
+	/* RX */
+	int num_rx_queues;
+	struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES];
+
+	struct timer_list watchdog_timer;
+	struct timer_list dma_err_timer;
+	struct timer_list phy_info_timer;
+
+	u32 wol;
+	u32 en_mng_pt;
+	u16 link_speed;
+	u16 link_duplex;
+
+	u8 port_num;
+
+	u8 __iomem *io_addr;
+	/* Interrupt Throttle Rate */
+	u32 rx_itr_setting;
+	u32 tx_itr_setting;
+
+	struct work_struct reset_task;
+	struct work_struct watchdog_task;
+	struct work_struct dma_err_task;
+	bool fc_autoneg;
+
+	u8 tx_timeout_factor;
+
+	int msg_enable;
+	u32 max_frame_size;
+	u32 min_frame_size;
+
+	ktime_t base_time;
+	ktime_t cycle_time;
+
+	/* OS defined structs */
+	struct pci_dev *pdev;
+	/* lock for statistics */
+	spinlock_t stats64_lock;
+	struct rtnl_link_stats64 stats64;
+
+	/* structs defined in igc_hw.h */
+	struct igc_hw hw;
+	struct igc_hw_stats stats;
+
+	struct igc_q_vector *q_vector[MAX_Q_VECTORS];
+	u32 eims_enable_mask;
+	u32 eims_other;
+
+	u16 tx_ring_count;
+	u16 rx_ring_count;
+
+	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
+	u32 rx_hwtstamp_cleared;
+
+	u32 rss_queues;
+	u32 rss_indir_tbl_init;
+
+	/* RX network flow classification support */
+	struct hlist_head nfc_filter_list;
+	struct hlist_head cls_flower_list;
+	unsigned int nfc_filter_count;
+
+	/* lock for RX network flow classification filter */
+	spinlock_t nfc_lock;
+	bool etype_bitmap[MAX_ETYPE_FILTER];
+
+	struct igc_mac_addr *mac_table;
+
+	u8 rss_indir_tbl[IGC_RETA_SIZE];
+
+	unsigned long link_check_timeout;
+	struct igc_info ei;
+
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_caps;
+	struct work_struct ptp_tx_work;
+	struct sk_buff *ptp_tx_skb;
+	struct hwtstamp_config tstamp_config;
+	unsigned long ptp_tx_start;
+	unsigned long last_rx_ptp_check;
+	unsigned long last_rx_timestamp;
+	unsigned int ptp_flags;
+	/* System time value lock */
+	spinlock_t tmreg_lock;
+	struct cyclecounter cc;
+	struct timecounter tc;
+};
 
 void igc_up(struct igc_adapter *adapter);
 void igc_down(struct igc_adapter *adapter);
@@ -50,7 +242,6 @@ extern char igc_driver_name[];
 extern char igc_driver_version[];
 
 #define IGC_REGS_LEN			740
-#define IGC_RETA_SIZE			128
 
 /* flags controlling PTP/1588 function */
 #define IGC_PTP_ENABLED		BIT(0)
@@ -100,13 +291,6 @@ extern char igc_driver_version[];
 #define IGC_MIN_RXD		80
 #define IGC_MAX_RXD		4096
 
-/* Transmit and receive queues */
-#define IGC_MAX_RX_QUEUES		4
-#define IGC_MAX_TX_QUEUES		4
-
-#define MAX_Q_VECTORS			8
-#define MAX_STD_JUMBO_FRAME_SIZE	9216
-
 /* Supported Rx Buffer Sizes */
 #define IGC_RXBUFFER_256		256
 #define IGC_RXBUFFER_2048		2048
@@ -233,86 +417,6 @@ struct igc_rx_buffer {
 	__u16 pagecnt_bias;
 };
 
-struct igc_tx_queue_stats {
-	u64 packets;
-	u64 bytes;
-	u64 restart_queue;
-	u64 restart_queue2;
-};
-
-struct igc_rx_queue_stats {
-	u64 packets;
-	u64 bytes;
-	u64 drops;
-	u64 csum_err;
-	u64 alloc_failed;
-};
-
-struct igc_rx_packet_stats {
-	u64 ipv4_packets;      /* IPv4 headers processed */
-	u64 ipv4e_packets;     /* IPv4E headers with extensions processed */
-	u64 ipv6_packets;      /* IPv6 headers processed */
-	u64 ipv6e_packets;     /* IPv6E headers with extensions processed */
-	u64 tcp_packets;       /* TCP headers processed */
-	u64 udp_packets;       /* UDP headers processed */
-	u64 sctp_packets;      /* SCTP headers processed */
-	u64 nfs_packets;       /* NFS headers processe */
-	u64 other_packets;
-};
-
-struct igc_ring_container {
-	struct igc_ring *ring;          /* pointer to linked list of rings */
-	unsigned int total_bytes;       /* total bytes processed this int */
-	unsigned int total_packets;     /* total packets processed this int */
-	u16 work_limit;                 /* total work allowed per interrupt */
-	u8 count;                       /* total number of rings in vector */
-	u8 itr;                         /* current ITR setting for ring */
-};
-
-struct igc_ring {
-	struct igc_q_vector *q_vector;  /* backlink to q_vector */
-	struct net_device *netdev;      /* back pointer to net_device */
-	struct device *dev;             /* device for dma mapping */
-	union {                         /* array of buffer info structs */
-		struct igc_tx_buffer *tx_buffer_info;
-		struct igc_rx_buffer *rx_buffer_info;
-	};
-	void *desc;                     /* descriptor ring memory */
-	unsigned long flags;            /* ring specific flags */
-	void __iomem *tail;             /* pointer to ring tail register */
-	dma_addr_t dma;                 /* phys address of the ring */
-	unsigned int size;              /* length of desc. ring in bytes */
-
-	u16 count;                      /* number of desc. in the ring */
-	u8 queue_index;                 /* logical index of the ring*/
-	u8 reg_idx;                     /* physical index of the ring */
-	bool launchtime_enable;		/* true if LaunchTime is enabled */
-
-	u32 start_time;
-	u32 end_time;
-
-	/* everything past this point are written often */
-	u16 next_to_clean;
-	u16 next_to_use;
-	u16 next_to_alloc;
-
-	union {
-		/* TX */
-		struct {
-			struct igc_tx_queue_stats tx_stats;
-			struct u64_stats_sync tx_syncp;
-			struct u64_stats_sync tx_syncp2;
-		};
-		/* RX */
-		struct {
-			struct igc_rx_queue_stats rx_stats;
-			struct igc_rx_packet_stats pkt_stats;
-			struct u64_stats_sync rx_syncp;
-			struct sk_buff *skb;
-		};
-	};
-} ____cacheline_internodealigned_in_smp;
-
 struct igc_q_vector {
 	struct igc_adapter *adapter;    /* backlink */
 	void __iomem *itr_register;
@@ -333,8 +437,6 @@ struct igc_q_vector {
 	struct igc_ring ring[] ____cacheline_internodealigned_in_smp;
 };
 
-#define MAX_ETYPE_FILTER		(4 - 1)
-
 enum igc_filter_match_flags {
 	IGC_FILTER_FLAG_ETHER_TYPE =	0x1,
 	IGC_FILTER_FLAG_VLAN_TCI   =	0x2,
@@ -378,111 +480,6 @@ struct igc_mac_addr {
 
 #define IGC_MAX_RXNFC_FILTERS		16
 
-/* Board specific private data structure */
-struct igc_adapter {
-	struct net_device *netdev;
-
-	unsigned long state;
-	unsigned int flags;
-	unsigned int num_q_vectors;
-
-	struct msix_entry *msix_entries;
-
-	/* TX */
-	u16 tx_work_limit;
-	u32 tx_timeout_count;
-	int num_tx_queues;
-	struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES];
-
-	/* RX */
-	int num_rx_queues;
-	struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES];
-
-	struct timer_list watchdog_timer;
-	struct timer_list dma_err_timer;
-	struct timer_list phy_info_timer;
-
-	u32 wol;
-	u32 en_mng_pt;
-	u16 link_speed;
-	u16 link_duplex;
-
-	u8 port_num;
-
-	u8 __iomem *io_addr;
-	/* Interrupt Throttle Rate */
-	u32 rx_itr_setting;
-	u32 tx_itr_setting;
-
-	struct work_struct reset_task;
-	struct work_struct watchdog_task;
-	struct work_struct dma_err_task;
-	bool fc_autoneg;
-
-	u8 tx_timeout_factor;
-
-	int msg_enable;
-	u32 max_frame_size;
-	u32 min_frame_size;
-
-	ktime_t base_time;
-	ktime_t cycle_time;
-
-	/* OS defined structs */
-	struct pci_dev *pdev;
-	/* lock for statistics */
-	spinlock_t stats64_lock;
-	struct rtnl_link_stats64 stats64;
-
-	/* structs defined in igc_hw.h */
-	struct igc_hw hw;
-	struct igc_hw_stats stats;
-
-	struct igc_q_vector *q_vector[MAX_Q_VECTORS];
-	u32 eims_enable_mask;
-	u32 eims_other;
-
-	u16 tx_ring_count;
-	u16 rx_ring_count;
-
-	u32 tx_hwtstamp_timeouts;
-	u32 tx_hwtstamp_skipped;
-	u32 rx_hwtstamp_cleared;
-
-	u32 rss_queues;
-	u32 rss_indir_tbl_init;
-
-	/* RX network flow classification support */
-	struct hlist_head nfc_filter_list;
-	struct hlist_head cls_flower_list;
-	unsigned int nfc_filter_count;
-
-	/* lock for RX network flow classification filter */
-	spinlock_t nfc_lock;
-	bool etype_bitmap[MAX_ETYPE_FILTER];
-
-	struct igc_mac_addr *mac_table;
-
-	u8 rss_indir_tbl[IGC_RETA_SIZE];
-
-	unsigned long link_check_timeout;
-	struct igc_info ei;
-
-	struct ptp_clock *ptp_clock;
-	struct ptp_clock_info ptp_caps;
-	struct work_struct ptp_tx_work;
-	struct sk_buff *ptp_tx_skb;
-	struct hwtstamp_config tstamp_config;
-	unsigned long ptp_tx_start;
-	unsigned long last_rx_ptp_check;
-	unsigned long last_rx_timestamp;
-	unsigned int ptp_flags;
-	/* System time value lock */
-	spinlock_t tmreg_lock;
-	struct cyclecounter cc;
-	struct timecounter tc;
-};
-
 /* igc_desc_unused - calculate if we have unused descriptors */
 static inline u16 igc_desc_unused(const struct igc_ring *ring)
 {
-- 
cgit v1.2.3


From b8a61ea15cdf8524f91dbad90a4f1fae13b0120b Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 28 Feb 2020 00:19:57 -0800
Subject: igc: Fix overwrites when dumping registers

This patch fixes some register overwriting when dumping registers via
ethtool.

We have a total of 16 RAL registers, starting at offset 139. So RAH
offset should be 139 + 16 = 155, not 145. As result some RAL registers
are overwritten. Likewise, RAH registers are also overwritten by TDBAL,
TDBAH, TDLEN, and TDH registers.

To fix this bug while preserving the ABI, this patch re-writes RAL and
RAH registers at the end of 'regs_buff' and bumps regs->version. It also
removes some pointless comments in the middle of igc_set_regs().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index f530fc29b074..ff2a40496e4e 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -153,7 +153,7 @@ static void igc_get_regs(struct net_device *netdev,
 
 	memset(p, 0, IGC_REGS_LEN * sizeof(u32));
 
-	regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id;
+	regs->version = (2u << 24) | (hw->revision_id << 16) | hw->device_id;
 
 	/* General Registers */
 	regs_buff[0] = rd32(IGC_CTRL);
@@ -306,6 +306,15 @@ static void igc_get_regs(struct net_device *netdev,
 		regs_buff[164 + i] = rd32(IGC_TDT(i));
 	for (i = 0; i < 4; i++)
 		regs_buff[168 + i] = rd32(IGC_TXDCTL(i));
+
+	/* XXX: Due to a bug few lines above, RAL and RAH registers are
+	 * overwritten. To preserve the ABI, we write these registers again in
+	 * regs_buff.
+	 */
+	for (i = 0; i < 16; i++)
+		regs_buff[172 + i] = rd32(IGC_RAL(i));
+	for (i = 0; i < 16; i++)
+		regs_buff[188 + i] = rd32(IGC_RAH(i));
 }
 
 static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
-- 
cgit v1.2.3


From 64900e8ff551dd6ae891651b6d74789378472ee1 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Fri, 28 Feb 2020 19:50:07 +0200
Subject: igc: Fix double definition

IGC_START_ITR has beed defined twice
This patch come to fix it

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index c7b0afd370d4..4643f358b843 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -246,9 +246,6 @@ extern char igc_driver_version[];
 /* flags controlling PTP/1588 function */
 #define IGC_PTP_ENABLED		BIT(0)
 
-/* Interrupt defines */
-#define IGC_START_ITR			648 /* ~6000 ints/sec */
-
 /* Flags definitions */
 #define IGC_FLAG_HAS_MSI		BIT(0)
 #define IGC_FLAG_QUEUE_PAIRS		BIT(3)
@@ -270,6 +267,7 @@ extern char igc_driver_version[];
 #define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
 #define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
 
+/* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
 #define IGC_20K_ITR			196
-- 
cgit v1.2.3


From 635071e2c48d4a9261a0df8401155dbd959efd3d Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 3 Mar 2020 02:28:08 +0200
Subject: igc: Enable NETIF_F_HW_TC flag

This assignment of the feature NETIF_F_HW_TC
occurs prior to the initial setup of the local
hw_features variable.

This ensures that NETIF_F_HW_TC are marked
as user changeable, and also enables it by
default when the driver loads.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 896b314035c9..800268da0834 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4903,6 +4903,7 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;
+	netdev->features |= NETIF_F_HW_TC;
 
 #define IGC_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
 				  NETIF_F_GSO_GRE_CSUM | \
-- 
cgit v1.2.3


From 2e39d2c8ff9654ba508c973ade5df332f53f41cc Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 3 Mar 2020 20:26:10 +0200
Subject: igc: Remove copper fiber switch control

i225 device support copper mode only
PHY signal detect indication for copper fiber switch
not applicable to i225 part

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 2 --
 drivers/net/ethernet/intel/igc/igc_main.c    | 9 ---------
 2 files changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 40d6f557079b..42fe4d75cc0d 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -91,8 +91,6 @@
 #define IGC_CTRL_RFCE		0x08000000  /* Receive Flow Control enable */
 #define IGC_CTRL_TFCE		0x10000000  /* Transmit flow control enable */
 
-#define IGC_CONNSW_AUTOSENSE_EN	0x1
-
 /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */
 #define MAX_JUMBO_FRAME_SIZE	0x2600
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 800268da0834..44366c1bec19 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4033,7 +4033,6 @@ static void igc_watchdog_task(struct work_struct *work)
 	struct igc_hw *hw = &adapter->hw;
 	struct igc_phy_info *phy = &hw->phy;
 	u16 phy_data, retry_count = 20;
-	u32 connsw;
 	u32 link;
 	int i;
 
@@ -4046,14 +4045,6 @@ static void igc_watchdog_task(struct work_struct *work)
 			link = false;
 	}
 
-	/* Force link down if we have fiber to swap to */
-	if (adapter->flags & IGC_FLAG_MAS_ENABLE) {
-		if (hw->phy.media_type == igc_media_type_copper) {
-			connsw = rd32(IGC_CONNSW);
-			if (!(connsw & IGC_CONNSW_AUTOSENSE_EN))
-				link = 0;
-		}
-	}
 	if (link) {
 		/* Cancel scheduled suspend requests. */
 		pm_runtime_resume(netdev->dev.parent);
-- 
cgit v1.2.3


From 27945ebe5b980f796fa04dd61511796ac5b80cc2 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 6 Mar 2020 15:54:03 -0800
Subject: igc: Fix NFC queue redirection support

The support for ethtool Network Flow Classification (NFC) queue
redirection based on destination MAC address is currently broken in IGC.
For instance, if we add the following rule, matching frames aren't
enqueued on the expected rx queue.

$ ethtool -N IFNAME flow-type ether dst 3c:fd:fe:9e:7f:71 queue 2

The issue here is due to the fact that igc_rar_set_index() is missing
code to enable the queue selection feature from Receive Address High
(RAH) register. This patch adds the missing code and fixes the issue.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h |  5 ++++-
 drivers/net/ethernet/intel/igc/igc_main.c    | 11 ++++++++---
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 42fe4d75cc0d..af0c03d77a39 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -63,8 +63,11 @@
  * (RAR[15]) for our directed address used by controllers with
  * manageability enabled, allowing us room for 15 multicast addresses.
  */
+#define IGC_RAH_QSEL_MASK	0x000C0000
+#define IGC_RAH_QSEL_SHIFT	18
+#define IGC_RAH_QSEL_ENABLE	BIT(28)
 #define IGC_RAH_AV		0x80000000 /* Receive descriptor valid */
-#define IGC_RAH_POOL_1		0x00040000
+
 #define IGC_RAL_MAC_ADDR_LEN	4
 #define IGC_RAH_MAC_ADDR_LEN	2
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 44366c1bec19..85df9366e172 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -780,13 +780,18 @@ static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
 	rar_low = le32_to_cpup((__le32 *)(addr));
 	rar_high = le16_to_cpup((__le16 *)(addr + 4));
 
+	if (adapter->mac_table[index].state & IGC_MAC_STATE_QUEUE_STEERING) {
+		u8 queue = adapter->mac_table[index].queue;
+		u32 qsel = IGC_RAH_QSEL_MASK & (queue << IGC_RAH_QSEL_SHIFT);
+
+		rar_high |= qsel;
+		rar_high |= IGC_RAH_QSEL_ENABLE;
+	}
+
 	/* Indicate to hardware the Address is Valid. */
 	if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
 		if (is_valid_ether_addr(addr))
 			rar_high |= IGC_RAH_AV;
-
-		rar_high |= IGC_RAH_POOL_1 <<
-			adapter->mac_table[index].queue;
 	}
 
 	wr32(IGC_RAL(index), rar_low);
-- 
cgit v1.2.3


From c24fd2481e0bd3d2c5755c7a3dc898ef249c0ddb Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 6 Mar 2020 16:36:42 -0800
Subject: igc: Remove dead code related to flower filter

IGC driver has no support for tc-flower filters so this patch removes
some leftover code, probably copied from IGB driver by mistake.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      | 1 -
 drivers/net/ethernet/intel/igc/igc_main.c | 3 ---
 2 files changed, 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 4643f358b843..5f21dcfe99ce 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -185,7 +185,6 @@ struct igc_adapter {
 
 	/* RX network flow classification support */
 	struct hlist_head nfc_filter_list;
-	struct hlist_head cls_flower_list;
 	unsigned int nfc_filter_count;
 
 	/* lock for RX network flow classification filter */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 85df9366e172..6acb85842d0a 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3487,9 +3487,6 @@ static void igc_nfc_filter_exit(struct igc_adapter *adapter)
 	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
 		igc_erase_filter(adapter, rule);
 
-	hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node)
-		igc_erase_filter(adapter, rule);
-
 	spin_unlock(&adapter->nfc_lock);
 }
 
-- 
cgit v1.2.3


From ac9156b27564a089ec52f526bfcb59f61c34e7c6 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Mon, 9 Mar 2020 16:10:40 -0700
Subject: igc: Fix default MAC address filter override

This patch fixes a bug when the user adds the first MAC address filter
via ethtool NFC mechanism.

When the first MAC address filter is added, it overwrites the default
MAC address filter configured at RAL[0] and RAH[0]. As consequence,
frames addressed to the interface MAC address are not sent to host
anymore.

This patch fixes the bug by calling igc_set_default_mac_filter() during
adapter init so the position 0 of adapter->mac_table[] is assigned to
the default MAC address.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 6acb85842d0a..9d1792e80e2e 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2354,7 +2354,9 @@ static void igc_configure(struct igc_adapter *adapter)
 	igc_setup_mrqc(adapter);
 	igc_setup_rctl(adapter);
 
+	igc_set_default_mac_filter(adapter);
 	igc_nfc_filter_restore(adapter);
+
 	igc_configure_tx(adapter);
 	igc_configure_rx(adapter);
 
-- 
cgit v1.2.3


From 89f9ffd3eb670bad1260bc579f5e13b8f2d5b3e0 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 17 Apr 2020 22:03:08 +0300
Subject: net: mscc: ocelot: deal with problematic MAC_ETYPE VCAP IS2 rules

By default, the VCAP IS2 will produce a single match for each frame, on
the most specific classification.

Example: a ping packet (ICMP over IPv4 over Ethernet) sent from an IP
address of 10.0.0.1 and a MAC address of 96:18:82:00:04:01 will match
this rule:

tc filter add dev swp0 ingress protocol ipv4 \
	flower skip_sw src_ip 10.0.0.1 action drop

but not this one:

tc filter add dev swp0 ingress \
	flower skip_sw src_mac 96:18:82:00:04:01 action drop

Currently the driver does not really warn the user in any way about
this, and the behavior is rather strange anyway.

The current patch is a workaround to force matches on MAC_ETYPE keys
(DMAC and SMAC) for all packets irrespective of higher layer protocol.
The setting is made at the port level.

Of course this breaks all other non-src_mac and non-dst_mac matches, so
rule exclusivity checks have been added to the driver, in order to never
have rules of both types on any ingress port.

The bits that discard higher-level protocol information are set only
once a MAC_ETYPE rule is added to a filter block, and only for the ports
that are bound to that filter block. Then all further non-MAC_ETYPE
rules added to that filter block should be denied by the ports bound to
it.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_ace.c    | 103 +++++++++++++++++++++++++++++-
 drivers/net/ethernet/mscc/ocelot_ace.h    |   5 +-
 drivers/net/ethernet/mscc/ocelot_flower.c |   2 +-
 3 files changed, 106 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_ace.c b/drivers/net/ethernet/mscc/ocelot_ace.c
index 3bd286044480..8a2f7d13ef6d 100644
--- a/drivers/net/ethernet/mscc/ocelot_ace.c
+++ b/drivers/net/ethernet/mscc/ocelot_ace.c
@@ -706,13 +706,114 @@ ocelot_ace_rule_get_rule_index(struct ocelot_acl_block *block, int index)
 	return NULL;
 }
 
+/* If @on=false, then SNAP, ARP, IP and OAM frames will not match on keys based
+ * on destination and source MAC addresses, but only on higher-level protocol
+ * information. The only frame types to match on keys containing MAC addresses
+ * in this case are non-SNAP, non-ARP, non-IP and non-OAM frames.
+ *
+ * If @on=true, then the above frame types (SNAP, ARP, IP and OAM) will match
+ * on MAC_ETYPE keys such as destination and source MAC on this ingress port.
+ * However the setting has the side effect of making these frames not matching
+ * on any _other_ keys than MAC_ETYPE ones.
+ */
+static void ocelot_match_all_as_mac_etype(struct ocelot *ocelot, int port,
+					  bool on)
+{
+	u32 val = 0;
+
+	if (on)
+		val = ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(3) |
+		      ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(3) |
+		      ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(3) |
+		      ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(3) |
+		      ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(3);
+
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS_M |
+		       ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS_M |
+		       ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS_M |
+		       ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS_M |
+		       ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS_M,
+		       ANA_PORT_VCAP_S2_CFG, port);
+}
+
+static bool ocelot_ace_is_problematic_mac_etype(struct ocelot_ace_rule *ace)
+{
+	if (ace->type != OCELOT_ACE_TYPE_ETYPE)
+		return false;
+	if (ether_addr_to_u64(ace->frame.etype.dmac.value) &
+	    ether_addr_to_u64(ace->frame.etype.dmac.mask))
+		return true;
+	if (ether_addr_to_u64(ace->frame.etype.smac.value) &
+	    ether_addr_to_u64(ace->frame.etype.smac.mask))
+		return true;
+	return false;
+}
+
+static bool ocelot_ace_is_problematic_non_mac_etype(struct ocelot_ace_rule *ace)
+{
+	if (ace->type == OCELOT_ACE_TYPE_SNAP)
+		return true;
+	if (ace->type == OCELOT_ACE_TYPE_ARP)
+		return true;
+	if (ace->type == OCELOT_ACE_TYPE_IPV4)
+		return true;
+	if (ace->type == OCELOT_ACE_TYPE_IPV6)
+		return true;
+	return false;
+}
+
+static bool ocelot_exclusive_mac_etype_ace_rules(struct ocelot *ocelot,
+						 struct ocelot_ace_rule *ace)
+{
+	struct ocelot_acl_block *block = &ocelot->acl_block;
+	struct ocelot_ace_rule *tmp;
+	unsigned long port;
+	int i;
+
+	if (ocelot_ace_is_problematic_mac_etype(ace)) {
+		/* Search for any non-MAC_ETYPE rules on the port */
+		for (i = 0; i < block->count; i++) {
+			tmp = ocelot_ace_rule_get_rule_index(block, i);
+			if (tmp->ingress_port_mask & ace->ingress_port_mask &&
+			    ocelot_ace_is_problematic_non_mac_etype(tmp))
+				return false;
+		}
+
+		for_each_set_bit(port, &ace->ingress_port_mask,
+				 ocelot->num_phys_ports)
+			ocelot_match_all_as_mac_etype(ocelot, port, true);
+	} else if (ocelot_ace_is_problematic_non_mac_etype(ace)) {
+		/* Search for any MAC_ETYPE rules on the port */
+		for (i = 0; i < block->count; i++) {
+			tmp = ocelot_ace_rule_get_rule_index(block, i);
+			if (tmp->ingress_port_mask & ace->ingress_port_mask &&
+			    ocelot_ace_is_problematic_mac_etype(tmp))
+				return false;
+		}
+
+		for_each_set_bit(port, &ace->ingress_port_mask,
+				 ocelot->num_phys_ports)
+			ocelot_match_all_as_mac_etype(ocelot, port, false);
+	}
+
+	return true;
+}
+
 int ocelot_ace_rule_offload_add(struct ocelot *ocelot,
-				struct ocelot_ace_rule *rule)
+				struct ocelot_ace_rule *rule,
+				struct netlink_ext_ack *extack)
 {
 	struct ocelot_acl_block *block = &ocelot->acl_block;
 	struct ocelot_ace_rule *ace;
 	int i, index;
 
+	if (!ocelot_exclusive_mac_etype_ace_rules(ocelot, rule)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot mix MAC_ETYPE with non-MAC_ETYPE rules");
+		return -EBUSY;
+	}
+
 	/* Add rule to the linked list */
 	ocelot_ace_rule_add(ocelot, block, rule);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_ace.h b/drivers/net/ethernet/mscc/ocelot_ace.h
index 29d22c566786..099e177f2617 100644
--- a/drivers/net/ethernet/mscc/ocelot_ace.h
+++ b/drivers/net/ethernet/mscc/ocelot_ace.h
@@ -194,7 +194,7 @@ struct ocelot_ace_rule {
 
 	enum ocelot_ace_action action;
 	struct ocelot_ace_stats stats;
-	u16 ingress_port_mask;
+	unsigned long ingress_port_mask;
 
 	enum ocelot_vcap_bit dmac_mc;
 	enum ocelot_vcap_bit dmac_bc;
@@ -215,7 +215,8 @@ struct ocelot_ace_rule {
 };
 
 int ocelot_ace_rule_offload_add(struct ocelot *ocelot,
-				struct ocelot_ace_rule *rule);
+				struct ocelot_ace_rule *rule,
+				struct netlink_ext_ack *extack);
 int ocelot_ace_rule_offload_del(struct ocelot *ocelot,
 				struct ocelot_ace_rule *rule);
 int ocelot_ace_rule_stats_update(struct ocelot *ocelot,
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 341923311fec..954cb67eeaa2 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -205,7 +205,7 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port,
 		return ret;
 	}
 
-	return ocelot_ace_rule_offload_add(ocelot, ace);
+	return ocelot_ace_rule_offload_add(ocelot, ace, f->common.extack);
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace);
 
-- 
cgit v1.2.3


From 7070eea5e95a3c1ea30b9afcedd8d29efcc28477 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 17 Apr 2020 22:07:55 +0300
Subject: enetc: permit configuration of rx-vlan-filter with ethtool

Each ENETC station interface (SI) has a VLAN filter list and a port
flag (PSIPVMR) by which it can be put in "VLAN promiscuous" mode, which
enables the reception of VLAN-tagged traffic even if it is not in the
VLAN filtering list.

Currently the handling of this setting works like this: the port starts
off as VLAN promiscuous, then it switches to enabling VLAN filtering as
soon as the first VLAN is installed in its filter via
.ndo_vlan_rx_add_vid. In practice that does not work out very well,
because more often than not, the first VLAN to be installed is out of
the control of the user: the 8021q module, if loaded, adds its rule for
802.1p (VID 0) traffic upon bringing the interface up.

What the user is currently seeing in ethtool is this:
ethtool -k eno2
rx-vlan-filter: on [fixed]

which doesn't match the intention of the code, but the practical reality
of having the 8021q module install its VID which has the side-effect of
turning on VLAN filtering in this driver. All in all, a slightly
confusing experience.

So instead of letting this driver switch the VLAN filtering state by
itself, just wire it up with the rx-vlan-filter feature from ethtool,
and let it be user-configurable just through that knob, except for one
case, see below.

In promiscuous mode, it is more intuitive that all traffic is received,
including VLAN tagged traffic. It appears that it is necessary to set
the flag in PSIPVMR for that to be the case, so VLAN promiscuous mode is
also temporarily enabled. On exit from promiscuous mode, the setting
made by ethtool is restored.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 44 +++++++++----------------
 1 file changed, 16 insertions(+), 28 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 85e2b741df41..de1ad4975074 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -50,21 +50,6 @@ static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map)
 	enetc_port_wr(hw, ENETC_PSIPVMR, ENETC_PSIPVMR_SET_VP(si_map) | val);
 }
 
-static bool enetc_si_vlan_promisc_is_on(struct enetc_pf *pf, int si_idx)
-{
-	return pf->vlan_promisc_simap & BIT(si_idx);
-}
-
-static bool enetc_vlan_filter_is_on(struct enetc_pf *pf)
-{
-	int i;
-
-	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID)
-		return true;
-
-	return false;
-}
-
 static void enetc_enable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
 {
 	pf->vlan_promisc_simap |= BIT(si_idx);
@@ -204,6 +189,7 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	char vlan_promisc_simap = pf->vlan_promisc_simap;
 	struct enetc_hw *hw = &priv->si->hw;
 	bool uprom = false, mprom = false;
 	struct enetc_mac_filter *filter;
@@ -216,16 +202,16 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
 		psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
 		uprom = true;
 		mprom = true;
-		/* enable VLAN promisc mode for SI0 */
-		if (!enetc_si_vlan_promisc_is_on(pf, 0))
-			enetc_enable_si_vlan_promisc(pf, 0);
-
+		/* Enable VLAN promiscuous mode for SI0 (PF) */
+		vlan_promisc_simap |= BIT(0);
 	} else if (ndev->flags & IFF_ALLMULTI) {
 		/* enable multi cast promisc mode for SI0 (PF) */
 		psipmr = ENETC_PSIPMR_SET_MP(0);
 		mprom = true;
 	}
 
+	enetc_set_vlan_promisc(&pf->si->hw, vlan_promisc_simap);
+
 	/* first 2 filter entries belong to PF */
 	if (!uprom) {
 		/* Update unicast filters */
@@ -306,9 +292,6 @@ static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
 	struct enetc_pf *pf = enetc_si_priv(priv->si);
 	int idx;
 
-	if (enetc_si_vlan_promisc_is_on(pf, 0))
-		enetc_disable_si_vlan_promisc(pf, 0);
-
 	__set_bit(vid, pf->active_vlans);
 
 	idx = enetc_vid_hash_idx(vid);
@@ -326,9 +309,6 @@ static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
 	__clear_bit(vid, pf->active_vlans);
 	enetc_sync_vlan_ht_filter(pf, true);
 
-	if (!enetc_vlan_filter_is_on(pf))
-		enetc_enable_si_vlan_promisc(pf, 0);
-
 	return 0;
 }
 
@@ -677,6 +657,15 @@ static int enetc_pf_set_features(struct net_device *ndev,
 		enetc_enable_txvlan(&priv->si->hw, 0,
 				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
 
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+		if (!!(features & NETIF_F_HW_VLAN_CTAG_FILTER))
+			enetc_disable_si_vlan_promisc(pf, 0);
+		else
+			enetc_enable_si_vlan_promisc(pf, 0);
+	}
+
 	if (changed & NETIF_F_LOOPBACK)
 		enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
 
@@ -719,12 +708,11 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-			    NETIF_F_LOOPBACK;
+			    NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
 			 NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
 			 NETIF_F_HW_VLAN_CTAG_TX |
-			 NETIF_F_HW_VLAN_CTAG_RX |
-			 NETIF_F_HW_VLAN_CTAG_FILTER;
+			 NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (si->num_rss)
 		ndev->hw_features |= NETIF_F_RXHASH;
-- 
cgit v1.2.3


From 0360c046ca186be1953d185d5a3631e415381820 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:06:51 +0200
Subject: r8169: move setting OCP base to generic init code

Move setting the ocp_base to rtl_init_one(). Where supported the value
is always the same, and if not supported it doesn't hurt.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index bf5bf05970a2..f882e8c09987 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -75,6 +75,8 @@
 #define R8169_TX_RING_BYTES	(NUM_TX_DESC * sizeof(struct TxDesc))
 #define R8169_RX_RING_BYTES	(NUM_RX_DESC * sizeof(struct RxDesc))
 
+#define OCP_STD_PHY_BASE	0xa400
+
 #define RTL_CFG_NO_GBIT	1
 
 /* write/read MMIO register */
@@ -847,8 +849,6 @@ static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask,
 	r8168_mac_ocp_write(tp, reg, (data & ~mask) | set);
 }
 
-#define OCP_STD_PHY_BASE	0xa400
-
 static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value)
 {
 	if (reg == 0x1f) {
@@ -5189,8 +5189,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 
 static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
-	tp->ocp_base = OCP_STD_PHY_BASE;
-
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 
 	if (!rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42))
@@ -5215,8 +5213,6 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 
 static void rtl_hw_init_8125(struct rtl8169_private *tp)
 {
-	tp->ocp_base = OCP_STD_PHY_BASE;
-
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 
 	if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
@@ -5353,6 +5349,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
 	tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1;
 	tp->eee_adv = -1;
+	tp->ocp_base = OCP_STD_PHY_BASE;
 
 	/* Get the *optional* external "ether_clk" used on some boards */
 	rc = rtl_get_ether_clk(tp);
-- 
cgit v1.2.3


From a9b3d56830a3d626a0d85adc285ea94e829b6e9d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:07:41 +0200
Subject: r8169: remove NETIF_F_HIGHDMA from vlan_features

NETIF_F_HIGHDMA is added to vlan_features by register_netdev(),
therefore we can omit this here.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index f882e8c09987..2d6c94652dc7 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5440,8 +5440,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 			   NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_HIGHDMA;
+	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	tp->cp_cmd |= RxChkSum;
-- 
cgit v1.2.3


From 85ab8b245ec6572eb489d0fe76c5573851d7b7ad Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:08:43 +0200
Subject: r8169: preserve VLAN setting on RTL8125 in rtl_init_rxcfg

So far we set RX_VLAN_8125 unconditionally, even if
NETIF_F_HW_VLAN_CTAG_RX may not be set. Don't touch these bits,
and let only rtl8169_set_features() control them.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2d6c94652dc7..e37ff1a5161d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2397,6 +2397,8 @@ static void rtl_pll_power_up(struct rtl8169_private *tp)
 
 static void rtl_init_rxcfg(struct rtl8169_private *tp)
 {
+	u32 vlan;
+
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
@@ -2411,8 +2413,9 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_61:
-		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_VLAN_8125 |
-				      RX_DMA_BURST);
+		/* VLAN flags are controlled by NETIF_F_HW_VLAN_CTAG_RX */
+		vlan = RTL_R32(tp, RxConfig) & RX_VLAN_8125;
+		RTL_W32(tp, RxConfig, vlan | RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
 	default:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST);
-- 
cgit v1.2.3


From 145192f83a1184ca8f2ef4508e7a93bb783bb444 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:10:03 +0200
Subject: r8169: use rtl8169_set_features in rtl8169_init_one

At that place in rtl_init_one() we can safely use rtl8169_set_features()
to configure the chip according to the default features.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index e37ff1a5161d..e8c55b795c76 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5446,10 +5446,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
-	tp->cp_cmd |= RxChkSum;
-	/* RTL8125 uses register RxConfig for VLAN offloading config */
-	if (!rtl_is_8125(tp))
-		tp->cp_cmd |= RxVlan;
 	/*
 	 * Pretend we are using VLANs; This bypasses a nasty bug where
 	 * Interrupts stop flowing on high load on 8110SCd controllers.
@@ -5481,6 +5477,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->hw_features |= NETIF_F_RXALL;
 	dev->hw_features |= NETIF_F_RXFCS;
 
+	/* configure chip for default features */
+	rtl8169_set_features(dev, dev->features);
+
 	jumbo_max = rtl_jumbo_max(tp);
 	if (jumbo_max)
 		dev->max_mtu = jumbo_max;
-- 
cgit v1.2.3


From 0623b98b41cd16073ee15f35e058194313e6dc51 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:10:44 +0200
Subject: r8169: improve rtl8169_tso_csum_v2

Simplify the code and avoid the overhead of calling vlan_get_protocol().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index e8c55b795c76..2cd2b038e4eb 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4127,25 +4127,20 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 				struct sk_buff *skb, u32 *opts)
 {
 	u32 transport_offset = (u32)skb_transport_offset(skb);
-	u32 mss = skb_shinfo(skb)->gso_size;
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	u32 mss = shinfo->gso_size;
 
 	if (mss) {
-		switch (vlan_get_protocol(skb)) {
-		case htons(ETH_P_IP):
+		if (shinfo->gso_type & SKB_GSO_TCPV4) {
 			opts[0] |= TD1_GTSENV4;
-			break;
-
-		case htons(ETH_P_IPV6):
+		} else if (shinfo->gso_type & SKB_GSO_TCPV6) {
 			if (skb_cow_head(skb, 0))
 				return false;
 
 			tcp_v6_gso_csum_prep(skb);
 			opts[0] |= TD1_GTSENV6;
-			break;
-
-		default:
+		} else {
 			WARN_ON_ONCE(1);
-			break;
 		}
 
 		opts[0] |= transport_offset << GTTCPHO_SHIFT;
-- 
cgit v1.2.3


From 773235f4e1cc41ea98f520a0cfe0a51a58b2d411 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 23:11:32 +0200
Subject: r8169: add workaround for RTL8168evl TSO hw issues

Add workaround for hw issues with TSO on RTL8168evl. This workaround is
based on information I got from Realtek, and *should* allow to safely
enable TSO on this chip version.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 34 +++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2cd2b038e4eb..a8696d958cd1 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4306,6 +4306,37 @@ err_stop_0:
 	return NETDEV_TX_BUSY;
 }
 
+static unsigned int rtl_last_frag_len(struct sk_buff *skb)
+{
+	struct skb_shared_info *info = skb_shinfo(skb);
+	unsigned int nr_frags = info->nr_frags;
+
+	if (!nr_frags)
+		return UINT_MAX;
+
+	return skb_frag_size(info->frags + nr_frags - 1);
+}
+
+/* Workaround for hw issues with TSO on RTL8168evl */
+static netdev_features_t rtl8168evl_fix_tso(struct sk_buff *skb,
+					    netdev_features_t features)
+{
+	/* IPv4 header has options field */
+	if (vlan_get_protocol(skb) == htons(ETH_P_IP) &&
+	    ip_hdrlen(skb) > sizeof(struct iphdr))
+		features &= ~NETIF_F_ALL_TSO;
+
+	/* IPv4 TCP header has options field */
+	else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 &&
+		 tcp_hdrlen(skb) > sizeof(struct tcphdr))
+		features &= ~NETIF_F_ALL_TSO;
+
+	else if (rtl_last_frag_len(skb) <= 6)
+		features &= ~NETIF_F_ALL_TSO;
+
+	return features;
+}
+
 static netdev_features_t rtl8169_features_check(struct sk_buff *skb,
 						struct net_device *dev,
 						netdev_features_t features)
@@ -4314,6 +4345,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb,
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	if (skb_is_gso(skb)) {
+		if (tp->mac_version == RTL_GIGA_MAC_VER_34)
+			features = rtl8168evl_fix_tso(skb, features);
+
 		if (transport_offset > GTTCPHO_MAX &&
 		    rtl_chip_supports_csum_v2(tp))
 			features &= ~NETIF_F_ALL_TSO;
-- 
cgit v1.2.3


From ec44e72b73b74af489196352152e53a20c8ad5eb Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 2 Apr 2020 15:17:40 +0300
Subject: net/mlx5: Open-code create and destroy QP calls

FPGA, IPoIB and SW steering don't need anything from the
mlx5_core_create_qp() and mlx5_core_destroy_qp() except calls
to mlx5_cmd_exec().

Let's open-code it, so we will be able to move qp.c to mlx5_ib.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    | 24 +++++++++--------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  | 30 ++++++++++------------
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 18 ++++++++-----
 3 files changed, 39 insertions(+), 33 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 61021133029e..7c3e7232852e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -534,8 +534,9 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 				    unsigned int tx_size, unsigned int rx_size)
 {
 	struct mlx5_fpga_device *fdev = conn->fdev;
+	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
 	struct mlx5_core_dev *mdev = fdev->mdev;
-	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {0};
+	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
 	void *in = NULL, *qpc;
 	int err, inlen;
 
@@ -600,10 +601,12 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 	mlx5_fill_page_frag_array(&conn->qp.wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas));
 
-	err = mlx5_core_create_qp(mdev, &conn->qp.mqp, in, inlen);
+	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
 	if (err)
 		goto err_sq_bufs;
 
+	conn->qp.mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
 	conn->qp.mqp.event = mlx5_fpga_conn_event;
 	mlx5_fpga_dbg(fdev, "Created QP #0x%x\n", conn->qp.mqp.qpn);
 
@@ -658,7 +661,14 @@ static void mlx5_fpga_conn_flush_send_bufs(struct mlx5_fpga_conn *conn)
 
 static void mlx5_fpga_conn_destroy_qp(struct mlx5_fpga_conn *conn)
 {
-	mlx5_core_destroy_qp(conn->fdev->mdev, &conn->qp.mqp);
+	struct mlx5_core_dev *dev = conn->fdev->mdev;
+	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+	struct mlx5_core_qp *qp = &conn->qp.mqp;
+
+	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	mlx5_cmd_exec_in(dev, destroy_qp, in);
+
 	mlx5_fpga_conn_free_recv_bufs(conn);
 	mlx5_fpga_conn_flush_send_bufs(conn);
 	kvfree(conn->qp.sq.bufs);
@@ -972,19 +982,11 @@ out:
 
 void mlx5_fpga_conn_destroy(struct mlx5_fpga_conn *conn)
 {
-	struct mlx5_fpga_device *fdev = conn->fdev;
-	struct mlx5_core_dev *mdev = fdev->mdev;
-	int err = 0;
-
 	conn->qp.active = false;
 	tasklet_disable(&conn->cq.tasklet);
 	synchronize_irq(conn->cq.mcq.irqn);
 
 	mlx5_fpga_destroy_qp(conn->fdev->mdev, conn->fpga_qpn);
-	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, NULL,
-				  &conn->qp.mqp);
-	if (err)
-		mlx5_fpga_warn(fdev, "qp_modify 2ERR failed: %d\n", err);
 	mlx5_fpga_conn_destroy_qp(conn);
 	mlx5_fpga_conn_destroy_cq(conn);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 673aaa815f57..8bca11cb1e19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -219,17 +219,12 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv)
 
 int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
-	u32 *in = NULL;
+	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {};
 	void *addr_path;
 	int ret = 0;
-	int inlen;
 	void *qpc;
 
-	inlen = MLX5_ST_SZ_BYTES(create_qp_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
 	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
 	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD);
 	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
@@ -240,20 +235,23 @@ int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp
 	MLX5_SET(ads, addr_path, vhca_port_num, 1);
 	MLX5_SET(ads, addr_path, grh, 1);
 
-	ret = mlx5_core_create_qp(mdev, qp, in, inlen);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed creating IPoIB QP err : %d\n", ret);
-		goto out;
-	}
+	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
+	ret = mlx5_cmd_exec_inout(mdev, create_qp, in, out);
+	if (ret)
+		return ret;
 
-out:
-	kvfree(in);
-	return ret;
+	qp->qpn = MLX5_GET(create_qp_out, out, qpn);
+
+	return 0;
 }
 
 void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
-	mlx5_core_destroy_qp(mdev, qp);
+	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+
+	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	mlx5_cmd_exec_in(mdev, destroy_qp, in);
 }
 
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index c0ab9cf74929..88bc94a8b8f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -108,6 +108,7 @@ static void dr_qp_event(struct mlx5_core_qp *mqp, int event)
 static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 					 struct dr_qp_init_attr *attr)
 {
+	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
 	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
 	struct mlx5_wq_param wqp;
 	struct mlx5dr_qp *dr_qp;
@@ -180,13 +181,12 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 				  (__be64 *)MLX5_ADDR_OF(create_qp_in,
 							 in, pas));
 
-	err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen);
+	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	dr_qp->mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
 	kfree(in);
-
-	if (err) {
-		mlx5_core_warn(mdev, " Can't create QP\n");
+	if (err)
 		goto err_in;
-	}
 	dr_qp->mqp.event = dr_qp_event;
 	dr_qp->uar = attr->uar;
 
@@ -204,7 +204,13 @@ err_wq:
 static void dr_destroy_qp(struct mlx5_core_dev *mdev,
 			  struct mlx5dr_qp *dr_qp)
 {
-	mlx5_core_destroy_qp(mdev, &dr_qp->mqp);
+	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+	struct mlx5_core_qp *qp = &dr_qp->mqp;
+
+	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	mlx5_cmd_exec_in(mdev, destroy_qp, in);
+
 	kfree(dr_qp->sq.wqe_head);
 	mlx5_wq_destroy(&dr_qp->wq_ctrl);
 	kfree(dr_qp);
-- 
cgit v1.2.3


From 73a75b96fc9a79779ad7491b61d65f0bbae04d11 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 6 Apr 2020 08:40:52 +0300
Subject: net/mlx5: Remove empty QP and CQ events handlers

The QP and CQ events functions do nothing except printing some debug
messages. There is nothing to do with this knowledge and such events,
so remove them.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c   | 19 -------------------
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c    | 14 --------------
 2 files changed, 33 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 7c3e7232852e..1d49894399af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -362,23 +362,6 @@ static void mlx5_fpga_conn_arm_cq(struct mlx5_fpga_conn *conn)
 		    conn->fdev->conn_res.uar->map, conn->cq.wq.cc);
 }
 
-static void mlx5_fpga_conn_cq_event(struct mlx5_core_cq *mcq,
-				    enum mlx5_event event)
-{
-	struct mlx5_fpga_conn *conn;
-
-	conn = container_of(mcq, struct mlx5_fpga_conn, cq.mcq);
-	mlx5_fpga_warn(conn->fdev, "CQ event %u on CQ #%u\n", event, mcq->cqn);
-}
-
-static void mlx5_fpga_conn_event(struct mlx5_core_qp *mqp, int event)
-{
-	struct mlx5_fpga_conn *conn;
-
-	conn = container_of(mqp, struct mlx5_fpga_conn, qp.mqp);
-	mlx5_fpga_warn(conn->fdev, "QP event %u on QP #%u\n", event, mqp->qpn);
-}
-
 static inline void mlx5_fpga_conn_cqes(struct mlx5_fpga_conn *conn,
 				       unsigned int budget)
 {
@@ -493,7 +476,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	*conn->cq.mcq.arm_db    = 0;
 	conn->cq.mcq.vector     = 0;
 	conn->cq.mcq.comp       = mlx5_fpga_conn_cq_complete;
-	conn->cq.mcq.event      = mlx5_fpga_conn_cq_event;
 	conn->cq.mcq.irqn       = irqn;
 	conn->cq.mcq.uar        = fdev->conn_res.uar;
 	tasklet_init(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet,
@@ -607,7 +589,6 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 		goto err_sq_bufs;
 
 	conn->qp.mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
-	conn->qp.mqp.event = mlx5_fpga_conn_event;
 	mlx5_fpga_dbg(fdev, "Created QP #0x%x\n", conn->qp.mqp.qpn);
 
 	goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 88bc94a8b8f1..690e4181db4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -100,11 +100,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
 	return err == CQ_POLL_ERR ? err : npolled;
 }
 
-static void dr_qp_event(struct mlx5_core_qp *mqp, int event)
-{
-	pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn);
-}
-
 static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 					 struct dr_qp_init_attr *attr)
 {
@@ -187,7 +182,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	kfree(in);
 	if (err)
 		goto err_in;
-	dr_qp->mqp.event = dr_qp_event;
 	dr_qp->uar = attr->uar;
 
 	return dr_qp;
@@ -695,12 +689,6 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
 	return 0;
 }
 
-static void dr_cq_event(struct mlx5_core_cq *mcq,
-			enum mlx5_event event)
-{
-	pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
-}
-
 static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 				      struct mlx5_uars_page *uar,
 				      size_t ncqe)
@@ -761,8 +749,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
 
-	cq->mcq.event = dr_cq_event;
-
 	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
 
-- 
cgit v1.2.3


From acab4b88e93ceb467623b991bb4b1594c893667a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 4 Apr 2020 18:25:48 +0300
Subject: net/mlx5: Open-code modify QP in steering module

Remove dependency on qp.c from SW steering by open
coding modify QP interface.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c    | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 690e4181db4c..266b913d2f9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -585,8 +585,10 @@ static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,
 	MLX5_SET(qpc, qpc, rre, 1);
 	MLX5_SET(qpc, qpc, rwe, 1);
 
-	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc,
-				   &dr_qp->mqp);
+	MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
+	MLX5_SET(rst2init_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+	return mlx5_cmd_exec_in(mdev, rst2init_qp, in);
 }
 
 static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
@@ -600,12 +602,13 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
 
-	MLX5_SET(qpc, qpc, log_ack_req_freq, 0);
 	MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
 	MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
 
-	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc,
-				   &dr_qp->mqp);
+	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
+	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+	return mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
 }
 
 static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
@@ -636,8 +639,10 @@ static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
 	MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num);
 	MLX5_SET(qpc, qpc, min_rnr_nak, 1);
 
-	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc,
-				   &dr_qp->mqp);
+	MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
+	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+	return mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
 }
 
 static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
-- 
cgit v1.2.3


From a6532fd925b981863161275dea6fd26b2e2c02e4 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 6 Apr 2020 09:42:43 +0300
Subject: net/mlx5: Open-code modify QP in the FPGA module

Remove dependency on qp.c from the FPGA by open coding
modify QP interface.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    | 84 ++++++++--------------
 1 file changed, 28 insertions(+), 56 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 1d49894399af..b00d834d2dbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -657,30 +657,29 @@ static void mlx5_fpga_conn_destroy_qp(struct mlx5_fpga_conn *conn)
 	mlx5_wq_destroy(&conn->qp.wq_ctrl);
 }
 
-static inline int mlx5_fpga_conn_reset_qp(struct mlx5_fpga_conn *conn)
+static int mlx5_fpga_conn_reset_qp(struct mlx5_fpga_conn *conn)
 {
 	struct mlx5_core_dev *mdev = conn->fdev->mdev;
+	u32 in[MLX5_ST_SZ_DW(qp_2rst_in)] = {};
 
 	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to RST\n", conn->qp.mqp.qpn);
 
-	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, NULL,
-				   &conn->qp.mqp);
+	MLX5_SET(qp_2rst_in, in, opcode, MLX5_CMD_OP_2RST_QP);
+	MLX5_SET(qp_2rst_in, in, qpn, conn->qp.mqp.qpn);
+
+	return mlx5_cmd_exec_in(mdev, qp_2rst, in);
 }
 
-static inline int mlx5_fpga_conn_init_qp(struct mlx5_fpga_conn *conn)
+static int mlx5_fpga_conn_init_qp(struct mlx5_fpga_conn *conn)
 {
+	u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {};
 	struct mlx5_fpga_device *fdev = conn->fdev;
 	struct mlx5_core_dev *mdev = fdev->mdev;
-	u32 *qpc = NULL;
-	int err;
+	u32 *qpc;
 
 	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to INIT\n", conn->qp.mqp.qpn);
 
-	qpc = kzalloc(MLX5_ST_SZ_BYTES(qpc), GFP_KERNEL);
-	if (!qpc) {
-		err = -ENOMEM;
-		goto out;
-	}
+	qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
 
 	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
 	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
@@ -691,32 +690,22 @@ static inline int mlx5_fpga_conn_init_qp(struct mlx5_fpga_conn *conn)
 	MLX5_SET(qpc, qpc, cqn_rcv, conn->cq.mcq.cqn);
 	MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma);
 
-	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc,
-				  &conn->qp.mqp);
-	if (err) {
-		mlx5_fpga_warn(fdev, "qp_modify RST2INIT failed: %d\n", err);
-		goto out;
-	}
+	MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
+	MLX5_SET(rst2init_qp_in, in, qpn, conn->qp.mqp.qpn);
 
-out:
-	kfree(qpc);
-	return err;
+	return mlx5_cmd_exec_in(mdev, rst2init_qp, in);
 }
 
-static inline int mlx5_fpga_conn_rtr_qp(struct mlx5_fpga_conn *conn)
+static int mlx5_fpga_conn_rtr_qp(struct mlx5_fpga_conn *conn)
 {
+	u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
 	struct mlx5_fpga_device *fdev = conn->fdev;
 	struct mlx5_core_dev *mdev = fdev->mdev;
-	u32 *qpc = NULL;
-	int err;
+	u32 *qpc;
 
 	mlx5_fpga_dbg(conn->fdev, "QP RTR\n");
 
-	qpc = kzalloc(MLX5_ST_SZ_BYTES(qpc), GFP_KERNEL);
-	if (!qpc) {
-		err = -ENOMEM;
-		goto out;
-	}
+	qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc);
 
 	MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_1K_BYTES);
 	MLX5_SET(qpc, qpc, log_msg_max, (u8)MLX5_CAP_GEN(mdev, log_max_msg));
@@ -736,33 +725,22 @@ static inline int mlx5_fpga_conn_rtr_qp(struct mlx5_fpga_conn *conn)
 	       MLX5_ADDR_OF(fpga_qpc, conn->fpga_qpc, fpga_ip),
 	       MLX5_FLD_SZ_BYTES(qpc, primary_address_path.rgid_rip));
 
-	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc,
-				  &conn->qp.mqp);
-	if (err) {
-		mlx5_fpga_warn(fdev, "qp_modify RST2INIT failed: %d\n", err);
-		goto out;
-	}
+	MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
+	MLX5_SET(init2rtr_qp_in, in, qpn, conn->qp.mqp.qpn);
 
-out:
-	kfree(qpc);
-	return err;
+	return mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
 }
 
-static inline int mlx5_fpga_conn_rts_qp(struct mlx5_fpga_conn *conn)
+static int mlx5_fpga_conn_rts_qp(struct mlx5_fpga_conn *conn)
 {
 	struct mlx5_fpga_device *fdev = conn->fdev;
+	u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
 	struct mlx5_core_dev *mdev = fdev->mdev;
-	u32 *qpc = NULL;
-	u32 opt_mask;
-	int err;
+	u32 *qpc;
 
 	mlx5_fpga_dbg(conn->fdev, "QP RTS\n");
 
-	qpc = kzalloc(MLX5_ST_SZ_BYTES(qpc), GFP_KERNEL);
-	if (!qpc) {
-		err = -ENOMEM;
-		goto out;
-	}
+	qpc = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc);
 
 	MLX5_SET(qpc, qpc, log_ack_req_freq, 8);
 	MLX5_SET(qpc, qpc, min_rnr_nak, 0x12);
@@ -772,17 +750,11 @@ static inline int mlx5_fpga_conn_rts_qp(struct mlx5_fpga_conn *conn)
 	MLX5_SET(qpc, qpc, retry_count, 7);
 	MLX5_SET(qpc, qpc, rnr_retry, 7); /* Infinite retry if RNR NACK */
 
-	opt_mask = MLX5_QP_OPTPAR_RNR_TIMEOUT;
-	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, opt_mask, qpc,
-				  &conn->qp.mqp);
-	if (err) {
-		mlx5_fpga_warn(fdev, "qp_modify RST2INIT failed: %d\n", err);
-		goto out;
-	}
+	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
+	MLX5_SET(rtr2rts_qp_in, in, qpn, conn->qp.mqp.qpn);
+	MLX5_SET(rtr2rts_qp_in, in, opt_param_mask, MLX5_QP_OPTPAR_RNR_TIMEOUT);
 
-out:
-	kfree(qpc);
-	return err;
+	return mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
 }
 
 static int mlx5_fpga_conn_connect(struct mlx5_fpga_conn *conn)
-- 
cgit v1.2.3


From a452e0e43669d5223f3f2264d0d4f08acdba98c0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 6 Apr 2020 13:43:14 +0300
Subject: net/mlx5: Open-code modify QP in the IPoIB module

Remove dependency on qp.c from the IPoIB by open coding
modify QP interface.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  | 76 ++++++++++++----------
 1 file changed, 42 insertions(+), 34 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 8bca11cb1e19..83b198d8e3d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -161,44 +161,54 @@ int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5i_priv *ipriv = priv->ppriv;
 	struct mlx5_core_qp *qp = &ipriv->qp;
-	struct mlx5_qp_context *context;
 	int ret;
 
-	/* QP states */
-	context = kzalloc(sizeof(*context), GFP_KERNEL);
-	if (!context)
-		return -ENOMEM;
+	{
+		u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {};
+		u32 *qpc;
 
-	context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11);
-	context->pri_path.port = 1;
-	context->pri_path.pkey_index = cpu_to_be16(ipriv->pkey_index);
-	context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY);
+		qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
 
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret);
-		goto err_qp_modify_to_err;
-	}
-	memset(context, 0, sizeof(*context));
+		MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+		MLX5_SET(qpc, qpc, primary_address_path.pkey_index,
+			 ipriv->pkey_index);
+		MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, 1);
+		MLX5_SET(qpc, qpc, q_key, IB_DEFAULT_Q_KEY);
 
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret);
-		goto err_qp_modify_to_err;
+		MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
+		MLX5_SET(rst2init_qp_in, in, qpn, qp->qpn);
+		ret = mlx5_cmd_exec_in(mdev, rst2init_qp, in);
+		if (ret)
+			goto err_qp_modify_to_err;
 	}
-
-	ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp);
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret);
-		goto err_qp_modify_to_err;
+	{
+		u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
+
+		MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
+		MLX5_SET(init2rtr_qp_in, in, qpn, qp->qpn);
+		ret = mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
+		if (ret)
+			goto err_qp_modify_to_err;
+	}
+	{
+		u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
+
+		MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
+		MLX5_SET(rtr2rts_qp_in, in, qpn, qp->qpn);
+		ret = mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
+		if (ret)
+			goto err_qp_modify_to_err;
 	}
-
-	kfree(context);
 	return 0;
 
 err_qp_modify_to_err:
-	mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, &context, qp);
-	kfree(context);
+	{
+		u32 in[MLX5_ST_SZ_DW(qp_2err_in)] = {};
+
+		MLX5_SET(qp_2err_in, in, opcode, MLX5_CMD_OP_2ERR_QP);
+		MLX5_SET(qp_2err_in, in, qpn, qp->qpn);
+		mlx5_cmd_exec_in(mdev, qp_2err, in);
+	}
 	return ret;
 }
 
@@ -206,13 +216,11 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_qp_context context;
-	int err;
+	u32 in[MLX5_ST_SZ_DW(qp_2rst_in)] = {};
 
-	err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context,
-				  &ipriv->qp);
-	if (err)
-		mlx5_core_err(mdev, "Failed to modify qp 2RST, err: %d\n", err);
+	MLX5_SET(qp_2rst_in, in, opcode, MLX5_CMD_OP_2RST_QP);
+	MLX5_SET(qp_2rst_in, in, qpn, ipriv->qp.qpn);
+	mlx5_cmd_exec_in(mdev, qp_2rst, in);
 }
 
 #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2
-- 
cgit v1.2.3


From f93f4f4f31492468d5c6903e35cc0e31a9cb2c48 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 6 Apr 2020 11:17:44 +0300
Subject: net/mlx5: Remove extra indirection while storing QPN

The FPGA, SW steering and IPoIB need to have only QPN from the
mlx5_core_qp struct, so reduce memory footprint by storing QPN
directly.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    | 23 ++++-----
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.h    |  2 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  | 60 +++++++++++-----------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h  |  6 +--
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 19 +++----
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 19 ++++---
 .../mellanox/mlx5/core/steering/dr_types.h         |  2 +-
 7 files changed, 64 insertions(+), 67 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index b00d834d2dbf..182d3ac3e73f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -165,7 +165,7 @@ static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
 	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
 	ctrl->opmod_idx_opcode = cpu_to_be32(((conn->qp.sq.pc & 0xffff) << 8) |
 					     MLX5_OPCODE_SEND);
-	ctrl->qpn_ds = cpu_to_be32(size | (conn->qp.mqp.qpn << 8));
+	ctrl->qpn_ds = cpu_to_be32(size | (conn->qp.qpn << 8));
 
 	conn->qp.sq.pc++;
 	conn->qp.sq.bufs[ix] = buf;
@@ -588,8 +588,8 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn,
 	if (err)
 		goto err_sq_bufs;
 
-	conn->qp.mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
-	mlx5_fpga_dbg(fdev, "Created QP #0x%x\n", conn->qp.mqp.qpn);
+	conn->qp.qpn = MLX5_GET(create_qp_out, out, qpn);
+	mlx5_fpga_dbg(fdev, "Created QP #0x%x\n", conn->qp.qpn);
 
 	goto out;
 
@@ -644,10 +644,9 @@ static void mlx5_fpga_conn_destroy_qp(struct mlx5_fpga_conn *conn)
 {
 	struct mlx5_core_dev *dev = conn->fdev->mdev;
 	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
-	struct mlx5_core_qp *qp = &conn->qp.mqp;
 
 	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, in, qpn, conn->qp.qpn);
 	mlx5_cmd_exec_in(dev, destroy_qp, in);
 
 	mlx5_fpga_conn_free_recv_bufs(conn);
@@ -662,10 +661,10 @@ static int mlx5_fpga_conn_reset_qp(struct mlx5_fpga_conn *conn)
 	struct mlx5_core_dev *mdev = conn->fdev->mdev;
 	u32 in[MLX5_ST_SZ_DW(qp_2rst_in)] = {};
 
-	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to RST\n", conn->qp.mqp.qpn);
+	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to RST\n", conn->qp.qpn);
 
 	MLX5_SET(qp_2rst_in, in, opcode, MLX5_CMD_OP_2RST_QP);
-	MLX5_SET(qp_2rst_in, in, qpn, conn->qp.mqp.qpn);
+	MLX5_SET(qp_2rst_in, in, qpn, conn->qp.qpn);
 
 	return mlx5_cmd_exec_in(mdev, qp_2rst, in);
 }
@@ -677,7 +676,7 @@ static int mlx5_fpga_conn_init_qp(struct mlx5_fpga_conn *conn)
 	struct mlx5_core_dev *mdev = fdev->mdev;
 	u32 *qpc;
 
-	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to INIT\n", conn->qp.mqp.qpn);
+	mlx5_fpga_dbg(conn->fdev, "Modifying QP %u to INIT\n", conn->qp.qpn);
 
 	qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
 
@@ -691,7 +690,7 @@ static int mlx5_fpga_conn_init_qp(struct mlx5_fpga_conn *conn)
 	MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma);
 
 	MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
-	MLX5_SET(rst2init_qp_in, in, qpn, conn->qp.mqp.qpn);
+	MLX5_SET(rst2init_qp_in, in, qpn, conn->qp.qpn);
 
 	return mlx5_cmd_exec_in(mdev, rst2init_qp, in);
 }
@@ -726,7 +725,7 @@ static int mlx5_fpga_conn_rtr_qp(struct mlx5_fpga_conn *conn)
 	       MLX5_FLD_SZ_BYTES(qpc, primary_address_path.rgid_rip));
 
 	MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
-	MLX5_SET(init2rtr_qp_in, in, qpn, conn->qp.mqp.qpn);
+	MLX5_SET(init2rtr_qp_in, in, qpn, conn->qp.qpn);
 
 	return mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
 }
@@ -751,7 +750,7 @@ static int mlx5_fpga_conn_rts_qp(struct mlx5_fpga_conn *conn)
 	MLX5_SET(qpc, qpc, rnr_retry, 7); /* Infinite retry if RNR NACK */
 
 	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
-	MLX5_SET(rtr2rts_qp_in, in, qpn, conn->qp.mqp.qpn);
+	MLX5_SET(rtr2rts_qp_in, in, qpn, conn->qp.qpn);
 	MLX5_SET(rtr2rts_qp_in, in, opt_param_mask, MLX5_QP_OPTPAR_RNR_TIMEOUT);
 
 	return mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
@@ -894,7 +893,7 @@ struct mlx5_fpga_conn *mlx5_fpga_conn_create(struct mlx5_fpga_device *fdev,
 	MLX5_SET(fpga_qpc, conn->fpga_qpc, next_rcv_psn, 1);
 	MLX5_SET(fpga_qpc, conn->fpga_qpc, next_send_psn, 0);
 	MLX5_SET(fpga_qpc, conn->fpga_qpc, pkey, MLX5_FPGA_PKEY);
-	MLX5_SET(fpga_qpc, conn->fpga_qpc, remote_qpn, conn->qp.mqp.qpn);
+	MLX5_SET(fpga_qpc, conn->fpga_qpc, remote_qpn, conn->qp.qpn);
 	MLX5_SET(fpga_qpc, conn->fpga_qpc, rnr_retry, 7);
 	MLX5_SET(fpga_qpc, conn->fpga_qpc, retry_count, 7);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h
index 634ae10e287b..5116e869a6e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h
@@ -65,7 +65,7 @@ struct mlx5_fpga_conn {
 		int sgid_index;
 		struct mlx5_wq_qp wq;
 		struct mlx5_wq_ctrl wq_ctrl;
-		struct mlx5_core_qp mqp;
+		u32 qpn;
 		struct {
 			spinlock_t lock; /* Protects all SQ state */
 			unsigned int pc;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 83b198d8e3d6..068578be00f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -160,7 +160,6 @@ int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5i_priv *ipriv = priv->ppriv;
-	struct mlx5_core_qp *qp = &ipriv->qp;
 	int ret;
 
 	{
@@ -176,7 +175,7 @@ int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
 		MLX5_SET(qpc, qpc, q_key, IB_DEFAULT_Q_KEY);
 
 		MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
-		MLX5_SET(rst2init_qp_in, in, qpn, qp->qpn);
+		MLX5_SET(rst2init_qp_in, in, qpn, ipriv->qpn);
 		ret = mlx5_cmd_exec_in(mdev, rst2init_qp, in);
 		if (ret)
 			goto err_qp_modify_to_err;
@@ -185,7 +184,7 @@ int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
 		u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
 
 		MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
-		MLX5_SET(init2rtr_qp_in, in, qpn, qp->qpn);
+		MLX5_SET(init2rtr_qp_in, in, qpn, ipriv->qpn);
 		ret = mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
 		if (ret)
 			goto err_qp_modify_to_err;
@@ -194,7 +193,7 @@ int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
 		u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
 
 		MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
-		MLX5_SET(rtr2rts_qp_in, in, qpn, qp->qpn);
+		MLX5_SET(rtr2rts_qp_in, in, qpn, ipriv->qpn);
 		ret = mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
 		if (ret)
 			goto err_qp_modify_to_err;
@@ -206,7 +205,7 @@ err_qp_modify_to_err:
 		u32 in[MLX5_ST_SZ_DW(qp_2err_in)] = {};
 
 		MLX5_SET(qp_2err_in, in, opcode, MLX5_CMD_OP_2ERR_QP);
-		MLX5_SET(qp_2err_in, in, qpn, qp->qpn);
+		MLX5_SET(qp_2err_in, in, qpn, ipriv->qpn);
 		mlx5_cmd_exec_in(mdev, qp_2err, in);
 	}
 	return ret;
@@ -219,16 +218,17 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv)
 	u32 in[MLX5_ST_SZ_DW(qp_2rst_in)] = {};
 
 	MLX5_SET(qp_2rst_in, in, opcode, MLX5_CMD_OP_2RST_QP);
-	MLX5_SET(qp_2rst_in, in, qpn, ipriv->qp.qpn);
+	MLX5_SET(qp_2rst_in, in, qpn, ipriv->qpn);
 	mlx5_cmd_exec_in(mdev, qp_2rst, in);
 }
 
 #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2
 
-int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+int mlx5i_create_underlay_qp(struct mlx5e_priv *priv)
 {
 	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {};
+	struct mlx5i_priv *ipriv = priv->ppriv;
 	void *addr_path;
 	int ret = 0;
 	void *qpc;
@@ -244,21 +244,21 @@ int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp
 	MLX5_SET(ads, addr_path, grh, 1);
 
 	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
-	ret = mlx5_cmd_exec_inout(mdev, create_qp, in, out);
+	ret = mlx5_cmd_exec_inout(priv->mdev, create_qp, in, out);
 	if (ret)
 		return ret;
 
-	qp->qpn = MLX5_GET(create_qp_out, out, qpn);
+	ipriv->qpn = MLX5_GET(create_qp_out, out, qpn);
 
 	return 0;
 }
 
-void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
+void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
 
 	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, in, qpn, qpn);
 	mlx5_cmd_exec_in(mdev, destroy_qp, in);
 }
 
@@ -279,13 +279,13 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 	struct mlx5i_priv *ipriv = priv->ppriv;
 	int err;
 
-	err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp);
+	err = mlx5i_create_underlay_qp(priv);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create underlay QP failed, %d\n", err);
 		return err;
 	}
 
-	err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0][0]);
+	err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &priv->tisn[0][0]);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
 		goto err_destroy_underlay_qp;
@@ -294,7 +294,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 	return 0;
 
 err_destroy_underlay_qp:
-	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+	mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn);
 	return err;
 }
 
@@ -303,7 +303,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
 	struct mlx5i_priv *ipriv = priv->ppriv;
 
 	mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]);
-	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+	mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn);
 }
 
 static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
@@ -506,12 +506,12 @@ int mlx5i_dev_init(struct net_device *dev)
 	struct mlx5i_priv    *ipriv  = priv->ppriv;
 
 	/* Set dev address using underlay QP */
-	dev->dev_addr[1] = (ipriv->qp.qpn >> 16) & 0xff;
-	dev->dev_addr[2] = (ipriv->qp.qpn >>  8) & 0xff;
-	dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff;
+	dev->dev_addr[1] = (ipriv->qpn >> 16) & 0xff;
+	dev->dev_addr[2] = (ipriv->qpn >>  8) & 0xff;
+	dev->dev_addr[3] = (ipriv->qpn) & 0xff;
 
 	/* Add QPN to net-device mapping to HT */
-	mlx5i_pkey_add_qpn(dev ,ipriv->qp.qpn);
+	mlx5i_pkey_add_qpn(dev, ipriv->qpn);
 
 	return 0;
 }
@@ -538,7 +538,7 @@ void mlx5i_dev_cleanup(struct net_device *dev)
 	mlx5i_uninit_underlay_qp(priv);
 
 	/* Delete QPN to net-device mapping from HT */
-	mlx5i_pkey_del_qpn(dev, ipriv->qp.qpn);
+	mlx5i_pkey_del_qpn(dev, ipriv->qpn);
 }
 
 static int mlx5i_open(struct net_device *netdev)
@@ -558,7 +558,7 @@ static int mlx5i_open(struct net_device *netdev)
 		goto err_clear_state_opened_flag;
 	}
 
-	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qpn);
 	if (err) {
 		mlx5_core_warn(mdev, "attach underlay qp to ft failed, %d\n", err);
 		goto err_reset_qp;
@@ -575,7 +575,7 @@ static int mlx5i_open(struct net_device *netdev)
 	return 0;
 
 err_remove_fs_underlay_qp:
-	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 err_reset_qp:
 	mlx5i_uninit_underlay_qp(epriv);
 err_clear_state_opened_flag:
@@ -601,7 +601,7 @@ static int mlx5i_close(struct net_device *netdev)
 	clear_bit(MLX5E_STATE_OPENED, &epriv->state);
 
 	netif_carrier_off(epriv->netdev);
-	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 	mlx5e_deactivate_priv_channels(epriv);
 	mlx5e_close_channels(&epriv->channels);
 	mlx5i_uninit_underlay_qp(epriv);
@@ -620,11 +620,12 @@ static int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca,
 	struct mlx5i_priv    *ipriv = epriv->ppriv;
 	int err;
 
-	mlx5_core_dbg(mdev, "attaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw);
-	err = mlx5_core_attach_mcg(mdev, gid, ipriv->qp.qpn);
+	mlx5_core_dbg(mdev, "attaching QPN 0x%x, MGID %pI6\n", ipriv->qpn,
+		      gid->raw);
+	err = mlx5_core_attach_mcg(mdev, gid, ipriv->qpn);
 	if (err)
 		mlx5_core_warn(mdev, "failed attaching QPN 0x%x, MGID %pI6\n",
-			       ipriv->qp.qpn, gid->raw);
+			       ipriv->qpn, gid->raw);
 
 	if (set_qkey) {
 		mlx5_core_dbg(mdev, "%s setting qkey 0x%x\n",
@@ -643,12 +644,13 @@ static int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
 	struct mlx5i_priv    *ipriv = epriv->ppriv;
 	int err;
 
-	mlx5_core_dbg(mdev, "detaching QPN 0x%x, MGID %pI6\n", ipriv->qp.qpn, gid->raw);
+	mlx5_core_dbg(mdev, "detaching QPN 0x%x, MGID %pI6\n", ipriv->qpn,
+		      gid->raw);
 
-	err = mlx5_core_detach_mcg(mdev, gid, ipriv->qp.qpn);
+	err = mlx5_core_detach_mcg(mdev, gid, ipriv->qpn);
 	if (err)
 		mlx5_core_dbg(mdev, "failed detaching QPN 0x%x, MGID %pI6\n",
-			      ipriv->qp.qpn, gid->raw);
+			      ipriv->qpn, gid->raw);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index de7e01a027bb..3483ba642cfe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -51,7 +51,7 @@ extern const struct ethtool_ops mlx5i_pkey_ethtool_ops;
 /* ipoib rdma netdev's private data structure */
 struct mlx5i_priv {
 	struct rdma_netdev rn; /* keep this first */
-	struct mlx5_core_qp qp;
+	u32 qpn;
 	bool   sub_interface;
 	u32    qkey;
 	u16    pkey_index;
@@ -62,8 +62,8 @@ struct mlx5i_priv {
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn);
 
 /* Underlay QP create/destroy functions */
-int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
-void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
+int mlx5i_create_underlay_qp(struct mlx5e_priv *priv);
+void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn);
 
 /* Underlay QP state modification init/uninit functions */
 int mlx5i_init_underlay_qp(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 96e64187c089..b9af37ad40bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -204,13 +204,13 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 		goto err_release_lock;
 	}
 
-	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qpn);
 	if (err) {
 		mlx5_core_warn(mdev, "attach child underlay qp to ft failed, %d\n", err);
 		goto err_unint_underlay_qp;
 	}
 
-	err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0][0]);
+	err = mlx5i_create_tis(mdev, ipriv->qpn, &epriv->tisn[0][0]);
 	if (err) {
 		mlx5_core_warn(mdev, "create child tis failed, %d\n", err);
 		goto err_remove_rx_uderlay_qp;
@@ -230,7 +230,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 err_clear_state_opened_flag:
 	mlx5e_destroy_tis(mdev, epriv->tisn[0][0]);
 err_remove_rx_uderlay_qp:
-	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 err_unint_underlay_qp:
 	mlx5i_uninit_underlay_qp(epriv);
 err_release_lock:
@@ -253,7 +253,7 @@ static int mlx5i_pkey_close(struct net_device *netdev)
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
 	netif_carrier_off(priv->netdev);
-	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
+	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 	mlx5i_uninit_underlay_qp(priv);
 	mlx5e_deactivate_priv_channels(priv);
 	mlx5e_close_channels(&priv->channels);
@@ -307,23 +307,20 @@ static void mlx5i_pkey_cleanup(struct mlx5e_priv *priv)
 
 static int mlx5i_pkey_init_tx(struct mlx5e_priv *priv)
 {
-	struct mlx5i_priv *ipriv = priv->ppriv;
 	int err;
 
-	err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp);
-	if (err) {
+	err = mlx5i_create_underlay_qp(priv);
+	if (err)
 		mlx5_core_warn(priv->mdev, "create child underlay QP failed, %d\n", err);
-		return err;
-	}
 
-	return 0;
+	return err;
 }
 
 static void mlx5i_pkey_cleanup_tx(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
 
-	mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp);
+	mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn);
 }
 
 static int mlx5i_pkey_init_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 266b913d2f9a..c4ed25bb9ac8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -178,7 +178,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
 	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
-	dr_qp->mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
+	dr_qp->qpn = MLX5_GET(create_qp_out, out, qpn);
 	kfree(in);
 	if (err)
 		goto err_in;
@@ -199,10 +199,9 @@ static void dr_destroy_qp(struct mlx5_core_dev *mdev,
 			  struct mlx5dr_qp *dr_qp)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
-	struct mlx5_core_qp *qp = &dr_qp->mqp;
 
 	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, in, qpn, dr_qp->qpn);
 	mlx5_cmd_exec_in(mdev, destroy_qp, in);
 
 	kfree(dr_qp->sq.wqe_head);
@@ -242,7 +241,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
 		MLX5_WQE_CTRL_CQ_UPDATE : 0;
 	wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) |
 						opcode);
-	wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8);
+	wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->qpn << 8);
 	wq_raddr = (void *)(wq_ctrl + 1);
 	wq_raddr->raddr = cpu_to_be64(remote_addr);
 	wq_raddr->rkey = cpu_to_be32(rkey);
@@ -586,7 +585,7 @@ static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,
 	MLX5_SET(qpc, qpc, rwe, 1);
 
 	MLX5_SET(rst2init_qp_in, in, opcode, MLX5_CMD_OP_RST2INIT_QP);
-	MLX5_SET(rst2init_qp_in, in, qpn, dr_qp->mqp.qpn);
+	MLX5_SET(rst2init_qp_in, in, qpn, dr_qp->qpn);
 
 	return mlx5_cmd_exec_in(mdev, rst2init_qp, in);
 }
@@ -600,13 +599,13 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
 
 	qpc  = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc);
 
-	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn);
 
 	MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
 	MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
 
 	MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
-	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn);
 
 	return mlx5_cmd_exec_in(mdev, rtr2rts_qp, in);
 }
@@ -620,7 +619,7 @@ static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
 
 	qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc);
 
-	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->qpn);
 
 	MLX5_SET(qpc, qpc, mtu, attr->mtu);
 	MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1);
@@ -640,7 +639,7 @@ static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
 	MLX5_SET(qpc, qpc, min_rnr_nak, 1);
 
 	MLX5_SET(init2rtr_qp_in, in, opcode, MLX5_CMD_OP_INIT2RTR_QP);
-	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->qpn);
 
 	return mlx5_cmd_exec_in(mdev, init2rtr_qp, in);
 }
@@ -668,7 +667,7 @@ static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
 		return ret;
 
 	rtr_attr.mtu		= mtu;
-	rtr_attr.qp_num		= dr_qp->mqp.qpn;
+	rtr_attr.qp_num		= dr_qp->qpn;
 	rtr_attr.min_rnr_timer	= 12;
 	rtr_attr.port_num	= port;
 	rtr_attr.sgid_index	= gid_index;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 3fa739951b34..984783238baa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -990,7 +990,7 @@ struct mlx5dr_qp {
 	struct mlx5_wq_qp wq;
 	struct mlx5_uars_page *uar;
 	struct mlx5_wq_ctrl wq_ctrl;
-	struct mlx5_core_qp mqp;
+	u32 qpn;
 	struct {
 		unsigned int pc;
 		unsigned int cc;
-- 
cgit v1.2.3


From 57a6c5e992f5d6ab92764a7eaaba855f6d4b2df8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 6 Apr 2020 15:53:06 +0300
Subject: net/mlx5: Replace hand written QP context struct with automatic
 getters

By changing debugfs to not use any QP related API, convert the debugfs
code to use MLX5_GET() directly to access QP context instead of hand
written struct.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 51 +++++++++--------------
 1 file changed, 20 insertions(+), 31 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 04854e5fbcd7..d40c3d5bd496 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -202,42 +202,37 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev)
 static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 			 int index, int *is_str)
 {
-	int outlen = MLX5_ST_SZ_BYTES(query_qp_out);
-	struct mlx5_qp_context *ctx;
+	u32 out[MLX5_ST_SZ_BYTES(query_qp_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_qp_in)] = {};
 	u64 param = 0;
-	u32 *out;
+	int state;
+	u32 *qpc;
 	int err;
-	int no_sq;
 
-	out = kzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return param;
-
-	err = mlx5_core_qp_query(dev, qp, out, outlen);
-	if (err) {
-		mlx5_core_warn(dev, "failed to query qp err=%d\n", err);
-		goto out;
-	}
+	MLX5_SET(query_qp_in, in, opcode, MLX5_CMD_OP_QUERY_QP);
+	MLX5_SET(query_qp_in, in, qpn, qp->qpn);
+	err = mlx5_cmd_exec_inout(dev, query_qp, in, out);
+	if (err)
+		return 0;
 
 	*is_str = 0;
 
-	/* FIXME: use MLX5_GET rather than mlx5_qp_context manual struct */
-	ctx = (struct mlx5_qp_context *)MLX5_ADDR_OF(query_qp_out, out, qpc);
-
+	qpc = MLX5_ADDR_OF(query_qp_out, out, qpc);
 	switch (index) {
 	case QP_PID:
 		param = qp->pid;
 		break;
 	case QP_STATE:
-		param = (unsigned long)mlx5_qp_state_str(be32_to_cpu(ctx->flags) >> 28);
+		state = MLX5_GET(qpc, qpc, state);
+		param = (unsigned long)mlx5_qp_state_str(state);
 		*is_str = 1;
 		break;
 	case QP_XPORT:
-		param = (unsigned long)mlx5_qp_type_str((be32_to_cpu(ctx->flags) >> 16) & 0xff);
+		param = (unsigned long)mlx5_qp_type_str(MLX5_GET(qpc, qpc, st));
 		*is_str = 1;
 		break;
 	case QP_MTU:
-		switch (ctx->mtu_msgmax >> 5) {
+		switch (MLX5_GET(qpc, qpc, mtu)) {
 		case IB_MTU_256:
 			param = 256;
 			break;
@@ -258,29 +253,23 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 		}
 		break;
 	case QP_N_RECV:
-		param = 1 << ((ctx->rq_size_stride >> 3) & 0xf);
+		param = 1 << MLX5_GET(qpc, qpc, log_rq_size);
 		break;
 	case QP_RECV_SZ:
-		param = 1 << ((ctx->rq_size_stride & 7) + 4);
+		param = 1 << (MLX5_GET(qpc, qpc, log_rq_stride) + 4);
 		break;
 	case QP_N_SEND:
-		no_sq = be16_to_cpu(ctx->sq_crq_size) >> 15;
-		if (!no_sq)
-			param = 1 << (be16_to_cpu(ctx->sq_crq_size) >> 11);
-		else
-			param = 0;
+		if (!MLX5_GET(qpc, qpc, no_sq))
+			param = 1 << MLX5_GET(qpc, qpc, log_sq_size);
 		break;
 	case QP_LOG_PG_SZ:
-		param = (be32_to_cpu(ctx->log_pg_sz_remote_qpn) >> 24) & 0x1f;
-		param += 12;
+		param = MLX5_GET(qpc, qpc, log_page_size) + 12;
 		break;
 	case QP_RQPN:
-		param = be32_to_cpu(ctx->log_pg_sz_remote_qpn) & 0xffffff;
+		param = MLX5_GET(qpc, qpc, remote_qpn);
 		break;
 	}
 
-out:
-	kfree(out);
 	return param;
 }
 
-- 
cgit v1.2.3


From 66247fbb280c2a699a8621708c52dae6acd2e4bc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Fri, 3 Apr 2020 11:28:28 +0300
Subject: net/mlx5: Remove Q counter low level helper APIs

mlx5 core users are encouraged to use low level API (mlx5_cmd_exec)
without the need of helper functions, do this for q counters, remove
helper functions and call mlx5_cmd_exec directly from users.

This will help reduce the total amount of code and reduction of the
mlx5_core symbol table.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  | 55 +++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 39 +++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 35 +++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/qp.c       | 39 ---------------
 include/linux/mlx5/qp.h                            |  4 --
 5 files changed, 80 insertions(+), 92 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 6679756506e6..b02d027ebf3b 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -5439,15 +5439,21 @@ static bool is_mdev_switchdev_mode(const struct mlx5_core_dev *mdev)
 
 static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev)
 {
+	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
 	int num_cnt_ports;
 	int i;
 
 	num_cnt_ports = is_mdev_switchdev_mode(dev->mdev) ? 1 : dev->num_ports;
 
+	MLX5_SET(dealloc_q_counter_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
+
 	for (i = 0; i < num_cnt_ports; i++) {
-		if (dev->port[i].cnts.set_id_valid)
-			mlx5_core_dealloc_q_counter(dev->mdev,
-						    dev->port[i].cnts.set_id);
+		if (dev->port[i].cnts.set_id_valid) {
+			MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+				 dev->port[i].cnts.set_id);
+			mlx5_cmd_exec_in(dev->mdev, dealloc_q_counter, in);
+		}
 		kfree(dev->port[i].cnts.names);
 		kfree(dev->port[i].cnts.offsets);
 	}
@@ -5638,27 +5644,23 @@ static int mlx5_ib_query_q_counters(struct mlx5_core_dev *mdev,
 				    struct rdma_hw_stats *stats,
 				    u16 set_id)
 {
-	int outlen = MLX5_ST_SZ_BYTES(query_q_counter_out);
-	void *out;
+	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
 	__be32 val;
 	int ret, i;
 
-	out = kvzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	ret = mlx5_core_query_q_counter(mdev, set_id, 0, out, outlen);
+	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
+	MLX5_SET(query_q_counter_in, in, counter_set_id, set_id);
+	ret = mlx5_cmd_exec_inout(mdev, query_q_counter, in, out);
 	if (ret)
-		goto free;
+		return ret;
 
 	for (i = 0; i < cnts->num_q_counters; i++) {
-		val = *(__be32 *)(out + cnts->offsets[i]);
+		val = *(__be32 *)((void *)out + cnts->offsets[i]);
 		stats->value[i] = (u64)be32_to_cpu(val);
 	}
 
-free:
-	kvfree(out);
-	return ret;
+	return 0;
 }
 
 static int mlx5_ib_query_ext_ppcnt_counters(struct mlx5_ib_dev *dev,
@@ -5765,6 +5767,20 @@ static int mlx5_ib_counter_update_stats(struct rdma_counter *counter)
 					counter->stats, counter->id);
 }
 
+static int mlx5_ib_counter_dealloc(struct rdma_counter *counter)
+{
+	struct mlx5_ib_dev *dev = to_mdev(counter->device);
+	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
+
+	if (!counter->id)
+		return 0;
+
+	MLX5_SET(dealloc_q_counter_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
+	MLX5_SET(dealloc_q_counter_in, in, counter_set_id, counter->id);
+	return mlx5_cmd_exec_in(dev->mdev, dealloc_q_counter, in);
+}
+
 static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 				   struct ib_qp *qp)
 {
@@ -5788,7 +5804,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 	return 0;
 
 fail_set_counter:
-	mlx5_core_dealloc_q_counter(dev->mdev, cnt_set_id);
+	mlx5_ib_counter_dealloc(counter);
 	counter->id = 0;
 
 	return err;
@@ -5799,13 +5815,6 @@ static int mlx5_ib_counter_unbind_qp(struct ib_qp *qp)
 	return mlx5_ib_qp_set_counter(qp, NULL);
 }
 
-static int mlx5_ib_counter_dealloc(struct rdma_counter *counter)
-{
-	struct mlx5_ib_dev *dev = to_mdev(counter->device);
-
-	return mlx5_core_dealloc_q_counter(dev->mdev, counter->id);
-}
-
 static int mlx5_ib_rn_get_params(struct ib_device *device, u8 port_num,
 				 enum rdma_netdev_t type,
 				 struct rdma_netdev_alloc_params *params)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dd7f338425eb..30970b405040 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4997,29 +4997,40 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 {
+	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	err = mlx5_core_alloc_q_counter(mdev, &priv->q_counter);
-	if (err) {
-		mlx5_core_warn(mdev, "alloc queue counter failed, %d\n", err);
-		priv->q_counter = 0;
-	}
+	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
+	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
+	if (!err)
+		priv->q_counter =
+			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
 
-	err = mlx5_core_alloc_q_counter(mdev, &priv->drop_rq_q_counter);
-	if (err) {
-		mlx5_core_warn(mdev, "alloc drop RQ counter failed, %d\n", err);
-		priv->drop_rq_q_counter = 0;
-	}
+	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
+	if (!err)
+		priv->drop_rq_q_counter =
+			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
 }
 
 void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
 {
-	if (priv->q_counter)
-		mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
+	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
+
+	MLX5_SET(dealloc_q_counter_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
+	if (priv->q_counter) {
+		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+			 priv->q_counter);
+		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
+	}
 
-	if (priv->drop_rq_q_counter)
-		mlx5_core_dealloc_q_counter(priv->mdev, priv->drop_rq_q_counter);
+	if (priv->drop_rq_q_counter) {
+		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+			 priv->drop_rq_q_counter);
+		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
+	}
 }
 
 static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 30b216d9284c..ff4002ebad90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -411,18 +411,29 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt)
 {
 	struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
-	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)];
-
-	if (priv->q_counter &&
-	    !mlx5_core_query_q_counter(priv->mdev, priv->q_counter, 0, out,
-				       sizeof(out)))
-		qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out,
-						  out, out_of_buffer);
-	if (priv->drop_rq_q_counter &&
-	    !mlx5_core_query_q_counter(priv->mdev, priv->drop_rq_q_counter, 0,
-				       out, sizeof(out)))
-		qcnt->rx_if_down_packets = MLX5_GET(query_q_counter_out, out,
-						    out_of_buffer);
+	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
+	int ret;
+
+	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
+
+	if (priv->q_counter) {
+		MLX5_SET(query_q_counter_in, in, counter_set_id,
+			 priv->q_counter);
+		ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out);
+		if (!ret)
+			qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out,
+							  out, out_of_buffer);
+	}
+
+	if (priv->drop_rq_q_counter) {
+		MLX5_SET(query_q_counter_in, in, counter_set_id,
+			 priv->drop_rq_q_counter);
+		ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out);
+		if (!ret)
+			qcnt->rx_if_down_packets = MLX5_GET(query_q_counter_out,
+							    out, out_of_buffer);
+	}
 }
 
 #define VNIC_ENV_OFF(c) MLX5_BYTE_OFF(query_vnic_env_out, c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index c3aea4cc2fff..e36790ad5256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -680,45 +680,6 @@ void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_core_destroy_sq_tracked);
 
-int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id)
-{
-	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {0};
-	int err;
-
-	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (!err)
-		*counter_id = MLX5_GET(alloc_q_counter_out, out,
-				       counter_set_id);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_alloc_q_counter);
-
-int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id)
-{
-	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(dealloc_q_counter_out)] = {0};
-
-	MLX5_SET(dealloc_q_counter_in, in, opcode,
-		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
-	MLX5_SET(dealloc_q_counter_in, in, counter_set_id, counter_id);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_dealloc_q_counter);
-
-int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
-			      int reset, void *out, int out_size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {0};
-
-	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
-	MLX5_SET(query_q_counter_in, in, clear, reset);
-	MLX5_SET(query_q_counter_in, in, counter_set_id, counter_id);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_query_q_counter);
-
 struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
 						int res_num,
 						enum mlx5_res_type res_type)
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index ae63b1ae9004..4d25a3d24182 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -595,10 +595,6 @@ int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
 				struct mlx5_core_qp *sq);
 void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev,
 				  struct mlx5_core_qp *sq);
-int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id);
-int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id);
-int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
-			      int reset, void *out, int out_size);
 
 struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
 						int res_num,
-- 
cgit v1.2.3


From 9c275ee4ad82aeb1f51981fdc9ee16b74d4b101a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 7 Apr 2020 16:09:15 +0300
Subject: net/mlx5: Delete not-used cmd header

The structures defined in the cmd header are not used and can be safely
removed from the driver. This patch removes that file and deletes all
relevant includes.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/mad.c                       | 1 -
 drivers/infiniband/hw/mlx5/srq_cmd.c                   | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/cq.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/eq.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c     | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/fw.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/health.c       | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/mcg.c          | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/mr.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c    | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/pd.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/qp.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/rl.c           | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/uar.c          | 1 -
 15 files changed, 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 14e0c17de6a9..f0ab6d7d8497 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -30,7 +30,6 @@
  * SOFTWARE.
  */
 
-#include <linux/mlx5/cmd.h>
 #include <linux/mlx5/vport.h>
 #include <rdma/ib_mad.h>
 #include <rdma/ib_smi.h>
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index 8fc3630a9d4c..88c0388f9fc6 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -5,7 +5,6 @@
 
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_ib.h"
 #include "srq.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 818edc63e428..4477a590b308 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -34,7 +34,6 @@
 #include <linux/module.h>
 #include <linux/hardirq.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/cq.h>
 #include "mlx5_core.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index cccea3a8eddd..bee419d01af2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -36,7 +36,6 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/eq.h>
-#include <linux/mlx5/cmd.h>
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
index c0fd2212e890..09769401c313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
@@ -31,7 +31,6 @@
  */
 
 #include <linux/etherdevice.h>
-#include <linux/mlx5/cmd.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/device.h>
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 90e3d0233101..3040e0466681 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -31,7 +31,6 @@
  */
 
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include <linux/mlx5/eswitch.h>
 #include <linux/module.h>
 #include "mlx5_core.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index fa1665caac46..3ae355453464 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -36,7 +36,6 @@
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/mlx5.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
index 48b5c847b642..8809a65ecefb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -4,7 +4,6 @@
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/port.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 #include "lib/port_tun.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
index ba2b09cc192f..6789fe658037 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include <rdma/ib_verbs.h>
 #include "mlx5_core.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 366f2cbfc6db..1feedf335dea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 91bd258ecf1b..a3959754b927 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -35,7 +35,6 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pd.c b/drivers/net/ethernet/mellanox/mlx5/core/pd.c
index bd830d8d6c5f..b92d6f621c83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pd.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index e36790ad5256..d9df3a5dd532 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -32,7 +32,6 @@
 
 #include <linux/gfp.h>
 #include <linux/export.h>
-#include <linux/mlx5/cmd.h>
 #include <linux/mlx5/qp.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/transobj.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index f3b29d9ade1f..c9599f7c5696 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -33,7 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 /* Scheduling element fw management */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 0d006224d7b0..816f9c434359 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -34,7 +34,6 @@
 #include <linux/module.h>
 #include <linux/io-mapping.h>
 #include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
-- 
cgit v1.2.3


From 333fbaa0255b8d471fc7ae767ef3a1766c732d6d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sat, 4 Apr 2020 10:40:24 +0300
Subject: net/mlx5: Move QP logic to mlx5_ib

The mlx5_core doesn't need any functionality coded in qp.c, so move
that file to drivers/infiniband/ be under mlx5_ib responsibility.

Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/Makefile               |   1 +
 drivers/infiniband/hw/mlx5/cq.c                   |   3 +-
 drivers/infiniband/hw/mlx5/devx.c                 |  10 +-
 drivers/infiniband/hw/mlx5/main.c                 |  10 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h              |   2 +
 drivers/infiniband/hw/mlx5/odp.c                  |   3 +-
 drivers/infiniband/hw/mlx5/qp.c                   |  47 +-
 drivers/infiniband/hw/mlx5/qp.h                   |  46 ++
 drivers/infiniband/hw/mlx5/qpc.c                  | 605 +++++++++++++++++++
 drivers/infiniband/hw/mlx5/srq_cmd.c              |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c    |   4 -
 drivers/net/ethernet/mellanox/mlx5/core/qp.c      | 697 ----------------------
 include/linux/mlx5/cmd.h                          |  51 --
 include/linux/mlx5/driver.h                       |   2 -
 include/linux/mlx5/qp.h                           |  45 --
 17 files changed, 699 insertions(+), 836 deletions(-)
 create mode 100644 drivers/infiniband/hw/mlx5/qp.h
 create mode 100644 drivers/infiniband/hw/mlx5/qpc.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/qp.c
 delete mode 100644 include/linux/mlx5/cmd.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index 375b341be8a1..228be05fbaf8 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -13,6 +13,7 @@ mlx5_ib-y := ah.o \
 	     mem.o \
 	     mr.o \
 	     qp.o \
+	     qpc.o \
 	     restrack.o \
 	     srq.o \
 	     srq_cmd.o
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 146ba2966744..32c05730dfe9 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -36,6 +36,7 @@
 #include <rdma/ib_cache.h>
 #include "mlx5_ib.h"
 #include "srq.h"
+#include "qp.h"
 
 static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe)
 {
@@ -484,7 +485,7 @@ repoll:
 		 * because CQs will be locked while QPs are removed
 		 * from the table.
 		 */
-		mqp = __mlx5_qp_lookup(dev->mdev, qpn);
+		mqp = radix_tree_lookup(&dev->qp_table.tree, qpn);
 		*cur_qp = to_mibqp(mqp);
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 46e1ab771f10..35b98c2d64d5 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -14,6 +14,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/fs.h>
 #include "mlx5_ib.h"
+#include "qp.h"
 #include <linux/xarray.h>
 
 #define UVERBS_MODULE_NAME mlx5_ib
@@ -1356,7 +1357,7 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	}
 
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
-		ret = mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
+		ret = mlx5_core_destroy_dct(obj->ib_dev, &obj->core_dct);
 	else if (obj->flags & DEVX_OBJ_FLAGS_CQ)
 		ret = mlx5_core_destroy_cq(obj->ib_dev->mdev, &obj->core_cq);
 	else
@@ -1450,9 +1451,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 
 	if (opcode == MLX5_CMD_OP_CREATE_DCT) {
 		obj->flags |= DEVX_OBJ_FLAGS_DCT;
-		err = mlx5_core_create_dct(dev->mdev, &obj->core_dct,
-					   cmd_in, cmd_in_len,
-					   cmd_out, cmd_out_len);
+		err = mlx5_core_create_dct(dev, &obj->core_dct, cmd_in,
+					   cmd_in_len, cmd_out, cmd_out_len);
 	} else if (opcode == MLX5_CMD_OP_CREATE_CQ) {
 		obj->flags |= DEVX_OBJ_FLAGS_CQ;
 		obj->core_cq.comp = devx_cq_comp;
@@ -1499,7 +1499,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 
 obj_destroy:
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
-		mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
+		mlx5_core_destroy_dct(obj->ib_dev, &obj->core_dct);
 	else if (obj->flags & DEVX_OBJ_FLAGS_CQ)
 		mlx5_core_destroy_cq(obj->ib_dev->mdev, &obj->core_cq);
 	else
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 76ea756d846b..f10675213115 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -59,6 +59,7 @@
 #include "ib_rep.h"
 #include "cmd.h"
 #include "srq.h"
+#include "qp.h"
 #include <linux/mlx5/fs_helpers.h>
 #include <linux/mlx5/accel.h>
 #include <rdma/uverbs_std_types.h>
@@ -4632,8 +4633,7 @@ static void delay_drop_handler(struct work_struct *work)
 	atomic_inc(&delay_drop->events_cnt);
 
 	mutex_lock(&delay_drop->lock);
-	err = mlx5_core_set_delay_drop(delay_drop->dev->mdev,
-				       delay_drop->timeout);
+	err = mlx5_core_set_delay_drop(delay_drop->dev, delay_drop->timeout);
 	if (err) {
 		mlx5_ib_warn(delay_drop->dev, "Failed to set delay drop, timeout=%u\n",
 			     delay_drop->timeout);
@@ -7193,6 +7193,9 @@ static const struct mlx5_ib_profile pf_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
 		     mlx5_ib_stage_roce_init,
 		     mlx5_ib_stage_roce_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_QP,
+		     mlx5_init_qp_table,
+		     mlx5_cleanup_qp_table),
 	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
 		     mlx5_init_srq_table,
 		     mlx5_cleanup_srq_table),
@@ -7250,6 +7253,9 @@ const struct mlx5_ib_profile raw_eth_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
 		     mlx5_ib_stage_raw_eth_roce_init,
 		     mlx5_ib_stage_raw_eth_roce_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_QP,
+		     mlx5_init_qp_table,
+		     mlx5_cleanup_qp_table),
 	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
 		     mlx5_init_srq_table,
 		     mlx5_cleanup_srq_table),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index cb2a021aa93c..aaabb8a98eed 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -869,6 +869,7 @@ enum mlx5_ib_stages {
 	MLX5_IB_STAGE_CAPS,
 	MLX5_IB_STAGE_NON_DEFAULT_CB,
 	MLX5_IB_STAGE_ROCE,
+	MLX5_IB_STAGE_QP,
 	MLX5_IB_STAGE_SRQ,
 	MLX5_IB_STAGE_DEVICE_RESOURCES,
 	MLX5_IB_STAGE_DEVICE_NOTIFIER,
@@ -1064,6 +1065,7 @@ struct mlx5_ib_dev {
 	struct mlx5_dm		dm;
 	u16			devx_whitelist_uid;
 	struct mlx5_srq_table   srq_table;
+	struct mlx5_qp_table    qp_table;
 	struct mlx5_async_ctx   async_ctx;
 	struct mlx5_devx_event_table devx_event_table;
 	struct mlx5_var_table var_table;
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 3de7606d4a1a..16af1105cfcf 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -36,6 +36,7 @@
 
 #include "mlx5_ib.h"
 #include "cmd.h"
+#include "qp.h"
 
 #include <linux/mlx5/eq.h>
 
@@ -1219,7 +1220,7 @@ static inline struct mlx5_core_rsc_common *odp_get_rsc(struct mlx5_ib_dev *dev,
 	case MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE:
 	case MLX5_WQE_PF_TYPE_RESP:
 	case MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC:
-		common = mlx5_core_res_hold(dev->mdev, wq_num, MLX5_RES_QP);
+		common = mlx5_core_res_hold(dev, wq_num, MLX5_RES_QP);
 		break;
 	default:
 		break;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 1456db4b6295..3ecd1864b3c8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -39,6 +39,7 @@
 #include "mlx5_ib.h"
 #include "ib_rep.h"
 #include "cmd.h"
+#include "qp.h"
 
 /* not supported currently */
 static int wq_signature;
@@ -1336,7 +1337,7 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 	pas = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
 	mlx5_ib_populate_pas(dev, sq->ubuffer.umem, page_shift, pas, 0);
 
-	err = mlx5_core_create_sq_tracked(dev->mdev, in, inlen, &sq->base.mqp);
+	err = mlx5_core_create_sq_tracked(dev, in, inlen, &sq->base.mqp);
 
 	kvfree(in);
 
@@ -1356,7 +1357,7 @@ static void destroy_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 				     struct mlx5_ib_sq *sq)
 {
 	destroy_flow_rule_vport_sq(sq);
-	mlx5_core_destroy_sq_tracked(dev->mdev, &sq->base.mqp);
+	mlx5_core_destroy_sq_tracked(dev, &sq->base.mqp);
 	ib_umem_release(sq->ubuffer.umem);
 }
 
@@ -1426,7 +1427,7 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 	qp_pas = (__be64 *)MLX5_ADDR_OF(create_qp_in, qpin, pas);
 	memcpy(pas, qp_pas, rq_pas_size);
 
-	err = mlx5_core_create_rq_tracked(dev->mdev, in, inlen, &rq->base.mqp);
+	err = mlx5_core_create_rq_tracked(dev, in, inlen, &rq->base.mqp);
 
 	kvfree(in);
 
@@ -1436,7 +1437,7 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 static void destroy_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 				     struct mlx5_ib_rq *rq)
 {
-	mlx5_core_destroy_rq_tracked(dev->mdev, &rq->base.mqp);
+	mlx5_core_destroy_rq_tracked(dev, &rq->base.mqp);
 }
 
 static bool tunnel_offload_supported(struct mlx5_core_dev *dev)
@@ -2347,7 +2348,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		err = create_raw_packet_qp(dev, qp, in, inlen, pd, udata,
 					   &resp);
 	} else {
-		err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen);
+		err = mlx5_core_create_qp(dev, &base->mqp, in, inlen);
 	}
 
 	if (err) {
@@ -2513,8 +2514,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp->state != IB_QPS_RESET) {
 		if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET &&
 		    !(qp->flags & MLX5_IB_QP_UNDERLAY)) {
-			err = mlx5_core_qp_modify(dev->mdev,
-						  MLX5_CMD_OP_2RST_QP, 0,
+			err = mlx5_core_qp_modify(dev, MLX5_CMD_OP_2RST_QP, 0,
 						  NULL, &base->mqp);
 		} else {
 			struct mlx5_modify_raw_qp_param raw_qp_param = {
@@ -2555,7 +2555,7 @@ static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	    qp->flags & MLX5_IB_QP_UNDERLAY) {
 		destroy_raw_packet_qp(dev, qp);
 	} else {
-		err = mlx5_core_destroy_qp(dev->mdev, &base->mqp);
+		err = mlx5_core_destroy_qp(dev, &base->mqp);
 		if (err)
 			mlx5_ib_warn(dev, "failed to destroy QP 0x%x\n",
 				     base->mqp.qpn);
@@ -2818,7 +2818,7 @@ static int mlx5_ib_destroy_dct(struct mlx5_ib_qp *mqp)
 	if (mqp->state == IB_QPS_RTR) {
 		int err;
 
-		err = mlx5_core_destroy_dct(dev->mdev, &mqp->dct.mdct);
+		err = mlx5_core_destroy_dct(dev, &mqp->dct.mdct);
 		if (err) {
 			mlx5_ib_warn(dev, "failed to destroy DCT %d\n", err);
 			return err;
@@ -3462,10 +3462,9 @@ static int __mlx5_ib_qp_set_counter(struct ib_qp *qp,
 	base = &mqp->trans_qp.base;
 	context.qp_counter_set_usr_page &= cpu_to_be32(0xffffff);
 	context.qp_counter_set_usr_page |= cpu_to_be32(set_id << 24);
-	return mlx5_core_qp_modify(dev->mdev,
-				   MLX5_CMD_OP_RTS2RTS_QP,
-				   MLX5_QP_OPTPAR_COUNTER_SET_ID,
-				   &context, &base->mqp);
+	return mlx5_core_qp_modify(dev, MLX5_CMD_OP_RTS2RTS_QP,
+				   MLX5_QP_OPTPAR_COUNTER_SET_ID, &context,
+				   &base->mqp);
 }
 
 static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
@@ -3752,8 +3751,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 
 		err = modify_raw_packet_qp(dev, qp, &raw_qp_param, tx_affinity);
 	} else {
-		err = mlx5_core_qp_modify(dev->mdev, op, optpar, context,
-					  &base->mqp);
+		err = mlx5_core_qp_modify(dev, op, optpar, context, &base->mqp);
 	}
 
 	if (err)
@@ -3927,7 +3925,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index);
 		MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
 
-		err = mlx5_core_create_dct(dev->mdev, &qp->dct.mdct, qp->dct.in,
+		err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in,
 					   MLX5_ST_SZ_BYTES(create_dct_in), out,
 					   sizeof(out));
 		if (err)
@@ -3935,7 +3933,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		resp.dctn = qp->dct.mdct.mqp.qpn;
 		err = ib_copy_to_udata(udata, &resp, resp.response_length);
 		if (err) {
-			mlx5_core_destroy_dct(dev->mdev, &qp->dct.mdct);
+			mlx5_core_destroy_dct(dev, &qp->dct.mdct);
 			return err;
 		}
 	} else {
@@ -5697,8 +5695,7 @@ static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (!outb)
 		return -ENOMEM;
 
-	err = mlx5_core_qp_query(dev->mdev, &qp->trans_qp.base.mqp, outb,
-				 outlen);
+	err = mlx5_core_qp_query(dev, &qp->trans_qp.base.mqp, outb, outlen);
 	if (err)
 		goto out;
 
@@ -5776,7 +5773,7 @@ static int mlx5_ib_dct_query_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *mqp,
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_core_dct_query(dev->mdev, dct, out, outlen);
+	err = mlx5_core_dct_query(dev, dct, out, outlen);
 	if (err)
 		goto out;
 
@@ -5962,7 +5959,7 @@ static int set_delay_drop(struct mlx5_ib_dev *dev)
 	if (dev->delay_drop.activate)
 		goto out;
 
-	err = mlx5_core_set_delay_drop(dev->mdev, dev->delay_drop.timeout);
+	err = mlx5_core_set_delay_drop(dev, dev->delay_drop.timeout);
 	if (err)
 		goto out;
 
@@ -6068,13 +6065,13 @@ static int  create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
 	}
 	rq_pas0 = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
 	mlx5_ib_populate_pas(dev, rwq->umem, rwq->page_shift, rq_pas0, 0);
-	err = mlx5_core_create_rq_tracked(dev->mdev, in, inlen, &rwq->core_qp);
+	err = mlx5_core_create_rq_tracked(dev, in, inlen, &rwq->core_qp);
 	if (!err && init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP) {
 		err = set_delay_drop(dev);
 		if (err) {
 			mlx5_ib_warn(dev, "Failed to enable delay drop err=%d\n",
 				     err);
-			mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
+			mlx5_core_destroy_rq_tracked(dev, &rwq->core_qp);
 		} else {
 			rwq->create_flags |= MLX5_IB_WQ_FLAGS_DELAY_DROP;
 		}
@@ -6256,7 +6253,7 @@ struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
 	return &rwq->ibwq;
 
 err_copy:
-	mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
+	mlx5_core_destroy_rq_tracked(dev, &rwq->core_qp);
 err_user_rq:
 	destroy_user_rq(dev, pd, rwq, udata);
 err:
@@ -6269,7 +6266,7 @@ void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
 	struct mlx5_ib_dev *dev = to_mdev(wq->device);
 	struct mlx5_ib_rwq *rwq = to_mrwq(wq);
 
-	mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
+	mlx5_core_destroy_rq_tracked(dev, &rwq->core_qp);
 	destroy_user_rq(dev, wq->pd, rwq, udata);
 	kfree(rwq);
 }
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
new file mode 100644
index 000000000000..ad9d76e3e18a
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2013-2020, Mellanox Technologies inc. All rights reserved.
+ */
+
+#ifndef _MLX5_IB_QP_H
+#define _MLX5_IB_QP_H
+
+#include "mlx5_ib.h"
+
+int mlx5_init_qp_table(struct mlx5_ib_dev *dev);
+void mlx5_cleanup_qp_table(struct mlx5_ib_dev *dev);
+
+int mlx5_core_create_dct(struct mlx5_ib_dev *dev, struct mlx5_core_dct *qp,
+			 u32 *in, int inlen, u32 *out, int outlen);
+int mlx5_core_create_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
+			u32 *in, int inlen);
+int mlx5_core_qp_modify(struct mlx5_ib_dev *dev, u16 opcode, u32 opt_param_mask,
+			void *qpc, struct mlx5_core_qp *qp);
+int mlx5_core_destroy_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp);
+int mlx5_core_destroy_dct(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct);
+int mlx5_core_qp_query(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
+		       u32 *out, int outlen);
+int mlx5_core_dct_query(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct,
+			u32 *out, int outlen);
+
+int mlx5_core_set_delay_drop(struct mlx5_ib_dev *dev, u32 timeout_usec);
+
+void mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_qp *rq);
+int mlx5_core_create_sq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen,
+				struct mlx5_core_qp *sq);
+void mlx5_core_destroy_sq_tracked(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_qp *sq);
+
+int mlx5_core_create_rq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen,
+				struct mlx5_core_qp *rq);
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_ib_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type);
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
+
+int mlx5_core_xrcd_alloc(struct mlx5_ib_dev *dev, u32 *xrcdn);
+int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
+#endif /* _MLX5_IB_QP_H */
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
new file mode 100644
index 000000000000..ea62735042f0
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2013-2020, Mellanox Technologies inc. All rights reserved.
+ */
+
+#include <linux/gfp.h>
+#include <linux/mlx5/qp.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_ib.h"
+#include "qp.h"
+
+static int mlx5_core_drain_dct(struct mlx5_ib_dev *dev,
+			       struct mlx5_core_dct *dct);
+
+static struct mlx5_core_rsc_common *
+mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
+{
+	struct mlx5_core_rsc_common *common;
+	unsigned long flags;
+
+	spin_lock_irqsave(&table->lock, flags);
+
+	common = radix_tree_lookup(&table->tree, rsn);
+	if (common)
+		refcount_inc(&common->refcount);
+
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	return common;
+}
+
+void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common)
+{
+	if (refcount_dec_and_test(&common->refcount))
+		complete(&common->free);
+}
+
+static u64 qp_allowed_event_types(void)
+{
+	u64 mask;
+
+	mask = BIT(MLX5_EVENT_TYPE_PATH_MIG) |
+	       BIT(MLX5_EVENT_TYPE_COMM_EST) |
+	       BIT(MLX5_EVENT_TYPE_SQ_DRAINED) |
+	       BIT(MLX5_EVENT_TYPE_SRQ_LAST_WQE) |
+	       BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR) |
+	       BIT(MLX5_EVENT_TYPE_PATH_MIG_FAILED) |
+	       BIT(MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR) |
+	       BIT(MLX5_EVENT_TYPE_WQ_ACCESS_ERROR);
+
+	return mask;
+}
+
+static u64 rq_allowed_event_types(void)
+{
+	u64 mask;
+
+	mask = BIT(MLX5_EVENT_TYPE_SRQ_LAST_WQE) |
+	       BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR);
+
+	return mask;
+}
+
+static u64 sq_allowed_event_types(void)
+{
+	return BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR);
+}
+
+static u64 dct_allowed_event_types(void)
+{
+	return BIT(MLX5_EVENT_TYPE_DCT_DRAINED);
+}
+
+static bool is_event_type_allowed(int rsc_type, int event_type)
+{
+	switch (rsc_type) {
+	case MLX5_EVENT_QUEUE_TYPE_QP:
+		return BIT(event_type) & qp_allowed_event_types();
+	case MLX5_EVENT_QUEUE_TYPE_RQ:
+		return BIT(event_type) & rq_allowed_event_types();
+	case MLX5_EVENT_QUEUE_TYPE_SQ:
+		return BIT(event_type) & sq_allowed_event_types();
+	case MLX5_EVENT_QUEUE_TYPE_DCT:
+		return BIT(event_type) & dct_allowed_event_types();
+	default:
+		WARN(1, "Event arrived for unknown resource type");
+		return false;
+	}
+}
+
+static int rsc_event_notifier(struct notifier_block *nb,
+			      unsigned long type, void *data)
+{
+	struct mlx5_core_rsc_common *common;
+	struct mlx5_qp_table *table;
+	struct mlx5_core_dct *dct;
+	u8 event_type = (u8)type;
+	struct mlx5_core_qp *qp;
+	struct mlx5_eqe *eqe;
+	u32 rsn;
+
+	switch (event_type) {
+	case MLX5_EVENT_TYPE_DCT_DRAINED:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
+		rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
+		break;
+	case MLX5_EVENT_TYPE_PATH_MIG:
+	case MLX5_EVENT_TYPE_COMM_EST:
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+		rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	table = container_of(nb, struct mlx5_qp_table, nb);
+	common = mlx5_get_rsc(table, rsn);
+	if (!common)
+		return NOTIFY_OK;
+
+	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type))
+		goto out;
+
+	switch (common->res) {
+	case MLX5_RES_QP:
+	case MLX5_RES_RQ:
+	case MLX5_RES_SQ:
+		qp = (struct mlx5_core_qp *)common;
+		qp->event(qp, event_type);
+		break;
+	case MLX5_RES_DCT:
+		dct = (struct mlx5_core_dct *)common;
+		if (event_type == MLX5_EVENT_TYPE_DCT_DRAINED)
+			complete(&dct->drained);
+		break;
+	default:
+		break;
+	}
+out:
+	mlx5_core_put_rsc(common);
+
+	return NOTIFY_OK;
+}
+
+static int create_resource_common(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_qp *qp, int rsc_type)
+{
+	struct mlx5_qp_table *table = &dev->qp_table;
+	int err;
+
+	qp->common.res = rsc_type;
+	spin_lock_irq(&table->lock);
+	err = radix_tree_insert(&table->tree,
+				qp->qpn | (rsc_type << MLX5_USER_INDEX_LEN),
+				qp);
+	spin_unlock_irq(&table->lock);
+	if (err)
+		return err;
+
+	refcount_set(&qp->common.refcount, 1);
+	init_completion(&qp->common.free);
+	qp->pid = current->pid;
+
+	return 0;
+}
+
+static void destroy_resource_common(struct mlx5_ib_dev *dev,
+				    struct mlx5_core_qp *qp)
+{
+	struct mlx5_qp_table *table = &dev->qp_table;
+	unsigned long flags;
+
+	spin_lock_irqsave(&table->lock, flags);
+	radix_tree_delete(&table->tree,
+			  qp->qpn | (qp->common.res << MLX5_USER_INDEX_LEN));
+	spin_unlock_irqrestore(&table->lock, flags);
+	mlx5_core_put_rsc((struct mlx5_core_rsc_common *)qp);
+	wait_for_completion(&qp->common.free);
+}
+
+static int _mlx5_core_destroy_dct(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_dct *dct, bool need_cleanup)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)] = {};
+	struct mlx5_core_qp *qp = &dct->mqp;
+	int err;
+
+	err = mlx5_core_drain_dct(dev, dct);
+	if (err) {
+		if (dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+			goto destroy;
+
+		return err;
+	}
+	wait_for_completion(&dct->drained);
+destroy:
+	if (need_cleanup)
+		destroy_resource_common(dev, &dct->mqp);
+	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
+	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
+	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
+	err = mlx5_cmd_exec_in(dev->mdev, destroy_dct, in);
+	return err;
+}
+
+int mlx5_core_create_dct(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct,
+			 u32 *in, int inlen, u32 *out, int outlen)
+{
+	struct mlx5_core_qp *qp = &dct->mqp;
+	int err;
+
+	init_completion(&dct->drained);
+	MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
+
+	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, outlen);
+	if (err)
+		return err;
+
+	qp->qpn = MLX5_GET(create_dct_out, out, dctn);
+	qp->uid = MLX5_GET(create_dct_in, in, uid);
+	err = create_resource_common(dev, qp, MLX5_RES_DCT);
+	if (err)
+		goto err_cmd;
+
+	return 0;
+err_cmd:
+	_mlx5_core_destroy_dct(dev, dct, false);
+	return err;
+}
+
+int mlx5_core_create_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
+			u32 *in, int inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
+	u32 din[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+	int err;
+
+	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
+
+	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
+	if (err)
+		return err;
+
+	qp->uid = MLX5_GET(create_qp_in, in, uid);
+	qp->qpn = MLX5_GET(create_qp_out, out, qpn);
+
+	err = create_resource_common(dev, qp, MLX5_RES_QP);
+	if (err)
+		goto err_cmd;
+
+	mlx5_debug_qp_add(dev->mdev, qp);
+
+	return 0;
+
+err_cmd:
+	MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, din, uid, qp->uid);
+	mlx5_cmd_exec_in(dev->mdev, destroy_qp, din);
+	return err;
+}
+
+static int mlx5_core_drain_dct(struct mlx5_ib_dev *dev,
+			       struct mlx5_core_dct *dct)
+{
+	u32 in[MLX5_ST_SZ_DW(drain_dct_in)] = {};
+	struct mlx5_core_qp *qp = &dct->mqp;
+
+	MLX5_SET(drain_dct_in, in, opcode, MLX5_CMD_OP_DRAIN_DCT);
+	MLX5_SET(drain_dct_in, in, dctn, qp->qpn);
+	MLX5_SET(drain_dct_in, in, uid, qp->uid);
+	return mlx5_cmd_exec_in(dev->mdev, drain_dct, in);
+}
+
+int mlx5_core_destroy_dct(struct mlx5_ib_dev *dev,
+			  struct mlx5_core_dct *dct)
+{
+	return _mlx5_core_destroy_dct(dev, dct, true);
+}
+
+int mlx5_core_destroy_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+
+	mlx5_debug_qp_remove(dev->mdev, qp);
+
+	destroy_resource_common(dev, qp);
+
+	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, in, uid, qp->uid);
+	mlx5_cmd_exec_in(dev->mdev, destroy_qp, in);
+	return 0;
+}
+
+int mlx5_core_set_delay_drop(struct mlx5_ib_dev *dev,
+			     u32 timeout_usec)
+{
+	u32 in[MLX5_ST_SZ_DW(set_delay_drop_params_in)] = {};
+
+	MLX5_SET(set_delay_drop_params_in, in, opcode,
+		 MLX5_CMD_OP_SET_DELAY_DROP_PARAMS);
+	MLX5_SET(set_delay_drop_params_in, in, delay_drop_timeout,
+		 timeout_usec / 100);
+	return mlx5_cmd_exec_in(dev->mdev, set_delay_drop_params, in);
+}
+
+struct mbox_info {
+	u32 *in;
+	u32 *out;
+	int inlen;
+	int outlen;
+};
+
+static int mbox_alloc(struct mbox_info *mbox, int inlen, int outlen)
+{
+	mbox->inlen  = inlen;
+	mbox->outlen = outlen;
+	mbox->in = kzalloc(mbox->inlen, GFP_KERNEL);
+	mbox->out = kzalloc(mbox->outlen, GFP_KERNEL);
+	if (!mbox->in || !mbox->out) {
+		kfree(mbox->in);
+		kfree(mbox->out);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void mbox_free(struct mbox_info *mbox)
+{
+	kfree(mbox->in);
+	kfree(mbox->out);
+}
+
+static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
+				u32 opt_param_mask, void *qpc,
+				struct mbox_info *mbox, u16 uid)
+{
+	mbox->out = NULL;
+	mbox->in = NULL;
+
+#define MBOX_ALLOC(mbox, typ)  \
+	mbox_alloc(mbox, MLX5_ST_SZ_BYTES(typ##_in), MLX5_ST_SZ_BYTES(typ##_out))
+
+#define MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid)                            \
+	do {                                                                   \
+		MLX5_SET(typ##_in, in, opcode, _opcode);                       \
+		MLX5_SET(typ##_in, in, qpn, _qpn);                             \
+		MLX5_SET(typ##_in, in, uid, _uid);                             \
+	} while (0)
+
+#define MOD_QP_IN_SET_QPC(typ, in, _opcode, _qpn, _opt_p, _qpc, _uid)          \
+	do {                                                                   \
+		MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid);                   \
+		MLX5_SET(typ##_in, in, opt_param_mask, _opt_p);                \
+		memcpy(MLX5_ADDR_OF(typ##_in, in, qpc), _qpc,                  \
+		       MLX5_ST_SZ_BYTES(qpc));                                 \
+	} while (0)
+
+	switch (opcode) {
+	/* 2RST & 2ERR */
+	case MLX5_CMD_OP_2RST_QP:
+		if (MBOX_ALLOC(mbox, qp_2rst))
+			return -ENOMEM;
+		MOD_QP_IN_SET(qp_2rst, mbox->in, opcode, qpn, uid);
+		break;
+	case MLX5_CMD_OP_2ERR_QP:
+		if (MBOX_ALLOC(mbox, qp_2err))
+			return -ENOMEM;
+		MOD_QP_IN_SET(qp_2err, mbox->in, opcode, qpn, uid);
+		break;
+
+	/* MODIFY with QPC */
+	case MLX5_CMD_OP_RST2INIT_QP:
+		if (MBOX_ALLOC(mbox, rst2init_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	case MLX5_CMD_OP_INIT2RTR_QP:
+		if (MBOX_ALLOC(mbox, init2rtr_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	case MLX5_CMD_OP_RTR2RTS_QP:
+		if (MBOX_ALLOC(mbox, rtr2rts_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	case MLX5_CMD_OP_RTS2RTS_QP:
+		if (MBOX_ALLOC(mbox, rts2rts_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(rts2rts_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	case MLX5_CMD_OP_SQERR2RTS_QP:
+		if (MBOX_ALLOC(mbox, sqerr2rts_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(sqerr2rts_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	case MLX5_CMD_OP_INIT2INIT_QP:
+		if (MBOX_ALLOC(mbox, init2init_qp))
+			return -ENOMEM;
+		MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn,
+				  opt_param_mask, qpc, uid);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int mlx5_core_qp_modify(struct mlx5_ib_dev *dev, u16 opcode, u32 opt_param_mask,
+			void *qpc, struct mlx5_core_qp *qp)
+{
+	struct mbox_info mbox;
+	int err;
+
+	err = modify_qp_mbox_alloc(dev->mdev, opcode, qp->qpn,
+				   opt_param_mask, qpc, &mbox, qp->uid);
+	if (err)
+		return err;
+
+	err = mlx5_cmd_exec(dev->mdev, mbox.in, mbox.inlen, mbox.out,
+			    mbox.outlen);
+	mbox_free(&mbox);
+	return err;
+}
+
+int mlx5_init_qp_table(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_qp_table *table = &dev->qp_table;
+
+	spin_lock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+	mlx5_qp_debugfs_init(dev->mdev);
+
+	table->nb.notifier_call = rsc_event_notifier;
+	mlx5_notifier_register(dev->mdev, &table->nb);
+
+	return 0;
+}
+
+void mlx5_cleanup_qp_table(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_qp_table *table = &dev->qp_table;
+
+	mlx5_notifier_unregister(dev->mdev, &table->nb);
+	mlx5_qp_debugfs_cleanup(dev->mdev);
+}
+
+int mlx5_core_qp_query(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
+		       u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_qp_in)] = {};
+
+	MLX5_SET(query_qp_in, in, opcode, MLX5_CMD_OP_QUERY_QP);
+	MLX5_SET(query_qp_in, in, qpn, qp->qpn);
+	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_core_dct_query(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct,
+			u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_dct_in)] = {};
+	struct mlx5_core_qp *qp = &dct->mqp;
+
+	MLX5_SET(query_dct_in, in, opcode, MLX5_CMD_OP_QUERY_DCT);
+	MLX5_SET(query_dct_in, in, dctn, qp->qpn);
+
+	return mlx5_cmd_exec(dev->mdev, (void *)&in, sizeof(in), (void *)out,
+			     outlen);
+}
+
+int mlx5_core_xrcd_alloc(struct mlx5_ib_dev *dev, u32 *xrcdn)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_xrcd_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_xrcd_in)] = {};
+	int err;
+
+	MLX5_SET(alloc_xrcd_in, in, opcode, MLX5_CMD_OP_ALLOC_XRCD);
+	err = mlx5_cmd_exec_inout(dev->mdev, alloc_xrcd, in, out);
+	if (!err)
+		*xrcdn = MLX5_GET(alloc_xrcd_out, out, xrcd);
+	return err;
+}
+
+int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_xrcd_in)] = {};
+
+	MLX5_SET(dealloc_xrcd_in, in, opcode, MLX5_CMD_OP_DEALLOC_XRCD);
+	MLX5_SET(dealloc_xrcd_in, in, xrcd, xrcdn);
+	return mlx5_cmd_exec_in(dev->mdev, dealloc_xrcd, in);
+}
+
+static void destroy_rq_tracked(struct mlx5_ib_dev *dev, u32 rqn, u16 uid)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rq_in)] = {};
+
+	MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ);
+	MLX5_SET(destroy_rq_in, in, rqn, rqn);
+	MLX5_SET(destroy_rq_in, in, uid, uid);
+	mlx5_cmd_exec_in(dev->mdev, destroy_rq, in);
+}
+
+int mlx5_core_create_rq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen,
+				struct mlx5_core_qp *rq)
+{
+	int err;
+	u32 rqn;
+
+	err = mlx5_core_create_rq(dev->mdev, in, inlen, &rqn);
+	if (err)
+		return err;
+
+	rq->uid = MLX5_GET(create_rq_in, in, uid);
+	rq->qpn = rqn;
+	err = create_resource_common(dev, rq, MLX5_RES_RQ);
+	if (err)
+		goto err_destroy_rq;
+
+	return 0;
+
+err_destroy_rq:
+	destroy_rq_tracked(dev, rq->qpn, rq->uid);
+
+	return err;
+}
+
+void mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_qp *rq)
+{
+	destroy_resource_common(dev, rq);
+	destroy_rq_tracked(dev, rq->qpn, rq->uid);
+}
+
+static void destroy_sq_tracked(struct mlx5_ib_dev *dev, u32 sqn, u16 uid)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_sq_in)] = {};
+
+	MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ);
+	MLX5_SET(destroy_sq_in, in, sqn, sqn);
+	MLX5_SET(destroy_sq_in, in, uid, uid);
+	mlx5_cmd_exec_in(dev->mdev, destroy_sq, in);
+}
+
+int mlx5_core_create_sq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen,
+				struct mlx5_core_qp *sq)
+{
+	u32 out[MLX5_ST_SZ_DW(create_sq_out)] = {};
+	int err;
+
+	MLX5_SET(create_sq_in, in, opcode, MLX5_CMD_OP_CREATE_SQ);
+	err = mlx5_cmd_exec(dev->mdev, in, inlen, out, sizeof(out));
+	if (err)
+		return err;
+
+	sq->qpn = MLX5_GET(create_sq_out, out, sqn);
+	sq->uid = MLX5_GET(create_sq_in, in, uid);
+	err = create_resource_common(dev, sq, MLX5_RES_SQ);
+	if (err)
+		goto err_destroy_sq;
+
+	return 0;
+
+err_destroy_sq:
+	destroy_sq_tracked(dev, sq->qpn, sq->uid);
+
+	return err;
+}
+
+void mlx5_core_destroy_sq_tracked(struct mlx5_ib_dev *dev,
+				  struct mlx5_core_qp *sq)
+{
+	destroy_resource_common(dev, sq);
+	destroy_sq_tracked(dev, sq->qpn, sq->uid);
+}
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_ib_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type)
+{
+	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+	struct mlx5_qp_table *table = &dev->qp_table;
+
+	return mlx5_get_rsc(table, rsn);
+}
+
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
+{
+	mlx5_core_put_rsc(res);
+}
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index 88c0388f9fc6..c851570791af 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -7,6 +7,7 @@
 #include <linux/mlx5/driver.h>
 #include "mlx5_ib.h"
 #include "srq.h"
+#include "qp.h"
 
 static int get_pas_size(struct mlx5_srq_attr *in)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 6d32915000fc..d3c7dbd7f1d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 # mlx5 core basic
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
-		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
+		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index d40c3d5bd496..65fef5a86644 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -101,15 +101,15 @@ void mlx5_unregister_debugfs(void)
 
 void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev)
 {
-	atomic_set(&dev->num_qps, 0);
-
 	dev->priv.qp_debugfs = debugfs_create_dir("QPs",  dev->priv.dbg_root);
 }
+EXPORT_SYMBOL(mlx5_qp_debugfs_init);
 
 void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev)
 {
 	debugfs_remove_recursive(dev->priv.qp_debugfs);
 }
+EXPORT_SYMBOL(mlx5_qp_debugfs_cleanup);
 
 void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev)
 {
@@ -450,6 +450,7 @@ int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp)
 
 	return err;
 }
+EXPORT_SYMBOL(mlx5_debug_qp_add);
 
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp)
 {
@@ -459,6 +460,7 @@ void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp)
 	if (qp->dbg)
 		rem_res_tree(qp->dbg);
 }
+EXPORT_SYMBOL(mlx5_debug_qp_remove);
 
 int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7af4210c1b96..6e19fa4d1310 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -836,8 +836,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	mlx5_cq_debugfs_init(dev);
 
-	mlx5_init_qp_table(dev);
-
 	mlx5_init_reserved_gids(dev);
 
 	mlx5_init_clock(dev);
@@ -896,7 +894,6 @@ err_rl_cleanup:
 err_tables_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
-	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
@@ -924,7 +921,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
-	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
deleted file mode 100644
index d9df3a5dd532..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ /dev/null
@@ -1,697 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/gfp.h>
-#include <linux/export.h>
-#include <linux/mlx5/qp.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/transobj.h>
-
-#include "mlx5_core.h"
-#include "lib/eq.h"
-
-static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
-			       struct mlx5_core_dct *dct);
-
-static struct mlx5_core_rsc_common *
-mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
-{
-	struct mlx5_core_rsc_common *common;
-	unsigned long flags;
-
-	spin_lock_irqsave(&table->lock, flags);
-
-	common = radix_tree_lookup(&table->tree, rsn);
-	if (common)
-		refcount_inc(&common->refcount);
-
-	spin_unlock_irqrestore(&table->lock, flags);
-
-	return common;
-}
-
-void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common)
-{
-	if (refcount_dec_and_test(&common->refcount))
-		complete(&common->free);
-}
-
-static u64 qp_allowed_event_types(void)
-{
-	u64 mask;
-
-	mask = BIT(MLX5_EVENT_TYPE_PATH_MIG) |
-	       BIT(MLX5_EVENT_TYPE_COMM_EST) |
-	       BIT(MLX5_EVENT_TYPE_SQ_DRAINED) |
-	       BIT(MLX5_EVENT_TYPE_SRQ_LAST_WQE) |
-	       BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR) |
-	       BIT(MLX5_EVENT_TYPE_PATH_MIG_FAILED) |
-	       BIT(MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR) |
-	       BIT(MLX5_EVENT_TYPE_WQ_ACCESS_ERROR);
-
-	return mask;
-}
-
-static u64 rq_allowed_event_types(void)
-{
-	u64 mask;
-
-	mask = BIT(MLX5_EVENT_TYPE_SRQ_LAST_WQE) |
-	       BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR);
-
-	return mask;
-}
-
-static u64 sq_allowed_event_types(void)
-{
-	return BIT(MLX5_EVENT_TYPE_WQ_CATAS_ERROR);
-}
-
-static u64 dct_allowed_event_types(void)
-{
-	return BIT(MLX5_EVENT_TYPE_DCT_DRAINED);
-}
-
-static bool is_event_type_allowed(int rsc_type, int event_type)
-{
-	switch (rsc_type) {
-	case MLX5_EVENT_QUEUE_TYPE_QP:
-		return BIT(event_type) & qp_allowed_event_types();
-	case MLX5_EVENT_QUEUE_TYPE_RQ:
-		return BIT(event_type) & rq_allowed_event_types();
-	case MLX5_EVENT_QUEUE_TYPE_SQ:
-		return BIT(event_type) & sq_allowed_event_types();
-	case MLX5_EVENT_QUEUE_TYPE_DCT:
-		return BIT(event_type) & dct_allowed_event_types();
-	default:
-		WARN(1, "Event arrived for unknown resource type");
-		return false;
-	}
-}
-
-static int rsc_event_notifier(struct notifier_block *nb,
-			      unsigned long type, void *data)
-{
-	struct mlx5_core_rsc_common *common;
-	struct mlx5_qp_table *table;
-	struct mlx5_core_dev *dev;
-	struct mlx5_core_dct *dct;
-	u8 event_type = (u8)type;
-	struct mlx5_core_qp *qp;
-	struct mlx5_priv *priv;
-	struct mlx5_eqe *eqe;
-	u32 rsn;
-
-	switch (event_type) {
-	case MLX5_EVENT_TYPE_DCT_DRAINED:
-		eqe = data;
-		rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
-		rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
-		break;
-	case MLX5_EVENT_TYPE_PATH_MIG:
-	case MLX5_EVENT_TYPE_COMM_EST:
-	case MLX5_EVENT_TYPE_SQ_DRAINED:
-	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-		eqe = data;
-		rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-		rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	table = container_of(nb, struct mlx5_qp_table, nb);
-	priv  = container_of(table, struct mlx5_priv, qp_table);
-	dev   = container_of(priv, struct mlx5_core_dev, priv);
-
-	mlx5_core_dbg(dev, "event (%d) arrived on resource 0x%x\n", eqe->type, rsn);
-
-	common = mlx5_get_rsc(table, rsn);
-	if (!common) {
-		mlx5_core_dbg(dev, "Async event for unknown resource 0x%x\n", rsn);
-		return NOTIFY_OK;
-	}
-
-	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
-		mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
-			       event_type, rsn);
-		goto out;
-	}
-
-	switch (common->res) {
-	case MLX5_RES_QP:
-	case MLX5_RES_RQ:
-	case MLX5_RES_SQ:
-		qp = (struct mlx5_core_qp *)common;
-		qp->event(qp, event_type);
-		break;
-	case MLX5_RES_DCT:
-		dct = (struct mlx5_core_dct *)common;
-		if (event_type == MLX5_EVENT_TYPE_DCT_DRAINED)
-			complete(&dct->drained);
-		break;
-	default:
-		mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
-	}
-out:
-	mlx5_core_put_rsc(common);
-
-	return NOTIFY_OK;
-}
-
-static int create_resource_common(struct mlx5_core_dev *dev,
-				  struct mlx5_core_qp *qp,
-				  int rsc_type)
-{
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
-	int err;
-
-	qp->common.res = rsc_type;
-	spin_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree,
-				qp->qpn | (rsc_type << MLX5_USER_INDEX_LEN),
-				qp);
-	spin_unlock_irq(&table->lock);
-	if (err)
-		return err;
-
-	refcount_set(&qp->common.refcount, 1);
-	init_completion(&qp->common.free);
-	qp->pid = current->pid;
-
-	return 0;
-}
-
-static void destroy_resource_common(struct mlx5_core_dev *dev,
-				    struct mlx5_core_qp *qp)
-{
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
-	unsigned long flags;
-
-	spin_lock_irqsave(&table->lock, flags);
-	radix_tree_delete(&table->tree,
-			  qp->qpn | (qp->common.res << MLX5_USER_INDEX_LEN));
-	spin_unlock_irqrestore(&table->lock, flags);
-	mlx5_core_put_rsc((struct mlx5_core_rsc_common *)qp);
-	wait_for_completion(&qp->common.free);
-}
-
-static int _mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
-				  struct mlx5_core_dct *dct, bool need_cleanup)
-{
-	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-	int err;
-
-	err = mlx5_core_drain_dct(dev, dct);
-	if (err) {
-		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-			goto destroy;
-		} else {
-			mlx5_core_warn(
-				dev, "failed drain DCT 0x%x with error 0x%x\n",
-				qp->qpn, err);
-			return err;
-		}
-	}
-	wait_for_completion(&dct->drained);
-destroy:
-	if (need_cleanup)
-		destroy_resource_common(dev, &dct->mqp);
-	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
-	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			    (void *)&out, sizeof(out));
-	return err;
-}
-
-int mlx5_core_create_dct(struct mlx5_core_dev *dev,
-			 struct mlx5_core_dct *dct,
-			 u32 *in, int inlen,
-			 u32 *out, int outlen)
-{
-	struct mlx5_core_qp *qp = &dct->mqp;
-	int err;
-
-	init_completion(&dct->drained);
-	MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
-
-	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
-	if (err) {
-		mlx5_core_warn(dev, "create DCT failed, ret %d\n", err);
-		return err;
-	}
-
-	qp->qpn = MLX5_GET(create_dct_out, out, dctn);
-	qp->uid = MLX5_GET(create_dct_in, in, uid);
-	err = create_resource_common(dev, qp, MLX5_RES_DCT);
-	if (err)
-		goto err_cmd;
-
-	return 0;
-err_cmd:
-	_mlx5_core_destroy_dct(dev, dct, false);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_create_dct);
-
-int mlx5_core_create_qp(struct mlx5_core_dev *dev,
-			struct mlx5_core_qp *qp,
-			u32 *in, int inlen)
-{
-	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {0};
-	u32 dout[MLX5_ST_SZ_DW(destroy_qp_out)];
-	u32 din[MLX5_ST_SZ_DW(destroy_qp_in)];
-	int err;
-
-	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
-
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-	if (err)
-		return err;
-
-	qp->uid = MLX5_GET(create_qp_in, in, uid);
-	qp->qpn = MLX5_GET(create_qp_out, out, qpn);
-	mlx5_core_dbg(dev, "qpn = 0x%x\n", qp->qpn);
-
-	err = create_resource_common(dev, qp, MLX5_RES_QP);
-	if (err)
-		goto err_cmd;
-
-	err = mlx5_debug_qp_add(dev, qp);
-	if (err)
-		mlx5_core_dbg(dev, "failed adding QP 0x%x to debug file system\n",
-			      qp->qpn);
-
-	atomic_inc(&dev->num_qps);
-
-	return 0;
-
-err_cmd:
-	memset(din, 0, sizeof(din));
-	memset(dout, 0, sizeof(dout));
-	MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
-	MLX5_SET(destroy_qp_in, din, uid, qp->uid);
-	mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_create_qp);
-
-static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
-			       struct mlx5_core_dct *dct)
-{
-	u32 out[MLX5_ST_SZ_DW(drain_dct_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(drain_dct_in)]   = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-
-	MLX5_SET(drain_dct_in, in, opcode, MLX5_CMD_OP_DRAIN_DCT);
-	MLX5_SET(drain_dct_in, in, dctn, qp->qpn);
-	MLX5_SET(drain_dct_in, in, uid, qp->uid);
-	return mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			     (void *)&out, sizeof(out));
-}
-
-int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
-			  struct mlx5_core_dct *dct)
-{
-	return _mlx5_core_destroy_dct(dev, dct, true);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct);
-
-int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
-			 struct mlx5_core_qp *qp)
-{
-	u32 out[MLX5_ST_SZ_DW(destroy_qp_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_qp_in)]   = {0};
-	int err;
-
-	mlx5_debug_qp_remove(dev, qp);
-
-	destroy_resource_common(dev, qp);
-
-	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
-	MLX5_SET(destroy_qp_in, in, uid, qp->uid);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (err)
-		return err;
-
-	atomic_dec(&dev->num_qps);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_destroy_qp);
-
-int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev,
-			     u32 timeout_usec)
-{
-	u32 out[MLX5_ST_SZ_DW(set_delay_drop_params_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(set_delay_drop_params_in)]   = {0};
-
-	MLX5_SET(set_delay_drop_params_in, in, opcode,
-		 MLX5_CMD_OP_SET_DELAY_DROP_PARAMS);
-	MLX5_SET(set_delay_drop_params_in, in, delay_drop_timeout,
-		 timeout_usec / 100);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_set_delay_drop);
-
-struct mbox_info {
-	u32 *in;
-	u32 *out;
-	int inlen;
-	int outlen;
-};
-
-static int mbox_alloc(struct mbox_info *mbox, int inlen, int outlen)
-{
-	mbox->inlen  = inlen;
-	mbox->outlen = outlen;
-	mbox->in = kzalloc(mbox->inlen, GFP_KERNEL);
-	mbox->out = kzalloc(mbox->outlen, GFP_KERNEL);
-	if (!mbox->in || !mbox->out) {
-		kfree(mbox->in);
-		kfree(mbox->out);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void mbox_free(struct mbox_info *mbox)
-{
-	kfree(mbox->in);
-	kfree(mbox->out);
-}
-
-static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn,
-				u32 opt_param_mask, void *qpc,
-				struct mbox_info *mbox, u16 uid)
-{
-	mbox->out = NULL;
-	mbox->in = NULL;
-
-#define MBOX_ALLOC(mbox, typ)  \
-	mbox_alloc(mbox, MLX5_ST_SZ_BYTES(typ##_in), MLX5_ST_SZ_BYTES(typ##_out))
-
-#define MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid)                            \
-	do {                                                                   \
-		MLX5_SET(typ##_in, in, opcode, _opcode);                       \
-		MLX5_SET(typ##_in, in, qpn, _qpn);                             \
-		MLX5_SET(typ##_in, in, uid, _uid);                             \
-	} while (0)
-
-#define MOD_QP_IN_SET_QPC(typ, in, _opcode, _qpn, _opt_p, _qpc, _uid)          \
-	do {                                                                   \
-		MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid);                   \
-		MLX5_SET(typ##_in, in, opt_param_mask, _opt_p);                \
-		memcpy(MLX5_ADDR_OF(typ##_in, in, qpc), _qpc,                  \
-		       MLX5_ST_SZ_BYTES(qpc));                                 \
-	} while (0)
-
-	switch (opcode) {
-	/* 2RST & 2ERR */
-	case MLX5_CMD_OP_2RST_QP:
-		if (MBOX_ALLOC(mbox, qp_2rst))
-			return -ENOMEM;
-		MOD_QP_IN_SET(qp_2rst, mbox->in, opcode, qpn, uid);
-		break;
-	case MLX5_CMD_OP_2ERR_QP:
-		if (MBOX_ALLOC(mbox, qp_2err))
-			return -ENOMEM;
-		MOD_QP_IN_SET(qp_2err, mbox->in, opcode, qpn, uid);
-		break;
-
-	/* MODIFY with QPC */
-	case MLX5_CMD_OP_RST2INIT_QP:
-		if (MBOX_ALLOC(mbox, rst2init_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	case MLX5_CMD_OP_INIT2RTR_QP:
-		if (MBOX_ALLOC(mbox, init2rtr_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	case MLX5_CMD_OP_RTR2RTS_QP:
-		if (MBOX_ALLOC(mbox, rtr2rts_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	case MLX5_CMD_OP_RTS2RTS_QP:
-		if (MBOX_ALLOC(mbox, rts2rts_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(rts2rts_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	case MLX5_CMD_OP_SQERR2RTS_QP:
-		if (MBOX_ALLOC(mbox, sqerr2rts_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(sqerr2rts_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	case MLX5_CMD_OP_INIT2INIT_QP:
-		if (MBOX_ALLOC(mbox, init2init_qp))
-			return -ENOMEM;
-		MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn,
-				  opt_param_mask, qpc, uid);
-		break;
-	default:
-		mlx5_core_err(dev, "Unknown transition for modify QP: OP(0x%x) QPN(0x%x)\n",
-			      opcode, qpn);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 opcode,
-			u32 opt_param_mask, void *qpc,
-			struct mlx5_core_qp *qp)
-{
-	struct mbox_info mbox;
-	int err;
-
-	err = modify_qp_mbox_alloc(dev, opcode, qp->qpn,
-				   opt_param_mask, qpc, &mbox, qp->uid);
-	if (err)
-		return err;
-
-	err = mlx5_cmd_exec(dev, mbox.in, mbox.inlen, mbox.out, mbox.outlen);
-	mbox_free(&mbox);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_qp_modify);
-
-void mlx5_init_qp_table(struct mlx5_core_dev *dev)
-{
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
-
-	memset(table, 0, sizeof(*table));
-	spin_lock_init(&table->lock);
-	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
-	mlx5_qp_debugfs_init(dev);
-
-	table->nb.notifier_call = rsc_event_notifier;
-	mlx5_notifier_register(dev, &table->nb);
-}
-
-void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev)
-{
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
-
-	mlx5_notifier_unregister(dev, &table->nb);
-	mlx5_qp_debugfs_cleanup(dev);
-}
-
-int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
-		       u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_qp_in)] = {0};
-
-	MLX5_SET(query_qp_in, in, opcode, MLX5_CMD_OP_QUERY_QP);
-	MLX5_SET(query_qp_in, in, qpn, qp->qpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_qp_query);
-
-int mlx5_core_dct_query(struct mlx5_core_dev *dev, struct mlx5_core_dct *dct,
-			u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_dct_in)] = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-
-	MLX5_SET(query_dct_in, in, opcode, MLX5_CMD_OP_QUERY_DCT);
-	MLX5_SET(query_dct_in, in, dctn, qp->qpn);
-
-	return mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			     (void *)out, outlen);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_dct_query);
-
-int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn)
-{
-	u32 out[MLX5_ST_SZ_DW(alloc_xrcd_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(alloc_xrcd_in)]   = {0};
-	int err;
-
-	MLX5_SET(alloc_xrcd_in, in, opcode, MLX5_CMD_OP_ALLOC_XRCD);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (!err)
-		*xrcdn = MLX5_GET(alloc_xrcd_out, out, xrcd);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_xrcd_alloc);
-
-int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn)
-{
-	u32 out[MLX5_ST_SZ_DW(dealloc_xrcd_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_xrcd_in)]   = {0};
-
-	MLX5_SET(dealloc_xrcd_in, in, opcode, MLX5_CMD_OP_DEALLOC_XRCD);
-	MLX5_SET(dealloc_xrcd_in, in, xrcd, xrcdn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_xrcd_dealloc);
-
-static void destroy_rq_tracked(struct mlx5_core_dev *dev, u32 rqn, u16 uid)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_rq_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(destroy_rq_out)] = {};
-
-	MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ);
-	MLX5_SET(destroy_rq_in, in, rqn, rqn);
-	MLX5_SET(destroy_rq_in, in, uid, uid);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
-				struct mlx5_core_qp *rq)
-{
-	int err;
-	u32 rqn;
-
-	err = mlx5_core_create_rq(dev, in, inlen, &rqn);
-	if (err)
-		return err;
-
-	rq->uid = MLX5_GET(create_rq_in, in, uid);
-	rq->qpn = rqn;
-	err = create_resource_common(dev, rq, MLX5_RES_RQ);
-	if (err)
-		goto err_destroy_rq;
-
-	return 0;
-
-err_destroy_rq:
-	destroy_rq_tracked(dev, rq->qpn, rq->uid);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_create_rq_tracked);
-
-void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev,
-				  struct mlx5_core_qp *rq)
-{
-	destroy_resource_common(dev, rq);
-	destroy_rq_tracked(dev, rq->qpn, rq->uid);
-}
-EXPORT_SYMBOL(mlx5_core_destroy_rq_tracked);
-
-static void destroy_sq_tracked(struct mlx5_core_dev *dev, u32 sqn, u16 uid)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_sq_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(destroy_sq_out)] = {};
-
-	MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ);
-	MLX5_SET(destroy_sq_in, in, sqn, sqn);
-	MLX5_SET(destroy_sq_in, in, uid, uid);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
-				struct mlx5_core_qp *sq)
-{
-	int err;
-	u32 sqn;
-
-	err = mlx5_core_create_sq(dev, in, inlen, &sqn);
-	if (err)
-		return err;
-
-	sq->uid = MLX5_GET(create_sq_in, in, uid);
-	sq->qpn = sqn;
-	err = create_resource_common(dev, sq, MLX5_RES_SQ);
-	if (err)
-		goto err_destroy_sq;
-
-	return 0;
-
-err_destroy_sq:
-	destroy_sq_tracked(dev, sq->qpn, sq->uid);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_create_sq_tracked);
-
-void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev,
-				  struct mlx5_core_qp *sq)
-{
-	destroy_resource_common(dev, sq);
-	destroy_sq_tracked(dev, sq->qpn, sq->uid);
-}
-EXPORT_SYMBOL(mlx5_core_destroy_sq_tracked);
-
-struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
-						int res_num,
-						enum mlx5_res_type res_type)
-{
-	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
-
-	return mlx5_get_rsc(table, rsn);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
-
-void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
-{
-	mlx5_core_put_rsc(res);
-}
-EXPORT_SYMBOL_GPL(mlx5_core_res_put);
diff --git a/include/linux/mlx5/cmd.h b/include/linux/mlx5/cmd.h
deleted file mode 100644
index 68cd08f02c2f..000000000000
--- a/include/linux/mlx5/cmd.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef MLX5_CMD_H
-#define MLX5_CMD_H
-
-#include <linux/types.h>
-
-struct manage_pages_layout {
-	u64	ptr;
-	u32	reserved;
-	u16	num_entries;
-	u16	func_id;
-};
-
-
-struct mlx5_cmd_alloc_uar_imm_out {
-	u32	rsvd[3];
-	u32	uarn;
-};
-
-#endif /* MLX5_CMD_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1caddfa85c4d..b60e5ab7906b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -541,7 +541,6 @@ struct mlx5_priv {
 	struct mlx5_core_health health;
 
 	/* start: qp staff */
-	struct mlx5_qp_table	qp_table;
 	struct dentry	       *qp_debugfs;
 	struct dentry	       *eq_debugfs;
 	struct dentry	       *cq_debugfs;
@@ -687,7 +686,6 @@ struct mlx5_core_dev {
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	*profile;
-	atomic_t		num_qps;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 4d25a3d24182..ef127a156a62 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -553,53 +553,8 @@ struct mlx5_qp_context {
 	u8			rsvd1[24];
 };
 
-static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u32 qpn)
-{
-	return radix_tree_lookup(&dev->priv.qp_table.tree, qpn);
-}
-
-int mlx5_core_create_dct(struct mlx5_core_dev *dev,
-			 struct mlx5_core_dct *qp,
-			 u32 *in, int inlen,
-			 u32 *out, int outlen);
-int mlx5_core_create_qp(struct mlx5_core_dev *dev,
-			struct mlx5_core_qp *qp,
-			u32 *in,
-			int inlen);
-int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 opcode,
-			u32 opt_param_mask, void *qpc,
-			struct mlx5_core_qp *qp);
-int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
-			 struct mlx5_core_qp *qp);
-int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
-			  struct mlx5_core_dct *dct);
-int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
-		       u32 *out, int outlen);
-int mlx5_core_dct_query(struct mlx5_core_dev *dev, struct mlx5_core_dct *dct,
-			u32 *out, int outlen);
-
-int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev,
-			     u32 timeout_usec);
-
-int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn);
-int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn);
-void mlx5_init_qp_table(struct mlx5_core_dev *dev);
-void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev);
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
-int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
-				struct mlx5_core_qp *rq);
-void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev,
-				  struct mlx5_core_qp *rq);
-int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
-				struct mlx5_core_qp *sq);
-void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev,
-				  struct mlx5_core_qp *sq);
-
-struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
-						int res_num,
-						enum mlx5_res_type res_type);
-void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
 
 static inline const char *mlx5_qp_type_str(int type)
 {
-- 
cgit v1.2.3


From a2a322f447b91a9b85d332b345a3b508d97506a9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 19 Mar 2020 11:43:59 +0200
Subject: net/mlx5: Refactor HCA capability set flow

Reduce the amount of kzalloc/kfree cycles by allocating
command structure in the parent function and leverage the
knowledge that set_caps() is called for HCA capabilities
only with specific HW structure as parameter to calculate
mailbox size.

Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 83 ++++++++++----------------
 1 file changed, 31 insertions(+), 52 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6e19fa4d1310..a000cd820ace 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -407,30 +407,28 @@ int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type)
 	return mlx5_core_get_caps_mode(dev, cap_type, HCA_CAP_OPMOD_GET_MAX);
 }
 
-static int set_caps(struct mlx5_core_dev *dev, void *in, int in_sz, int opmod)
+static int set_caps(struct mlx5_core_dev *dev, void *in, int opmod)
 {
-	u32 out[MLX5_ST_SZ_DW(set_hca_cap_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(set_hca_cap_out)] = {};
 
 	MLX5_SET(set_hca_cap_in, in, opcode, MLX5_CMD_OP_SET_HCA_CAP);
 	MLX5_SET(set_hca_cap_in, in, op_mod, opmod << 1);
-	return mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out));
+	return mlx5_cmd_exec(dev, in, MLX5_ST_SZ_BYTES(set_hca_cap_in), out,
+			     sizeof(out));
 }
 
-static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
+static int handle_hca_cap_atomic(struct mlx5_core_dev *dev, void *set_ctx)
 {
-	void *set_ctx;
 	void *set_hca_cap;
-	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
 	int req_endianness;
 	int err;
 
-	if (MLX5_CAP_GEN(dev, atomic)) {
-		err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC);
-		if (err)
-			return err;
-	} else {
+	if (!MLX5_CAP_GEN(dev, atomic))
 		return 0;
-	}
+
+	err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC);
+	if (err)
+		return err;
 
 	req_endianness =
 		MLX5_CAP_ATOMIC(dev,
@@ -439,27 +437,18 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
 	if (req_endianness != MLX5_ATOMIC_REQ_MODE_HOST_ENDIANNESS)
 		return 0;
 
-	set_ctx = kzalloc(set_sz, GFP_KERNEL);
-	if (!set_ctx)
-		return -ENOMEM;
-
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
 
 	/* Set requestor to host endianness */
 	MLX5_SET(atomic_caps, set_hca_cap, atomic_req_8B_endianness_mode,
 		 MLX5_ATOMIC_REQ_MODE_HOST_ENDIANNESS);
 
-	err = set_caps(dev, set_ctx, set_sz, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC);
-
-	kfree(set_ctx);
-	return err;
+	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC);
 }
 
-static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
+static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	void *set_hca_cap;
-	void *set_ctx;
-	int set_sz;
 	bool do_set = false;
 	int err;
 
@@ -471,11 +460,6 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
-	set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
-	set_ctx = kzalloc(set_sz, GFP_KERNEL);
-	if (!set_ctx)
-		return -ENOMEM;
-
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
 	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
 	       MLX5_ST_SZ_BYTES(odp_cap));
@@ -504,30 +488,21 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
 	ODP_CAP_SET_MAX(dev, dc_odp_caps.read);
 	ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic);
 
-	if (do_set)
-		err = set_caps(dev, set_ctx, set_sz,
-			       MLX5_SET_HCA_CAP_OP_MOD_ODP);
-
-	kfree(set_ctx);
+	if (!do_set)
+		return 0;
 
-	return err;
+	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 }
 
-static int handle_hca_cap(struct mlx5_core_dev *dev)
+static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
-	void *set_ctx = NULL;
 	struct mlx5_profile *prof = dev->profile;
-	int err = -ENOMEM;
-	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
 	void *set_hca_cap;
-
-	set_ctx = kzalloc(set_sz, GFP_KERNEL);
-	if (!set_ctx)
-		goto query_ex;
+	int err;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
 	if (err)
-		goto query_ex;
+		return err;
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx,
 				   capability);
@@ -578,37 +553,41 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 			 num_vhca_ports,
 			 MLX5_CAP_GEN_MAX(dev, num_vhca_ports));
 
-	err = set_caps(dev, set_ctx, set_sz,
-		       MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
-
-query_ex:
-	kfree(set_ctx);
-	return err;
+	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
 static int set_hca_cap(struct mlx5_core_dev *dev)
 {
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *set_ctx;
 	int err;
 
-	err = handle_hca_cap(dev);
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
+	if (!set_ctx)
+		return -ENOMEM;
+
+	err = handle_hca_cap(dev, set_ctx);
 	if (err) {
 		mlx5_core_err(dev, "handle_hca_cap failed\n");
 		goto out;
 	}
 
-	err = handle_hca_cap_atomic(dev);
+	memset(set_ctx, 0, set_sz);
+	err = handle_hca_cap_atomic(dev, set_ctx);
 	if (err) {
 		mlx5_core_err(dev, "handle_hca_cap_atomic failed\n");
 		goto out;
 	}
 
-	err = handle_hca_cap_odp(dev);
+	memset(set_ctx, 0, set_sz);
+	err = handle_hca_cap_odp(dev, set_ctx);
 	if (err) {
 		mlx5_core_err(dev, "handle_hca_cap_odp failed\n");
 		goto out;
 	}
 
 out:
+	kfree(set_ctx);
 	return err;
 }
 
-- 
cgit v1.2.3


From 59e9e8e4fe83f68e599b87c06aaf239dcc64887b Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Tue, 14 Jan 2020 05:06:25 +0200
Subject: net/mlx5: Enable SW-defined RoCEv2 UDP source port

When this is enabled, UDP source port for RoCEv2 packets are defined
by software instead of firmware.

Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 32 ++++++++++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                  |  5 +++-
 2 files changed, 36 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a000cd820ace..0044aa5cc676 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -556,6 +556,31 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
+static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx)
+{
+	void *set_hca_cap;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, roce))
+		return 0;
+
+	err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE);
+	if (err)
+		return err;
+
+	if (MLX5_CAP_ROCE(dev, sw_r_roce_src_udp_port) ||
+	    !MLX5_CAP_ROCE_MAX(dev, sw_r_roce_src_udp_port))
+		return 0;
+
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
+	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ROCE],
+	       MLX5_ST_SZ_BYTES(roce_cap));
+	MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1);
+
+	err = set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ROCE);
+	return err;
+}
+
 static int set_hca_cap(struct mlx5_core_dev *dev)
 {
 	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
@@ -586,6 +611,13 @@ static int set_hca_cap(struct mlx5_core_dev *dev)
 		goto out;
 	}
 
+	memset(set_ctx, 0, set_sz);
+	err = handle_hca_cap_roce(dev, set_ctx);
+	if (err) {
+		mlx5_core_err(dev, "handle_hca_cap_roce failed\n");
+		goto out;
+	}
+
 out:
 	kfree(set_ctx);
 	return err;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 69b27c7dfc3e..6fa24918eade 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -74,6 +74,7 @@ enum {
 	MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE        = 0x0,
 	MLX5_SET_HCA_CAP_OP_MOD_ODP                   = 0x2,
 	MLX5_SET_HCA_CAP_OP_MOD_ATOMIC                = 0x3,
+	MLX5_SET_HCA_CAP_OP_MOD_ROCE                  = 0x4,
 };
 
 enum {
@@ -903,7 +904,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 
 struct mlx5_ifc_roce_cap_bits {
 	u8         roce_apm[0x1];
-	u8         reserved_at_1[0x1f];
+	u8         reserved_at_1[0x3];
+	u8         sw_r_roce_src_udp_port[0x1];
+	u8         reserved_at_5[0x1b];
 
 	u8         reserved_at_20[0x60];
 
-- 
cgit v1.2.3


From c2a3f8febc69f222d9fc3248bf774c8f0c5725f3 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 11 Mar 2020 11:35:06 +0200
Subject: igc: Add new device IDs for i225 part

Add new device IDs for the next step of i225

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_base.c | 3 +++
 drivers/net/ethernet/intel/igc/igc_hw.h   | 3 +++
 drivers/net/ethernet/intel/igc/igc_main.c | 3 +++
 3 files changed, 9 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 5a506440560a..f7fb18d8d8f5 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -212,6 +212,9 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 	case IGC_DEV_ID_I225_I:
 	case IGC_DEV_ID_I220_V:
 	case IGC_DEV_ID_I225_K:
+	case IGC_DEV_ID_I225_K2:
+	case IGC_DEV_ID_I225_LMVP:
+	case IGC_DEV_ID_I225_IT:
 	case IGC_DEV_ID_I225_BLANK_NVM:
 		mac->type = igc_i225;
 		break;
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index 90ac0e0144d8..af34ae310327 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -21,6 +21,9 @@
 #define IGC_DEV_ID_I225_I			0x15F8
 #define IGC_DEV_ID_I220_V			0x15F7
 #define IGC_DEV_ID_I225_K			0x3100
+#define IGC_DEV_ID_I225_K2			0x3101
+#define IGC_DEV_ID_I225_LMVP			0x5502
+#define IGC_DEV_ID_I225_IT			0x0D9F
 #define IGC_DEV_ID_I225_BLANK_NVM		0x15FD
 
 /* Function pointers for the MAC. */
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9d1792e80e2e..6a7c1b081792 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -47,6 +47,9 @@ static const struct pci_device_id igc_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K2), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LMVP), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_IT), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_BLANK_NVM), board_base },
 	/* required last entry */
 	{0, }
-- 
cgit v1.2.3


From 632fbd5eb5b0e01f03f1acb90a2b9ac1352b5dc7 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Thu, 12 Mar 2020 13:57:07 +0200
Subject: e1000e: fix S0ix flows for cable connected case

Added a fix to S0ix entry and exit flows for TGP and above
MAC types, to the case when the Ethernet cable is connected
and the link is up. With that the system is able to reach
SLP_S0 when going to freeze power state.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 54 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/intel/e1000e/regs.h   |  3 ++
 2 files changed, 57 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 177c6da80c57..e0b074820b47 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6404,6 +6404,31 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
 	mac_data |= BIT(3);
 	ew32(CTRL_EXT, mac_data);
 
+	/* Disable disconnected cable conditioning for Power Gating */
+	mac_data = er32(DPGFR);
+	mac_data |= BIT(2);
+	ew32(DPGFR, mac_data);
+
+	/* Don't wake from dynamic Power Gating with clock request */
+	mac_data = er32(FEXTNVM12);
+	mac_data |= BIT(12);
+	ew32(FEXTNVM12, mac_data);
+
+	/* Ungate PGCB clock */
+	mac_data = er32(FEXTNVM9);
+	mac_data |= BIT(28);
+	ew32(FEXTNVM9, mac_data);
+
+	/* Enable K1 off to enable mPHY Power Gating */
+	mac_data = er32(FEXTNVM6);
+	mac_data |= BIT(31);
+	ew32(FEXTNVM12, mac_data);
+
+	/* Enable mPHY power gating for any link and speed */
+	mac_data = er32(FEXTNVM8);
+	mac_data |= BIT(9);
+	ew32(FEXTNVM8, mac_data);
+
 	/* Enable the Dynamic Clock Gating in the DMA and MAC */
 	mac_data = er32(CTRL_EXT);
 	mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN;
@@ -6433,6 +6458,35 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter)
 	mac_data |= BIT(0);
 	ew32(FEXTNVM7, mac_data);
 
+	/* Disable mPHY power gating for any link and speed */
+	mac_data = er32(FEXTNVM8);
+	mac_data &= ~BIT(9);
+	ew32(FEXTNVM8, mac_data);
+
+	/* Disable K1 off */
+	mac_data = er32(FEXTNVM6);
+	mac_data &= ~BIT(31);
+	ew32(FEXTNVM12, mac_data);
+
+	/* Disable Ungate PGCB clock */
+	mac_data = er32(FEXTNVM9);
+	mac_data &= ~BIT(28);
+	ew32(FEXTNVM9, mac_data);
+
+	/* Cancel not waking from dynamic
+	 * Power Gating with clock request
+	 */
+	mac_data = er32(FEXTNVM12);
+	mac_data &= ~BIT(12);
+	ew32(FEXTNVM12, mac_data);
+
+	/* Cancel disable disconnected cable conditioning
+	 * for Power Gating
+	 */
+	mac_data = er32(DPGFR);
+	mac_data &= ~BIT(2);
+	ew32(DPGFR, mac_data);
+
 	/* Disable Dynamic Power Gating */
 	mac_data = er32(CTRL_EXT);
 	mac_data &= 0xFFFFFFF7;
diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h
index df59fd1d660c..8165ba2619a4 100644
--- a/drivers/net/ethernet/intel/e1000e/regs.h
+++ b/drivers/net/ethernet/intel/e1000e/regs.h
@@ -21,9 +21,12 @@
 #define E1000_FEXTNVM5	0x00014	/* Future Extended NVM 5 - RW */
 #define E1000_FEXTNVM6	0x00010	/* Future Extended NVM 6 - RW */
 #define E1000_FEXTNVM7	0x000E4	/* Future Extended NVM 7 - RW */
+#define E1000_FEXTNVM8	0x5BB0	/* Future Extended NVM 8 - RW */
 #define E1000_FEXTNVM9	0x5BB4	/* Future Extended NVM 9 - RW */
 #define E1000_FEXTNVM11	0x5BBC	/* Future Extended NVM 11 - RW */
+#define E1000_FEXTNVM12	0x5BC0	/* Future Extended NVM 12 - RW */
 #define E1000_PCIEANACFG	0x00F18	/* PCIE Analog Config */
+#define E1000_DPGFR	0x00FAC	/* Dynamic Power Gate Force Control Register */
 #define E1000_FCT	0x00030	/* Flow Control Type - RW */
 #define E1000_VET	0x00038	/* VLAN Ether Type - RW */
 #define E1000_ICR	0x000C0	/* Interrupt Cause Read - R/clr */
-- 
cgit v1.2.3


From 0c2e060859aa1cb8b13376554d802a251f750fa9 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:51 -0700
Subject: igc: Remove duplicate code in MAC filtering logic

This patch does a code refactoring in the MAC address filtering logic to
get rid of some duplicate code.

IGC driver has two functions to add MAC address filters that are pretty
much the same: igc_add_mac_filter() and igc_add_mac_filter_flags(). The
only difference is that the latter allows the callee to specify the
'flags' parameter while the former has it hard coded as zero. The same
rationale applies to filter deletion counterparts.

So this patch refactors igc_add_mac_filter() and igc_del_mac_filter() so
they handle the 'flags' parameters, removes the _flags() functions, and
fixes callees accordingly.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 112 ++++--------------------------
 1 file changed, 13 insertions(+), 99 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 6a7c1b081792..ade460f08ed1 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2191,8 +2191,8 @@ static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
  * default for the destination address, if matching by source address
  * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
  */
-static int igc_add_mac_filter(struct igc_adapter *adapter,
-			      const u8 *addr, const u8 queue)
+static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+			      const u8 queue, const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -2207,12 +2207,12 @@ static int igc_add_mac_filter(struct igc_adapter *adapter,
 	 */
 	for (i = 0; i < rar_entries; i++) {
 		if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
-					       addr, 0))
+					       addr, flags))
 			continue;
 
 		ether_addr_copy(adapter->mac_table[i].addr, addr);
 		adapter->mac_table[i].queue = queue;
-		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE;
+		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
 
 		igc_rar_set_index(adapter, i);
 		return i;
@@ -2227,8 +2227,8 @@ static int igc_add_mac_filter(struct igc_adapter *adapter,
  * matching by source address is to be removed the flag
  * IGC_MAC_STATE_SRC_ADDR can be used.
  */
-static int igc_del_mac_filter(struct igc_adapter *adapter,
-			      const u8 *addr, const u8 queue)
+static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+			      const u8 queue, const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -2244,7 +2244,7 @@ static int igc_del_mac_filter(struct igc_adapter *adapter,
 	for (i = 0; i < rar_entries; i++) {
 		if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
 			continue;
-		if (adapter->mac_table[i].state != 0)
+		if (flags && (adapter->mac_table[i].state & flags) != flags)
 			continue;
 		if (adapter->mac_table[i].queue != queue)
 			continue;
@@ -2276,7 +2276,7 @@ static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int ret;
 
-	ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues);
+	ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
 
 	return min_t(int, ret, 0);
 }
@@ -2285,7 +2285,7 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	igc_del_mac_filter(adapter, addr, adapter->num_rx_queues);
+	igc_del_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
 
 	return 0;
 }
@@ -3720,104 +3720,18 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
-/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
- * 'flags' is used to indicate what kind of match is made, match is by
- * default for the destination address, if matching by source address
- * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
- */
-static int igc_add_mac_filter_flags(struct igc_adapter *adapter,
-				    const u8 *addr, const u8 queue,
-				    const u8 flags)
-{
-	struct igc_hw *hw = &adapter->hw;
-	int rar_entries = hw->mac.rar_entry_count;
-	int i;
-
-	if (is_zero_ether_addr(addr))
-		return -EINVAL;
-
-	/* Search for the first empty entry in the MAC table.
-	 * Do not touch entries at the end of the table reserved for the VF MAC
-	 * addresses.
-	 */
-	for (i = 0; i < rar_entries; i++) {
-		if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
-					       addr, flags))
-			continue;
-
-		ether_addr_copy(adapter->mac_table[i].addr, addr);
-		adapter->mac_table[i].queue = queue;
-		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
-
-		igc_rar_set_index(adapter, i);
-		return i;
-	}
-
-	return -ENOSPC;
-}
-
 int igc_add_mac_steering_filter(struct igc_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags)
 {
-	return igc_add_mac_filter_flags(adapter, addr, queue,
-					IGC_MAC_STATE_QUEUE_STEERING | flags);
-}
-
-/* Remove a MAC filter for 'addr' directing matching traffic to
- * 'queue', 'flags' is used to indicate what kind of match need to be
- * removed, match is by default for the destination address, if
- * matching by source address is to be removed the flag
- * IGC_MAC_STATE_SRC_ADDR can be used.
- */
-static int igc_del_mac_filter_flags(struct igc_adapter *adapter,
-				    const u8 *addr, const u8 queue,
-				    const u8 flags)
-{
-	struct igc_hw *hw = &adapter->hw;
-	int rar_entries = hw->mac.rar_entry_count;
-	int i;
-
-	if (is_zero_ether_addr(addr))
-		return -EINVAL;
-
-	/* Search for matching entry in the MAC table based on given address
-	 * and queue. Do not touch entries at the end of the table reserved
-	 * for the VF MAC addresses.
-	 */
-	for (i = 0; i < rar_entries; i++) {
-		if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
-			continue;
-		if ((adapter->mac_table[i].state & flags) != flags)
-			continue;
-		if (adapter->mac_table[i].queue != queue)
-			continue;
-		if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
-			continue;
-
-		/* When a filter for the default address is "deleted",
-		 * we return it to its initial configuration
-		 */
-		if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
-			adapter->mac_table[i].state =
-				IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
-		} else {
-			adapter->mac_table[i].state = 0;
-			adapter->mac_table[i].queue = 0;
-			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
-		}
-
-		igc_rar_set_index(adapter, i);
-		return 0;
-	}
-
-	return -ENOENT;
+	return igc_add_mac_filter(adapter, addr, queue,
+				  IGC_MAC_STATE_QUEUE_STEERING | flags);
 }
 
 int igc_del_mac_steering_filter(struct igc_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags)
 {
-	return igc_del_mac_filter_flags(adapter, addr, queue,
-					IGC_MAC_STATE_QUEUE_STEERING | flags);
+	return igc_del_mac_filter(adapter, addr, queue,
+				  IGC_MAC_STATE_QUEUE_STEERING | flags);
 }
 
 static void igc_tsync_interrupt(struct igc_adapter *adapter)
-- 
cgit v1.2.3


From 23b7b511675669702ad32bf7f92dcf2ae05015ba Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:52 -0700
Subject: igc: Check unsupported flag in igc_add_mac_filter()

The IGC_MAC_STATE_SRC_ADDR flags is not supported by igc_add_mac_
filter() so this patch adds a check for it and returns -ENOTSUPP
in case it is set.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ade460f08ed1..66b3a689bb05 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2200,6 +2200,8 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 
 	if (is_zero_ether_addr(addr))
 		return -EINVAL;
+	if (flags & IGC_MAC_STATE_SRC_ADDR)
+		return -ENOTSUPP;
 
 	/* Search for the first empty entry in the MAC table.
 	 * Do not touch entries at the end of the table reserved for the VF MAC
-- 
cgit v1.2.3


From 58184b8ff0786b219772016a50ce07c6b3020846 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:53 -0700
Subject: igc: Change igc_add_mac_filter() returning value

In case of success, igc_add_mac_filter() returns the index in
adapter->mac_table where the requested filter was added. This
information, however, is not used by any caller of that function.
In fact, callers have extra code just to handle this returning
index as 0 (success).

So this patch changes the function to return 0 on success instead,
and cleans up the extra code.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 2 --
 drivers/net/ethernet/intel/igc/igc_main.c    | 7 ++-----
 2 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index ff2a40496e4e..c9f4552c018b 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1269,7 +1269,6 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 		err = igc_add_mac_steering_filter(adapter,
 						  input->filter.dst_addr,
 						  input->action, 0);
-		err = min_t(int, err, 0);
 		if (err)
 			return err;
 	}
@@ -1279,7 +1278,6 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 						  input->filter.src_addr,
 						  input->action,
 						  IGC_MAC_STATE_SRC_ADDR);
-		err = min_t(int, err, 0);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 66b3a689bb05..7c060c731a7e 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2217,7 +2217,7 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
 
 		igc_rar_set_index(adapter, i);
-		return i;
+		return 0;
 	}
 
 	return -ENOSPC;
@@ -2276,11 +2276,8 @@ static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
-	int ret;
-
-	ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
 
-	return min_t(int, ret, 0);
+	return igc_add_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
 }
 
 static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
-- 
cgit v1.2.3


From ec00f1090735259151568f6b74d19c3230d65787 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:54 -0700
Subject: igc: Fix igc_uc_unsync()

In case igc_del_mac_filter() returns error, that error is masked
since the functions always return 0 (success). This patch fixes
igc_uc_unsync() so it returns whatever value igc_del_mac_filter()
returns (0 on success, negative number on error).

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 7c060c731a7e..dc4632428117 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2284,9 +2284,7 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	igc_del_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
-
-	return 0;
+	return igc_del_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
 }
 
 /**
-- 
cgit v1.2.3


From 424045bec085575fe4818428e6a68dac7cca48f3 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 1 Apr 2020 14:36:45 -0700
Subject: igc: Refactor igc_rar_set_index()

Current igc_rar_set_index() implementation is a bit convoluted so this
patch does some code refactoring to improve it.

The helper igc_rar_set_index() is about writing MAC filter settings into
hardware registers. Logic such as address validation belongs to
functions upper in the call chain such as igc_set_mac() and
igc_add_mac_filter(). So this patch moves the is_valid_ether_addr() call
to igc_add_mac_filter(). No need to touch igc_set_mac() since it already
checks it.

The variables 'rar_low' and 'rar_high' represent the value in registers
RAL and RAH so we rename them to 'ral' and 'rah', respectively, to
match the registers names.

To make it explicit, filter settings are passed as arguments to the
function instead of reading them from adapter->mac_table "under the
hood". Also, the function was renamed to igc_set_mac_filter_hw to make
it more clear what it does.

Finally, the patch removes some wrfl() calls and comments not needed.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 73 ++++++++++++++++++-------------
 1 file changed, 42 insertions(+), 31 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index dc4632428117..2f6c8f7fa6f4 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -765,42 +765,52 @@ static void igc_setup_tctl(struct igc_adapter *adapter)
 }
 
 /**
- * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
- * @adapter: address of board private structure
- * @index: Index of the RAR entry which need to be synced with MAC table
+ * igc_set_mac_filter_hw() - Set MAC address filter in hardware
+ * @adapter: Pointer to adapter where the filter should be set
+ * @index: Filter index
+ * @addr: Destination MAC address
+ * @queue: If non-negative, queue assignment feature is enabled and frames
+ *         matching the filter are enqueued onto 'queue'. Otherwise, queue
+ *         assignment is disabled.
  */
-static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
+static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
+				  const u8 *addr, int queue)
 {
-	u8 *addr = adapter->mac_table[index].addr;
 	struct igc_hw *hw = &adapter->hw;
-	u32 rar_low, rar_high;
+	u32 ral, rah;
 
-	/* HW expects these to be in network order when they are plugged
-	 * into the registers which are little endian.  In order to guarantee
-	 * that ordering we need to do an leXX_to_cpup here in order to be
-	 * ready for the byteswap that occurs with writel
-	 */
-	rar_low = le32_to_cpup((__le32 *)(addr));
-	rar_high = le16_to_cpup((__le16 *)(addr + 4));
+	if (WARN_ON(index >= hw->mac.rar_entry_count))
+		return;
 
-	if (adapter->mac_table[index].state & IGC_MAC_STATE_QUEUE_STEERING) {
-		u8 queue = adapter->mac_table[index].queue;
-		u32 qsel = IGC_RAH_QSEL_MASK & (queue << IGC_RAH_QSEL_SHIFT);
+	ral = le32_to_cpup((__le32 *)(addr));
+	rah = le16_to_cpup((__le16 *)(addr + 4));
 
-		rar_high |= qsel;
-		rar_high |= IGC_RAH_QSEL_ENABLE;
+	if (queue >= 0) {
+		rah &= ~IGC_RAH_QSEL_MASK;
+		rah |= (queue << IGC_RAH_QSEL_SHIFT);
+		rah |= IGC_RAH_QSEL_ENABLE;
 	}
 
-	/* Indicate to hardware the Address is Valid. */
-	if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) {
-		if (is_valid_ether_addr(addr))
-			rar_high |= IGC_RAH_AV;
-	}
+	rah |= IGC_RAH_AV;
 
-	wr32(IGC_RAL(index), rar_low);
-	wrfl();
-	wr32(IGC_RAH(index), rar_high);
-	wrfl();
+	wr32(IGC_RAL(index), ral);
+	wr32(IGC_RAH(index), rah);
+}
+
+/**
+ * igc_clear_mac_filter_hw() - Clear MAC address filter in hardware
+ * @adapter: Pointer to adapter where the filter should be cleared
+ * @index: Filter index
+ */
+static void igc_clear_mac_filter_hw(struct igc_adapter *adapter, int index)
+{
+	struct igc_hw *hw = &adapter->hw;
+
+	if (WARN_ON(index >= hw->mac.rar_entry_count))
+		return;
+
+	wr32(IGC_RAL(index), 0);
+	wr32(IGC_RAH(index), 0);
 }
 
 /* Set default MAC address for the PF in the first RAR entry */
@@ -811,7 +821,7 @@ static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 	ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
 	mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
 
-	igc_rar_set_index(adapter, 0);
+	igc_set_mac_filter_hw(adapter, 0, mac_table->addr, -1);
 }
 
 /**
@@ -2198,7 +2208,7 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	int rar_entries = hw->mac.rar_entry_count;
 	int i;
 
-	if (is_zero_ether_addr(addr))
+	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 	if (flags & IGC_MAC_STATE_SRC_ADDR)
 		return -ENOTSUPP;
@@ -2216,7 +2226,7 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		adapter->mac_table[i].queue = queue;
 		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
 
-		igc_rar_set_index(adapter, i);
+		igc_set_mac_filter_hw(adapter, i, addr, queue);
 		return 0;
 	}
 
@@ -2260,13 +2270,14 @@ static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 			adapter->mac_table[i].state =
 				IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
 			adapter->mac_table[i].queue = 0;
+			igc_set_mac_filter_hw(adapter, 0, addr, -1);
 		} else {
 			adapter->mac_table[i].state = 0;
 			adapter->mac_table[i].queue = 0;
 			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+			igc_clear_mac_filter_hw(adapter, i);
 		}
 
-		igc_rar_set_index(adapter, i);
 		return 0;
 	}
 
-- 
cgit v1.2.3


From a73eb651005eef079a6bf3b448d1b6eb607bc80b Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:56 -0700
Subject: igc: Improve address check in igc_del_mac_filter()

igc_add_mac_filter() doesn't allow filters with invalid MAC address to
be added to adapter->mac_table so, in igc_del_mac_filter(), we can early
return if MAC address is invalid. No need to traverse the table.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 2f6c8f7fa6f4..070df92bb4e9 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2246,7 +2246,7 @@ static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	int rar_entries = hw->mac.rar_entry_count;
 	int i;
 
-	if (is_zero_ether_addr(addr))
+	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
 	/* Search for matching entry in the MAC table based on given address
-- 
cgit v1.2.3


From c6aae5917b8a244dcb4114be806ba3ac52e3480a Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 1 Apr 2020 14:41:43 -0700
Subject: igc: Remove 'queue' check in igc_del_mac_filter()

igc_add_mac_filter() doesn't allow us to have more than one entry with
the same address and address type in adapter->mac_table so checking if
'queue' matches in igc_del_mac_filter() isn't necessary. This patch
removes that check.

This patch also takes the opportunity to improve the igc_del_mac_filter
documentation and remove comment which is not applicable to this I225
controller.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 070df92bb4e9..badb8ecf38dc 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2233,14 +2233,17 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	return -ENOSPC;
 }
 
-/* Remove a MAC filter for 'addr' directing matching traffic to
- * 'queue', 'flags' is used to indicate what kind of match need to be
- * removed, match is by default for the destination address, if
- * matching by source address is to be removed the flag
- * IGC_MAC_STATE_SRC_ADDR can be used.
+/**
+ * igc_del_mac_filter() - Delete MAC address filter
+ * @adapter: Pointer to adapter where the filter should be deleted from
+ * @addr: MAC address
+ * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source
+ *         address
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
  */
 static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-			      const u8 queue, const u8 flags)
+			      const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -2249,17 +2252,11 @@ static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
-	/* Search for matching entry in the MAC table based on given address
-	 * and queue. Do not touch entries at the end of the table reserved
-	 * for the VF MAC addresses.
-	 */
 	for (i = 0; i < rar_entries; i++) {
 		if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
 			continue;
 		if (flags && (adapter->mac_table[i].state & flags) != flags)
 			continue;
-		if (adapter->mac_table[i].queue != queue)
-			continue;
 		if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
 			continue;
 
@@ -2295,7 +2292,7 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_del_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
+	return igc_del_mac_filter(adapter, addr, 0);
 }
 
 /**
@@ -3738,7 +3735,7 @@ int igc_add_mac_steering_filter(struct igc_adapter *adapter,
 int igc_del_mac_steering_filter(struct igc_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags)
 {
-	return igc_del_mac_filter(adapter, addr, queue,
+	return igc_del_mac_filter(adapter, addr,
 				  IGC_MAC_STATE_QUEUE_STEERING | flags);
 }
 
-- 
cgit v1.2.3


From e9736fa407e53224e9f23a092b17d8f2d1eb705d Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 1 Apr 2020 14:43:58 -0700
Subject: igc: Remove IGC_MAC_STATE_QUEUE_STEERING

The IGC_MAC_STATE_QUEUE_STEERING bit in mac_table[i].state is
utilized to indicate that frames matching the filter are assigned to
mac_table[i].queue. This bit is not strictly necessary since we can
convey the same information as follows: queue == -1 means queue
assignment is disabled, otherwise it is enabled.

In addition to make the code simpler, this change fixes some awkward
situations where we pass a complete misleading 'queue' value such as in
igc_uc_sync().

So this patch removes IGC_MAC_STATE_QUEUE_STEERING and also takes the
opportunity to improve the igc_add_mac_filter documentation.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      |  3 +--
 drivers/net/ethernet/intel/igc/igc_main.c | 32 ++++++++++++++++++-------------
 2 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5f21dcfe99ce..8d5ebe2103ee 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -466,14 +466,13 @@ struct igc_nfc_filter {
 
 struct igc_mac_addr {
 	u8 addr[ETH_ALEN];
-	u8 queue;
+	s8 queue;
 	u8 state; /* bitmask */
 };
 
 #define IGC_MAC_STATE_DEFAULT		0x1
 #define IGC_MAC_STATE_IN_USE		0x2
 #define IGC_MAC_STATE_SRC_ADDR		0x4
-#define IGC_MAC_STATE_QUEUE_STEERING	0x8
 
 #define IGC_MAX_RXNFC_FILTERS		16
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index badb8ecf38dc..e195400cd490 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -820,8 +820,9 @@ static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 
 	ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
 	mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+	mac_table->queue = -1;
 
-	igc_set_mac_filter_hw(adapter, 0, mac_table->addr, -1);
+	igc_set_mac_filter_hw(adapter, 0, mac_table->addr, mac_table->queue);
 }
 
 /**
@@ -2196,13 +2197,20 @@ static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
 	return true;
 }
 
-/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
- * 'flags' is used to indicate what kind of match is made, match is by
- * default for the destination address, if matching by source address
- * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
+/**
+ * igc_add_mac_filter() - Add MAC address filter
+ * @adapter: Pointer to adapter where the filter should be added
+ * @addr: MAC address
+ * @queue: If non-negative, queue assignment feature is enabled and frames
+ *         matching the filter are enqueued onto 'queue'. Otherwise, queue
+ *         assignment is disabled.
+ * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source
+ *         address
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
  */
 static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-			      const u8 queue, const u8 flags)
+			      const s8 queue, const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -2266,11 +2274,11 @@ static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
 			adapter->mac_table[i].state =
 				IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
-			adapter->mac_table[i].queue = 0;
+			adapter->mac_table[i].queue = -1;
 			igc_set_mac_filter_hw(adapter, 0, addr, -1);
 		} else {
 			adapter->mac_table[i].state = 0;
-			adapter->mac_table[i].queue = 0;
+			adapter->mac_table[i].queue = -1;
 			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
 			igc_clear_mac_filter_hw(adapter, i);
 		}
@@ -2285,7 +2293,7 @@ static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_add_mac_filter(adapter, addr, adapter->num_rx_queues, 0);
+	return igc_add_mac_filter(adapter, addr, -1, 0);
 }
 
 static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
@@ -3728,15 +3736,13 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev,
 int igc_add_mac_steering_filter(struct igc_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags)
 {
-	return igc_add_mac_filter(adapter, addr, queue,
-				  IGC_MAC_STATE_QUEUE_STEERING | flags);
+	return igc_add_mac_filter(adapter, addr, queue, flags);
 }
 
 int igc_del_mac_steering_filter(struct igc_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags)
 {
-	return igc_del_mac_filter(adapter, addr,
-				  IGC_MAC_STATE_QUEUE_STEERING | flags);
+	return igc_del_mac_filter(adapter, addr, flags);
 }
 
 static void igc_tsync_interrupt(struct igc_adapter *adapter)
-- 
cgit v1.2.3


From 83ba21b9ef7706413bdaf9fa8357b93c4986d8a0 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:00:59 -0700
Subject: igc: Remove igc_*_mac_steering_filter() wrappers

With the previous two patches, igc_add_mac_steering_filter() and
igc_del_mac_steering_filter() became a pointless wrapper of
igc_add_mac_filter() and igc_del_mac_filter().

This patch removes these wrappers and update callers to call
igc_add_mac_filter() and igc_del_mac_filter() directly.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  8 ++++----
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 20 ++++++++------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 20 ++++----------------
 3 files changed, 16 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 8d5ebe2103ee..8ddc39482a8e 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -227,10 +227,10 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
 bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
-int igc_add_mac_steering_filter(struct igc_adapter *adapter,
-				const u8 *addr, u8 queue, u8 flags);
-int igc_del_mac_steering_filter(struct igc_adapter *adapter,
-				const u8 *addr, u8 queue, u8 flags);
+int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+		       const s8 queue, const u8 flags);
+int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+		       const u8 flags);
 void igc_update_stats(struct igc_adapter *adapter);
 
 /* igc_dump declarations */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index c9f4552c018b..0a8c4a7412a4 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1266,18 +1266,16 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
-		err = igc_add_mac_steering_filter(adapter,
-						  input->filter.dst_addr,
-						  input->action, 0);
+		err = igc_add_mac_filter(adapter, input->filter.dst_addr,
+					 input->action, 0);
 		if (err)
 			return err;
 	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-		err = igc_add_mac_steering_filter(adapter,
-						  input->filter.src_addr,
-						  input->action,
-						  IGC_MAC_STATE_SRC_ADDR);
+		err = igc_add_mac_filter(adapter, input->filter.src_addr,
+					 input->action,
+					 IGC_MAC_STATE_SRC_ADDR);
 		if (err)
 			return err;
 	}
@@ -1331,13 +1329,11 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 					   ntohs(input->filter.vlan_tci));
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
-		igc_del_mac_steering_filter(adapter, input->filter.src_addr,
-					    input->action,
-					    IGC_MAC_STATE_SRC_ADDR);
+		igc_del_mac_filter(adapter, input->filter.src_addr,
+				   IGC_MAC_STATE_SRC_ADDR);
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
-		igc_del_mac_steering_filter(adapter, input->filter.dst_addr,
-					    input->action, 0);
+		igc_del_mac_filter(adapter, input->filter.dst_addr, 0);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e195400cd490..3af6ce1712d5 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2209,8 +2209,8 @@ static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-			      const s8 queue, const u8 flags)
+int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+		       const s8 queue, const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -2250,8 +2250,8 @@ static int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-static int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-			      const u8 flags)
+int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+		       const u8 flags)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int rar_entries = hw->mac.rar_entry_count;
@@ -3733,18 +3733,6 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
-int igc_add_mac_steering_filter(struct igc_adapter *adapter,
-				const u8 *addr, u8 queue, u8 flags)
-{
-	return igc_add_mac_filter(adapter, addr, queue, flags);
-}
-
-int igc_del_mac_steering_filter(struct igc_adapter *adapter,
-				const u8 *addr, u8 queue, u8 flags)
-{
-	return igc_del_mac_filter(adapter, addr, flags);
-}
-
 static void igc_tsync_interrupt(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-- 
cgit v1.2.3


From 794e5bc817bcc16ca955691e957e23908edbef9c Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:01:00 -0700
Subject: igc: Refactor igc_mac_entry_can_be_used()

The helper igc_mac_entry_can_be_used() implementation is a bit
convoluted since it does two different things: find a not-in-use slot
in mac_table or find an in-use slot where the address and address type
match. This patch does a code refactoring and break it up into two
helper functions.

With this patch we might traverse mac_table twice in some situations,
but this is not harmful performance-wise (mac_table has only 16 entries
and adding mac filters is not hot-path), and it improves igc_add_mac_
filter() readability considerably.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 80 ++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 33 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 3af6ce1712d5..79a9875e0767 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2176,25 +2176,44 @@ static void igc_nfc_filter_restore(struct igc_adapter *adapter)
 	spin_unlock(&adapter->nfc_lock);
 }
 
-/* If the filter to be added and an already existing filter express
- * the same address and address type, it should be possible to only
- * override the other configurations, for example the queue to steer
- * traffic.
- */
-static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
-				      const u8 *addr, const u8 flags)
+static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr,
+			       u8 flags)
 {
-	if (!(entry->state & IGC_MAC_STATE_IN_USE))
-		return true;
+	int max_entries = adapter->hw.mac.rar_entry_count;
+	struct igc_mac_addr *entry;
+	int i;
 
-	if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
-	    (flags & IGC_MAC_STATE_SRC_ADDR))
-		return false;
+	for (i = 0; i < max_entries; i++) {
+		entry = &adapter->mac_table[i];
 
-	if (!ether_addr_equal(addr, entry->addr))
-		return false;
+		if (!(entry->state & IGC_MAC_STATE_IN_USE))
+			continue;
+		if (!ether_addr_equal(addr, entry->addr))
+			continue;
+		if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
+		    (flags & IGC_MAC_STATE_SRC_ADDR))
+			continue;
 
-	return true;
+		return i;
+	}
+
+	return -1;
+}
+
+static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
+{
+	int max_entries = adapter->hw.mac.rar_entry_count;
+	struct igc_mac_addr *entry;
+	int i;
+
+	for (i = 0; i < max_entries; i++) {
+		entry = &adapter->mac_table[i];
+
+		if (!(entry->state & IGC_MAC_STATE_IN_USE))
+			return i;
+	}
+
+	return -1;
 }
 
 /**
@@ -2212,33 +2231,28 @@ static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
 int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const s8 queue, const u8 flags)
 {
-	struct igc_hw *hw = &adapter->hw;
-	int rar_entries = hw->mac.rar_entry_count;
-	int i;
+	int index;
 
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 	if (flags & IGC_MAC_STATE_SRC_ADDR)
 		return -ENOTSUPP;
 
-	/* Search for the first empty entry in the MAC table.
-	 * Do not touch entries at the end of the table reserved for the VF MAC
-	 * addresses.
-	 */
-	for (i = 0; i < rar_entries; i++) {
-		if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
-					       addr, flags))
-			continue;
+	index = igc_find_mac_filter(adapter, addr, flags);
+	if (index >= 0)
+		goto update_queue_assignment;
 
-		ether_addr_copy(adapter->mac_table[i].addr, addr);
-		adapter->mac_table[i].queue = queue;
-		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
+	index = igc_get_avail_mac_filter_slot(adapter);
+	if (index < 0)
+		return -ENOSPC;
 
-		igc_set_mac_filter_hw(adapter, i, addr, queue);
-		return 0;
-	}
+	ether_addr_copy(adapter->mac_table[index].addr, addr);
+	adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE | flags;
+update_queue_assignment:
+	adapter->mac_table[index].queue = queue;
 
-	return -ENOSPC;
+	igc_set_mac_filter_hw(adapter, index, addr, queue);
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 5f930713728b5551f5c07b918cc8030dacb75fe1 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:01:01 -0700
Subject: igc: Refactor igc_del_mac_filter()

This patch does a code refactoring in igc_del_mac_filter() so it uses
the new helper igc_find_mac_filter() and improves the comment about the
special handling when deleting the default filter.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 45 +++++++++++++------------------
 1 file changed, 19 insertions(+), 26 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 79a9875e0767..78753f12b8a0 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2267,40 +2267,33 @@ update_queue_assignment:
 int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const u8 flags)
 {
-	struct igc_hw *hw = &adapter->hw;
-	int rar_entries = hw->mac.rar_entry_count;
-	int i;
+	struct igc_mac_addr *entry;
+	int index;
 
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
-	for (i = 0; i < rar_entries; i++) {
-		if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
-			continue;
-		if (flags && (adapter->mac_table[i].state & flags) != flags)
-			continue;
-		if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
-			continue;
+	index = igc_find_mac_filter(adapter, addr, flags);
+	if (index < 0)
+		return -ENOENT;
 
-		/* When a filter for the default address is "deleted",
-		 * we return it to its initial configuration
-		 */
-		if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
-			adapter->mac_table[i].state =
-				IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
-			adapter->mac_table[i].queue = -1;
-			igc_set_mac_filter_hw(adapter, 0, addr, -1);
-		} else {
-			adapter->mac_table[i].state = 0;
-			adapter->mac_table[i].queue = -1;
-			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
-			igc_clear_mac_filter_hw(adapter, i);
-		}
+	entry = &adapter->mac_table[index];
 
-		return 0;
+	if (entry->state & IGC_MAC_STATE_DEFAULT) {
+		/* If this is the default filter, we don't actually delete it.
+		 * We just reset to its default value i.e. disable queue
+		 * assignment.
+		 */
+		entry->queue = -1;
+		igc_set_mac_filter_hw(adapter, 0, addr, entry->queue);
+	} else {
+		entry->state = 0;
+		entry->queue = -1;
+		memset(entry->addr, 0, ETH_ALEN);
+		igc_clear_mac_filter_hw(adapter, index);
 	}
 
-	return -ENOENT;
+	return 0;
 }
 
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
-- 
cgit v1.2.3


From 949b922e8b1b2bebfec90c68edd888723ab8bc23 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Wed, 18 Mar 2020 16:01:02 -0700
Subject: igc: Add debug messages to MAC filter code

This patch adds log messages to functions related to the MAC address
filtering code to ease debugging.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 78753f12b8a0..9d5f8287c704 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -776,6 +776,7 @@ static void igc_setup_tctl(struct igc_adapter *adapter)
 static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
 				  const u8 *addr, int queue)
 {
+	struct net_device *dev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
 	u32 ral, rah;
 
@@ -795,6 +796,8 @@ static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
 
 	wr32(IGC_RAL(index), ral);
 	wr32(IGC_RAH(index), rah);
+
+	netdev_dbg(dev, "MAC address filter set in HW: index %d", index);
 }
 
 /**
@@ -804,6 +807,7 @@ static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
  */
 static void igc_clear_mac_filter_hw(struct igc_adapter *adapter, int index)
 {
+	struct net_device *dev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
 
 	if (WARN_ON(index >= hw->mac.rar_entry_count))
@@ -811,18 +815,24 @@ static void igc_clear_mac_filter_hw(struct igc_adapter *adapter, int index)
 
 	wr32(IGC_RAL(index), 0);
 	wr32(IGC_RAH(index), 0);
+
+	netdev_dbg(dev, "MAC address filter cleared in HW: index %d", index);
 }
 
 /* Set default MAC address for the PF in the first RAR entry */
 static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 {
 	struct igc_mac_addr *mac_table = &adapter->mac_table[0];
+	struct net_device *dev = adapter->netdev;
+	u8 *addr = adapter->hw.mac.addr;
+
+	netdev_dbg(dev, "Set default MAC address filter: address %pM", addr);
 
-	ether_addr_copy(mac_table->addr, adapter->hw.mac.addr);
+	ether_addr_copy(mac_table->addr, addr);
 	mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
 	mac_table->queue = -1;
 
-	igc_set_mac_filter_hw(adapter, 0, mac_table->addr, mac_table->queue);
+	igc_set_mac_filter_hw(adapter, 0, addr, mac_table->queue);
 }
 
 /**
@@ -2231,6 +2241,7 @@ static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
 int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const s8 queue, const u8 flags)
 {
+	struct net_device *dev = adapter->netdev;
 	int index;
 
 	if (!is_valid_ether_addr(addr))
@@ -2246,6 +2257,9 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	if (index < 0)
 		return -ENOSPC;
 
+	netdev_dbg(dev, "Add MAC address filter: index %d address %pM queue %d",
+		   index, addr, queue);
+
 	ether_addr_copy(adapter->mac_table[index].addr, addr);
 	adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE | flags;
 update_queue_assignment:
@@ -2267,6 +2281,7 @@ update_queue_assignment:
 int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const u8 flags)
 {
+	struct net_device *dev = adapter->netdev;
 	struct igc_mac_addr *entry;
 	int index;
 
@@ -2284,9 +2299,14 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		 * We just reset to its default value i.e. disable queue
 		 * assignment.
 		 */
+		netdev_dbg(dev, "Disable default MAC filter queue assignment");
+
 		entry->queue = -1;
 		igc_set_mac_filter_hw(adapter, 0, addr, entry->queue);
 	} else {
+		netdev_dbg(dev, "Delete MAC address filter: index %d address %pM",
+			   index, addr);
+
 		entry->state = 0;
 		entry->queue = -1;
 		memset(entry->addr, 0, ETH_ALEN);
-- 
cgit v1.2.3


From 6d92797716003a462bd75bbda3740718ce54bcdd Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Sat, 18 Apr 2020 16:42:12 +0800
Subject: net: hns: use true,false for bool variables

Fix the following coccicheck warning:

drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:700:2-8: WARNING:
Assignment of 0/1 to bool variable
drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:702:2-8: WARNING:
Assignment of 0/1 to bool variable

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 8aace2de0cc9..9a907947ba19 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -697,9 +697,9 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 		return rc;
 
 	if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_XGMII)))
-		is_c45 = 1;
+		is_c45 = true;
 	else if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_SGMII)))
-		is_c45 = 0;
+		is_c45 = false;
 	else
 		return -ENODATA;
 
-- 
cgit v1.2.3


From 109f0cf23b094b0b780a22ce1c9ea267ebcd3974 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 18 Apr 2020 22:09:42 +0200
Subject: r8169: remove PHY resume delay that is handled in the PHY driver now

The Realtek PHY driver takes care of adding the needed delay now,
therefore we can remove the delay here.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a8696d958cd1..1bc415d00cb8 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2391,8 +2391,6 @@ static void rtl_pll_power_up(struct rtl8169_private *tp)
 	}
 
 	phy_resume(tp->phydev);
-	/* give MAC/PHY some time to resume */
-	msleep(20);
 }
 
 static void rtl_init_rxcfg(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From cec2500d44751a7782d16ce99fca104e77e324a5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 19 Apr 2020 10:01:05 +0300
Subject: mlxsw: spectrum_router: Re-increase scale of IPv6 nexthop groups

As explained in commit fc25996e6f46 ("mlxsw: spectrum_router: Increase
scale of IPv6 nexthop groups"), each nexthop group is hashed by XOR-ing
the interface indexes of all the member nexthop devices.

To avoid many different nexthop groups ending up using the same key, the
above commit started hashing the interface indexes themselves before
they are XOR-ed.

However, in cases in which there are many nexthop groups that all use
the same nexthop device and only differ in the gateway IP, we can still
end up in a situation in which all the groups are using the same key.
This eventually leads to -EBUSY error from rhashtable during insertion.

Improve the situation by also making the gateway IP part of the key.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Veber <alexve@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Tested-by: Alex Veber <alexve@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index d5bca1be3ef5..71aee4914619 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2999,6 +2999,7 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed)
 		for (i = 0; i < nh_grp->count; i++) {
 			nh = &nh_grp->nexthops[i];
 			val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed);
+			val ^= jhash(&nh->gw_addr, sizeof(nh->gw_addr), seed);
 		}
 		return jhash(&val, sizeof(val), seed);
 	default:
@@ -3012,11 +3013,14 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed)
 {
 	unsigned int val = fib6_entry->nrt6;
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
-	struct net_device *dev;
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
-		dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev;
+		struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
+		struct net_device *dev = fib6_nh->fib_nh_dev;
+		struct in6_addr *gw = &fib6_nh->fib_nh_gw6;
+
 		val ^= jhash(&dev->ifindex, sizeof(dev->ifindex), seed);
+		val ^= jhash(gw, sizeof(*gw), seed);
 	}
 
 	return jhash(&val, sizeof(val), seed);
-- 
cgit v1.2.3


From b7f03b0b2a213474f452a802769ecd9fcee209a9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 19 Apr 2020 10:01:06 +0300
Subject: mlxsw: reg: Increase register field length to 13 bits

The Infrastructure Entry Delete Register (IEDR) is used to delete
entries stored in the KVD linear database. Currently, it is only
possible to delete entries of size up to 2048. Future firmware versions
will support deletion of entries of size up to 4096.

Increase the size of the field so that the driver will be able to
perform such deletions in the future, when required.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 9b39b8e70519..3c3db1c874b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3203,7 +3203,7 @@ MLXSW_ITEM32_INDEXED(reg, iedr, rec_type, MLXSW_REG_IEDR_BASE_LEN, 24, 8,
  * Size of entries do be deleted. The unit is 1 entry, regardless of entry type.
  * Access: OP
  */
-MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 11,
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 13,
 		     MLXSW_REG_IEDR_REC_LEN, 0x00, false);
 
 /* reg_iedr_rec_index_start
-- 
cgit v1.2.3


From 92efe48e8fe2b6848ca56e14436c2b7d20c986d4 Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Sun, 19 Apr 2020 20:02:53 +0800
Subject: net: ethernet: dnet: convert to
 devm_platform_get_and_ioremap_resource

use devm_platform_get_and_ioremap_resource() to simplify code, which
contains platform_get_resource() and devm_ioremap_resource(), it also
get the resource for use by the following code.

Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dnet.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index 057a508dd6e2..db98274501a0 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -776,8 +776,7 @@ static int dnet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&bp->lock);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	bp->regs = devm_ioremap_resource(&pdev->dev, res);
+	bp->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(bp->regs)) {
 		err = PTR_ERR(bp->regs);
 		goto err_out_free_dev;
-- 
cgit v1.2.3


From 5333fdbed0c860c7a17dc12f328203d29947eff7 Mon Sep 17 00:00:00 2001
From: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Date: Sun, 19 Apr 2020 21:14:43 +0530
Subject: net: sun: Remove unneeded cast from memory allocation

Remove casting the values returned by memory allocation function.

Coccinelle emits WARNING: casting value returned by memory allocation
function to (struct cas_init_block *) is useless.

This issue was detected by using the Coccinelle software.

Signed-off-by: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/cassini.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index e6d1aa882fa5..3ee6ab104cb9 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -5059,7 +5059,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (cp->cas_flags & CAS_FLAG_SATURN)
 		cas_saturn_firmware_init(cp);
 
-	cp->init_block = (struct cas_init_block *)
+	cp->init_block =
 		pci_alloc_consistent(pdev, sizeof(struct cas_init_block),
 				     &cp->block_dvma);
 	if (!cp->init_block) {
-- 
cgit v1.2.3


From 745e5ad5084db32e093a143de324afa4ed95f14d Mon Sep 17 00:00:00 2001
From: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Date: Sun, 19 Apr 2020 21:59:17 +0530
Subject: net: qed: Remove unneeded cast from memory allocation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove casting the values returned by memory allocation function.

Coccinelle emits WARNING: casting value returned by memory allocation
function to struct pointer is useless.

This issue was detected by using the Coccinelle.

Signed-off-by: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_roce.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 37e70562a964..475b89903f46 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -736,9 +736,9 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 
 	p_ramrod = &p_ent->ramrod.roce_destroy_qp_resp;
 
-	p_ramrod_res = (struct roce_destroy_qp_resp_output_params *)
-	    dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, sizeof(*p_ramrod_res),
-			       &ramrod_res_phys, GFP_KERNEL);
+	p_ramrod_res = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+					  sizeof(*p_ramrod_res),
+					  &ramrod_res_phys, GFP_KERNEL);
 
 	if (!p_ramrod_res) {
 		rc = -ENOMEM;
@@ -872,10 +872,10 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Send a query responder ramrod to FW to get RQ-PSN and state */
-	p_resp_ramrod_res = (struct roce_query_qp_resp_output_params *)
-	    dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
-			       sizeof(*p_resp_ramrod_res),
-			       &resp_ramrod_res_phys, GFP_KERNEL);
+	p_resp_ramrod_res =
+		dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+				   sizeof(*p_resp_ramrod_res),
+				   &resp_ramrod_res_phys, GFP_KERNEL);
 	if (!p_resp_ramrod_res) {
 		DP_NOTICE(p_hwfn,
 			  "qed query qp failed: cannot allocate memory (ramrod)\n");
@@ -920,8 +920,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 	}
 
 	/* Send a query requester ramrod to FW to get SQ-PSN and state */
-	p_req_ramrod_res = (struct roce_query_qp_req_output_params *)
-			   dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+	p_req_ramrod_res = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
 					      sizeof(*p_req_ramrod_res),
 					      &req_ramrod_res_phys,
 					      GFP_KERNEL);
-- 
cgit v1.2.3


From 2ac1fa439ee97aaaa124c37340a316918bb0a8bc Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 19 Apr 2020 23:07:39 +0200
Subject: r8169: inline rtl8169_mark_as_last_descriptor

rtl8169_mark_as_last_descriptor() has just one user, so inline it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1bc415d00cb8..3b8ae49c3ea2 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3939,11 +3939,6 @@ static void rtl8169_rx_clear(struct rtl8169_private *tp)
 	}
 }
 
-static inline void rtl8169_mark_as_last_descriptor(struct RxDesc *desc)
-{
-	desc->opts1 |= cpu_to_le32(RingEnd);
-}
-
 static int rtl8169_rx_fill(struct rtl8169_private *tp)
 {
 	unsigned int i;
@@ -3959,7 +3954,8 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp)
 		tp->Rx_databuff[i] = data;
 	}
 
-	rtl8169_mark_as_last_descriptor(tp->RxDescArray + NUM_RX_DESC - 1);
+	/* mark as last descriptor in the ring */
+	tp->RxDescArray[NUM_RX_DESC - 1].opts1 |= cpu_to_le32(RingEnd);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 9d3679fe0f30b5a4c1ae6303611c9f2bbeb9961d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 19 Apr 2020 23:16:55 +0200
Subject: r8169: inline rtl8169_make_unusable_by_asic

Inline rtl8169_make_unusable_by_asic() and simplify it:
- Address field doesn't need to be poisoned because descriptor is
  owned by CPU now
- desc->opts1 is set by rtl8169_mark_to_asic() and rtl8169_rx_fill(),
  therefore we don't have to preserve any field parts.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 3b8ae49c3ea2..b8cc064ee9f5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3882,12 +3882,6 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc)
-{
-	desc->addr = cpu_to_le64(0x0badbadbadbadbadull);
-	desc->opts1 &= ~cpu_to_le32(DescOwn | RsvdMask);
-}
-
 static inline void rtl8169_mark_to_asic(struct RxDesc *desc)
 {
 	u32 eor = le32_to_cpu(desc->opts1) & RingEnd;
@@ -3935,7 +3929,8 @@ static void rtl8169_rx_clear(struct rtl8169_private *tp)
 			       R8169_RX_BUF_SIZE, DMA_FROM_DEVICE);
 		__free_pages(tp->Rx_databuff[i], get_order(R8169_RX_BUF_SIZE));
 		tp->Rx_databuff[i] = NULL;
-		rtl8169_make_unusable_by_asic(tp->RxDescArray + i);
+		tp->RxDescArray[i].addr = 0;
+		tp->RxDescArray[i].opts1 = 0;
 	}
 }
 
-- 
cgit v1.2.3


From 29ae6bd1b0d8a57d7c00ab12cbb949fc41986eef Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 20 Apr 2020 00:04:00 +0200
Subject: net: ethernet: fec: Replace interrupt driven MDIO with polled IO

Measurements of the MDIO bus have shown that driving the MDIO bus
using interrupts is slow. Back to back MDIO transactions take about
90us, with 25us spent performing the transaction, and the remainder of
the time the bus is idle.

Replacing the completion interrupt with polled IO results in back to
back transactions of 40us. The polling loop waiting for the hardware
to complete the transaction takes around 28us. Which suggests
interrupt handling has an overhead of 50us, and polled IO nearly
halves this overhead, and doubles the MDIO performance.

Suggested-by: Chris Heally <cphealy@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |  4 +-
 drivers/net/ethernet/freescale/fec_main.c | 67 ++++++++++++++++---------------
 2 files changed, 35 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index e74dd1f86bba..a6cdd5b61921 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -376,8 +376,7 @@ struct bufdesc_ex {
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
 #define FEC_ENET_TS_TIMER       ((uint)0x00008000)
 
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
-#define FEC_NAPI_IMASK	FEC_ENET_MII
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF)
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
 /* ENET interrupt coalescing macro define */
@@ -543,7 +542,6 @@ struct fec_enet_private {
 	int	link;
 	int	full_duplex;
 	int	speed;
-	struct	completion mdio_done;
 	int	irq[FEC_IRQ_NUM];
 	bool	bufdesc_ex;
 	int	pause_flag;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index dc6f8763a5d4..2267bf75784e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -976,8 +976,8 @@ fec_restart(struct net_device *ndev)
 	writel((__force u32)cpu_to_be32(temp_mac[1]),
 	       fep->hwp + FEC_ADDR_HIGH);
 
-	/* Clear any outstanding interrupt. */
-	writel(0xffffffff, fep->hwp + FEC_IEVENT);
+	/* Clear any outstanding interrupt, except MDIO. */
+	writel((0xffffffff & ~FEC_ENET_MII), fep->hwp + FEC_IEVENT);
 
 	fec_enet_bd_init(ndev);
 
@@ -1123,7 +1123,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->link)
 		writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 	else
-		writel(FEC_ENET_MII, fep->hwp + FEC_IMASK);
+		writel(0, fep->hwp + FEC_IMASK);
 
 	/* Init the interrupt coalescing */
 	fec_enet_itr_coal_init(ndev);
@@ -1652,6 +1652,10 @@ fec_enet_interrupt(int irq, void *dev_id)
 	irqreturn_t ret = IRQ_NONE;
 
 	int_events = readl(fep->hwp + FEC_IEVENT);
+
+	/* Don't clear MDIO events, we poll for those */
+	int_events &= ~FEC_ENET_MII;
+
 	writel(int_events, fep->hwp + FEC_IEVENT);
 	fec_enet_collect_events(fep, int_events);
 
@@ -1659,16 +1663,12 @@ fec_enet_interrupt(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 
 		if (napi_schedule_prep(&fep->napi)) {
-			/* Disable the NAPI interrupts */
-			writel(FEC_NAPI_IMASK, fep->hwp + FEC_IMASK);
+			/* Disable interrupts */
+			writel(0, fep->hwp + FEC_IMASK);
 			__napi_schedule(&fep->napi);
 		}
 	}
 
-	if (int_events & FEC_ENET_MII) {
-		ret = IRQ_HANDLED;
-		complete(&fep->mdio_done);
-	}
 	return ret;
 }
 
@@ -1818,11 +1818,24 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 		phy_print_status(phy_dev);
 }
 
+static int fec_enet_mdio_wait(struct fec_enet_private *fep)
+{
+	uint ievent;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(fep->hwp + FEC_IEVENT, ievent,
+					ievent & FEC_ENET_MII, 2, 30000);
+
+	if (!ret)
+		writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
+
+	return ret;
+}
+
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
-	unsigned long time_left;
 	int ret = 0, frame_start, frame_addr, frame_op;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1830,8 +1843,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ret < 0)
 		return ret;
 
-	reinit_completion(&fep->mdio_done);
-
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1843,11 +1854,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		time_left = wait_for_completion_timeout(&fep->mdio_done,
-				usecs_to_jiffies(FEC_MII_TIMEOUT));
-		if (time_left == 0) {
+		ret = fec_enet_mdio_wait(fep);
+		if (ret) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
-			ret = -ETIMEDOUT;
 			goto out;
 		}
 
@@ -1866,11 +1875,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		FEC_MMFR_TA, fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-	if (time_left == 0) {
+	ret = fec_enet_mdio_wait(fep);
+	if (ret) {
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		ret = -ETIMEDOUT;
 		goto out;
 	}
 
@@ -1888,7 +1895,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
-	unsigned long time_left;
 	int ret, frame_start, frame_addr;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1898,8 +1904,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	else
 		ret = 0;
 
-	reinit_completion(&fep->mdio_done);
-
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1911,11 +1915,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-		if (time_left == 0) {
+		ret = fec_enet_mdio_wait(fep);
+		if (ret) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
-			ret = -ETIMEDOUT;
 			goto out;
 		}
 	} else {
@@ -1931,12 +1933,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-	if (time_left == 0) {
+	ret = fec_enet_mdio_wait(fep);
+	if (ret)
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		ret  = -ETIMEDOUT;
-	}
 
 out:
 	pm_runtime_mark_last_busy(dev);
@@ -2132,6 +2131,9 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
+	/* Clear any pending transaction complete indication */
+	writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
+
 	fep->mii_bus = mdiobus_alloc();
 	if (fep->mii_bus == NULL) {
 		err = -ENOMEM;
@@ -3674,7 +3676,6 @@ fec_probe(struct platform_device *pdev)
 		fep->irq[i] = irq;
 	}
 
-	init_completion(&fep->mdio_done);
 	ret = fec_enet_mii_init(pdev);
 	if (ret)
 		goto failed_mii_init;
-- 
cgit v1.2.3


From 3e782985cb3ce00a32c372b37d8feefdae18ddf1 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 20 Apr 2020 00:04:01 +0200
Subject: net: ethernet: fec: Allow configuration of MDIO bus speed

MDIO busses typically operate at 2.5MHz. However many devices can
operate at faster speeds. This then allows more MDIO transactions per
second, useful for Ethernet switch statistics, or Ethernet PHY TDR
data. Allow the bus speed to be configured, using the standard
"clock-frequency" property, which i2c busses use to indicate the bus
speed. Before using this property, ensure all devices on the bus do
actually support the requested clock speed.

Suggested-by: Chris Healy <Chris.Healy@zii.aero>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/fsl-fec.txt |  1 +
 Documentation/devicetree/bindings/net/mdio.yaml   |  6 ++++++
 drivers/net/ethernet/freescale/fec_main.c         | 11 ++++++++---
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index ff8b0f211aa1..26c492a2e0e1 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -82,6 +82,7 @@ ethernet@83fec000 {
 	phy-supply = <&reg_fec_supply>;
 	phy-handle = <&ethphy>;
 	mdio {
+	        clock-frequency = <5000000>;
 		ethphy: ethernet-phy@6 {
 			compatible = "ethernet-phy-ieee802.3-c22";
 			reg = <6>;
diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml
index 50c3397a82bc..ab4a9df8b8e2 100644
--- a/Documentation/devicetree/bindings/net/mdio.yaml
+++ b/Documentation/devicetree/bindings/net/mdio.yaml
@@ -39,6 +39,12 @@ properties:
       and must therefore be appropriately determined based on all PHY
       requirements (maximum value of all per-PHY RESET pulse widths).
 
+  clock-frequency:
+    description:
+      Desired MDIO bus clock frequency in Hz. Values greater than IEEE 802.3
+      defined 2.5MHz should only be used when all devices on the bus support
+      the given clock speed.
+
 patternProperties:
   "^ethernet-phy@[0-9a-f]+$":
     type: object
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2267bf75784e..832a24e2805c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2067,6 +2067,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	struct device_node *node;
 	int err = -ENXIO;
 	u32 mii_speed, holdtime;
+	u32 bus_freq;
 
 	/*
 	 * The i.MX28 dual fec interfaces are not equal.
@@ -2094,15 +2095,20 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
+	bus_freq = 2500000; /* 2.5MHz by default */
+	node = of_get_child_by_name(pdev->dev.of_node, "mdio");
+	if (node)
+		of_property_read_u32(node, "clock-frequency", &bus_freq);
+
 	/*
-	 * Set MII speed to 2.5 MHz (= clk_get_rate() / 2 * phy_speed)
+	 * Set MII speed (= clk_get_rate() / 2 * phy_speed)
 	 *
 	 * The formula for FEC MDC is 'ref_freq / (MII_SPEED x 2)' while
 	 * for ENET-MAC is 'ref_freq / ((MII_SPEED + 1) x 2)'.  The i.MX28
 	 * Reference Manual has an error on this, and gets fixed on i.MX6Q
 	 * document.
 	 */
-	mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000);
+	mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), bus_freq * 2);
 	if (fep->quirks & FEC_QUIRK_ENET_MAC)
 		mii_speed--;
 	if (mii_speed > 63) {
@@ -2148,7 +2154,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	fep->mii_bus->priv = fep;
 	fep->mii_bus->parent = &pdev->dev;
 
-	node = of_get_child_by_name(pdev->dev.of_node, "mdio");
 	err = of_mdiobus_register(fep->mii_bus, node);
 	of_node_put(node);
 	if (err)
-- 
cgit v1.2.3


From 3c01eb62d1bd85a5dd1d22d74339728666ae2c45 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 20 Apr 2020 00:04:02 +0200
Subject: net: ethernet: fec: Allow the MDIO preamble to be disabled

An MDIO transaction normally starts with 32 1s as a preamble. However
not all devices requires such a preamble. Add a device tree property
which allows the preamble to be suppressed. This will half the size of
the MDIO transaction, allowing faster transactions. But it should only
be used when all devices on the bus support suppressed preamble.

Suggested-by: Chris Healy <Chris.Healy@zii.aero>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/mdio.yaml | 6 ++++++
 drivers/net/ethernet/freescale/fec_main.c       | 9 ++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml
index ab4a9df8b8e2..cd6c6ae6dabb 100644
--- a/Documentation/devicetree/bindings/net/mdio.yaml
+++ b/Documentation/devicetree/bindings/net/mdio.yaml
@@ -45,6 +45,12 @@ properties:
       defined 2.5MHz should only be used when all devices on the bus support
       the given clock speed.
 
+  suppress-preamble:
+    description:
+      The 32 bit preamble should be suppressed. In order for this to
+      work, all devices on the bus must support suppressed preamble.
+    type: boolean
+
 patternProperties:
   "^ethernet-phy@[0-9a-f]+$":
     type: object
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 832a24e2805c..1ae075a246a3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2064,6 +2064,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	static struct mii_bus *fec0_mii_bus;
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	bool suppress_preamble = false;
 	struct device_node *node;
 	int err = -ENXIO;
 	u32 mii_speed, holdtime;
@@ -2097,8 +2098,11 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 
 	bus_freq = 2500000; /* 2.5MHz by default */
 	node = of_get_child_by_name(pdev->dev.of_node, "mdio");
-	if (node)
+	if (node) {
 		of_property_read_u32(node, "clock-frequency", &bus_freq);
+		suppress_preamble = of_property_read_bool(node,
+							  "suppress-preamble");
+	}
 
 	/*
 	 * Set MII speed (= clk_get_rate() / 2 * phy_speed)
@@ -2135,6 +2139,9 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 
 	fep->phy_speed = mii_speed << 1 | holdtime << 8;
 
+	if (suppress_preamble)
+		fep->phy_speed |= BIT(7);
+
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 	/* Clear any pending transaction complete indication */
-- 
cgit v1.2.3


From 736fc0e17fade807e59cd9001af88ec4bcca62ef Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Mon, 20 Apr 2020 10:17:26 +0800
Subject: net: hns3: split out hclge_fd_check_ether_tuple()

For readability and maintainability, this patch separates the
handling part of each flow type in hclge_fd_check_ether_tuple()
into standalone functions.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 285 +++++++++++++--------
 1 file changed, 173 insertions(+), 112 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a758f9ae32be..80d0651145df 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5244,157 +5244,158 @@ static int hclge_config_action(struct hclge_dev *hdev, u8 stage,
 	return hclge_fd_ad_config(hdev, stage, ad_data.ad_id, &ad_data);
 }
 
-static int hclge_fd_check_spec(struct hclge_dev *hdev,
-			       struct ethtool_rx_flow_spec *fs, u32 *unused)
+static int hclge_fd_check_tcpip4_tuple(struct ethtool_tcpip4_spec *spec,
+				       u32 *unused_tuple)
 {
-	struct ethtool_tcpip4_spec *tcp_ip4_spec;
-	struct ethtool_usrip4_spec *usr_ip4_spec;
-	struct ethtool_tcpip6_spec *tcp_ip6_spec;
-	struct ethtool_usrip6_spec *usr_ip6_spec;
-	struct ethhdr *ether_spec;
-
-	if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
+	if (!spec || !unused_tuple)
 		return -EINVAL;
 
-	if (!(fs->flow_type & hdev->fd_cfg.proto_support))
-		return -EOPNOTSUPP;
-
-	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) {
-		dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n");
-		return -EOPNOTSUPP;
-	}
+	*unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC);
 
-	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
-	case SCTP_V4_FLOW:
-	case TCP_V4_FLOW:
-	case UDP_V4_FLOW:
-		tcp_ip4_spec = &fs->h_u.tcp_ip4_spec;
-		*unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC);
+	if (!spec->ip4src)
+		*unused_tuple |= BIT(INNER_SRC_IP);
 
-		if (!tcp_ip4_spec->ip4src)
-			*unused |= BIT(INNER_SRC_IP);
+	if (!spec->ip4dst)
+		*unused_tuple |= BIT(INNER_DST_IP);
 
-		if (!tcp_ip4_spec->ip4dst)
-			*unused |= BIT(INNER_DST_IP);
+	if (!spec->psrc)
+		*unused_tuple |= BIT(INNER_SRC_PORT);
 
-		if (!tcp_ip4_spec->psrc)
-			*unused |= BIT(INNER_SRC_PORT);
+	if (!spec->pdst)
+		*unused_tuple |= BIT(INNER_DST_PORT);
 
-		if (!tcp_ip4_spec->pdst)
-			*unused |= BIT(INNER_DST_PORT);
+	if (!spec->tos)
+		*unused_tuple |= BIT(INNER_IP_TOS);
 
-		if (!tcp_ip4_spec->tos)
-			*unused |= BIT(INNER_IP_TOS);
+	return 0;
+}
 
-		break;
-	case IP_USER_FLOW:
-		usr_ip4_spec = &fs->h_u.usr_ip4_spec;
-		*unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
-			BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT);
+static int hclge_fd_check_ip4_tuple(struct ethtool_usrip4_spec *spec,
+				    u32 *unused_tuple)
+{
+	if (!spec || !unused_tuple)
+		return -EINVAL;
 
-		if (!usr_ip4_spec->ip4src)
-			*unused |= BIT(INNER_SRC_IP);
+	*unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
+		BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT);
 
-		if (!usr_ip4_spec->ip4dst)
-			*unused |= BIT(INNER_DST_IP);
+	if (!spec->ip4src)
+		*unused_tuple |= BIT(INNER_SRC_IP);
 
-		if (!usr_ip4_spec->tos)
-			*unused |= BIT(INNER_IP_TOS);
+	if (!spec->ip4dst)
+		*unused_tuple |= BIT(INNER_DST_IP);
 
-		if (!usr_ip4_spec->proto)
-			*unused |= BIT(INNER_IP_PROTO);
+	if (!spec->tos)
+		*unused_tuple |= BIT(INNER_IP_TOS);
 
-		if (usr_ip4_spec->l4_4_bytes)
-			return -EOPNOTSUPP;
+	if (!spec->proto)
+		*unused_tuple |= BIT(INNER_IP_PROTO);
 
-		if (usr_ip4_spec->ip_ver != ETH_RX_NFC_IP4)
-			return -EOPNOTSUPP;
+	if (spec->l4_4_bytes)
+		return -EOPNOTSUPP;
 
-		break;
-	case SCTP_V6_FLOW:
-	case TCP_V6_FLOW:
-	case UDP_V6_FLOW:
-		tcp_ip6_spec = &fs->h_u.tcp_ip6_spec;
-		*unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
-			BIT(INNER_IP_TOS);
+	if (spec->ip_ver != ETH_RX_NFC_IP4)
+		return -EOPNOTSUPP;
 
-		/* check whether src/dst ip address used */
-		if (!tcp_ip6_spec->ip6src[0] && !tcp_ip6_spec->ip6src[1] &&
-		    !tcp_ip6_spec->ip6src[2] && !tcp_ip6_spec->ip6src[3])
-			*unused |= BIT(INNER_SRC_IP);
+	return 0;
+}
 
-		if (!tcp_ip6_spec->ip6dst[0] && !tcp_ip6_spec->ip6dst[1] &&
-		    !tcp_ip6_spec->ip6dst[2] && !tcp_ip6_spec->ip6dst[3])
-			*unused |= BIT(INNER_DST_IP);
+static int hclge_fd_check_tcpip6_tuple(struct ethtool_tcpip6_spec *spec,
+				       u32 *unused_tuple)
+{
+	if (!spec || !unused_tuple)
+		return -EINVAL;
 
-		if (!tcp_ip6_spec->psrc)
-			*unused |= BIT(INNER_SRC_PORT);
+	*unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
+		BIT(INNER_IP_TOS);
 
-		if (!tcp_ip6_spec->pdst)
-			*unused |= BIT(INNER_DST_PORT);
+	/* check whether src/dst ip address used */
+	if (!spec->ip6src[0] && !spec->ip6src[1] &&
+	    !spec->ip6src[2] && !spec->ip6src[3])
+		*unused_tuple |= BIT(INNER_SRC_IP);
 
-		if (tcp_ip6_spec->tclass)
-			return -EOPNOTSUPP;
+	if (!spec->ip6dst[0] && !spec->ip6dst[1] &&
+	    !spec->ip6dst[2] && !spec->ip6dst[3])
+		*unused_tuple |= BIT(INNER_DST_IP);
 
-		break;
-	case IPV6_USER_FLOW:
-		usr_ip6_spec = &fs->h_u.usr_ip6_spec;
-		*unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
-			BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) |
-			BIT(INNER_DST_PORT);
+	if (!spec->psrc)
+		*unused_tuple |= BIT(INNER_SRC_PORT);
 
-		/* check whether src/dst ip address used */
-		if (!usr_ip6_spec->ip6src[0] && !usr_ip6_spec->ip6src[1] &&
-		    !usr_ip6_spec->ip6src[2] && !usr_ip6_spec->ip6src[3])
-			*unused |= BIT(INNER_SRC_IP);
+	if (!spec->pdst)
+		*unused_tuple |= BIT(INNER_DST_PORT);
 
-		if (!usr_ip6_spec->ip6dst[0] && !usr_ip6_spec->ip6dst[1] &&
-		    !usr_ip6_spec->ip6dst[2] && !usr_ip6_spec->ip6dst[3])
-			*unused |= BIT(INNER_DST_IP);
+	if (spec->tclass)
+		return -EOPNOTSUPP;
 
-		if (!usr_ip6_spec->l4_proto)
-			*unused |= BIT(INNER_IP_PROTO);
+	return 0;
+}
 
-		if (usr_ip6_spec->tclass)
-			return -EOPNOTSUPP;
+static int hclge_fd_check_ip6_tuple(struct ethtool_usrip6_spec *spec,
+				    u32 *unused_tuple)
+{
+	if (!spec || !unused_tuple)
+		return -EINVAL;
 
-		if (usr_ip6_spec->l4_4_bytes)
-			return -EOPNOTSUPP;
+	*unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
+		BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT);
 
-		break;
-	case ETHER_FLOW:
-		ether_spec = &fs->h_u.ether_spec;
-		*unused |= BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) |
-			BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT) |
-			BIT(INNER_IP_TOS) | BIT(INNER_IP_PROTO);
+	/* check whether src/dst ip address used */
+	if (!spec->ip6src[0] && !spec->ip6src[1] &&
+	    !spec->ip6src[2] && !spec->ip6src[3])
+		*unused_tuple |= BIT(INNER_SRC_IP);
 
-		if (is_zero_ether_addr(ether_spec->h_source))
-			*unused |= BIT(INNER_SRC_MAC);
+	if (!spec->ip6dst[0] && !spec->ip6dst[1] &&
+	    !spec->ip6dst[2] && !spec->ip6dst[3])
+		*unused_tuple |= BIT(INNER_DST_IP);
 
-		if (is_zero_ether_addr(ether_spec->h_dest))
-			*unused |= BIT(INNER_DST_MAC);
+	if (!spec->l4_proto)
+		*unused_tuple |= BIT(INNER_IP_PROTO);
 
-		if (!ether_spec->h_proto)
-			*unused |= BIT(INNER_ETH_TYPE);
+	if (spec->tclass)
+		return -EOPNOTSUPP;
 
-		break;
-	default:
+	if (spec->l4_4_bytes)
 		return -EOPNOTSUPP;
-	}
 
+	return 0;
+}
+
+static int hclge_fd_check_ether_tuple(struct ethhdr *spec, u32 *unused_tuple)
+{
+	if (!spec || !unused_tuple)
+		return -EINVAL;
+
+	*unused_tuple |= BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) |
+		BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT) |
+		BIT(INNER_IP_TOS) | BIT(INNER_IP_PROTO);
+
+	if (is_zero_ether_addr(spec->h_source))
+		*unused_tuple |= BIT(INNER_SRC_MAC);
+
+	if (is_zero_ether_addr(spec->h_dest))
+		*unused_tuple |= BIT(INNER_DST_MAC);
+
+	if (!spec->h_proto)
+		*unused_tuple |= BIT(INNER_ETH_TYPE);
+
+	return 0;
+}
+
+static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev,
+				    struct ethtool_rx_flow_spec *fs,
+				    u32 *unused_tuple)
+{
 	if ((fs->flow_type & FLOW_EXT)) {
 		if (fs->h_ext.vlan_etype)
 			return -EOPNOTSUPP;
 		if (!fs->h_ext.vlan_tci)
-			*unused |= BIT(INNER_VLAN_TAG_FST);
+			*unused_tuple |= BIT(INNER_VLAN_TAG_FST);
 
-		if (fs->m_ext.vlan_tci) {
-			if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
-				return -EINVAL;
-		}
+		if (fs->m_ext.vlan_tci &&
+		    be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
+			return -EINVAL;
 	} else {
-		*unused |= BIT(INNER_VLAN_TAG_FST);
+		*unused_tuple |= BIT(INNER_VLAN_TAG_FST);
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT) {
@@ -5402,14 +5403,74 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 			return -EOPNOTSUPP;
 
 		if (is_zero_ether_addr(fs->h_ext.h_dest))
-			*unused |= BIT(INNER_DST_MAC);
+			*unused_tuple |= BIT(INNER_DST_MAC);
 		else
-			*unused &= ~(BIT(INNER_DST_MAC));
+			*unused_tuple &= ~(BIT(INNER_DST_MAC));
 	}
 
 	return 0;
 }
 
+static int hclge_fd_check_spec(struct hclge_dev *hdev,
+			       struct ethtool_rx_flow_spec *fs,
+			       u32 *unused_tuple)
+{
+	int ret;
+
+	if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
+		return -EINVAL;
+
+	if (!(fs->flow_type & hdev->fd_cfg.proto_support))
+		return -EOPNOTSUPP;
+
+	if ((fs->flow_type & FLOW_EXT) &&
+	    (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) {
+		dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case SCTP_V4_FLOW:
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		ret = hclge_fd_check_tcpip4_tuple(&fs->h_u.tcp_ip4_spec,
+						  unused_tuple);
+		break;
+	case IP_USER_FLOW:
+		ret = hclge_fd_check_ip4_tuple(&fs->h_u.usr_ip4_spec,
+					       unused_tuple);
+		break;
+	case SCTP_V6_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = hclge_fd_check_tcpip6_tuple(&fs->h_u.tcp_ip6_spec,
+						  unused_tuple);
+		break;
+	case IPV6_USER_FLOW:
+		ret = hclge_fd_check_ip6_tuple(&fs->h_u.usr_ip6_spec,
+					       unused_tuple);
+		break;
+	case ETHER_FLOW:
+		if (hdev->fd_cfg.fd_mode !=
+			HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1) {
+			dev_err(&hdev->pdev->dev,
+				"ETHER_FLOW is not supported in current fd mode!\n");
+			return -EOPNOTSUPP;
+		}
+
+		ret = hclge_fd_check_ether_tuple(&fs->h_u.ether_spec,
+						 unused_tuple);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (ret)
+		return ret;
+
+	return hclge_fd_check_ext_tuple(hdev, fs, unused_tuple);
+}
+
 static bool hclge_fd_rule_exist(struct hclge_dev *hdev, u16 location)
 {
 	struct hclge_fd_rule *rule = NULL;
-- 
cgit v1.2.3


From fa663c096052ec8c5dfef29fc1cd30190e5aba93 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Mon, 20 Apr 2020 10:17:27 +0800
Subject: net: hns3: split out hclge_get_fd_rule_info()

hclge_get_fd_rule_info() is bloated, this patch separates
it into several standalone functions for readability and
maintainability.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 303 +++++++++++----------
 1 file changed, 159 insertions(+), 144 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 80d0651145df..b1fe204c9e40 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5938,6 +5938,149 @@ static int hclge_get_fd_rule_cnt(struct hnae3_handle *handle,
 	return 0;
 }
 
+static void hclge_fd_get_tcpip4_info(struct hclge_fd_rule *rule,
+				     struct ethtool_tcpip4_spec *spec,
+				     struct ethtool_tcpip4_spec *spec_mask)
+{
+	spec->ip4src = cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
+	spec_mask->ip4src = rule->unused_tuple & BIT(INNER_SRC_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
+
+	spec->ip4dst = cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
+	spec_mask->ip4dst = rule->unused_tuple & BIT(INNER_DST_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
+
+	spec->psrc = cpu_to_be16(rule->tuples.src_port);
+	spec_mask->psrc = rule->unused_tuple & BIT(INNER_SRC_PORT) ?
+			0 : cpu_to_be16(rule->tuples_mask.src_port);
+
+	spec->pdst = cpu_to_be16(rule->tuples.dst_port);
+	spec_mask->pdst = rule->unused_tuple & BIT(INNER_DST_PORT) ?
+			0 : cpu_to_be16(rule->tuples_mask.dst_port);
+
+	spec->tos = rule->tuples.ip_tos;
+	spec_mask->tos = rule->unused_tuple & BIT(INNER_IP_TOS) ?
+			0 : rule->tuples_mask.ip_tos;
+}
+
+static void hclge_fd_get_ip4_info(struct hclge_fd_rule *rule,
+				  struct ethtool_usrip4_spec *spec,
+				  struct ethtool_usrip4_spec *spec_mask)
+{
+	spec->ip4src = cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
+	spec_mask->ip4src = rule->unused_tuple & BIT(INNER_SRC_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
+
+	spec->ip4dst = cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
+	spec_mask->ip4dst = rule->unused_tuple & BIT(INNER_DST_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
+
+	spec->tos = rule->tuples.ip_tos;
+	spec_mask->tos = rule->unused_tuple & BIT(INNER_IP_TOS) ?
+			0 : rule->tuples_mask.ip_tos;
+
+	spec->proto = rule->tuples.ip_proto;
+	spec_mask->proto = rule->unused_tuple & BIT(INNER_IP_PROTO) ?
+			0 : rule->tuples_mask.ip_proto;
+
+	spec->ip_ver = ETH_RX_NFC_IP4;
+}
+
+static void hclge_fd_get_tcpip6_info(struct hclge_fd_rule *rule,
+				     struct ethtool_tcpip6_spec *spec,
+				     struct ethtool_tcpip6_spec *spec_mask)
+{
+	cpu_to_be32_array(spec->ip6src,
+			  rule->tuples.src_ip, IPV6_SIZE);
+	cpu_to_be32_array(spec->ip6dst,
+			  rule->tuples.dst_ip, IPV6_SIZE);
+	if (rule->unused_tuple & BIT(INNER_SRC_IP))
+		memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src));
+	else
+		cpu_to_be32_array(spec_mask->ip6src, rule->tuples_mask.src_ip,
+				  IPV6_SIZE);
+
+	if (rule->unused_tuple & BIT(INNER_DST_IP))
+		memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst));
+	else
+		cpu_to_be32_array(spec_mask->ip6dst, rule->tuples_mask.dst_ip,
+				  IPV6_SIZE);
+
+	spec->psrc = cpu_to_be16(rule->tuples.src_port);
+	spec_mask->psrc = rule->unused_tuple & BIT(INNER_SRC_PORT) ?
+			0 : cpu_to_be16(rule->tuples_mask.src_port);
+
+	spec->pdst = cpu_to_be16(rule->tuples.dst_port);
+	spec_mask->pdst = rule->unused_tuple & BIT(INNER_DST_PORT) ?
+			0 : cpu_to_be16(rule->tuples_mask.dst_port);
+}
+
+static void hclge_fd_get_ip6_info(struct hclge_fd_rule *rule,
+				  struct ethtool_usrip6_spec *spec,
+				  struct ethtool_usrip6_spec *spec_mask)
+{
+	cpu_to_be32_array(spec->ip6src, rule->tuples.src_ip, IPV6_SIZE);
+	cpu_to_be32_array(spec->ip6dst, rule->tuples.dst_ip, IPV6_SIZE);
+	if (rule->unused_tuple & BIT(INNER_SRC_IP))
+		memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src));
+	else
+		cpu_to_be32_array(spec_mask->ip6src,
+				  rule->tuples_mask.src_ip, IPV6_SIZE);
+
+	if (rule->unused_tuple & BIT(INNER_DST_IP))
+		memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst));
+	else
+		cpu_to_be32_array(spec_mask->ip6dst,
+				  rule->tuples_mask.dst_ip, IPV6_SIZE);
+
+	spec->l4_proto = rule->tuples.ip_proto;
+	spec_mask->l4_proto = rule->unused_tuple & BIT(INNER_IP_PROTO) ?
+			0 : rule->tuples_mask.ip_proto;
+}
+
+static void hclge_fd_get_ether_info(struct hclge_fd_rule *rule,
+				    struct ethhdr *spec,
+				    struct ethhdr *spec_mask)
+{
+	ether_addr_copy(spec->h_source, rule->tuples.src_mac);
+	ether_addr_copy(spec->h_dest, rule->tuples.dst_mac);
+
+	if (rule->unused_tuple & BIT(INNER_SRC_MAC))
+		eth_zero_addr(spec_mask->h_source);
+	else
+		ether_addr_copy(spec_mask->h_source, rule->tuples_mask.src_mac);
+
+	if (rule->unused_tuple & BIT(INNER_DST_MAC))
+		eth_zero_addr(spec_mask->h_dest);
+	else
+		ether_addr_copy(spec_mask->h_dest, rule->tuples_mask.dst_mac);
+
+	spec->h_proto = cpu_to_be16(rule->tuples.ether_proto);
+	spec_mask->h_proto = rule->unused_tuple & BIT(INNER_ETH_TYPE) ?
+			0 : cpu_to_be16(rule->tuples_mask.ether_proto);
+}
+
+static void hclge_fd_get_ext_info(struct ethtool_rx_flow_spec *fs,
+				  struct hclge_fd_rule *rule)
+{
+	if (fs->flow_type & FLOW_EXT) {
+		fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1);
+		fs->m_ext.vlan_tci =
+				rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ?
+				cpu_to_be16(VLAN_VID_MASK) :
+				cpu_to_be16(rule->tuples_mask.vlan_tag1);
+	}
+
+	if (fs->flow_type & FLOW_MAC_EXT) {
+		ether_addr_copy(fs->h_ext.h_dest, rule->tuples.dst_mac);
+		if (rule->unused_tuple & BIT(INNER_DST_MAC))
+			eth_zero_addr(fs->m_u.ether_spec.h_dest);
+		else
+			ether_addr_copy(fs->m_u.ether_spec.h_dest,
+					rule->tuples_mask.dst_mac);
+	}
+}
+
 static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 				  struct ethtool_rxnfc *cmd)
 {
@@ -5970,162 +6113,34 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 	case SCTP_V4_FLOW:
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
-		fs->h_u.tcp_ip4_spec.ip4src =
-				cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
-		fs->m_u.tcp_ip4_spec.ip4src =
-			rule->unused_tuple & BIT(INNER_SRC_IP) ?
-			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
-
-		fs->h_u.tcp_ip4_spec.ip4dst =
-				cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
-		fs->m_u.tcp_ip4_spec.ip4dst =
-			rule->unused_tuple & BIT(INNER_DST_IP) ?
-			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
-
-		fs->h_u.tcp_ip4_spec.psrc = cpu_to_be16(rule->tuples.src_port);
-		fs->m_u.tcp_ip4_spec.psrc =
-				rule->unused_tuple & BIT(INNER_SRC_PORT) ?
-				0 : cpu_to_be16(rule->tuples_mask.src_port);
-
-		fs->h_u.tcp_ip4_spec.pdst = cpu_to_be16(rule->tuples.dst_port);
-		fs->m_u.tcp_ip4_spec.pdst =
-				rule->unused_tuple & BIT(INNER_DST_PORT) ?
-				0 : cpu_to_be16(rule->tuples_mask.dst_port);
-
-		fs->h_u.tcp_ip4_spec.tos = rule->tuples.ip_tos;
-		fs->m_u.tcp_ip4_spec.tos =
-				rule->unused_tuple & BIT(INNER_IP_TOS) ?
-				0 : rule->tuples_mask.ip_tos;
-
+		hclge_fd_get_tcpip4_info(rule, &fs->h_u.tcp_ip4_spec,
+					 &fs->m_u.tcp_ip4_spec);
 		break;
 	case IP_USER_FLOW:
-		fs->h_u.usr_ip4_spec.ip4src =
-				cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
-		fs->m_u.tcp_ip4_spec.ip4src =
-			rule->unused_tuple & BIT(INNER_SRC_IP) ?
-			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
-
-		fs->h_u.usr_ip4_spec.ip4dst =
-				cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
-		fs->m_u.usr_ip4_spec.ip4dst =
-			rule->unused_tuple & BIT(INNER_DST_IP) ?
-			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
-
-		fs->h_u.usr_ip4_spec.tos = rule->tuples.ip_tos;
-		fs->m_u.usr_ip4_spec.tos =
-				rule->unused_tuple & BIT(INNER_IP_TOS) ?
-				0 : rule->tuples_mask.ip_tos;
-
-		fs->h_u.usr_ip4_spec.proto = rule->tuples.ip_proto;
-		fs->m_u.usr_ip4_spec.proto =
-				rule->unused_tuple & BIT(INNER_IP_PROTO) ?
-				0 : rule->tuples_mask.ip_proto;
-
-		fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
-
+		hclge_fd_get_ip4_info(rule, &fs->h_u.usr_ip4_spec,
+				      &fs->m_u.usr_ip4_spec);
 		break;
 	case SCTP_V6_FLOW:
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
-		cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6src,
-				  rule->tuples.src_ip, IPV6_SIZE);
-		if (rule->unused_tuple & BIT(INNER_SRC_IP))
-			memset(fs->m_u.tcp_ip6_spec.ip6src, 0,
-			       sizeof(int) * IPV6_SIZE);
-		else
-			cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6src,
-					  rule->tuples_mask.src_ip, IPV6_SIZE);
-
-		cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6dst,
-				  rule->tuples.dst_ip, IPV6_SIZE);
-		if (rule->unused_tuple & BIT(INNER_DST_IP))
-			memset(fs->m_u.tcp_ip6_spec.ip6dst, 0,
-			       sizeof(int) * IPV6_SIZE);
-		else
-			cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6dst,
-					  rule->tuples_mask.dst_ip, IPV6_SIZE);
-
-		fs->h_u.tcp_ip6_spec.psrc = cpu_to_be16(rule->tuples.src_port);
-		fs->m_u.tcp_ip6_spec.psrc =
-				rule->unused_tuple & BIT(INNER_SRC_PORT) ?
-				0 : cpu_to_be16(rule->tuples_mask.src_port);
-
-		fs->h_u.tcp_ip6_spec.pdst = cpu_to_be16(rule->tuples.dst_port);
-		fs->m_u.tcp_ip6_spec.pdst =
-				rule->unused_tuple & BIT(INNER_DST_PORT) ?
-				0 : cpu_to_be16(rule->tuples_mask.dst_port);
-
+		hclge_fd_get_tcpip6_info(rule, &fs->h_u.tcp_ip6_spec,
+					 &fs->m_u.tcp_ip6_spec);
 		break;
 	case IPV6_USER_FLOW:
-		cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6src,
-				  rule->tuples.src_ip, IPV6_SIZE);
-		if (rule->unused_tuple & BIT(INNER_SRC_IP))
-			memset(fs->m_u.usr_ip6_spec.ip6src, 0,
-			       sizeof(int) * IPV6_SIZE);
-		else
-			cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6src,
-					  rule->tuples_mask.src_ip, IPV6_SIZE);
-
-		cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6dst,
-				  rule->tuples.dst_ip, IPV6_SIZE);
-		if (rule->unused_tuple & BIT(INNER_DST_IP))
-			memset(fs->m_u.usr_ip6_spec.ip6dst, 0,
-			       sizeof(int) * IPV6_SIZE);
-		else
-			cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6dst,
-					  rule->tuples_mask.dst_ip, IPV6_SIZE);
-
-		fs->h_u.usr_ip6_spec.l4_proto = rule->tuples.ip_proto;
-		fs->m_u.usr_ip6_spec.l4_proto =
-				rule->unused_tuple & BIT(INNER_IP_PROTO) ?
-				0 : rule->tuples_mask.ip_proto;
-
-		break;
-	case ETHER_FLOW:
-		ether_addr_copy(fs->h_u.ether_spec.h_source,
-				rule->tuples.src_mac);
-		if (rule->unused_tuple & BIT(INNER_SRC_MAC))
-			eth_zero_addr(fs->m_u.ether_spec.h_source);
-		else
-			ether_addr_copy(fs->m_u.ether_spec.h_source,
-					rule->tuples_mask.src_mac);
-
-		ether_addr_copy(fs->h_u.ether_spec.h_dest,
-				rule->tuples.dst_mac);
-		if (rule->unused_tuple & BIT(INNER_DST_MAC))
-			eth_zero_addr(fs->m_u.ether_spec.h_dest);
-		else
-			ether_addr_copy(fs->m_u.ether_spec.h_dest,
-					rule->tuples_mask.dst_mac);
-
-		fs->h_u.ether_spec.h_proto =
-				cpu_to_be16(rule->tuples.ether_proto);
-		fs->m_u.ether_spec.h_proto =
-				rule->unused_tuple & BIT(INNER_ETH_TYPE) ?
-				0 : cpu_to_be16(rule->tuples_mask.ether_proto);
-
+		hclge_fd_get_ip6_info(rule, &fs->h_u.usr_ip6_spec,
+				      &fs->m_u.usr_ip6_spec);
 		break;
+	/* The flow type of fd rule has been checked before adding in to rule
+	 * list. As other flow types have been handled, it must be ETHER_FLOW
+	 * for the default case
+	 */
 	default:
-		spin_unlock_bh(&hdev->fd_rule_lock);
-		return -EOPNOTSUPP;
-	}
-
-	if (fs->flow_type & FLOW_EXT) {
-		fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1);
-		fs->m_ext.vlan_tci =
-				rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ?
-				cpu_to_be16(VLAN_VID_MASK) :
-				cpu_to_be16(rule->tuples_mask.vlan_tag1);
+		hclge_fd_get_ether_info(rule, &fs->h_u.ether_spec,
+					&fs->m_u.ether_spec);
+		break;
 	}
 
-	if (fs->flow_type & FLOW_MAC_EXT) {
-		ether_addr_copy(fs->h_ext.h_dest, rule->tuples.dst_mac);
-		if (rule->unused_tuple & BIT(INNER_DST_MAC))
-			eth_zero_addr(fs->m_u.ether_spec.h_dest);
-		else
-			ether_addr_copy(fs->m_u.ether_spec.h_dest,
-					rule->tuples_mask.dst_mac);
-	}
+	hclge_fd_get_ext_info(fs, rule);
 
 	if (rule->action == HCLGE_FD_ACTION_DROP_PACKET) {
 		fs->ring_cookie = RX_CLS_FLOW_DISC;
-- 
cgit v1.2.3


From e9368c4094f54c1af44a842814c1d87d4365c684 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 20 Apr 2020 10:17:28 +0800
Subject: net: hns3: remove an unnecessary case 0 in hclge_fd_convert_tuple()

Since case default has included case 0, so removes this
redundant case 0.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b1fe204c9e40..999f05686f06 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5006,8 +5006,6 @@ static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y,
 		return true;
 
 	switch (tuple_bit) {
-	case 0:
-		return false;
 	case BIT(INNER_DST_MAC):
 		for (i = 0; i < ETH_ALEN; i++) {
 			calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.dst_mac[i],
-- 
cgit v1.2.3


From 16505f878e3065f2c0457e38ec867cdd6d3ce243 Mon Sep 17 00:00:00 2001
From: Guojia Liao <liaoguojia@huawei.com>
Date: Mon, 20 Apr 2020 10:17:29 +0800
Subject: net: hns3: remove useless proto_support field in struct hclge_fd_cfg

proto_support field in struct hclge_fd_cfg shows what protocols
in flow direct table are supported now. It is unnecessary since
checking which one is unsupported will be more efficient,
so this patch removes it.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 17 ++++++-----------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h |  1 -
 2 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 999f05686f06..e238a9df6282 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4876,9 +4876,6 @@ static int hclge_init_fd_config(struct hclge_dev *hdev)
 		return -EOPNOTSUPP;
 	}
 
-	hdev->fd_cfg.proto_support =
-		TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW |
-		UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW;
 	key_cfg = &hdev->fd_cfg.key_cfg[HCLGE_FD_STAGE_1];
 	key_cfg->key_sel = HCLGE_FD_KEY_BASE_ON_TUPLE,
 	key_cfg->inner_sipv6_word_en = LOW_2_WORDS;
@@ -4892,11 +4889,9 @@ static int hclge_init_fd_config(struct hclge_dev *hdev)
 				BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT);
 
 	/* If use max 400bit key, we can support tuples for ether type */
-	if (hdev->fd_cfg.max_key_length == MAX_KEY_LENGTH) {
-		hdev->fd_cfg.proto_support |= ETHER_FLOW;
+	if (hdev->fd_cfg.fd_mode == HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1)
 		key_cfg->tuple_active |=
 				BIT(INNER_DST_MAC) | BIT(INNER_SRC_MAC);
-	}
 
 	/* roce_type is used to filter roce frames
 	 * dst_vport is used to specify the rule
@@ -5397,7 +5392,8 @@ static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev,
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT) {
-		if (!(hdev->fd_cfg.proto_support & ETHER_FLOW))
+		if (hdev->fd_cfg.fd_mode !=
+		    HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1)
 			return -EOPNOTSUPP;
 
 		if (is_zero_ether_addr(fs->h_ext.h_dest))
@@ -5413,21 +5409,20 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 			       struct ethtool_rx_flow_spec *fs,
 			       u32 *unused_tuple)
 {
+	u32 flow_type;
 	int ret;
 
 	if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
 		return -EINVAL;
 
-	if (!(fs->flow_type & hdev->fd_cfg.proto_support))
-		return -EOPNOTSUPP;
-
 	if ((fs->flow_type & FLOW_EXT) &&
 	    (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) {
 		dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
+	switch (flow_type) {
 	case SCTP_V4_FLOW:
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 71df23d5f1b4..a58c26200ea0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -580,7 +580,6 @@ struct hclge_fd_key_cfg {
 struct hclge_fd_cfg {
 	u8 fd_mode;
 	u16 max_key_length; /* use bit as unit */
-	u32 proto_support;
 	u32 rule_num[MAX_STAGE_NUM]; /* rule entry number */
 	u16 cnt_num[MAX_STAGE_NUM]; /* rule hit counter number */
 	struct hclge_fd_key_cfg key_cfg[MAX_STAGE_NUM];
-- 
cgit v1.2.3


From f84f6a8634f3424244e91fc3fd460152dae689cf Mon Sep 17 00:00:00 2001
From: Guojia Liao <liaoguojia@huawei.com>
Date: Mon, 20 Apr 2020 10:17:30 +0800
Subject: net: hns3: remove two unused structures in hclge_cmd.h

struct hclge_mac_vlan_remove_cmd and hclge_mac_vlan_add_cmd are unused.
So removes them from hclge_cmd.h.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 25 ----------------------
 1 file changed, 25 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 96498d9b4754..90e422efe590 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -733,31 +733,6 @@ struct hclge_mac_mgr_tbl_entry_cmd {
 	u8      rsv3[2];
 };
 
-struct hclge_mac_vlan_add_cmd {
-	__le16  flags;
-	__le16  mac_addr_hi16;
-	__le32  mac_addr_lo32;
-	__le32  mac_addr_msk_hi32;
-	__le16  mac_addr_msk_lo16;
-	__le16  vlan_tag;
-	__le16  ingress_port;
-	__le16  egress_port;
-	u8      rsv[4];
-};
-
-#define HNS3_MAC_VLAN_CFG_FLAG_BIT 0
-struct hclge_mac_vlan_remove_cmd {
-	__le16  flags;
-	__le16  mac_addr_hi16;
-	__le32  mac_addr_lo32;
-	__le32  mac_addr_msk_hi32;
-	__le16  mac_addr_msk_lo16;
-	__le16  vlan_tag;
-	__le16  ingress_port;
-	__le16  egress_port;
-	u8      rsv[4];
-};
-
 struct hclge_vlan_filter_ctrl_cmd {
 	u8 vlan_type;
 	u8 vlan_fe;
-- 
cgit v1.2.3


From 84944d5c4797df7aa0b2677283db5064a2560633 Mon Sep 17 00:00:00 2001
From: Guojia Liao <liaoguojia@huawei.com>
Date: Mon, 20 Apr 2020 10:17:31 +0800
Subject: net: hns3: modify some unsuitable type declaration

In hclge_set_fd_key_config(), parameter 'stage' should be
as enum HCLGE_FD_STAGE, and in hclge_config_key(), 'tuple_size'
should be type u8, also simplify unsigned int with u32 for 'i'.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e238a9df6282..9edee7d94bbf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4822,7 +4822,8 @@ static int hclge_get_fd_allocation(struct hclge_dev *hdev,
 	return ret;
 }
 
-static int hclge_set_fd_key_config(struct hclge_dev *hdev, int stage_num)
+static int hclge_set_fd_key_config(struct hclge_dev *hdev,
+				   enum HCLGE_FD_STAGE stage_num)
 {
 	struct hclge_set_fd_key_config_cmd *req;
 	struct hclge_fd_key_cfg *stage;
@@ -5158,9 +5159,10 @@ static int hclge_config_key(struct hclge_dev *hdev, u8 stage,
 	struct hclge_fd_key_cfg *key_cfg = &hdev->fd_cfg.key_cfg[stage];
 	u8 key_x[MAX_KEY_BYTES], key_y[MAX_KEY_BYTES];
 	u8 *cur_key_x, *cur_key_y;
-	unsigned int i;
-	int ret, tuple_size;
 	u8 meta_data_region;
+	u8 tuple_size;
+	int ret;
+	u32 i;
 
 	memset(key_x, 0, sizeof(key_x));
 	memset(key_y, 0, sizeof(key_y));
-- 
cgit v1.2.3


From 0b4bdc55df6163f2861fe935755e892963dc9512 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 20 Apr 2020 10:17:32 +0800
Subject: net: hns3: clean up some coding style issue

This patch removes some unnecessary blank lines, redundant
parentheses, and changes one tab to blank in
hclge_dbg_dump_reg_common().

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c |  2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 10 +++-------
 2 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 17228288d4df..cfc9300ff715 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -143,7 +143,7 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 		return;
 	}
 
-	buf_len	= sizeof(struct hclge_desc) * bd_num;
+	buf_len = sizeof(struct hclge_desc) * bd_num;
 	desc_src = kzalloc(buf_len, GFP_KERNEL);
 	if (!desc_src)
 		return;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 9edee7d94bbf..635aec2ffba4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5380,7 +5380,7 @@ static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev,
 				    struct ethtool_rx_flow_spec *fs,
 				    u32 *unused_tuple)
 {
-	if ((fs->flow_type & FLOW_EXT)) {
+	if (fs->flow_type & FLOW_EXT) {
 		if (fs->h_ext.vlan_etype)
 			return -EOPNOTSUPP;
 		if (!fs->h_ext.vlan_tci)
@@ -5401,7 +5401,7 @@ static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev,
 		if (is_zero_ether_addr(fs->h_ext.h_dest))
 			*unused_tuple |= BIT(INNER_DST_MAC);
 		else
-			*unused_tuple &= ~(BIT(INNER_DST_MAC));
+			*unused_tuple &= ~BIT(INNER_DST_MAC);
 	}
 
 	return 0;
@@ -5674,7 +5674,7 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 		break;
 	}
 
-	if ((fs->flow_type & FLOW_EXT)) {
+	if (fs->flow_type & FLOW_EXT) {
 		rule->tuples.vlan_tag1 = be16_to_cpu(fs->h_ext.vlan_tci);
 		rule->tuples_mask.vlan_tag1 = be16_to_cpu(fs->m_ext.vlan_tci);
 	}
@@ -5785,7 +5785,6 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 	}
 
 	rule->flow_type = fs->flow_type;
-
 	rule->location = fs->location;
 	rule->unused_tuple = unused;
 	rule->vf_id = dst_vport_id;
@@ -6273,7 +6272,6 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id,
 	 */
 	if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) {
 		spin_unlock_bh(&hdev->fd_rule_lock);
-
 		return -EOPNOTSUPP;
 	}
 
@@ -6287,14 +6285,12 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id,
 		bit_id = find_first_zero_bit(hdev->fd_bmap, MAX_FD_FILTER_NUM);
 		if (bit_id >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) {
 			spin_unlock_bh(&hdev->fd_rule_lock);
-
 			return -ENOSPC;
 		}
 
 		rule = kzalloc(sizeof(*rule), GFP_ATOMIC);
 		if (!rule) {
 			spin_unlock_bh(&hdev->fd_rule_lock);
-
 			return -ENOMEM;
 		}
 
-- 
cgit v1.2.3


From a3ca5e9048be07576259d2ba9628dc8187f7690e Mon Sep 17 00:00:00 2001
From: Guojia Liao <liaoguojia@huawei.com>
Date: Mon, 20 Apr 2020 10:17:33 +0800
Subject: net: hns3: add debug information for flow table when failed

Adds some debug information for failures of processing flow table,
removes the redundant printing when hclge_fd_check_spec() returns
error, and modifies the printing level for FD not enable error.

Signed-off-by: Guojia Liao <liaoguojia@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 45 ++++++++++++++++------
 1 file changed, 34 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 635aec2ffba4..0618f22e6f14 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5381,22 +5381,32 @@ static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev,
 				    u32 *unused_tuple)
 {
 	if (fs->flow_type & FLOW_EXT) {
-		if (fs->h_ext.vlan_etype)
+		if (fs->h_ext.vlan_etype) {
+			dev_err(&hdev->pdev->dev, "vlan-etype is not supported!\n");
 			return -EOPNOTSUPP;
+		}
+
 		if (!fs->h_ext.vlan_tci)
 			*unused_tuple |= BIT(INNER_VLAN_TAG_FST);
 
 		if (fs->m_ext.vlan_tci &&
-		    be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
+		    be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID) {
+			dev_err(&hdev->pdev->dev,
+				"failed to config vlan_tci, invalid vlan_tci: %u, max is %u.\n",
+				ntohs(fs->h_ext.vlan_tci), VLAN_N_VID - 1);
 			return -EINVAL;
+		}
 	} else {
 		*unused_tuple |= BIT(INNER_VLAN_TAG_FST);
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT) {
 		if (hdev->fd_cfg.fd_mode !=
-		    HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1)
+		    HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1) {
+			dev_err(&hdev->pdev->dev,
+				"FLOW_MAC_EXT is not supported in current fd mode!\n");
 			return -EOPNOTSUPP;
+		}
 
 		if (is_zero_ether_addr(fs->h_ext.h_dest))
 			*unused_tuple |= BIT(INNER_DST_MAC);
@@ -5414,8 +5424,13 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 	u32 flow_type;
 	int ret;
 
-	if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
+	if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) {
+		dev_err(&hdev->pdev->dev,
+			"failed to config fd rules, invalid rule location: %u, max is %u\n.",
+			fs->location,
+			hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1] - 1);
 		return -EINVAL;
+	}
 
 	if ((fs->flow_type & FLOW_EXT) &&
 	    (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) {
@@ -5457,11 +5472,18 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 						 unused_tuple);
 		break;
 	default:
+		dev_err(&hdev->pdev->dev,
+			"unsupported protocol type, protocol type = %#x\n",
+			flow_type);
 		return -EOPNOTSUPP;
 	}
 
-	if (ret)
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to check flow union tuple, ret = %d\n",
+			ret);
 		return ret;
+	}
 
 	return hclge_fd_check_ext_tuple(hdev, fs, unused_tuple);
 }
@@ -5729,22 +5751,23 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 	u8 action;
 	int ret;
 
-	if (!hnae3_dev_fd_supported(hdev))
+	if (!hnae3_dev_fd_supported(hdev)) {
+		dev_err(&hdev->pdev->dev,
+			"flow table director is not supported\n");
 		return -EOPNOTSUPP;
+	}
 
 	if (!hdev->fd_en) {
-		dev_warn(&hdev->pdev->dev,
-			 "Please enable flow director first\n");
+		dev_err(&hdev->pdev->dev,
+			"please enable flow director first\n");
 		return -EOPNOTSUPP;
 	}
 
 	fs = (struct ethtool_rx_flow_spec *)&cmd->fs;
 
 	ret = hclge_fd_check_spec(hdev, fs, &unused);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "Check fd spec failed\n");
+	if (ret)
 		return ret;
-	}
 
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
 		action = HCLGE_FD_ACTION_DROP_PACKET;
-- 
cgit v1.2.3


From 5cb51cfe8ad65117d4404b82fb8531768b149ad9 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Mon, 20 Apr 2020 10:17:34 +0800
Subject: net: hns3: add support for dumping MAC reg in debugfs

This patch adds support for dumping MAC reg in debugfs,
which will be helpful for debugging.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |   2 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 113 +++++++++++++++++++++
 2 files changed, 114 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index e1d88095a77e..c934f328c040 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -270,7 +270,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 		" [igu egu <port_id>] [rpu <tc_queue_num>]",
 		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
 	strncat(printf_buf + strlen(printf_buf),
-		" [rtc] [ppp] [rcb] [tqp <queue_num>]]\n",
+		" [rtc] [ppp] [rcb] [tqp <queue_num>] [mac]]\n",
 		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
 	dev_info(&h->pdev->dev, "%s", printf_buf);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index cfc9300ff715..66c1ad3a156b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -173,6 +173,114 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 	kfree(desc_src);
 }
 
+static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev)
+{
+	struct hclge_config_mac_mode_cmd *req;
+	struct hclge_desc desc;
+	u32 loop_en;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump mac enable status, ret = %d\n", ret);
+		return;
+	}
+
+	req = (struct hclge_config_mac_mode_cmd *)desc.data;
+	loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
+
+	dev_info(&hdev->pdev->dev, "config_mac_trans_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B));
+	dev_info(&hdev->pdev->dev, "config_mac_rcv_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B));
+	dev_info(&hdev->pdev->dev, "config_pad_trans_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B));
+	dev_info(&hdev->pdev->dev, "config_pad_rcv_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B));
+	dev_info(&hdev->pdev->dev, "config_1588_trans_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B));
+	dev_info(&hdev->pdev->dev, "config_1588_rcv_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B));
+	dev_info(&hdev->pdev->dev, "config_mac_app_loop_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B));
+	dev_info(&hdev->pdev->dev, "config_mac_line_loop_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B));
+	dev_info(&hdev->pdev->dev, "config_mac_fcs_tx_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B));
+	dev_info(&hdev->pdev->dev, "config_mac_rx_oversize_truncate_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B));
+	dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_strip_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B));
+	dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B));
+	dev_info(&hdev->pdev->dev, "config_mac_tx_under_min_err_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B));
+	dev_info(&hdev->pdev->dev, "config_mac_tx_oversize_truncate_en: %#x\n",
+		 hnae3_get_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B));
+}
+
+static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev)
+{
+	struct hclge_config_max_frm_size_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump mac frame size, ret = %d\n", ret);
+		return;
+	}
+
+	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
+
+	dev_info(&hdev->pdev->dev, "max_frame_size: %u\n",
+		 le16_to_cpu(req->max_frm_size));
+	dev_info(&hdev->pdev->dev, "min_frame_size: %u\n", req->min_frm_size);
+}
+
+static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev)
+{
+#define HCLGE_MAC_SPEED_SHIFT	0
+#define HCLGE_MAC_SPEED_MASK	GENMASK(5, 0)
+#define HCLGE_MAC_DUPLEX_SHIFT	7
+
+	struct hclge_config_mac_speed_dup_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to dump mac speed duplex, ret = %d\n", ret);
+		return;
+	}
+
+	req = (struct hclge_config_mac_speed_dup_cmd *)desc.data;
+
+	dev_info(&hdev->pdev->dev, "speed: %#lx\n",
+		 hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK,
+				 HCLGE_MAC_SPEED_SHIFT));
+	dev_info(&hdev->pdev->dev, "duplex: %#x\n",
+		 hnae3_get_bit(req->speed_dup, HCLGE_MAC_DUPLEX_SHIFT));
+}
+
+static void hclge_dbg_dump_mac(struct hclge_dev *hdev)
+{
+	hclge_dbg_dump_mac_enable_status(hdev);
+
+	hclge_dbg_dump_mac_frame_size(hdev);
+
+	hclge_dbg_dump_mac_speed_duplex(hdev);
+}
+
 static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf)
 {
 	struct device *dev = &hdev->pdev->dev;
@@ -304,6 +412,11 @@ static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf)
 		}
 	}
 
+	if (strncmp(cmd_buf, "mac", strlen("mac")) == 0) {
+		hclge_dbg_dump_mac(hdev);
+		has_dump = true;
+	}
+
 	if (strncmp(cmd_buf, "dcb", 3) == 0) {
 		hclge_dbg_dump_dcb(hdev, &cmd_buf[sizeof("dcb")]);
 		has_dump = true;
-- 
cgit v1.2.3


From d8355240cf8fb8b9e002b5c8458578435cea85c2 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Mon, 20 Apr 2020 10:17:35 +0800
Subject: net: hns3: add trace event support for PF/VF mailbox

This patch adds trace event support for PF/VF mailbox.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/Makefile    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c |  7 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_trace.h   | 87 ++++++++++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3vf/Makefile    |  1 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c   |  7 ++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h | 87 ++++++++++++++++++++++
 6 files changed, 190 insertions(+)
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
 create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 0fb61d440d3b..6c28c8f6292c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -4,6 +4,7 @@
 #
 
 ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
+ccflags-y += -I $(srctree)/$(src)
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
 hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 7f24fcb4f96a..103c2ec777b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -5,6 +5,9 @@
 #include "hclge_mbx.h"
 #include "hnae3.h"
 
+#define CREATE_TRACE_POINTS
+#include "hclge_trace.h"
+
 static u16 hclge_errno_to_resp(int errno)
 {
 	return abs(errno);
@@ -90,6 +93,8 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
 
 	memcpy(&resp_pf_to_vf->msg.vf_mbx_msg_code, msg, msg_len);
 
+	trace_hclge_pf_mbx_send(hdev, resp_pf_to_vf);
+
 	status = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (status)
 		dev_err(&hdev->pdev->dev,
@@ -674,6 +679,8 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 
 		vport = &hdev->vport[req->mbx_src_vfid];
 
+		trace_hclge_pf_mbx_get(hdev, req);
+
 		switch (req->msg.code) {
 		case HCLGE_MBX_MAP_RING_TO_VECTOR:
 			ret = hclge_map_unmap_ring_to_vf_vector(vport, true,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
new file mode 100644
index 000000000000..5b0b71bd6120
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018-2020 Hisilicon Limited. */
+
+/* This must be outside ifdef _HCLGE_TRACE_H */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hns3
+
+#if !defined(_HCLGE_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _HCLGE_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+#define PF_GET_MBX_LEN	(sizeof(struct hclge_mbx_vf_to_pf_cmd) / sizeof(u32))
+#define PF_SEND_MBX_LEN	(sizeof(struct hclge_mbx_pf_to_vf_cmd) / sizeof(u32))
+
+TRACE_EVENT(hclge_pf_mbx_get,
+	TP_PROTO(
+		struct hclge_dev *hdev,
+		struct hclge_mbx_vf_to_pf_cmd *req),
+	TP_ARGS(hdev, req),
+
+	TP_STRUCT__entry(
+		__field(u8, vfid)
+		__field(u8, code)
+		__field(u8, subcode)
+		__string(pciname, pci_name(hdev->pdev))
+		__string(devname, &hdev->vport[0].nic.kinfo.netdev->name)
+		__array(u32, mbx_data, PF_GET_MBX_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->vfid = req->mbx_src_vfid;
+		__entry->code = req->msg.code;
+		__entry->subcode = req->msg.subcode;
+		__assign_str(pciname, pci_name(hdev->pdev));
+		__assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name);
+		memcpy(__entry->mbx_data, req,
+		       sizeof(struct hclge_mbx_vf_to_pf_cmd));
+	),
+
+	TP_printk(
+		"%s %s vfid:%u code:%u subcode:%u data:%s",
+		__get_str(pciname), __get_str(devname), __entry->vfid,
+		__entry->code, __entry->subcode,
+		__print_array(__entry->mbx_data, PF_GET_MBX_LEN, sizeof(u32))
+	)
+);
+
+TRACE_EVENT(hclge_pf_mbx_send,
+	TP_PROTO(
+		struct hclge_dev *hdev,
+		struct hclge_mbx_pf_to_vf_cmd *req),
+	TP_ARGS(hdev, req),
+
+	TP_STRUCT__entry(
+		__field(u8, vfid)
+		__field(u16, code)
+		__string(pciname, pci_name(hdev->pdev))
+		__string(devname, &hdev->vport[0].nic.kinfo.netdev->name)
+		__array(u32, mbx_data, PF_SEND_MBX_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->vfid = req->dest_vfid;
+		__entry->code = req->msg.code;
+		__assign_str(pciname, pci_name(hdev->pdev));
+		__assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name);
+		memcpy(__entry->mbx_data, req,
+		       sizeof(struct hclge_mbx_pf_to_vf_cmd));
+	),
+
+	TP_printk(
+		"%s %s vfid:%u code:%u data:%s",
+		__get_str(pciname), __get_str(devname), __entry->vfid,
+		__entry->code,
+		__print_array(__entry->mbx_data, PF_SEND_MBX_LEN, sizeof(u32))
+	)
+);
+
+#endif /* _HCLGE_TRACE_H_ */
+
+/* This must be outside ifdef _HCLGE_TRACE_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE hclge_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
index 53804d95ea90..2c26ea607a53 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
@@ -4,6 +4,7 @@
 #
 
 ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
+ccflags-y += -I $(srctree)/$(src)
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
 hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 9b8154955f91..5b2dcd97c107 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -5,6 +5,9 @@
 #include "hclgevf_main.h"
 #include "hnae3.h"
 
+#define CREATE_TRACE_POINTS
+#include "hclgevf_trace.h"
+
 static int hclgevf_resp_to_errno(u16 resp_code)
 {
 	return resp_code ? -resp_code : 0;
@@ -106,6 +109,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,
 
 	memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg));
 
+	trace_hclge_vf_mbx_send(hdev, req);
+
 	/* synchronous send */
 	if (need_resp) {
 		mutex_lock(&hdev->mbx_resp.mbx_mutex);
@@ -179,6 +184,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			continue;
 		}
 
+		trace_hclge_vf_mbx_get(hdev, req);
+
 		/* synchronous messages are time critical and need preferential
 		 * treatment. Therefore, we need to acknowledge all the sync
 		 * responses as quickly as possible so that waiting tasks do not
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h
new file mode 100644
index 000000000000..e4bfb6191fef
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+/* This must be outside ifdef _HCLGEVF_TRACE_H */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hns3
+
+#if !defined(_HCLGEVF_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _HCLGEVF_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+#define VF_GET_MBX_LEN	(sizeof(struct hclge_mbx_pf_to_vf_cmd) / sizeof(u32))
+#define VF_SEND_MBX_LEN	(sizeof(struct hclge_mbx_vf_to_pf_cmd) / sizeof(u32))
+
+TRACE_EVENT(hclge_vf_mbx_get,
+	TP_PROTO(
+		struct hclgevf_dev *hdev,
+		struct hclge_mbx_pf_to_vf_cmd *req),
+	TP_ARGS(hdev, req),
+
+	TP_STRUCT__entry(
+		__field(u8, vfid)
+		__field(u16, code)
+		__string(pciname, pci_name(hdev->pdev))
+		__string(devname, &hdev->nic.kinfo.netdev->name)
+		__array(u32, mbx_data, VF_GET_MBX_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->vfid = req->dest_vfid;
+		__entry->code = req->msg.code;
+		__assign_str(pciname, pci_name(hdev->pdev));
+		__assign_str(devname, &hdev->nic.kinfo.netdev->name);
+		memcpy(__entry->mbx_data, req,
+		       sizeof(struct hclge_mbx_pf_to_vf_cmd));
+	),
+
+	TP_printk(
+		"%s %s vfid:%u code:%u data:%s",
+		__get_str(pciname), __get_str(devname), __entry->vfid,
+		__entry->code,
+		__print_array(__entry->mbx_data, VF_GET_MBX_LEN, sizeof(u32))
+	)
+);
+
+TRACE_EVENT(hclge_vf_mbx_send,
+	TP_PROTO(
+		struct hclgevf_dev *hdev,
+		struct hclge_mbx_vf_to_pf_cmd *req),
+	TP_ARGS(hdev, req),
+
+	TP_STRUCT__entry(
+		__field(u8, vfid)
+		__field(u8, code)
+		__field(u8, subcode)
+		__string(pciname, pci_name(hdev->pdev))
+		__string(devname, &hdev->nic.kinfo.netdev->name)
+		__array(u32, mbx_data, VF_SEND_MBX_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->vfid = req->mbx_src_vfid;
+		__entry->code = req->msg.code;
+		__entry->subcode = req->msg.subcode;
+		__assign_str(pciname, pci_name(hdev->pdev));
+		__assign_str(devname, &hdev->nic.kinfo.netdev->name);
+		memcpy(__entry->mbx_data, req,
+		       sizeof(struct hclge_mbx_vf_to_pf_cmd));
+	),
+
+	TP_printk(
+		"%s %s vfid:%u code:%u subcode:%u data:%s",
+		__get_str(pciname), __get_str(devname), __entry->vfid,
+		__entry->code, __entry->subcode,
+		__print_array(__entry->mbx_data, VF_SEND_MBX_LEN, sizeof(u32))
+	)
+);
+
+#endif /* _HCLGEVF_TRACE_H_ */
+
+/* This must be outside ifdef _HCLGEVF_TRACE_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE hclgevf_trace
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 82ebc889091a488b4dd95e682b3c3b889a50713c Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Mon, 20 Apr 2020 12:27:20 +0800
Subject: qed: use true,false for bool variables
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following coccicheck warning:

drivers/net/ethernet/qlogic/qed/qed_dev.c:4395:2-34: WARNING:
Assignment of 0/1 to bool variable
drivers/net/ethernet/qlogic/qed/qed_dev.c:1975:2-34: WARNING:
Assignment of 0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 38a65b984e47..7119a18af19e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1972,7 +1972,7 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
 		return 0;
 
 	if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
-		p_hwfn->hw_info.multi_tc_roce_en = 0;
+		p_hwfn->hw_info.multi_tc_roce_en = false;
 		DP_NOTICE(p_hwfn,
 			  "multi-tc roce was disabled to reduce requested amount of pqs\n");
 		if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
@@ -4392,7 +4392,7 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 	}
 
 	if (QED_IS_ROCE_PERSONALITY(p_hwfn))
-		p_hwfn->hw_info.multi_tc_roce_en = 1;
+		p_hwfn->hw_info.multi_tc_roce_en = true;
 
 	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
 	p_hwfn->hw_info.num_active_tc = 1;
-- 
cgit v1.2.3


From 8c8eea07c1fd46455b3a275a03c27326ddc42b20 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 23 Oct 2019 16:03:12 +0300
Subject: net/mlx5: Use the correct IPsec capability function for FPGA ops

Currently the IPsec acceleration capability function is also used
at IPsec fpga capable device code.

This could cause a future bug as the acceleration layer is agnostic
to the device implementing its API.

Fix by using the IPsec FPGA capability function instead of acceleration
layer capability function in case of FPGA IPsec only related operations.

Downstream patches will add support for Connect-X IPsec, this can avoid
a future bug.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h | 15 ++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c    |  5 +++--
 3 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index b794888fa3ba..c8736b6b4172 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -602,7 +602,7 @@ static bool mlx5_is_fpga_ipsec_rule(struct mlx5_core_dev *dev,
 				    const u32 *match_c,
 				    const u32 *match_v)
 {
-	u32 ipsec_dev_caps = mlx5_accel_ipsec_device_caps(dev);
+	u32 ipsec_dev_caps = mlx5_fpga_ipsec_device_caps(dev);
 	bool ipv6_flow;
 
 	ipv6_flow = mlx5_fs_is_outer_ipv6_flow(dev, match_c, match_v);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
index 382985e65b48..d01b1fc8e11b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
@@ -37,6 +37,7 @@
 #include "accel/ipsec.h"
 #include "fs_cmd.h"
 
+#ifdef CONFIG_MLX5_FPGA_IPSEC
 u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev);
 unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev);
 int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
@@ -63,5 +64,17 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 
 const struct mlx5_flow_cmds *
 mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type);
+#else
+static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev)
+{
+	return 0;
+}
 
-#endif	/* __MLX5_FPGA_SADB_H__ */
+static inline const struct mlx5_flow_cmds *
+mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type)
+{
+	return mlx5_fs_cmd_get_default(type);
+}
+
+#endif /* CONFIG_MLX5_FPGA_IPSEC */
+#endif	/* __MLX5_FPGA_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d5defe09339a..2da45e9b9b6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2359,7 +2359,7 @@ static struct mlx5_flow_root_namespace
 	struct mlx5_flow_root_namespace *root_ns;
 	struct mlx5_flow_namespace *ns;
 
-	if (mlx5_accel_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE &&
+	if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE &&
 	    (table_type == FS_FT_NIC_RX || table_type == FS_FT_NIC_TX))
 		cmds = mlx5_fs_cmd_get_default_ipsec_fpga_cmds(table_type);
 
@@ -2943,7 +2943,8 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
+	if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE ||
+	    MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
 		err = init_egress_root_ns(steering);
 		if (err)
 			goto err;
-- 
cgit v1.2.3


From 9425c595bd513948537ef355c07a65595dd2c771 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Mon, 20 Jan 2020 15:03:00 +0200
Subject: net/mlx5e: en_accel, Add missing net/geneve.h include

The cited commit relies on include <net/geneve.h> being included
implicitly prior to include "en_accel/en_accel.h".
This mandates that all files that needs to include en_accel.h
to redantantly include net/geneve.h.

Include net/geneve.h explicitly at "en_accel/en_accel.h" to avoid
undesired constrain as above.

Fixes: e3cfc7e6b7bd ("net/mlx5e: TX, Add geneve tunnel stateless offload support")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 3022463f2284..a6f65d4b2f36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -42,6 +42,8 @@
 #include "en/txrx.h"
 
 #if IS_ENABLED(CONFIG_GENEVE)
+#include <net/geneve.h>
+
 static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev)
 {
 	return mlx5_tx_swp_supported(mdev);
-- 
cgit v1.2.3


From 1dbd51d0a71a561056579e2d4f406e5ce5343af0 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Tue, 10 Dec 2019 13:20:55 +0200
Subject: net/mlx5: Refactor mlx5_accel_esp_create_hw_context parameter list

Currently the FPGA IPsec is the only hw implementation of the IPsec
acceleration api, and so the mlx5_accel_esp_create_hw_context was
wrongly made to suit this HW api, among other in its parameter list
and some of its parameter endianness.

This implementation might not be suitable for different HW.

Refactor by group and pass all function arguments of
mlx5_accel_esp_create_hw_context in common mlx5_accel_esp_xfrm_attrs
struct field of mlx5_accel_esp_xfrm struct and correct the endianness
according to the HW being called.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.c  | 20 +++++++++++++------
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.h  | 10 ++--------
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 23 +++++++++-------------
 include/linux/mlx5/accel.h                         | 12 +++++++++++
 4 files changed, 37 insertions(+), 28 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index eddc34e4a762..a92cd88d369c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -57,13 +57,21 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 }
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				       struct mlx5_accel_esp_xfrm *xfrm,
-				       const __be32 saddr[4],
-				       const __be32 daddr[4],
-				       const __be32 spi, bool is_ipv6)
+				       struct mlx5_accel_esp_xfrm *xfrm)
 {
-	return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr, daddr,
-					     spi, is_ipv6);
+	__be32 saddr[4] = {}, daddr[4] = {};
+
+	if (!xfrm->attrs.is_ipv6) {
+		saddr[3] = xfrm->attrs.saddr.a4;
+		daddr[3] = xfrm->attrs.daddr.a4;
+	} else {
+		memcpy(saddr, xfrm->attrs.saddr.a6, sizeof(saddr));
+		memcpy(daddr, xfrm->attrs.daddr.a6, sizeof(daddr));
+	}
+
+	return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr,
+					     daddr, xfrm->attrs.spi,
+					     xfrm->attrs.is_ipv6);
 }
 
 void mlx5_accel_esp_free_hw_context(void *context)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
index 530e428d46ab..f9b8e2a041c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
@@ -47,10 +47,7 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 				   unsigned int count);
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				       struct mlx5_accel_esp_xfrm *xfrm,
-				       const __be32 saddr[4],
-				       const __be32 daddr[4],
-				       const __be32 spi, bool is_ipv6);
+				       struct mlx5_accel_esp_xfrm *xfrm);
 void mlx5_accel_esp_free_hw_context(void *context);
 
 int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
@@ -63,10 +60,7 @@ void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
 
 static inline void *
 mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				 struct mlx5_accel_esp_xfrm *xfrm,
-				 const __be32 saddr[4],
-				 const __be32 daddr[4],
-				 const __be32 spi, bool is_ipv6)
+				 struct mlx5_accel_esp_xfrm *xfrm)
 {
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 29626c6c9c25..9e6c2216c93e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -199,6 +199,14 @@ mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	attrs->flags |= (x->props.mode == XFRM_MODE_TRANSPORT) ?
 			MLX5_ACCEL_ESP_FLAGS_TRANSPORT :
 			MLX5_ACCEL_ESP_FLAGS_TUNNEL;
+
+	/* spi */
+	attrs->spi = x->id.spi;
+
+	/* source , destination ips */
+	memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr));
+	memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr));
+	attrs->is_ipv6 = (x->props.family != AF_INET);
 }
 
 static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x)
@@ -284,8 +292,6 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 	struct net_device *netdev = x->xso.dev;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	struct mlx5e_priv *priv;
-	__be32 saddr[4] = {0}, daddr[4] = {0}, spi;
-	bool is_ipv6 = false;
 	int err;
 
 	priv = netdev_priv(netdev);
@@ -331,20 +337,9 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 	}
 
 	/* create hw context */
-	if (x->props.family == AF_INET) {
-		saddr[3] = x->props.saddr.a4;
-		daddr[3] = x->id.daddr.a4;
-	} else {
-		memcpy(saddr, x->props.saddr.a6, sizeof(saddr));
-		memcpy(daddr, x->id.daddr.a6, sizeof(daddr));
-		is_ipv6 = true;
-	}
-	spi = x->id.spi;
 	sa_entry->hw_context =
 			mlx5_accel_esp_create_hw_context(priv->mdev,
-							 sa_entry->xfrm,
-							 saddr, daddr, spi,
-							 is_ipv6);
+							 sa_entry->xfrm);
 	if (IS_ERR(sa_entry->hw_context)) {
 		err = PTR_ERR(sa_entry->hw_context);
 		goto err_xfrm;
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
index 5613e677a5f9..b919d143a9a6 100644
--- a/include/linux/mlx5/accel.h
+++ b/include/linux/mlx5/accel.h
@@ -92,6 +92,18 @@ struct mlx5_accel_esp_xfrm_attrs {
 	union {
 		struct aes_gcm_keymat aes_gcm;
 	} keymat;
+
+	union {
+		__be32 a4;
+		__be32 a6[4];
+	} saddr;
+
+	union {
+		__be32 a4;
+		__be32 a6[4];
+	} daddr;
+
+	u8 is_ipv6;
 };
 
 struct mlx5_accel_esp_xfrm {
-- 
cgit v1.2.3


From 0aab3e1b04aeeb5682c1ae7c862f107334ab79c0 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 8 Jan 2020 11:48:37 +0200
Subject: net/mlx5e: IPSec, Expose IPsec HW stat only for supporting HW

The current HW counters are supported only by Innova, split the ipsec
stats group into two groups, one for HW and one for SW. And expose
the HW counters to ethtool only if Innova HW is used for IPsec offload.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   | 25 ------
 .../mellanox/mlx5/core/en_accel/ipsec_stats.c      | 88 +++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 29 ++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  2 +
 4 files changed, 58 insertions(+), 86 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 93bf10e6508c..c85151a1e008 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -109,11 +109,6 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv);
 void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv);
 void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv);
 
-int mlx5e_ipsec_get_count(struct mlx5e_priv *priv);
-int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv, uint8_t *data);
-void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv);
-int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data);
-
 struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *dev,
 					      unsigned int handle);
 
@@ -136,26 +131,6 @@ static inline void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 {
 }
 
-static inline int mlx5e_ipsec_get_count(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
-static inline int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv,
-					  uint8_t *data)
-{
-	return 0;
-}
-
-static inline void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv)
-{
-}
-
-static inline int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data)
-{
-	return 0;
-}
-
 #endif
 
 #endif	/* __MLX5E_IPSEC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 6fea59223dc4..6c5c54bcd9be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -38,6 +38,7 @@
 #include "accel/ipsec.h"
 #include "fpga/sdk.h"
 #include "en_accel/ipsec.h"
+#include "fpga/ipsec.h"
 
 static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_stats, ipsec_dec_in_packets) },
@@ -73,61 +74,74 @@ static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = {
 #define NUM_IPSEC_HW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_hw_stats_desc)
 #define NUM_IPSEC_SW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_sw_stats_desc)
 
-#define NUM_IPSEC_COUNTERS (NUM_IPSEC_HW_COUNTERS + NUM_IPSEC_SW_COUNTERS)
-
-int mlx5e_ipsec_get_count(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_sw)
 {
-	if (!priv->ipsec)
-		return 0;
-
-	return NUM_IPSEC_COUNTERS;
+	return NUM_IPSEC_SW_COUNTERS;
 }
 
-int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv, uint8_t *data)
-{
-	unsigned int i, idx = 0;
+static inline MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_sw) {}
 
-	if (!priv->ipsec)
-		return 0;
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_sw)
+{
+	unsigned int i;
 
-	for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_ipsec_hw_stats_desc[i].format);
+	if (priv->ipsec)
+		for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       mlx5e_ipsec_sw_stats_desc[i].format);
+	return idx;
+}
 
-	for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       mlx5e_ipsec_sw_stats_desc[i].format);
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw)
+{
+	int i;
 
-	return NUM_IPSEC_COUNTERS;
+	if (priv->ipsec)
+		for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
+			data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->sw_stats,
+							      mlx5e_ipsec_sw_stats_desc, i);
+	return idx;
 }
 
-void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv)
+static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_hw)
 {
-	int ret;
+	return (mlx5_fpga_ipsec_device_caps(priv->mdev)) ? NUM_IPSEC_HW_COUNTERS : 0;
+}
 
-	if (!priv->ipsec)
-		return;
+static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw)
+{
+	int ret = 0;
 
-	ret = mlx5_accel_ipsec_counters_read(priv->mdev, (u64 *)&priv->ipsec->stats,
-					     NUM_IPSEC_HW_COUNTERS);
+	if (priv->ipsec)
+		ret = mlx5_accel_ipsec_counters_read(priv->mdev, (u64 *)&priv->ipsec->stats,
+						     NUM_IPSEC_HW_COUNTERS);
 	if (ret)
 		memset(&priv->ipsec->stats, 0, sizeof(priv->ipsec->stats));
 }
 
-int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data)
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_hw)
 {
-	int i, idx = 0;
-
-	if (!priv->ipsec)
-		return 0;
+	unsigned int i;
 
-	for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(&priv->ipsec->stats,
-						   mlx5e_ipsec_hw_stats_desc, i);
+	if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev))
+		for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       mlx5e_ipsec_hw_stats_desc[i].format);
 
-	for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->sw_stats,
-						      mlx5e_ipsec_sw_stats_desc, i);
+	return idx;
+}
 
-	return NUM_IPSEC_COUNTERS;
+static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw)
+{
+	int i;
+
+	if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev))
+		for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++)
+			data[idx++] = MLX5E_READ_CTR64_CPU(&priv->ipsec->stats,
+							   mlx5e_ipsec_hw_stats_desc,
+							   i);
+	return idx;
 }
+
+MLX5E_DEFINE_STATS_GRP(ipsec_sw, 0);
+MLX5E_DEFINE_STATS_GRP(ipsec_hw, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 30b216d9284c..6eb0e8236bbf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -32,8 +32,8 @@
 
 #include "lib/mlx5.h"
 #include "en.h"
-#include "en_accel/ipsec.h"
 #include "en_accel/tls.h"
+#include "en_accel/en_accel.h"
 
 static unsigned int stats_grps_num(struct mlx5e_priv *priv)
 {
@@ -1424,27 +1424,6 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pme)
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pme) { return; }
 
-static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec)
-{
-	return mlx5e_ipsec_get_count(priv);
-}
-
-static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec)
-{
-	return idx + mlx5e_ipsec_get_strings(priv,
-					     data + idx * ETH_GSTRING_LEN);
-}
-
-static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec)
-{
-	return idx + mlx5e_ipsec_get_stats(priv, data + idx);
-}
-
-static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec)
-{
-	mlx5e_ipsec_update_stats(priv);
-}
-
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(tls)
 {
 	return mlx5e_tls_get_count(priv);
@@ -1714,7 +1693,6 @@ MLX5E_DEFINE_STATS_GRP(pme, 0);
 MLX5E_DEFINE_STATS_GRP(channels, 0);
 MLX5E_DEFINE_STATS_GRP(per_port_buff_congest, 0);
 MLX5E_DEFINE_STATS_GRP(eth_ext, 0);
-static MLX5E_DEFINE_STATS_GRP(ipsec, 0);
 static MLX5E_DEFINE_STATS_GRP(tls, 0);
 
 /* The stats groups order is opposite to the update_stats() order calls */
@@ -1731,7 +1709,10 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = {
 	&MLX5E_STATS_GRP(pcie),
 	&MLX5E_STATS_GRP(per_prio),
 	&MLX5E_STATS_GRP(pme),
-	&MLX5E_STATS_GRP(ipsec),
+#ifdef CONFIG_MLX5_EN_IPSEC
+	&MLX5E_STATS_GRP(ipsec_sw),
+	&MLX5E_STATS_GRP(ipsec_hw),
+#endif
 	&MLX5E_STATS_GRP(tls),
 	&MLX5E_STATS_GRP(channels),
 	&MLX5E_STATS_GRP(per_port_buff_congest),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 092b39ffa32a..2b83ba990714 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -390,5 +390,7 @@ extern MLX5E_DECLARE_STATS_GRP(per_prio);
 extern MLX5E_DECLARE_STATS_GRP(pme);
 extern MLX5E_DECLARE_STATS_GRP(channels);
 extern MLX5E_DECLARE_STATS_GRP(per_port_buff_congest);
+extern MLX5E_DECLARE_STATS_GRP(ipsec_hw);
+extern MLX5E_DECLARE_STATS_GRP(ipsec_sw);
 
 #endif /* __MLX5_EN_STATS_H__ */
-- 
cgit v1.2.3


From 7dfee4b1d79e1800818abcfb47747b162c9a2d31 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 23 Oct 2019 17:04:13 +0300
Subject: net/mlx5: IPsec, Refactor SA handle creation and destruction

Currently the SA handle is created and managed as part of the common
code for different IPsec supporting HW, this handle is passed to HW
to be used on Rx to identify the SA handle that was used to
return the xfrm state to stack.

The above implementation pose a limitation on managing this handle.

Refactor by moving management of this field to the specific HW code.

Downstream patches will introduce the Connect-X support for IPsec that
will use this handle differently than current implementation.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.c  |  5 +-
 .../net/ethernet/mellanox/mlx5/core/accel/ipsec.h  |  6 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 68 +++++++++-------------
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c   | 29 ++++++++-
 .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.h   |  3 +-
 5 files changed, 63 insertions(+), 48 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index a92cd88d369c..8a4985d8cbfe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -57,7 +57,8 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 }
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				       struct mlx5_accel_esp_xfrm *xfrm)
+				       struct mlx5_accel_esp_xfrm *xfrm,
+				       u32 *sa_handle)
 {
 	__be32 saddr[4] = {}, daddr[4] = {};
 
@@ -71,7 +72,7 @@ void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 
 	return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr,
 					     daddr, xfrm->attrs.spi,
-					     xfrm->attrs.is_ipv6);
+					     xfrm->attrs.is_ipv6, sa_handle);
 }
 
 void mlx5_accel_esp_free_hw_context(void *context)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
index f9b8e2a041c1..e89747674712 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
@@ -47,7 +47,8 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
 				   unsigned int count);
 
 void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				       struct mlx5_accel_esp_xfrm *xfrm);
+				       struct mlx5_accel_esp_xfrm *xfrm,
+				       u32 *sa_handle);
 void mlx5_accel_esp_free_hw_context(void *context);
 
 int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
@@ -60,7 +61,8 @@ void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
 
 static inline void *
 mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
-				 struct mlx5_accel_esp_xfrm *xfrm)
+				 struct mlx5_accel_esp_xfrm *xfrm,
+				 u32 *sa_handle)
 {
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 9e6c2216c93e..92eb3bad4acd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -75,18 +75,23 @@ struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *ipsec,
 	return ret;
 }
 
-static int mlx5e_ipsec_sadb_rx_add(struct mlx5e_ipsec_sa_entry *sa_entry)
+static int  mlx5e_ipsec_sadb_rx_add(struct mlx5e_ipsec_sa_entry *sa_entry,
+				    unsigned int handle)
 {
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5e_ipsec_sa_entry *_sa_entry;
 	unsigned long flags;
-	int ret;
 
-	ret = ida_simple_get(&ipsec->halloc, 1, 0, GFP_KERNEL);
-	if (ret < 0)
-		return ret;
+	rcu_read_lock();
+	hash_for_each_possible_rcu(ipsec->sadb_rx, _sa_entry, hlist, handle)
+		if (_sa_entry->handle == handle) {
+			rcu_read_unlock();
+			return  -EEXIST;
+		}
+	rcu_read_unlock();
 
 	spin_lock_irqsave(&ipsec->sadb_rx_lock, flags);
-	sa_entry->handle = ret;
+	sa_entry->handle = handle;
 	hash_add_rcu(ipsec->sadb_rx, &sa_entry->hlist, sa_entry->handle);
 	spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags);
 
@@ -103,15 +108,6 @@ static void mlx5e_ipsec_sadb_rx_del(struct mlx5e_ipsec_sa_entry *sa_entry)
 	spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags);
 }
 
-static void mlx5e_ipsec_sadb_rx_free(struct mlx5e_ipsec_sa_entry *sa_entry)
-{
-	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
-
-	/* xfrm already doing sync rcu between del and free callbacks */
-
-	ida_simple_remove(&ipsec->halloc, sa_entry->handle);
-}
-
 static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct xfrm_replay_state_esn *replay_esn;
@@ -292,6 +288,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 	struct net_device *netdev = x->xso.dev;
 	struct mlx5_accel_esp_xfrm_attrs attrs;
 	struct mlx5e_priv *priv;
+	unsigned int sa_handle;
 	int err;
 
 	priv = netdev_priv(netdev);
@@ -309,20 +306,6 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 	sa_entry->x = x;
 	sa_entry->ipsec = priv->ipsec;
 
-	/* Add the SA to handle processed incoming packets before the add SA
-	 * completion was received
-	 */
-	if (x->xso.flags & XFRM_OFFLOAD_INBOUND) {
-		err = mlx5e_ipsec_sadb_rx_add(sa_entry);
-		if (err) {
-			netdev_info(netdev, "Failed adding to SADB_RX: %d\n", err);
-			goto err_entry;
-		}
-	} else {
-		sa_entry->set_iv_op = (x->props.flags & XFRM_STATE_ESN) ?
-				mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv;
-	}
-
 	/* check esn */
 	mlx5e_ipsec_update_esn_state(sa_entry);
 
@@ -333,30 +316,38 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x)
 					   MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA);
 	if (IS_ERR(sa_entry->xfrm)) {
 		err = PTR_ERR(sa_entry->xfrm);
-		goto err_sadb_rx;
+		goto err_sa_entry;
 	}
 
 	/* create hw context */
 	sa_entry->hw_context =
 			mlx5_accel_esp_create_hw_context(priv->mdev,
-							 sa_entry->xfrm);
+							 sa_entry->xfrm,
+							 &sa_handle);
 	if (IS_ERR(sa_entry->hw_context)) {
 		err = PTR_ERR(sa_entry->hw_context);
 		goto err_xfrm;
 	}
 
+	if (x->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		err = mlx5e_ipsec_sadb_rx_add(sa_entry, sa_handle);
+		if (err)
+			goto err_hw_ctx;
+	} else {
+		sa_entry->set_iv_op = (x->props.flags & XFRM_STATE_ESN) ?
+				mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv;
+	}
+
 	x->xso.offload_handle = (unsigned long)sa_entry;
 	goto out;
 
+err_hw_ctx:
+	mlx5_accel_esp_free_hw_context(sa_entry->hw_context);
 err_xfrm:
 	mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm);
-err_sadb_rx:
-	if (x->xso.flags & XFRM_OFFLOAD_INBOUND) {
-		mlx5e_ipsec_sadb_rx_del(sa_entry);
-		mlx5e_ipsec_sadb_rx_free(sa_entry);
-	}
-err_entry:
+err_sa_entry:
 	kfree(sa_entry);
+
 out:
 	return err;
 }
@@ -385,9 +376,6 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 		mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm);
 	}
 
-	if (x->xso.flags & XFRM_OFFLOAD_INBOUND)
-		mlx5e_ipsec_sadb_rx_free(sa_entry);
-
 	kfree(sa_entry);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index c8736b6b4172..0604216eb94f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -65,6 +65,7 @@ struct mlx5_fpga_esp_xfrm;
 struct mlx5_fpga_ipsec_sa_ctx {
 	struct rhash_head		hash;
 	struct mlx5_ifc_fpga_ipsec_sa	hw_sa;
+	u32				sa_handle;
 	struct mlx5_core_dev		*dev;
 	struct mlx5_fpga_esp_xfrm	*fpga_xfrm;
 };
@@ -119,6 +120,8 @@ struct mlx5_fpga_ipsec {
 	 */
 	struct rb_root rules_rb;
 	struct mutex rules_rb_lock; /* rules lock */
+
+	struct ida halloc;
 };
 
 static bool mlx5_fpga_is_ipsec_device(struct mlx5_core_dev *mdev)
@@ -666,7 +669,8 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
 				    struct mlx5_accel_esp_xfrm *accel_xfrm,
 				    const __be32 saddr[4],
 				    const __be32 daddr[4],
-				    const __be32 spi, bool is_ipv6)
+				    const __be32 spi, bool is_ipv6,
+				    u32 *sa_handle)
 {
 	struct mlx5_fpga_ipsec_sa_ctx *sa_ctx;
 	struct mlx5_fpga_esp_xfrm *fpga_xfrm =
@@ -704,6 +708,17 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
 		goto exists;
 	}
 
+	if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT) {
+		err = ida_simple_get(&fipsec->halloc, 1, 0, GFP_KERNEL);
+		if (err < 0) {
+			context = ERR_PTR(err);
+			goto exists;
+		}
+
+		sa_ctx->sa_handle = err;
+		if (sa_handle)
+			*sa_handle = sa_ctx->sa_handle;
+	}
 	/* This is unbounded fpga_xfrm, try to add to hash */
 	mutex_lock(&fipsec->sa_hash_lock);
 
@@ -744,7 +759,8 @@ delete_hash:
 				       rhash_sa));
 unlock_hash:
 	mutex_unlock(&fipsec->sa_hash_lock);
-
+	if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		ida_simple_remove(&fipsec->halloc, sa_ctx->sa_handle);
 exists:
 	mutex_unlock(&fpga_xfrm->lock);
 	kfree(sa_ctx);
@@ -816,7 +832,7 @@ mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev,
 	/* create */
 	return mlx5_fpga_ipsec_create_sa_ctx(mdev, accel_xfrm,
 					     saddr, daddr,
-					     spi, is_ipv6);
+					     spi, is_ipv6, NULL);
 }
 
 static void
@@ -836,6 +852,10 @@ mlx5_fpga_ipsec_release_sa_ctx(struct mlx5_fpga_ipsec_sa_ctx *sa_ctx)
 		return;
 	}
 
+	if (sa_ctx->fpga_xfrm->accel_xfrm.attrs.action &
+	    MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		ida_simple_remove(&fipsec->halloc, sa_ctx->sa_handle);
+
 	mutex_lock(&fipsec->sa_hash_lock);
 	WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash, &sa_ctx->hash,
 				       rhash_sa));
@@ -1299,6 +1319,8 @@ int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev)
 		goto err_destroy_hash;
 	}
 
+	ida_init(&fdev->ipsec->halloc);
+
 	return 0;
 
 err_destroy_hash:
@@ -1331,6 +1353,7 @@ void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev)
 	if (!mlx5_fpga_is_ipsec_device(mdev))
 		return;
 
+	ida_destroy(&fdev->ipsec->halloc);
 	destroy_rules_rb(&fdev->ipsec->rules_rb);
 	rhashtable_destroy(&fdev->ipsec->sa_hash);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
index d01b1fc8e11b..9ba637f0f0f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
@@ -47,7 +47,8 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
 				    struct mlx5_accel_esp_xfrm *accel_xfrm,
 				    const __be32 saddr[4],
 				    const __be32 daddr[4],
-				    const __be32 spi, bool is_ipv6);
+				    const __be32 spi, bool is_ipv6,
+				    u32 *sa_handle);
 void mlx5_fpga_ipsec_delete_sa_ctx(void *context);
 
 int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev);
-- 
cgit v1.2.3


From 82fe2996419830b0bb2c7e1f2fed2d3a8a1a65cd Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 18 Feb 2020 12:27:25 +0200
Subject: net/mlx5e: Set of completion request bit should not clear other
 adjacent bits

In notify HW (ring doorbell) flow, we set the bit to request a completion
on the TX descriptor.
When doing so, we should not unset other bits in the same byte.
Currently, this does not fix a real issue, as we still don't have a flow
where both MLX5_WQE_CTRL_CQ_UPDATE and any adjacent bit are set together.

Fixes: 542578c67936 ("net/mlx5e: Move helper functions to a new txrx datapath header")
Fixes: 864b2d715300 ("net/mlx5e: Generalize tx helper functions for different SQ types")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index f07b1399744e..9f6967d76053 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -102,7 +102,7 @@ static inline void
 mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 		struct mlx5_wqe_ctrl_seg *ctrl)
 {
-	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
+	ctrl->fm_ce_se |= MLX5_WQE_CTRL_CQ_UPDATE;
 	/* ensure wqe is visible to device before updating doorbell record */
 	dma_wmb();
 
-- 
cgit v1.2.3


From d7a42ad062cc6b20b2c2a8c09dc61df2d4f5751f Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 25 Mar 2020 11:32:56 +0200
Subject: net/mlx5e: Allow partial data mask for tunnel options

We use mapping to save and restore the tunnel options.
Save also the tunnel options mask.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 32 +++++++++++++++++--------
 1 file changed, 22 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a574c588269a..7d2b05576f44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -171,6 +171,11 @@ struct tunnel_match_key {
 	int filter_ifindex;
 };
 
+struct tunnel_match_enc_opts {
+	struct flow_dissector_key_enc_opts key;
+	struct flow_dissector_key_enc_opts mask;
+};
+
 /* Tunnel_id mapping is TUNNEL_INFO_BITS + ENC_OPTS_BITS.
  * Upper TUNNEL_INFO_BITS for general tunnel info.
  * Lower ENC_OPTS_BITS bits for enc_opts.
@@ -1824,9 +1829,7 @@ enc_opts_is_dont_care_or_full_match(struct mlx5e_priv *priv,
 			*dont_care = false;
 
 			if (opt->opt_class != U16_MAX ||
-			    opt->type != U8_MAX ||
-			    memchr_inv(opt->opt_data, 0xFF,
-				       opt->length * 4)) {
+			    opt->type != U8_MAX) {
 				NL_SET_ERR_MSG(extack,
 					       "Partial match of tunnel options in chain > 0 isn't supported");
 				netdev_warn(priv->netdev,
@@ -1863,6 +1866,7 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts;
 	struct flow_match_enc_opts enc_opts_match;
+	struct tunnel_match_enc_opts tun_enc_opts;
 	struct mlx5_rep_uplink_priv *uplink_priv;
 	struct mlx5e_rep_priv *uplink_rpriv;
 	struct tunnel_match_key tunnel_key;
@@ -1905,8 +1909,14 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv,
 		goto err_enc_opts;
 
 	if (!enc_opts_is_dont_care) {
+		memset(&tun_enc_opts, 0, sizeof(tun_enc_opts));
+		memcpy(&tun_enc_opts.key, enc_opts_match.key,
+		       sizeof(*enc_opts_match.key));
+		memcpy(&tun_enc_opts.mask, enc_opts_match.mask,
+		       sizeof(*enc_opts_match.mask));
+
 		err = mapping_add(uplink_priv->tunnel_enc_opts_mapping,
-				  enc_opts_match.key, &enc_opts_id);
+				  &tun_enc_opts, &enc_opts_id);
 		if (err)
 			goto err_enc_opts;
 	}
@@ -4707,7 +4717,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 {
-	const size_t sz_enc_opts = sizeof(struct flow_dissector_key_enc_opts);
+	const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts);
 	struct mlx5_rep_uplink_priv *uplink_priv;
 	struct mlx5e_rep_priv *priv;
 	struct mapping_ctx *mapping;
@@ -4802,7 +4812,7 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
 				 u32 tunnel_id)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct flow_dissector_key_enc_opts enc_opts = {};
+	struct tunnel_match_enc_opts enc_opts = {};
 	struct mlx5_rep_uplink_priv *uplink_priv;
 	struct mlx5e_rep_priv *uplink_rpriv;
 	struct metadata_dst *tun_dst;
@@ -4840,7 +4850,7 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
 		}
 	}
 
-	tun_dst = tun_rx_dst(enc_opts.len);
+	tun_dst = tun_rx_dst(enc_opts.key.len);
 	if (!tun_dst) {
 		WARN_ON_ONCE(true);
 		return false;
@@ -4854,9 +4864,11 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
 			   key32_to_tunnel_id(key.enc_key_id.keyid),
 			   TUNNEL_KEY);
 
-	if (enc_opts.len)
-		ip_tunnel_info_opts_set(&tun_dst->u.tun_info, enc_opts.data,
-					enc_opts.len, enc_opts.dst_opt_type);
+	if (enc_opts.key.len)
+		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
+					enc_opts.key.data,
+					enc_opts.key.len,
+					enc_opts.key.dst_opt_type);
 
 	skb_dst_set(skb, (struct dst_entry *)tun_dst);
 	dev = dev_get_by_index(&init_net, key.filter_ifindex);
-- 
cgit v1.2.3


From fa3748775b92692331cfcab6f7b09a04a23694d9 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 19 Mar 2020 17:32:27 +0200
Subject: net/mlx5e: Handle errors from netif_set_real_num_{tx,rx}_queues

netif_set_real_num_tx_queues and netif_set_real_num_rx_queues may fail.
Now that mlx5e supports handling errors in the preactivate hook, this
commit leverages that functionality to handle errors from those
functions and roll back all changes on failure.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 59 +++++++++++++++++-----
 2 files changed, 48 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6d703ddee4e2..4ab78b5c2393 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -432,7 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		*cur_params = new_channels.params;
-		mlx5e_num_channels_changed(priv);
+		err = mlx5e_num_channels_changed(priv);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f02150a97ac8..e057822898f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2839,11 +2839,8 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
 				ETH_MAX_MTU);
 }
 
-static void mlx5e_netdev_set_tcs(struct net_device *netdev)
+static void mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int nch = priv->channels.params.num_channels;
-	int ntc = priv->channels.params.num_tc;
 	int tc;
 
 	netdev_reset_tc(netdev);
@@ -2860,15 +2857,47 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv, u16 count)
+static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 {
-	int num_txqs = count * priv->channels.params.num_tc;
-	int num_rxqs = count * priv->profile->rq_groups;
 	struct net_device *netdev = priv->netdev;
+	int num_txqs, num_rxqs, nch, ntc;
+	int old_num_txqs, old_ntc;
+	int err;
+
+	old_num_txqs = netdev->real_num_tx_queues;
+	old_ntc = netdev->num_tc;
 
-	mlx5e_netdev_set_tcs(netdev);
-	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, num_rxqs);
+	nch = priv->channels.params.num_channels;
+	ntc = priv->channels.params.num_tc;
+	num_txqs = nch * ntc;
+	num_rxqs = nch * priv->profile->rq_groups;
+
+	mlx5e_netdev_set_tcs(netdev, nch, ntc);
+
+	err = netif_set_real_num_tx_queues(netdev, num_txqs);
+	if (err) {
+		netdev_warn(netdev, "netif_set_real_num_tx_queues failed, %d\n", err);
+		goto err_tcs;
+	}
+	err = netif_set_real_num_rx_queues(netdev, num_rxqs);
+	if (err) {
+		netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err);
+		goto err_txqs;
+	}
+
+	return 0;
+
+err_txqs:
+	/* netif_set_real_num_rx_queues could fail only when nch increased. Only
+	 * one of nch and ntc is changed in this function. That means, the call
+	 * to netif_set_real_num_tx_queues below should not fail, because it
+	 * decreases the number of TX queues.
+	 */
+	WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs));
+
+err_tcs:
+	mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc);
+	return err;
 }
 
 static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
@@ -2895,8 +2924,12 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 int mlx5e_num_channels_changed(struct mlx5e_priv *priv)
 {
 	u16 count = priv->channels.params.num_channels;
+	int err;
+
+	err = mlx5e_update_netdev_queues(priv);
+	if (err)
+		return err;
 
-	mlx5e_update_netdev_queues(priv, count);
 	mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params);
 
 	if (!netif_is_rxfh_configured(priv->netdev))
@@ -5358,9 +5391,11 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	 */
 	if (take_rtnl)
 		rtnl_lock();
-	mlx5e_num_channels_changed(priv);
+	err = mlx5e_num_channels_changed(priv);
 	if (take_rtnl)
 		rtnl_unlock();
+	if (err)
+		goto out;
 
 	err = profile->init_tx(priv);
 	if (err)
-- 
cgit v1.2.3


From c89da067a2e4d0f94f0f314c2918dca50348789c Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Sun, 8 Mar 2020 21:41:22 -0500
Subject: net/mlx5: Read embedded cpu bit only once

Embedded CPU bit doesn't change with PCI resume/suspend.
Hence read it only once while probing the PCI device.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7af4210c1b96..5a97e98e937c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -782,7 +782,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	}
 
 	mlx5_pci_vsc_init(dev);
-
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	return 0;
 
 err_clr_master:
@@ -1180,7 +1180,6 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 {
 	int err = 0;
 
-	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		mlx5_core_warn(dev, "interface is up, NOP\n");
-- 
cgit v1.2.3


From 6533380dfd003ea7636cb5672f4f85124b56328b Mon Sep 17 00:00:00 2001
From: Hu Haowen <xianfengting221@163.com>
Date: Wed, 1 Apr 2020 20:57:20 +0800
Subject: net/mlx5: improve some comments

Replaced "its" with "it's".

Signed-off-by: Hu Haowen <xianfengting221@163.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index c9c9b479bda5..0a8adda073c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -684,7 +684,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 		get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]);
 
 	while (block_timestamp > tracer->last_timestamp) {
-		/* Check block override if its not the first block */
+		/* Check block override if it's not the first block */
 		if (!tracer->last_timestamp) {
 			u64 *ts_event;
 			/* To avoid block override be the HW in case of buffer
-- 
cgit v1.2.3


From 794867ee6730fe3f0d419d3911f35a725cafe3a8 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 20 Apr 2020 22:52:59 +0200
Subject: r8169: change wmb to smb_wmb in rtl8169_start_xmit

A barrier is needed here to ensure that rtl_tx sees the descriptor
changes (DescOwn set) before the updated tp->cur_tx value. Else it may
wrongly assume that the transfer has been finished already. For this
purpose smp_wmb() is sufficient.

No separate barrier is needed for ordering the descriptor changes
with the MMIO doorbell write. The needed barrier is included in
the non-relaxed writel() used by rtl8169_doorbell().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b8cc064ee9f5..b7a2853e7396 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4249,8 +4249,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd_first->opts1 |= cpu_to_le32(DescOwn | FirstFrag);
 
-	/* Force all memory writes to complete before notifying device */
-	wmb();
+	/* rtl_tx needs to see descriptor changes before updated tp->cur_tx */
+	smp_wmb();
 
 	tp->cur_tx += frags + 1;
 
-- 
cgit v1.2.3


From d4d9b47e4b10679d5c794e62f9866ee5ee204c0d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Apr 2020 00:51:17 +0300
Subject: net: bcmgenet: Drop ACPI_PTR() to avoid compiler warning

When compiled with CONFIG_ACPI=n, ACPI_PTR() will be no-op, and thus
genet_acpi_match table defined, but not used. Compiler is not happy about
such data. Drop ACPI_PTR() for good.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index d975338bf78d..9f2f0e681656 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3740,7 +3740,7 @@ static struct platform_driver bcmgenet_driver = {
 		.name	= "bcmgenet",
 		.of_match_table = bcmgenet_match,
 		.pm	= &bcmgenet_pm_ops,
-		.acpi_match_table = ACPI_PTR(genet_acpi_match),
+		.acpi_match_table = genet_acpi_match,
 	},
 };
 module_platform_driver(bcmgenet_driver);
-- 
cgit v1.2.3


From 9a965942a9cabb2cdca1d7e99c985d6978ece96c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Apr 2020 00:51:18 +0300
Subject: net: bcmgenet: Drop useless OF code

There is nothing which needs a set of OF headers, followed by redundant
OF node ID check. Drop them for good.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9f2f0e681656..ef275db018f7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -23,11 +23,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/pm.h>
 #include <linux/clk.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/of_net.h>
-#include <linux/of_platform.h>
 #include <net/arp.h>
 
 #include <linux/mii.h>
@@ -3417,8 +3412,6 @@ MODULE_DEVICE_TABLE(of, bcmgenet_match);
 static int bcmgenet_probe(struct platform_device *pdev)
 {
 	struct bcmgenet_platform_data *pd = pdev->dev.platform_data;
-	struct device_node *dn = pdev->dev.of_node;
-	const struct of_device_id *of_id = NULL;
 	const struct bcmgenet_plat_data *pdata;
 	struct bcmgenet_priv *priv;
 	struct net_device *dev;
@@ -3433,12 +3426,6 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	if (dn) {
-		of_id = of_match_node(bcmgenet_match, dn);
-		if (!of_id)
-			return -EINVAL;
-	}
-
 	priv = netdev_priv(dev);
 	priv->irq0 = platform_get_irq(pdev, 0);
 	if (priv->irq0 < 0) {
-- 
cgit v1.2.3


From c80d36ff63a5fb447616e03d4339d2eef7884d28 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Apr 2020 00:51:19 +0300
Subject: net: bcmgenet: Use devm_clk_get_optional() to get the clocks

Conversion to devm_clk_get_optional() makes it explicit that clocks are
optional. This change allows to handle deferred probe in case clocks are
defined, but not yet probed. Due to above changes bail out in error case.

While here, check potential error when enable main clock.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ef275db018f7..86666e9ab3e7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3487,13 +3487,16 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH;
 	}
 
-	priv->clk = devm_clk_get(&priv->pdev->dev, "enet");
+	priv->clk = devm_clk_get_optional(&priv->pdev->dev, "enet");
 	if (IS_ERR(priv->clk)) {
 		dev_dbg(&priv->pdev->dev, "failed to get enet clock\n");
-		priv->clk = NULL;
+		err = PTR_ERR(priv->clk);
+		goto err;
 	}
 
-	clk_prepare_enable(priv->clk);
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		goto err;
 
 	bcmgenet_set_hw_params(priv);
 
@@ -3511,16 +3514,18 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	priv->rx_buf_len = RX_BUF_LENGTH;
 	INIT_WORK(&priv->bcmgenet_irq_work, bcmgenet_irq_task);
 
-	priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol");
+	priv->clk_wol = devm_clk_get_optional(&priv->pdev->dev, "enet-wol");
 	if (IS_ERR(priv->clk_wol)) {
 		dev_dbg(&priv->pdev->dev, "failed to get enet-wol clock\n");
-		priv->clk_wol = NULL;
+		err = PTR_ERR(priv->clk_wol);
+		goto err;
 	}
 
-	priv->clk_eee = devm_clk_get(&priv->pdev->dev, "enet-eee");
+	priv->clk_eee = devm_clk_get_optional(&priv->pdev->dev, "enet-eee");
 	if (IS_ERR(priv->clk_eee)) {
 		dev_dbg(&priv->pdev->dev, "failed to get enet-eee clock\n");
-		priv->clk_eee = NULL;
+		err = PTR_ERR(priv->clk_eee);
+		goto err;
 	}
 
 	/* If this is an internal GPHY, power it on now, before UniMAC is
-- 
cgit v1.2.3


From d2af1420cbc84f5eabcca6b667d7fb2339c398e2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Apr 2020 00:51:20 +0300
Subject: net: bcmgenet: Use get_unligned_beXX() and put_unaligned_beXX()

It's convenient to use get_unligned_beXX() and put_unaligned_beXX() helpers
to get or set MAC instead of open-coded variants.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 86666e9ab3e7..2c9881032a24 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2702,9 +2702,8 @@ static void bcmgenet_umac_reset(struct bcmgenet_priv *priv)
 static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv,
 				 unsigned char *addr)
 {
-	bcmgenet_umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) |
-			(addr[2] << 8) | addr[3], UMAC_MAC0);
-	bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1);
+	bcmgenet_umac_writel(priv, get_unaligned_be32(&addr[0]), UMAC_MAC0);
+	bcmgenet_umac_writel(priv, get_unaligned_be16(&addr[4]), UMAC_MAC1);
 }
 
 static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
@@ -2713,13 +2712,9 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
 	u32 addr_tmp;
 
 	addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC0);
-	addr[0] = addr_tmp >> 24;
-	addr[1] = (addr_tmp >> 16) & 0xff;
-	addr[2] = (addr_tmp >>	8) & 0xff;
-	addr[3] = addr_tmp & 0xff;
+	put_unaligned_be32(addr_tmp, &addr[0]);
 	addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC1);
-	addr[4] = (addr_tmp >> 8) & 0xff;
-	addr[5] = addr_tmp & 0xff;
+	put_unaligned_be16(addr_tmp, &addr[4]);
 }
 
 /* Returns a reusable dma control register value */
-- 
cgit v1.2.3


From 7d3cca75c169710048b0fea08522f635efcea893 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 21 Apr 2020 00:51:21 +0300
Subject: net: bcmgenet: Drop too many parentheses in bcmgenet_probe()

No need to have parentheses around plain pointer variable or
negation operator. Drop them for good.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 2c9881032a24..20aba79becce 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3529,7 +3529,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	if ((pd) && (!IS_ERR_OR_NULL(pd->mac_address)))
+	if (pd && !IS_ERR_OR_NULL(pd->mac_address))
 		ether_addr_copy(dev->dev_addr, pd->mac_address);
 	else
 		if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN))
-- 
cgit v1.2.3


From 1c79031f8a75c132bbd42e3ef20267af97b67466 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 19 Apr 2020 17:18:47 +0300
Subject: drivers: Remove inclusion of vermagic header

Get rid of linux/vermagic.h includes, so that MODULE_ARCH_VERMAGIC from
the arch header arch/x86/include/asm/module.h won't be redefined.

  In file included from ./include/linux/module.h:30,
                   from drivers/net/ethernet/3com/3c515.c:56:
  ./arch/x86/include/asm/module.h:73: warning: "MODULE_ARCH_VERMAGIC"
redefined
     73 | # define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
        |
  In file included from drivers/net/ethernet/3com/3c515.c:25:
  ./include/linux/vermagic.h:28: note: this is the location of the
previous definition
     28 | #define MODULE_ARCH_VERMAGIC ""
        |

Fixes: 6bba2e89a88c ("net/3com: Delete driver and module versions from 3com drivers")
Co-developed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Shannon Nelson <snelson@pensando.io> # ionic
Acked-by: Sebastian Reichel <sre@kernel.org> # power
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bonding_priv.h               | 2 +-
 drivers/net/ethernet/3com/3c509.c                | 1 -
 drivers/net/ethernet/3com/3c515.c                | 1 -
 drivers/net/ethernet/adaptec/starfire.c          | 1 -
 drivers/net/ethernet/pensando/ionic/ionic_main.c | 2 +-
 drivers/power/supply/test_power.c                | 2 +-
 net/ethtool/ioctl.c                              | 3 +--
 7 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h
index 45b77bc8c7b3..48cdf3a49a7d 100644
--- a/drivers/net/bonding/bonding_priv.h
+++ b/drivers/net/bonding/bonding_priv.h
@@ -14,7 +14,7 @@
 
 #ifndef _BONDING_PRIV_H
 #define _BONDING_PRIV_H
-#include <linux/vermagic.h>
+#include <generated/utsrelease.h>
 
 #define DRV_NAME	"bonding"
 #define DRV_DESCRIPTION	"Ethernet Channel Bonding Driver"
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index b762176a1406..139d0120f511 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -85,7 +85,6 @@
 #include <linux/device.h>
 #include <linux/eisa.h>
 #include <linux/bitops.h>
-#include <linux/vermagic.h>
 
 #include <linux/uaccess.h>
 #include <asm/io.h>
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index 90312fcd6319..47b4215bb93b 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -22,7 +22,6 @@
 
 */
 
-#include <linux/vermagic.h>
 #define DRV_NAME		"3c515"
 
 #define CORKSCREW 1
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 2db42211329f..a64191fc2af9 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -45,7 +45,6 @@
 #include <asm/processor.h>		/* Processor type for cache alignment. */
 #include <linux/uaccess.h>
 #include <asm/io.h>
-#include <linux/vermagic.h>
 
 /*
  * The current frame processor firmware fails to checksum a fragment
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 588c62e9add7..3ed150512091 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -6,7 +6,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/utsname.h>
-#include <linux/vermagic.h>
+#include <generated/utsrelease.h>
 
 #include "ionic.h"
 #include "ionic_bus.h"
diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c
index 65c23ef6408d..b3c05ff05783 100644
--- a/drivers/power/supply/test_power.c
+++ b/drivers/power/supply/test_power.c
@@ -16,7 +16,7 @@
 #include <linux/power_supply.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <linux/vermagic.h>
+#include <generated/utsrelease.h>
 
 enum test_power_id {
 	TEST_AC,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 593fa665f820..226d5ecdd567 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -17,7 +17,6 @@
 #include <linux/phy.h>
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
-#include <linux/vermagic.h>
 #include <linux/vmalloc.h>
 #include <linux/sfp.h>
 #include <linux/slab.h>
@@ -28,7 +27,7 @@
 #include <net/xdp_sock.h>
 #include <net/flow_offload.h>
 #include <linux/ethtool_netlink.h>
-
+#include <generated/utsrelease.h>
 #include "common.h"
 
 /*
-- 
cgit v1.2.3


From cad99e506887e257ce8bce826ec25f7854b7e69a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 19 Apr 2020 17:18:48 +0300
Subject: net/hns: Remove custom driver version in favour of global one

Use globally defined kernel version instead of custom driver variant.

Reported-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 3 ---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    | 4 ----
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 ----
 3 files changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index da98fd7c8eca..ac3a48a24d86 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -15,7 +15,6 @@
 #include <linux/aer.h>
 #include <linux/skbuff.h>
 #include <linux/sctp.h>
-#include <linux/vermagic.h>
 #include <net/gre.h>
 #include <net/ip6_checksum.h>
 #include <net/pkt_cls.h>
@@ -44,7 +43,6 @@ static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
 static void hns3_remove_hw_addr(struct net_device *netdev);
 
 static const char hns3_driver_name[] = "hns3";
-const char hns3_driver_version[] = VERMAGIC_STRING;
 static const char hns3_driver_string[] =
 			"Hisilicon Ethernet Network Driver for Hip08 Family";
 static const char hns3_copyright[] = "Copyright (c) 2017 Huawei Corporation.";
@@ -4765,4 +4763,3 @@ MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet Driver");
 MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("pci:hns-nic");
-MODULE_VERSION(HNS3_MOD_VERSION);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index abefd7a179f7..4b3f0abf0715 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -8,10 +8,6 @@
 
 #include "hnae3.h"
 
-#define HNS3_MOD_VERSION "1.0"
-
-extern const char hns3_driver_version[];
-
 enum hns3_nic_state {
 	HNS3_NIC_STATE_TESTING,
 	HNS3_NIC_STATE_RESETTING,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 28b81f24afa1..6a0734be4a1a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -546,10 +546,6 @@ static void hns3_get_drvinfo(struct net_device *netdev,
 		return;
 	}
 
-	strncpy(drvinfo->version, hns3_driver_version,
-		sizeof(drvinfo->version));
-	drvinfo->version[sizeof(drvinfo->version) - 1] = '\0';
-
 	strncpy(drvinfo->driver, h->pdev->driver->name,
 		sizeof(drvinfo->driver));
 	drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0';
-- 
cgit v1.2.3


From b4f37219813fd126b2cda6d7805d8c61b8cf801a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 19 Apr 2020 17:18:49 +0300
Subject: net/nfp: Update driver to use global kernel version

Change nfp driver to use globally defined kernel version.

Reported-by: Borislav Petkov <bp@suse.de>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_main.c        | 3 ---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 --
 2 files changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 4d282fc56009..7ff2ccbd43b0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -14,7 +14,6 @@
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
-#include <linux/vermagic.h>
 #include <linux/vmalloc.h>
 #include <net/devlink.h>
 
@@ -31,7 +30,6 @@
 #include "nfp_net.h"
 
 static const char nfp_driver_name[] = "nfp";
-const char nfp_driver_version[] = VERMAGIC_STRING;
 
 static const struct pci_device_id nfp_pci_device_ids[] = {
 	{ PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000,
@@ -920,4 +918,3 @@ MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_1x10_1x25.nffw");
 MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("The Netronome Flow Processor (NFP) driver.");
-MODULE_VERSION(UTS_RELEASE);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 2779f1526d1e..a5aa3219d112 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -203,8 +203,6 @@ nfp_get_drvinfo(struct nfp_app *app, struct pci_dev *pdev,
 	char nsp_version[ETHTOOL_FWVERS_LEN] = {};
 
 	strlcpy(drvinfo->driver, pdev->driver->name, sizeof(drvinfo->driver));
-	strlcpy(drvinfo->version, nfp_driver_version, sizeof(drvinfo->version));
-
 	nfp_net_get_nspinfo(app, nsp_version);
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%s %s %s %s", vnic_version, nsp_version,
-- 
cgit v1.2.3


From 2b49d128b3f8d8fff8972afcbc603802e5e40c6a Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 20 Apr 2020 10:46:45 +0800
Subject: net: mscc: ocelot: move ocelot ptp clock code out of ocelot.c

The Ocelot PTP clock driver had been embedded into ocelot.c driver.
It had supported basic gettime64/settime64/adjtime/adjfine functions
by now which were used by both Ocelot switch and Felix switch.

This patch is to move current ptp clock code out of ocelot.c driver
maintaining as a single ocelot_ptp.c.
For futher new features implementation, the common code could be put
in ocelot_ptp.c and the switch specific code should be in specific
switch driver. The interrupt implementation in SoC is different
between Ocelot and Felix.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c           |  25 ++++
 drivers/net/ethernet/mscc/Makefile       |   2 +-
 drivers/net/ethernet/mscc/ocelot.c       | 206 -------------------------------
 drivers/net/ethernet/mscc/ocelot.h       |   3 +-
 drivers/net/ethernet/mscc/ocelot_board.c |  25 ++++
 drivers/net/ethernet/mscc/ocelot_ptp.c   | 203 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot_ptp.h   |  41 ------
 include/soc/mscc/ocelot.h                |   1 -
 include/soc/mscc/ocelot_ptp.h            |  52 ++++++++
 9 files changed, 307 insertions(+), 251 deletions(-)
 create mode 100644 drivers/net/ethernet/mscc/ocelot_ptp.c
 delete mode 100644 drivers/net/ethernet/mscc/ocelot_ptp.h
 create mode 100644 include/soc/mscc/ocelot_ptp.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index d0a3764ff0cf..44015a24b087 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -7,6 +7,7 @@
 #include <soc/mscc/ocelot_sys.h>
 #include <soc/mscc/ocelot_dev.h>
 #include <soc/mscc/ocelot_ana.h>
+#include <soc/mscc/ocelot_ptp.h>
 #include <soc/mscc/ocelot.h>
 #include <linux/packing.h>
 #include <linux/module.h>
@@ -494,6 +495,21 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	return 0;
 }
 
+static struct ptp_clock_info ocelot_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.name		= "felix ptp",
+	.max_adj	= 0x7fffffff,
+	.n_alarm	= 0,
+	.n_ext_ts	= 0,
+	.n_per_out	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.gettime64	= ocelot_ptp_gettime64,
+	.settime64	= ocelot_ptp_settime64,
+	.adjtime	= ocelot_ptp_adjtime,
+	.adjfine	= ocelot_ptp_adjfine,
+};
+
 /* Hardware initialization done here so that we can allocate structures with
  * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing
  * us to allocate structures twice (leak memory) and map PCI memory twice
@@ -510,6 +526,14 @@ static int felix_setup(struct dsa_switch *ds)
 		return err;
 
 	ocelot_init(ocelot);
+	if (ocelot->ptp) {
+		err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info);
+		if (err) {
+			dev_err(ocelot->dev,
+				"Timestamp initialization failed\n");
+			ocelot->ptp = 0;
+		}
+	}
 
 	for (port = 0; port < ds->num_ports; port++) {
 		ocelot_init_port(ocelot, port);
@@ -548,6 +572,7 @@ static void felix_teardown(struct dsa_switch *ds)
 	if (felix->info->mdio_bus_free)
 		felix->info->mdio_bus_free(ocelot);
 
+	ocelot_deinit_timestamp(ocelot);
 	/* stop workqueue thread */
 	ocelot_deinit(ocelot);
 }
diff --git a/drivers/net/ethernet/mscc/Makefile b/drivers/net/ethernet/mscc/Makefile
index 9a36c26095c8..91b33b55054e 100644
--- a/drivers/net/ethernet/mscc/Makefile
+++ b/drivers/net/ethernet/mscc/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: (GPL-2.0 OR MIT)
 obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot_common.o
 mscc_ocelot_common-y := ocelot.o ocelot_io.o
-mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o
+mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o ocelot_ptp.o
 obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_board.o
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index a8c48a4a708f..7c4165af9f66 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include <linux/ptp_clock_kernel.h>
 #include <linux/skbuff.h>
 #include <linux/iopoll.h>
 #include <net/arp.h>
@@ -1991,200 +1990,6 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = {
 };
 EXPORT_SYMBOL(ocelot_switchdev_blocking_nb);
 
-int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts)
-{
-	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
-	unsigned long flags;
-	time64_t s;
-	u32 val;
-	s64 ns;
-
-	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
-
-	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
-	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
-	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE);
-	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
-
-	s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff;
-	s <<= 32;
-	s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN);
-	ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
-
-	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
-
-	/* Deal with negative values */
-	if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) {
-		s--;
-		ns &= 0xf;
-		ns += 999999984;
-	}
-
-	set_normalized_timespec64(ts, s, ns);
-	return 0;
-}
-EXPORT_SYMBOL(ocelot_ptp_gettime64);
-
-static int ocelot_ptp_settime64(struct ptp_clock_info *ptp,
-				const struct timespec64 *ts)
-{
-	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
-	unsigned long flags;
-	u32 val;
-
-	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
-
-	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
-	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
-	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE);
-
-	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
-
-	ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB,
-			 TOD_ACC_PIN);
-	ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB,
-			 TOD_ACC_PIN);
-	ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
-
-	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
-	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
-	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD);
-
-	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
-
-	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
-	return 0;
-}
-
-static int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
-{
-	if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) {
-		struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
-		unsigned long flags;
-		u32 val;
-
-		spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
-
-		val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
-		val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
-		val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE);
-
-		ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
-
-		ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN);
-		ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN);
-		ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
-
-		val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
-		val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
-		val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA);
-
-		ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
-
-		spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
-	} else {
-		/* Fall back using ocelot_ptp_settime64 which is not exact. */
-		struct timespec64 ts;
-		u64 now;
-
-		ocelot_ptp_gettime64(ptp, &ts);
-
-		now = ktime_to_ns(timespec64_to_ktime(ts));
-		ts = ns_to_timespec64(now + delta);
-
-		ocelot_ptp_settime64(ptp, &ts);
-	}
-	return 0;
-}
-
-static int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
-{
-	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
-	u32 unit = 0, direction = 0;
-	unsigned long flags;
-	u64 adj = 0;
-
-	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
-
-	if (!scaled_ppm)
-		goto disable_adj;
-
-	if (scaled_ppm < 0) {
-		direction = PTP_CFG_CLK_ADJ_CFG_DIR;
-		scaled_ppm = -scaled_ppm;
-	}
-
-	adj = PSEC_PER_SEC << 16;
-	do_div(adj, scaled_ppm);
-	do_div(adj, 1000);
-
-	/* If the adjustment value is too large, use ns instead */
-	if (adj >= (1L << 30)) {
-		unit = PTP_CFG_CLK_ADJ_FREQ_NS;
-		do_div(adj, 1000);
-	}
-
-	/* Still too big */
-	if (adj >= (1L << 30))
-		goto disable_adj;
-
-	ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ);
-	ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction,
-		     PTP_CLK_CFG_ADJ_CFG);
-
-	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
-	return 0;
-
-disable_adj:
-	ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG);
-
-	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
-	return 0;
-}
-
-static struct ptp_clock_info ocelot_ptp_clock_info = {
-	.owner		= THIS_MODULE,
-	.name		= "ocelot ptp",
-	.max_adj	= 0x7fffffff,
-	.n_alarm	= 0,
-	.n_ext_ts	= 0,
-	.n_per_out	= 0,
-	.n_pins		= 0,
-	.pps		= 0,
-	.gettime64	= ocelot_ptp_gettime64,
-	.settime64	= ocelot_ptp_settime64,
-	.adjtime	= ocelot_ptp_adjtime,
-	.adjfine	= ocelot_ptp_adjfine,
-};
-
-static int ocelot_init_timestamp(struct ocelot *ocelot)
-{
-	struct ptp_clock *ptp_clock;
-
-	ocelot->ptp_info = ocelot_ptp_clock_info;
-	ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev);
-	if (IS_ERR(ptp_clock))
-		return PTR_ERR(ptp_clock);
-	/* Check if PHC support is missing at the configuration level */
-	if (!ptp_clock)
-		return 0;
-
-	ocelot->ptp_clock = ptp_clock;
-
-	ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG);
-	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW);
-	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH);
-
-	ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC);
-
-	/* There is no device reconfiguration, PTP Rx stamping is always
-	 * enabled.
-	 */
-	ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
-
-	return 0;
-}
-
 /* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu.
  * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG.
  * In the special case that it's the NPI port that we're configuring, the
@@ -2530,15 +2335,6 @@ int ocelot_init(struct ocelot *ocelot)
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
 
-	if (ocelot->ptp) {
-		ret = ocelot_init_timestamp(ocelot);
-		if (ret) {
-			dev_err(ocelot->dev,
-				"Timestamp initialization failed\n");
-			return ret;
-		}
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(ocelot_init);
@@ -2551,8 +2347,6 @@ void ocelot_deinit(struct ocelot *ocelot)
 	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
-	if (ocelot->ptp_clock)
-		ptp_clock_unregister(ocelot->ptp_clock);
 
 	for (i = 0; i < ocelot->num_phys_ports; i++) {
 		port = ocelot->ports[i];
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 641af929497f..f0a15aa187f2 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -15,18 +15,17 @@
 #include <linux/phy.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
-#include <linux/ptp_clock_kernel.h>
 #include <linux/regmap.h>
 
 #include <soc/mscc/ocelot_qsys.h>
 #include <soc/mscc/ocelot_sys.h>
 #include <soc/mscc/ocelot_dev.h>
 #include <soc/mscc/ocelot_ana.h>
+#include <soc/mscc/ocelot_ptp.h>
 #include <soc/mscc/ocelot.h>
 #include "ocelot_rew.h"
 #include "ocelot_qs.h"
 #include "ocelot_tc.h"
-#include "ocelot_ptp.h"
 
 #define OCELOT_BUFFER_CELL_SZ 60
 
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 0ac9fbf77a01..ee016f7ed934 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -366,6 +366,21 @@ static const struct vcap_props vsc7514_vcap_props[] = {
 	},
 };
 
+static struct ptp_clock_info ocelot_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.name		= "ocelot ptp",
+	.max_adj	= 0x7fffffff,
+	.n_alarm	= 0,
+	.n_ext_ts	= 0,
+	.n_per_out	= 0,
+	.n_pins		= 0,
+	.pps		= 0,
+	.gettime64	= ocelot_ptp_gettime64,
+	.settime64	= ocelot_ptp_settime64,
+	.adjtime	= ocelot_ptp_adjtime,
+	.adjfine	= ocelot_ptp_adjfine,
+};
+
 static int mscc_ocelot_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -469,6 +484,15 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	ocelot->vcap = vsc7514_vcap_props;
 
 	ocelot_init(ocelot);
+	if (ocelot->ptp) {
+		err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info);
+		if (err) {
+			dev_err(ocelot->dev,
+				"Timestamp initialization failed\n");
+			ocelot->ptp = 0;
+		}
+	}
+
 	/* No NPI port */
 	ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
 			     OCELOT_TAG_PREFIX_NONE);
@@ -574,6 +598,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
 {
 	struct ocelot *ocelot = platform_get_drvdata(pdev);
 
+	ocelot_deinit_timestamp(ocelot);
 	ocelot_deinit(ocelot);
 	unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 	unregister_switchdev_notifier(&ocelot_switchdev_nb);
diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
new file mode 100644
index 000000000000..69d4e5677343
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Microsemi Ocelot PTP clock driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ * Copyright 2020 NXP
+ */
+#include <soc/mscc/ocelot_ptp.h>
+#include <soc/mscc/ocelot_sys.h>
+#include <soc/mscc/ocelot.h>
+
+int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
+	unsigned long flags;
+	time64_t s;
+	u32 val;
+	s64 ns;
+
+	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+
+	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
+	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
+	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE);
+	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
+
+	s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff;
+	s <<= 32;
+	s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN);
+	ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
+
+	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+
+	/* Deal with negative values */
+	if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) {
+		s--;
+		ns &= 0xf;
+		ns += 999999984;
+	}
+
+	set_normalized_timespec64(ts, s, ns);
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_gettime64);
+
+int ocelot_ptp_settime64(struct ptp_clock_info *ptp,
+			 const struct timespec64 *ts)
+{
+	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+
+	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
+	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
+	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE);
+
+	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
+
+	ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB,
+			 TOD_ACC_PIN);
+	ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB,
+			 TOD_ACC_PIN);
+	ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
+
+	val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
+	val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM);
+	val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD);
+
+	ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
+
+	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_settime64);
+
+int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) {
+		struct ocelot *ocelot = container_of(ptp, struct ocelot,
+						     ptp_info);
+		unsigned long flags;
+		u32 val;
+
+		spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+
+		val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
+		val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK |
+			 PTP_PIN_CFG_DOM);
+		val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE);
+
+		ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
+
+		ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN);
+		ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN);
+		ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN);
+
+		val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN);
+		val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK |
+			 PTP_PIN_CFG_DOM);
+		val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA);
+
+		ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN);
+
+		spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+	} else {
+		/* Fall back using ocelot_ptp_settime64 which is not exact. */
+		struct timespec64 ts;
+		u64 now;
+
+		ocelot_ptp_gettime64(ptp, &ts);
+
+		now = ktime_to_ns(timespec64_to_ktime(ts));
+		ts = ns_to_timespec64(now + delta);
+
+		ocelot_ptp_settime64(ptp, &ts);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_adjtime);
+
+int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
+	u32 unit = 0, direction = 0;
+	unsigned long flags;
+	u64 adj = 0;
+
+	spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+
+	if (!scaled_ppm)
+		goto disable_adj;
+
+	if (scaled_ppm < 0) {
+		direction = PTP_CFG_CLK_ADJ_CFG_DIR;
+		scaled_ppm = -scaled_ppm;
+	}
+
+	adj = PSEC_PER_SEC << 16;
+	do_div(adj, scaled_ppm);
+	do_div(adj, 1000);
+
+	/* If the adjustment value is too large, use ns instead */
+	if (adj >= (1L << 30)) {
+		unit = PTP_CFG_CLK_ADJ_FREQ_NS;
+		do_div(adj, 1000);
+	}
+
+	/* Still too big */
+	if (adj >= (1L << 30))
+		goto disable_adj;
+
+	ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ);
+	ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction,
+		     PTP_CLK_CFG_ADJ_CFG);
+
+	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+	return 0;
+
+disable_adj:
+	ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG);
+
+	spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_adjfine);
+
+int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info)
+{
+	struct ptp_clock *ptp_clock;
+
+	ocelot->ptp_info = *info;
+	ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev);
+	if (IS_ERR(ptp_clock))
+		return PTR_ERR(ptp_clock);
+	/* Check if PHC support is missing at the configuration level */
+	if (!ptp_clock)
+		return 0;
+
+	ocelot->ptp_clock = ptp_clock;
+
+	ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG);
+	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW);
+	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH);
+
+	ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC);
+
+	/* There is no device reconfiguration, PTP Rx stamping is always
+	 * enabled.
+	 */
+	ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_init_timestamp);
+
+int ocelot_deinit_timestamp(struct ocelot *ocelot)
+{
+	if (ocelot->ptp_clock)
+		ptp_clock_unregister(ocelot->ptp_clock);
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_deinit_timestamp);
diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.h b/drivers/net/ethernet/mscc/ocelot_ptp.h
deleted file mode 100644
index 9ede14a12573..000000000000
--- a/drivers/net/ethernet/mscc/ocelot_ptp.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
-/*
- * Microsemi Ocelot Switch driver
- *
- * License: Dual MIT/GPL
- * Copyright (c) 2017 Microsemi Corporation
- */
-
-#ifndef _MSCC_OCELOT_PTP_H_
-#define _MSCC_OCELOT_PTP_H_
-
-#define PTP_PIN_CFG_RSZ			0x20
-#define PTP_PIN_TOD_SEC_MSB_RSZ		PTP_PIN_CFG_RSZ
-#define PTP_PIN_TOD_SEC_LSB_RSZ		PTP_PIN_CFG_RSZ
-#define PTP_PIN_TOD_NSEC_RSZ		PTP_PIN_CFG_RSZ
-
-#define PTP_PIN_CFG_DOM			BIT(0)
-#define PTP_PIN_CFG_SYNC		BIT(2)
-#define PTP_PIN_CFG_ACTION(x)		((x) << 3)
-#define PTP_PIN_CFG_ACTION_MASK		PTP_PIN_CFG_ACTION(0x7)
-
-enum {
-	PTP_PIN_ACTION_IDLE = 0,
-	PTP_PIN_ACTION_LOAD,
-	PTP_PIN_ACTION_SAVE,
-	PTP_PIN_ACTION_CLOCK,
-	PTP_PIN_ACTION_DELTA,
-	PTP_PIN_ACTION_NOSYNC,
-	PTP_PIN_ACTION_SYNC,
-};
-
-#define PTP_CFG_MISC_PTP_EN		BIT(2)
-
-#define PSEC_PER_SEC			1000000000000LL
-
-#define PTP_CFG_CLK_ADJ_CFG_ENA		BIT(0)
-#define PTP_CFG_CLK_ADJ_CFG_DIR		BIT(1)
-
-#define PTP_CFG_CLK_ADJ_FREQ_NS		BIT(30)
-
-#endif
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 6d6a3947c8b7..6fd88ee622cf 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -620,7 +620,6 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid);
 int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr);
 int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr);
-int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts);
 int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port,
 				 struct sk_buff *skb);
 void ocelot_get_txtstamp(struct ocelot *ocelot);
diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h
new file mode 100644
index 000000000000..f01b0ce4e4cb
--- /dev/null
+++ b/include/soc/mscc/ocelot_ptp.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * License: Dual MIT/GPL
+ * Copyright (c) 2017 Microsemi Corporation
+ * Copyright 2020 NXP
+ */
+
+#ifndef _MSCC_OCELOT_PTP_H_
+#define _MSCC_OCELOT_PTP_H_
+
+#include <linux/ptp_clock_kernel.h>
+#include <soc/mscc/ocelot.h>
+
+#define PTP_PIN_CFG_RSZ			0x20
+#define PTP_PIN_TOD_SEC_MSB_RSZ		PTP_PIN_CFG_RSZ
+#define PTP_PIN_TOD_SEC_LSB_RSZ		PTP_PIN_CFG_RSZ
+#define PTP_PIN_TOD_NSEC_RSZ		PTP_PIN_CFG_RSZ
+
+#define PTP_PIN_CFG_DOM			BIT(0)
+#define PTP_PIN_CFG_SYNC		BIT(2)
+#define PTP_PIN_CFG_ACTION(x)		((x) << 3)
+#define PTP_PIN_CFG_ACTION_MASK		PTP_PIN_CFG_ACTION(0x7)
+
+enum {
+	PTP_PIN_ACTION_IDLE = 0,
+	PTP_PIN_ACTION_LOAD,
+	PTP_PIN_ACTION_SAVE,
+	PTP_PIN_ACTION_CLOCK,
+	PTP_PIN_ACTION_DELTA,
+	PTP_PIN_ACTION_NOSYNC,
+	PTP_PIN_ACTION_SYNC,
+};
+
+#define PTP_CFG_MISC_PTP_EN		BIT(2)
+
+#define PSEC_PER_SEC			1000000000000LL
+
+#define PTP_CFG_CLK_ADJ_CFG_ENA		BIT(0)
+#define PTP_CFG_CLK_ADJ_CFG_DIR		BIT(1)
+
+#define PTP_CFG_CLK_ADJ_FREQ_NS		BIT(30)
+
+int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts);
+int ocelot_ptp_settime64(struct ptp_clock_info *ptp,
+			 const struct timespec64 *ts);
+int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta);
+int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm);
+int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info);
+int ocelot_deinit_timestamp(struct ocelot *ocelot);
+#endif
-- 
cgit v1.2.3


From d2b09a8e7bcbfa47e7161b20d6387ac968834c21 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 20 Apr 2020 10:46:46 +0800
Subject: net: mscc: ocelot: fix timestamp info if ptp clock does not work

The timestamp info should be only software timestamp capabilities
if ptp clock does not work.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 7c4165af9f66..a2b9b85612a4 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1349,6 +1349,12 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 {
 	info->phc_index = ocelot->ptp_clock ?
 			  ptp_clock_index(ocelot->ptp_clock) : -1;
+	if (info->phc_index == -1) {
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+					 SOF_TIMESTAMPING_RX_SOFTWARE |
+					 SOF_TIMESTAMPING_SOFTWARE;
+		return 0;
+	}
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
 				 SOF_TIMESTAMPING_RX_SOFTWARE |
 				 SOF_TIMESTAMPING_SOFTWARE |
-- 
cgit v1.2.3


From 94aca0824443d32987b31e656044ff7da425c523 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 20 Apr 2020 10:46:48 +0800
Subject: net: mscc: ocelot: add wave programming registers definitions

Add wave programming registers definitions for Ocelot platforms.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix_vsc9959.c  | 2 ++
 drivers/net/ethernet/mscc/ocelot_regs.c | 2 ++
 include/soc/mscc/ocelot.h               | 2 ++
 include/soc/mscc/ocelot_ptp.h           | 2 ++
 4 files changed, 8 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4078f3c5c38..4fe707ef54b8 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -313,6 +313,8 @@ static const u32 vsc9959_ptp_regmap[] = {
 	REG(PTP_PIN_TOD_SEC_MSB,           0x000004),
 	REG(PTP_PIN_TOD_SEC_LSB,           0x000008),
 	REG(PTP_PIN_TOD_NSEC,              0x00000c),
+	REG(PTP_PIN_WF_HIGH_PERIOD,        0x000014),
+	REG(PTP_PIN_WF_LOW_PERIOD,         0x000018),
 	REG(PTP_CFG_MISC,                  0x0000a0),
 	REG(PTP_CLK_CFG_ADJ_CFG,           0x0000a4),
 	REG(PTP_CLK_CFG_ADJ_FREQ,          0x0000a8),
diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c
index b88b5899b227..ed4dd01a41ad 100644
--- a/drivers/net/ethernet/mscc/ocelot_regs.c
+++ b/drivers/net/ethernet/mscc/ocelot_regs.c
@@ -239,6 +239,8 @@ static const u32 ocelot_ptp_regmap[] = {
 	REG(PTP_PIN_TOD_SEC_MSB,           0x000004),
 	REG(PTP_PIN_TOD_SEC_LSB,           0x000008),
 	REG(PTP_PIN_TOD_NSEC,              0x00000c),
+	REG(PTP_PIN_WF_HIGH_PERIOD,        0x000014),
+	REG(PTP_PIN_WF_LOW_PERIOD,         0x000018),
 	REG(PTP_CFG_MISC,                  0x0000a0),
 	REG(PTP_CLK_CFG_ADJ_CFG,           0x0000a4),
 	REG(PTP_CLK_CFG_ADJ_FREQ,          0x0000a8),
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 7d44d3508869..31193ad3a545 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -385,6 +385,8 @@ enum ocelot_reg {
 	PTP_PIN_TOD_SEC_MSB,
 	PTP_PIN_TOD_SEC_LSB,
 	PTP_PIN_TOD_NSEC,
+	PTP_PIN_WF_HIGH_PERIOD,
+	PTP_PIN_WF_LOW_PERIOD,
 	PTP_CFG_MISC,
 	PTP_CLK_CFG_ADJ_CFG,
 	PTP_CLK_CFG_ADJ_FREQ,
diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h
index f01b0ce4e4cb..aae1570eecb1 100644
--- a/include/soc/mscc/ocelot_ptp.h
+++ b/include/soc/mscc/ocelot_ptp.h
@@ -17,6 +17,8 @@
 #define PTP_PIN_TOD_SEC_MSB_RSZ		PTP_PIN_CFG_RSZ
 #define PTP_PIN_TOD_SEC_LSB_RSZ		PTP_PIN_CFG_RSZ
 #define PTP_PIN_TOD_NSEC_RSZ		PTP_PIN_CFG_RSZ
+#define PTP_PIN_WF_HIGH_PERIOD_RSZ	PTP_PIN_CFG_RSZ
+#define PTP_PIN_WF_LOW_PERIOD_RSZ	PTP_PIN_CFG_RSZ
 
 #define PTP_PIN_CFG_DOM			BIT(0)
 #define PTP_PIN_CFG_SYNC		BIT(2)
-- 
cgit v1.2.3


From cc2d87bb83407c7dfb0900d63b3fcfbf6a59202f Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 20 Apr 2020 10:46:49 +0800
Subject: net: mscc: ocelot: support 4 PTP programmable pins

Support 4 PTP programmable pins with only PTP_PF_PEROUT function
for now. The PTP_PF_EXTTS function will be supported in the
future, and it should be implemented separately for Felix and
Ocelot, because of different hardware interrupt implementation
in them.

Since the hardware is not able to support absolute start time,
the periodic clock request only allows start time 0 0. But nsec
could be accepted for PPS case for phase adjustment.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_ptp.c | 121 +++++++++++++++++++++++++++++++++
 include/soc/mscc/ocelot.h              |   3 +
 include/soc/mscc/ocelot_ptp.h          |   4 ++
 3 files changed, 128 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
index 69d4e5677343..a3088a1676ed 100644
--- a/drivers/net/ethernet/mscc/ocelot_ptp.c
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -165,11 +165,132 @@ disable_adj:
 }
 EXPORT_SYMBOL(ocelot_ptp_adjfine);
 
+int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+		      enum ptp_pin_function func, unsigned int chan)
+{
+	switch (func) {
+	case PTP_PF_NONE:
+	case PTP_PF_PEROUT:
+		break;
+	case PTP_PF_EXTTS:
+	case PTP_PF_PHYSYNC:
+		return -1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_verify);
+
+int ocelot_ptp_enable(struct ptp_clock_info *ptp,
+		      struct ptp_clock_request *rq, int on)
+{
+	struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info);
+	struct timespec64 ts_start, ts_period;
+	enum ocelot_ptp_pins ptp_pin;
+	unsigned long flags;
+	bool pps = false;
+	int pin = -1;
+	u32 val;
+	s64 ns;
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_PEROUT:
+		/* Reject requests with unsupported flags */
+		if (rq->perout.flags)
+			return -EOPNOTSUPP;
+
+		pin = ptp_find_pin(ocelot->ptp_clock, PTP_PF_PEROUT,
+				   rq->perout.index);
+		if (pin == 0)
+			ptp_pin = PTP_PIN_0;
+		else if (pin == 1)
+			ptp_pin = PTP_PIN_1;
+		else if (pin == 2)
+			ptp_pin = PTP_PIN_2;
+		else if (pin == 3)
+			ptp_pin = PTP_PIN_3;
+		else
+			return -EBUSY;
+
+		ts_start.tv_sec = rq->perout.start.sec;
+		ts_start.tv_nsec = rq->perout.start.nsec;
+		ts_period.tv_sec = rq->perout.period.sec;
+		ts_period.tv_nsec = rq->perout.period.nsec;
+
+		if (ts_period.tv_sec == 1 && ts_period.tv_nsec == 0)
+			pps = true;
+
+		if (ts_start.tv_sec || (ts_start.tv_nsec && !pps)) {
+			dev_warn(ocelot->dev,
+				 "Absolute start time not supported!\n");
+			dev_warn(ocelot->dev,
+				 "Accept nsec for PPS phase adjustment, otherwise start time should be 0 0.\n");
+			return -EINVAL;
+		}
+
+		/* Handle turning off */
+		if (!on) {
+			spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+			val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE);
+			ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin);
+			spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+			break;
+		}
+
+		/* Handle PPS request */
+		if (pps) {
+			spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+			/* Pulse generated perout.start.nsec after TOD has
+			 * increased seconds.
+			 * Pulse width is set to 1us.
+			 */
+			ocelot_write_rix(ocelot, ts_start.tv_nsec,
+					 PTP_PIN_WF_LOW_PERIOD, ptp_pin);
+			ocelot_write_rix(ocelot, 1000,
+					 PTP_PIN_WF_HIGH_PERIOD, ptp_pin);
+			val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_CLOCK);
+			val |= PTP_PIN_CFG_SYNC;
+			ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin);
+			spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+			break;
+		}
+
+		/* Handle periodic clock */
+		ns = timespec64_to_ns(&ts_period);
+		ns = ns >> 1;
+		if (ns > 0x3fffffff || ns <= 0x6)
+			return -EINVAL;
+
+		spin_lock_irqsave(&ocelot->ptp_clock_lock, flags);
+		ocelot_write_rix(ocelot, ns, PTP_PIN_WF_LOW_PERIOD, ptp_pin);
+		ocelot_write_rix(ocelot, ns, PTP_PIN_WF_HIGH_PERIOD, ptp_pin);
+		val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_CLOCK);
+		ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin);
+		spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_ptp_enable);
+
 int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info)
 {
 	struct ptp_clock *ptp_clock;
+	int i;
 
 	ocelot->ptp_info = *info;
+
+	for (i = 0; i < OCELOT_PTP_PINS_NUM; i++) {
+		struct ptp_pin_desc *p = &ocelot->ptp_pins[i];
+
+		snprintf(p->name, sizeof(p->name), "switch_1588_dat%d", i);
+		p->index = i;
+		p->func = PTP_PF_NONE;
+	}
+
+	ocelot->ptp_info.pin_config = &ocelot->ptp_pins[0];
+
 	ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev);
 	if (IS_ERR(ptp_clock))
 		return PTR_ERR(ptp_clock);
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 31193ad3a545..a025fb798164 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -92,6 +92,8 @@
 #define OCELOT_SPEED_100		2
 #define OCELOT_SPEED_10			3
 
+#define OCELOT_PTP_PINS_NUM		4
+
 #define TARGET_OFFSET			24
 #define REG_MASK			GENMASK(TARGET_OFFSET - 1, 0)
 #define REG(reg, offset)		[reg & REG_MASK] = offset
@@ -552,6 +554,7 @@ struct ocelot {
 	struct mutex			ptp_lock;
 	/* Protects the PTP clock */
 	spinlock_t			ptp_clock_lock;
+	struct ptp_pin_desc		ptp_pins[OCELOT_PTP_PINS_NUM];
 };
 
 struct ocelot_policer {
diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h
index aae1570eecb1..4a6b2f71b6b2 100644
--- a/include/soc/mscc/ocelot_ptp.h
+++ b/include/soc/mscc/ocelot_ptp.h
@@ -49,6 +49,10 @@ int ocelot_ptp_settime64(struct ptp_clock_info *ptp,
 			 const struct timespec64 *ts);
 int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta);
 int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm);
+int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+		      enum ptp_pin_function func, unsigned int chan);
+int ocelot_ptp_enable(struct ptp_clock_info *ptp,
+		      struct ptp_clock_request *rq, int on);
 int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info);
 int ocelot_deinit_timestamp(struct ocelot *ocelot);
 #endif
-- 
cgit v1.2.3


From aabb2bb07c963c67b8072aafcca3677e2b235be0 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 20 Apr 2020 10:46:50 +0800
Subject: net: mscc: ocelot: enable PTP programmable pin

Enable PTP programmable pin.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index ee016f7ed934..67a8d61c926a 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -372,13 +372,15 @@ static struct ptp_clock_info ocelot_ptp_clock_info = {
 	.max_adj	= 0x7fffffff,
 	.n_alarm	= 0,
 	.n_ext_ts	= 0,
-	.n_per_out	= 0,
-	.n_pins		= 0,
+	.n_per_out	= OCELOT_PTP_PINS_NUM,
+	.n_pins		= OCELOT_PTP_PINS_NUM,
 	.pps		= 0,
 	.gettime64	= ocelot_ptp_gettime64,
 	.settime64	= ocelot_ptp_settime64,
 	.adjtime	= ocelot_ptp_adjtime,
 	.adjfine	= ocelot_ptp_adjfine,
+	.verify		= ocelot_ptp_verify,
+	.enable		= ocelot_ptp_enable,
 };
 
 static int mscc_ocelot_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From 86b956de119c09818d0aabaf668280d8e4bd0d4b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 20 Apr 2020 19:27:41 +0300
Subject: net: mscc: ocelot: support matching on EtherType

Currently, the filter's protocol is ignored except for a few special
cases (IPv4 and IPv6).

The EtherType can be matched inside VCAP IS2 by using a MAC_ETYPE key.
So there are 2 cases in which EtherType matches are supported:

  - As part of a larger MAC_ETYPE rule, such as:

    tc filter add dev swp0 ingress protocol ip \
            flower skip_sw src_mac 42:be:24:9b:76:20 action drop

  - Standalone (matching on protocol only):

    tc filter add dev swp0 ingress protocol arp \
            flower skip_sw action drop

As before, if the protocol is not specified, is it implicitly "all" and
the EtherType mask in the MAC_ETYPE half key is set to zero.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_flower.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 954cb67eeaa2..67f0f5455ff0 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -51,6 +51,8 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
+	u16 proto = ntohs(f->common.protocol);
+	bool match_protocol = true;
 
 	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
@@ -71,7 +73,6 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct flow_match_eth_addrs match;
-		u16 proto = ntohs(f->common.protocol);
 
 		/* The hw support mac matches only for MAC_ETYPE key,
 		 * therefore if other matches(port, tcp flags, etc) are added
@@ -114,6 +115,7 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 				match.key->ip_proto;
 			ace->frame.ipv4.proto.mask[0] =
 				match.mask->ip_proto;
+			match_protocol = false;
 		}
 		if (ntohs(match.key->n_proto) == ETH_P_IPV6) {
 			ace->type = OCELOT_ACE_TYPE_IPV6;
@@ -121,11 +123,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 				match.key->ip_proto;
 			ace->frame.ipv6.proto.mask[0] =
 				match.mask->ip_proto;
+			match_protocol = false;
 		}
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) &&
-	    ntohs(f->common.protocol) == ETH_P_IP) {
+	    proto == ETH_P_IP) {
 		struct flow_match_ipv4_addrs match;
 		u8 *tmp;
 
@@ -141,10 +144,11 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 
 		tmp = &ace->frame.ipv4.dip.mask.addr[0];
 		memcpy(tmp, &match.mask->dst, 4);
+		match_protocol = false;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) &&
-	    ntohs(f->common.protocol) == ETH_P_IPV6) {
+	    proto == ETH_P_IPV6) {
 		return -EOPNOTSUPP;
 	}
 
@@ -156,6 +160,7 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 		ace->frame.ipv4.sport.mask = ntohs(match.mask->src);
 		ace->frame.ipv4.dport.value = ntohs(match.key->dst);
 		ace->frame.ipv4.dport.mask = ntohs(match.mask->dst);
+		match_protocol = false;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
@@ -167,9 +172,20 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 		ace->vlan.vid.mask = match.mask->vlan_id;
 		ace->vlan.pcp.value[0] = match.key->vlan_priority;
 		ace->vlan.pcp.mask[0] = match.mask->vlan_priority;
+		match_protocol = false;
 	}
 
 finished_key_parsing:
+	if (match_protocol && proto != ETH_P_ALL) {
+		/* TODO: support SNAP, LLC etc */
+		if (proto < ETH_P_802_3_MIN)
+			return -EOPNOTSUPP;
+		ace->type = OCELOT_ACE_TYPE_ETYPE;
+		*(u16 *)ace->frame.etype.etype.value = htons(proto);
+		*(u16 *)ace->frame.etype.etype.mask = 0xffff;
+	}
+	/* else, a rule of type OCELOT_ACE_TYPE_ANY is implicitly added */
+
 	ace->prio = f->common.prio;
 	ace->id = f->cookie;
 	return ocelot_flower_parse_action(f, ace);
-- 
cgit v1.2.3


From 7dec902f4fc0cf1162e18030f2598440e311a2d2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 20 Apr 2020 19:27:42 +0300
Subject: net: mscc: ocelot: refine the ocelot_ace_is_problematic_mac_etype
 function

The commit mentioned below was a bit too harsh, and while it restricted
the invalid key combinations which are known to not work, such as:

tc filter add dev swp0 ingress proto ip \
      flower src_ip 192.0.2.1 action drop
tc filter add dev swp0 ingress proto all \
      flower src_mac 00:11:22:33:44:55 action drop

it also restricted some which still should work, such as:

tc filter add dev swp0 ingress proto ip \
      flower src_ip 192.0.2.1 action drop
tc filter add dev swp0 ingress proto 0x22f0 \
      flower src_mac 00:11:22:33:44:55 action drop

What actually does not match "sanely" is a MAC_ETYPE rule on frames
having an EtherType of ARP, IPv4, IPv6, in addition to SNAP and OAM
frames (which the ocelot tc-flower implementation does not parse yet, so
the function might need to be revisited again in the future).

So just make the function recognize the problematic MAC_ETYPE rules by
EtherType - thus the VCAP IS2 can be forced to match even on those
packets.

This patch makes it possible for IP rules to live on a port together
with MAC_ETYPE rules that are non-all, non-arp, non-ip and non-ipv6.

Fixes: d4d0cb741d7b ("net: mscc: ocelot: deal with problematic MAC_ETYPE VCAP IS2 rules")
Reported-by: Allan W. Nielsen <allan.nielsen@microchip.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_ace.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_ace.c b/drivers/net/ethernet/mscc/ocelot_ace.c
index 8a2f7d13ef6d..dfd82a3baab2 100644
--- a/drivers/net/ethernet/mscc/ocelot_ace.c
+++ b/drivers/net/ethernet/mscc/ocelot_ace.c
@@ -739,14 +739,24 @@ static void ocelot_match_all_as_mac_etype(struct ocelot *ocelot, int port,
 
 static bool ocelot_ace_is_problematic_mac_etype(struct ocelot_ace_rule *ace)
 {
+	u16 proto, mask;
+
 	if (ace->type != OCELOT_ACE_TYPE_ETYPE)
 		return false;
-	if (ether_addr_to_u64(ace->frame.etype.dmac.value) &
-	    ether_addr_to_u64(ace->frame.etype.dmac.mask))
+
+	proto = ntohs(*(u16 *)ace->frame.etype.etype.value);
+	mask = ntohs(*(u16 *)ace->frame.etype.etype.mask);
+
+	/* ETH_P_ALL match, so all protocols below are included */
+	if (mask == 0)
 		return true;
-	if (ether_addr_to_u64(ace->frame.etype.smac.value) &
-	    ether_addr_to_u64(ace->frame.etype.smac.mask))
+	if (proto == ETH_P_ARP)
 		return true;
+	if (proto == ETH_P_IP)
+		return true;
+	if (proto == ETH_P_IPV6)
+		return true;
+
 	return false;
 }
 
-- 
cgit v1.2.3


From 4faa2e06433fbba16a13a21e1380ee4d246b95fc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 20 Apr 2020 19:27:43 +0300
Subject: net: mscc: ocelot: lift protocol restriction for flow_match_eth_addrs
 keys

An attempt was made in commit fe3490e6107e ("net: mscc: ocelot: Hardware
ofload for tc flower filter") to avoid clashes between MAC_ETYPE rules
and IP rules. Because the protocol blacklist should have included
ETH_P_ALL too, it created some confusion, but now the situation should
be dealt with a bit better by the patch immediately previous to this one
("net: mscc: ocelot: refine the ocelot_ace_is_problematic_mac_etype
function").

So now we can remove that check. MAC_ETYPE rules with a protocol of
ETH_P_IP, ETH_P_IPV6, ETH_P_ARP and ETH_P_ALL _are_ supported, with some
restrictions regarding per-port exclusivity which are enforced now.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_flower.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 67f0f5455ff0..5ce172e22b43 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -87,11 +87,6 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 		     BIT(FLOW_DISSECTOR_KEY_CONTROL)))
 			return -EOPNOTSUPP;
 
-		if (proto == ETH_P_IP ||
-		    proto == ETH_P_IPV6 ||
-		    proto == ETH_P_ARP)
-			return -EOPNOTSUPP;
-
 		flow_rule_match_eth_addrs(rule, &match);
 		ace->type = OCELOT_ACE_TYPE_ETYPE;
 		ether_addr_copy(ace->frame.etype.dmac.value,
-- 
cgit v1.2.3


From 0785dad48003408da27579845db2f83c024636df Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 20 Apr 2020 23:29:55 +0200
Subject: r8169: use devm_mdiobus_register

Use new function devm_mdiobus_register() to simplify the driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b7a2853e7396..4c616701856a 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5185,20 +5185,18 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
 
-	ret = mdiobus_register(new_bus);
+	ret = devm_mdiobus_register(new_bus);
 	if (ret)
 		return ret;
 
 	tp->phydev = mdiobus_get_phy(new_bus, 0);
 	if (!tp->phydev) {
-		mdiobus_unregister(new_bus);
 		return -ENODEV;
 	} else if (!tp->phydev->drv) {
 		/* Most chip versions fail with the genphy driver.
 		 * Therefore ensure that the dedicated PHY driver is loaded.
 		 */
 		dev_err(&pdev->dev, "realtek.ko not loaded, maybe it needs to be added to initramfs?\n");
-		mdiobus_unregister(new_bus);
 		return -EUNATCH;
 	}
 
@@ -5523,7 +5521,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rc = register_netdev(dev);
 	if (rc)
-		goto err_mdio_unregister;
+		return rc;
 
 	netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n",
 		   rtl_chip_infos[chipset].name, dev->dev_addr, xid,
@@ -5542,10 +5540,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pm_runtime_put_sync(&pdev->dev);
 
 	return 0;
-
-err_mdio_unregister:
-	mdiobus_unregister(tp->phydev->mdio.bus);
-	return rc;
 }
 
 static struct pci_driver rtl8169_pci_driver = {
-- 
cgit v1.2.3


From c89f44ff10fd4cdcfbebf4854aa1282fdad8de5d Mon Sep 17 00:00:00 2001
From: "Chuah, Kim Tatt" <kim.tatt.chuah@intel.com>
Date: Wed, 22 Apr 2020 11:31:06 +0800
Subject: net: stmmac: Add support for VLAN promiscuous mode

For dwmac4, enable VLAN promiscuity when MAC controller is requested to
enter promiscuous mode.

Signed-off-by: Chuah, Kim Tatt <kim.tatt.chuah@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Tan, Tee Min <tee.min.tan@intel.com>
Signed-off-by: Wong Vee Khee <vee.khee.wong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h      |  1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac4.h      |  1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 67 +++++++++++++++++++++++
 3 files changed, 69 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 6208a68a331d..127f75862962 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -473,6 +473,7 @@ struct mac_device_info {
 	unsigned int xlgmac;
 	unsigned int num_vlan;
 	u32 vlan_filter[32];
+	unsigned int promisc;
 };
 
 struct stmmac_rx_routing {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 28cac28253b8..61f3249bd724 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -90,6 +90,7 @@
 #define GMAC_VLAN_CSVL			BIT(19)
 #define GMAC_VLAN_VLC			GENMASK(17, 16)
 #define GMAC_VLAN_VLC_SHIFT		16
+#define GMAC_VLAN_VLHT			GENMASK(15, 0)
 
 /* MAC VLAN Tag */
 #define GMAC_VLAN_TAG_VID		GENMASK(15, 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 39692d15d80c..ecd834e0e121 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -450,6 +450,12 @@ static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev,
 	if (vid > 4095)
 		return -EINVAL;
 
+	if (hw->promisc) {
+		netdev_err(dev,
+			   "Adding VLAN in promisc mode not supported\n");
+		return -EPERM;
+	}
+
 	/* Single Rx VLAN Filter */
 	if (hw->num_vlan == 1) {
 		/* For single VLAN filter, VID 0 means VLAN promiscuous */
@@ -499,6 +505,12 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev,
 {
 	int i, ret = 0;
 
+	if (hw->promisc) {
+		netdev_err(dev,
+			   "Deleting VLAN in promisc mode not supported\n");
+		return -EPERM;
+	}
+
 	/* Single Rx VLAN Filter */
 	if (hw->num_vlan == 1) {
 		if ((hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) == vid) {
@@ -523,9 +535,45 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev,
 	return ret;
 }
 
+static void dwmac4_vlan_promisc_enable(struct net_device *dev,
+				       struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+	u32 hash;
+	u32 val;
+	int i;
+
+	/* Single Rx VLAN Filter */
+	if (hw->num_vlan == 1) {
+		dwmac4_write_single_vlan(dev, 0);
+		return;
+	}
+
+	/* Extended Rx VLAN Filter Enable */
+	for (i = 0; i < hw->num_vlan; i++) {
+		if (hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN) {
+			val = hw->vlan_filter[i] & ~GMAC_VLAN_TAG_DATA_VEN;
+			dwmac4_write_vlan_filter(dev, hw, i, val);
+		}
+	}
+
+	hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE);
+	if (hash & GMAC_VLAN_VLHT) {
+		value = readl(ioaddr + GMAC_VLAN_TAG);
+		if (value & GMAC_VLAN_VTHM) {
+			value &= ~GMAC_VLAN_VTHM;
+			writel(value, ioaddr + GMAC_VLAN_TAG);
+		}
+	}
+}
+
 static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev,
 					   struct mac_device_info *hw)
 {
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+	u32 hash;
 	u32 val;
 	int i;
 
@@ -542,6 +590,13 @@ static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev,
 			dwmac4_write_vlan_filter(dev, hw, i, val);
 		}
 	}
+
+	hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE);
+	if (hash & GMAC_VLAN_VLHT) {
+		value = readl(ioaddr + GMAC_VLAN_TAG);
+		value |= GMAC_VLAN_VTHM;
+		writel(value, ioaddr + GMAC_VLAN_TAG);
+	}
 }
 
 static void dwmac4_set_filter(struct mac_device_info *hw,
@@ -624,6 +679,18 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 		value |= GMAC_PACKET_FILTER_VTFE;
 
 	writel(value, ioaddr + GMAC_PACKET_FILTER);
+
+	if (dev->flags & IFF_PROMISC) {
+		if (!hw->promisc) {
+			hw->promisc = 1;
+			dwmac4_vlan_promisc_enable(dev, hw);
+		}
+	} else {
+		if (hw->promisc) {
+			hw->promisc = 0;
+			dwmac4_restore_hw_vlan_rx_fltr(dev, hw);
+		}
+	}
 }
 
 static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-- 
cgit v1.2.3


From 48c0481e5ad1d1eec6ccfaee6bb8a030fbbd07f7 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 22 Apr 2020 15:05:10 +0300
Subject: dpaa2-eth: return num_enqueued frames from enqueue callback

The enqueue dpaa2-eth callback now returns the number of successfully
enqueued frames. This is a preliminary patch necessary for adding
support for bulk ring mode enqueue.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 34 ++++++++++++++++--------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  5 ++--
 2 files changed, 26 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index b6c46639aa4c..7b41ece8f160 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016-2019 NXP
+ * Copyright 2016-2020 NXP
  */
 #include <linux/init.h>
 #include <linux/module.h>
@@ -268,7 +268,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 
 	fq = &priv->fq[queue_id];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, fd, 0);
+		err = priv->enqueue(priv, fq, fd, 0, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -847,7 +847,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 * the Tx confirmation callback for this frame
 	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, prio);
+		err = priv->enqueue(priv, fq, &fd, prio, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -1937,7 +1937,7 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 
 	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, 0);
+		err = priv->enqueue(priv, fq, &fd, 0, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -2523,19 +2523,31 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 
 static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
 				       struct dpaa2_eth_fq *fq,
-				       struct dpaa2_fd *fd, u8 prio)
+				       struct dpaa2_fd *fd, u8 prio,
+				       int *frames_enqueued)
 {
-	return dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-					   priv->tx_qdid, prio,
-					   fq->tx_qdbin, fd);
+	int err;
+
+	err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
+					  priv->tx_qdid, prio,
+					  fq->tx_qdbin, fd);
+	if (!err && frames_enqueued)
+		*frames_enqueued = 1;
+	return err;
 }
 
 static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
 				       struct dpaa2_eth_fq *fq,
-				       struct dpaa2_fd *fd, u8 prio)
+				       struct dpaa2_fd *fd, u8 prio,
+				       int *frames_enqueued)
 {
-	return dpaa2_io_service_enqueue_fq(fq->channel->dpio,
-					   fq->tx_fqid[prio], fd);
+	int err;
+
+	err = dpaa2_io_service_enqueue_fq(fq->channel->dpio,
+					  fq->tx_fqid[prio], fd);
+	if (!err && frames_enqueued)
+		*frames_enqueued = 1;
+	return err;
 }
 
 static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 7635db3ef903..085ff750e4b5 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016 NXP
+ * Copyright 2016-2020 NXP
  */
 
 #ifndef __DPAA2_ETH_H
@@ -371,7 +371,8 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES];
 	int (*enqueue)(struct dpaa2_eth_priv *priv,
 		       struct dpaa2_eth_fq *fq,
-		       struct dpaa2_fd *fd, u8 prio);
+		       struct dpaa2_fd *fd, u8 prio,
+		       int *frames_enqueued);
 
 	u8 num_channels;
 	struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS];
-- 
cgit v1.2.3


From 6ff8044751bdc40fd3199813bfe9b93d056fc15d Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 22 Apr 2020 15:05:11 +0300
Subject: dpaa2-eth: use the bulk ring mode enqueue interface

Update the dpaa2-eth driver to use the bulk enqueue function introduced
with the change to QBMAN ring mode. At the moment, no functional changes
are made but rather the driver just transitions to the new interface
while still enqueuing just one frame at a time.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 35 ++++++++++++++----------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  1 +
 2 files changed, 22 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 7b41ece8f160..26c2868435d5 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -268,7 +268,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 
 	fq = &priv->fq[queue_id];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, fd, 0, NULL);
+		err = priv->enqueue(priv, fq, fd, 0, 1, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -847,7 +847,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 * the Tx confirmation callback for this frame
 	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, prio, NULL);
+		err = priv->enqueue(priv, fq, &fd, prio, 1, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -1937,7 +1937,7 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 
 	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, 0, NULL);
+		err = priv->enqueue(priv, fq, &fd, 0, 1, NULL);
 		if (err != -EBUSY)
 			break;
 	}
@@ -2524,6 +2524,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
 				       struct dpaa2_eth_fq *fq,
 				       struct dpaa2_fd *fd, u8 prio,
+				       u32 num_frames __always_unused,
 				       int *frames_enqueued)
 {
 	int err;
@@ -2536,18 +2537,24 @@ static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
 	return err;
 }
 
-static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
-				       struct dpaa2_eth_fq *fq,
-				       struct dpaa2_fd *fd, u8 prio,
-				       int *frames_enqueued)
+static inline int dpaa2_eth_enqueue_fq_multiple(struct dpaa2_eth_priv *priv,
+						struct dpaa2_eth_fq *fq,
+						struct dpaa2_fd *fd,
+						u8 prio, u32 num_frames,
+						int *frames_enqueued)
 {
 	int err;
 
-	err = dpaa2_io_service_enqueue_fq(fq->channel->dpio,
-					  fq->tx_fqid[prio], fd);
-	if (!err && frames_enqueued)
-		*frames_enqueued = 1;
-	return err;
+	err = dpaa2_io_service_enqueue_multiple_fq(fq->channel->dpio,
+						   fq->tx_fqid[prio],
+						   fd, num_frames);
+
+	if (err == 0)
+		return -EBUSY;
+
+	if (frames_enqueued)
+		*frames_enqueued = err;
+	return 0;
 }
 
 static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
@@ -2556,7 +2563,7 @@ static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
 				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
 		priv->enqueue = dpaa2_eth_enqueue_qd;
 	else
-		priv->enqueue = dpaa2_eth_enqueue_fq;
+		priv->enqueue = dpaa2_eth_enqueue_fq_multiple;
 }
 
 static int set_pause(struct dpaa2_eth_priv *priv)
@@ -2617,7 +2624,7 @@ static void update_tx_fqids(struct dpaa2_eth_priv *priv)
 		}
 	}
 
-	priv->enqueue = dpaa2_eth_enqueue_fq;
+	priv->enqueue = dpaa2_eth_enqueue_fq_multiple;
 
 	return;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 085ff750e4b5..2440ba6b21ef 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -372,6 +372,7 @@ struct dpaa2_eth_priv {
 	int (*enqueue)(struct dpaa2_eth_priv *priv,
 		       struct dpaa2_eth_fq *fq,
 		       struct dpaa2_fd *fd, u8 prio,
+		       u32 num_frames,
 		       int *frames_enqueued);
 
 	u8 num_channels;
-- 
cgit v1.2.3


From 6aa40b9e5b1ee732e07e406ffa6e17d152b3a216 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 22 Apr 2020 15:05:12 +0300
Subject: dpaa2-eth: split the .ndo_xdp_xmit callback into two stages

Instead of having a function that both creates a frame descriptor from
an xdp_frame and enqueues it, split this into two stages.
Add the dpaa2_eth_xdp_create_fd that just transforms an xdp_frame into a
FD while the actual enqueue callback is called directly from the ndo for
each frame.
This is particulary useful in conjunction with bulk enqueue.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 76 +++++++++++++-----------
 1 file changed, 40 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 26c2868435d5..9a0432cd893c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1880,20 +1880,16 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	return 0;
 }
 
-static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
-				    struct xdp_frame *xdpf)
+static int dpaa2_eth_xdp_create_fd(struct net_device *net_dev,
+				   struct xdp_frame *xdpf,
+				   struct dpaa2_fd *fd)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct device *dev = net_dev->dev.parent;
-	struct rtnl_link_stats64 *percpu_stats;
-	struct dpaa2_eth_drv_stats *percpu_extras;
 	unsigned int needed_headroom;
 	struct dpaa2_eth_swa *swa;
-	struct dpaa2_eth_fq *fq;
-	struct dpaa2_fd fd;
 	void *buffer_start, *aligned_start;
 	dma_addr_t addr;
-	int err, i;
 
 	/* We require a minimum headroom to be able to transmit the frame.
 	 * Otherwise return an error and let the original net_device handle it
@@ -1902,11 +1898,8 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 	if (xdpf->headroom < needed_headroom)
 		return -EINVAL;
 
-	percpu_stats = this_cpu_ptr(priv->percpu_stats);
-	percpu_extras = this_cpu_ptr(priv->percpu_extras);
-
 	/* Setup the FD fields */
-	memset(&fd, 0, sizeof(fd));
+	memset(fd, 0, sizeof(*fd));
 
 	/* Align FD address, if possible */
 	buffer_start = xdpf->data - needed_headroom;
@@ -1924,32 +1917,14 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 	addr = dma_map_single(dev, buffer_start,
 			      swa->xdp.dma_size,
 			      DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(dev, addr))) {
-		percpu_stats->tx_dropped++;
+	if (unlikely(dma_mapping_error(dev, addr)))
 		return -ENOMEM;
-	}
-
-	dpaa2_fd_set_addr(&fd, addr);
-	dpaa2_fd_set_offset(&fd, xdpf->data - buffer_start);
-	dpaa2_fd_set_len(&fd, xdpf->len);
-	dpaa2_fd_set_format(&fd, dpaa2_fd_single);
-	dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA);
-
-	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
-	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, &fd, 0, 1, NULL);
-		if (err != -EBUSY)
-			break;
-	}
-	percpu_extras->tx_portal_busy += i;
-	if (unlikely(err < 0)) {
-		percpu_stats->tx_errors++;
-		/* let the Rx device handle the cleanup */
-		return err;
-	}
 
-	percpu_stats->tx_packets++;
-	percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+	dpaa2_fd_set_addr(fd, addr);
+	dpaa2_fd_set_offset(fd, xdpf->data - buffer_start);
+	dpaa2_fd_set_len(fd, xdpf->len);
+	dpaa2_fd_set_format(fd, dpaa2_fd_single);
+	dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA);
 
 	return 0;
 }
@@ -1957,6 +1932,11 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 			      struct xdp_frame **frames, u32 flags)
 {
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct dpaa2_eth_drv_stats *percpu_extras;
+	struct rtnl_link_stats64 *percpu_stats;
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_fd fd;
 	int drops = 0;
 	int i, err;
 
@@ -1966,14 +1946,38 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 	if (!netif_running(net_dev))
 		return -ENETDOWN;
 
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+	percpu_extras = this_cpu_ptr(priv->percpu_extras);
+
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 
-		err = dpaa2_eth_xdp_xmit_frame(net_dev, xdpf);
+		/* create the FD from the xdp_frame */
+		err = dpaa2_eth_xdp_create_fd(net_dev, xdpf, &fd);
 		if (err) {
+			percpu_stats->tx_dropped++;
 			xdp_return_frame_rx_napi(xdpf);
 			drops++;
+			continue;
+		}
+
+		/* enqueue the newly created FD */
+		fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
+		for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
+			err = priv->enqueue(priv, fq, &fd, 0, 1);
+			if (err != -EBUSY)
+				break;
 		}
+
+		percpu_extras->tx_portal_busy += i;
+		if (unlikely(err < 0)) {
+			percpu_stats->tx_errors++;
+			xdp_return_frame_rx_napi(xdpf);
+			continue;
+		}
+
+		percpu_stats->tx_packets++;
+		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
 	}
 
 	return n - drops;
-- 
cgit v1.2.3


From 8665d9780e6efafa3cd9865ae3a77826326fe8c6 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 22 Apr 2020 15:05:13 +0300
Subject: dpaa2-eth: use bulk enqueue in .ndo_xdp_xmit

Take advantage of the bulk enqueue feature in .ndo_xdp_xmit.
We cannot use the XDP_XMIT_FLUSH since the architecture is not capable
to store all the frames dequeued in a NAPI cycle so we instead are
enqueueing all the frames received in a ndo_xdp_xmit call right away.

After setting up all FDs for the xdp_frames received, enqueue multiple
frames at a time until all are sent or the maximum number of retries is
hit.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 57 ++++++++++++------------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  2 +
 2 files changed, 30 insertions(+), 29 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 9a0432cd893c..9d4061bba0b8 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1933,12 +1933,12 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 			      struct xdp_frame **frames, u32 flags)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	int total_enqueued = 0, retries = 0, enqueued;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct rtnl_link_stats64 *percpu_stats;
+	int num_fds, i, err, max_retries;
 	struct dpaa2_eth_fq *fq;
-	struct dpaa2_fd fd;
-	int drops = 0;
-	int i, err;
+	struct dpaa2_fd *fds;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
@@ -1946,41 +1946,40 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 	if (!netif_running(net_dev))
 		return -ENETDOWN;
 
+	fq = &priv->fq[smp_processor_id()];
+	fds = fq->xdp_fds;
+
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 
+	/* create a FD for each xdp_frame in the list received */
 	for (i = 0; i < n; i++) {
-		struct xdp_frame *xdpf = frames[i];
-
-		/* create the FD from the xdp_frame */
-		err = dpaa2_eth_xdp_create_fd(net_dev, xdpf, &fd);
-		if (err) {
-			percpu_stats->tx_dropped++;
-			xdp_return_frame_rx_napi(xdpf);
-			drops++;
-			continue;
-		}
-
-		/* enqueue the newly created FD */
-		fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
-		for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-			err = priv->enqueue(priv, fq, &fd, 0, 1);
-			if (err != -EBUSY)
-				break;
-		}
+		err = dpaa2_eth_xdp_create_fd(net_dev, frames[i], &fds[i]);
+		if (err)
+			break;
+	}
+	num_fds = i;
 
-		percpu_extras->tx_portal_busy += i;
-		if (unlikely(err < 0)) {
-			percpu_stats->tx_errors++;
-			xdp_return_frame_rx_napi(xdpf);
+	/* try to enqueue all the FDs until the max number of retries is hit */
+	max_retries = num_fds * DPAA2_ETH_ENQUEUE_RETRIES;
+	while (total_enqueued < num_fds && retries < max_retries) {
+		err = priv->enqueue(priv, fq, &fds[total_enqueued],
+				    0, num_fds - total_enqueued, &enqueued);
+		if (err == -EBUSY) {
+			percpu_extras->tx_portal_busy += ++retries;
 			continue;
 		}
-
-		percpu_stats->tx_packets++;
-		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+		total_enqueued += enqueued;
 	}
 
-	return n - drops;
+	/* update statistics */
+	percpu_stats->tx_packets += total_enqueued;
+	for (i = 0; i < total_enqueued; i++)
+		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]);
+	for (i = total_enqueued; i < n; i++)
+		xdp_return_frame_rx_napi(frames[i]);
+
+	return total_enqueued;
 }
 
 static int update_xps(struct dpaa2_eth_priv *priv)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 2440ba6b21ef..289053099974 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -325,6 +325,8 @@ struct dpaa2_eth_fq {
 			const struct dpaa2_fd *fd,
 			struct dpaa2_eth_fq *fq);
 	struct dpaa2_eth_fq_stats stats;
+
+	struct dpaa2_fd xdp_fds[DEV_MAP_BULK_SIZE];
 };
 
 struct dpaa2_eth_ch_xdp {
-- 
cgit v1.2.3


From 5d1c9a114a6efba2c8391e39d4ac3e4e5c7b6d32 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 7 Apr 2020 18:59:51 +0300
Subject: net/mlx5: Update vport.c to new cmd interface

Do mass update of vport.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/ib_virt.c            |   2 +-
 drivers/infiniband/hw/mlx5/mad.c                |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 142 +++++++++++-------------
 include/linux/mlx5/vport.h                      |   3 +-
 4 files changed, 71 insertions(+), 80 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c
index b61165359954..46b2d370fb3f 100644
--- a/drivers/infiniband/hw/mlx5/ib_virt.c
+++ b/drivers/infiniband/hw/mlx5/ib_virt.c
@@ -134,7 +134,7 @@ int mlx5_ib_get_vf_stats(struct ib_device *device, int vf,
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_core_query_vport_counter(mdev, true, vf, port, out, out_sz);
+	err = mlx5_core_query_vport_counter(mdev, true, vf, port, out);
 	if (err)
 		goto ex;
 
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index f0ab6d7d8497..454ce5de2de7 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -187,8 +187,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u8 port_num,
 			goto done;
 		}
 
-		err = mlx5_core_query_vport_counter(mdev, 0, 0,
-						    mdev_port_num, out_cnt, sz);
+		err = mlx5_core_query_vport_counter(mdev, 0, 0, mdev_port_num,
+						    out_cnt);
 		if (!err)
 			pma_cnt_ext_assign(pma_cnt_ext, out_cnt);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 23f879da9104..c107d92dc118 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -40,10 +40,11 @@
 /* Mutex to hold while enabling or disabling RoCE */
 static DEFINE_MUTEX(mlx5_roce_en_lock);
 
-static int _mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod,
-				   u16 vport, u32 *out, int outlen)
+u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 {
-	u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {};
+	int err;
 
 	MLX5_SET(query_vport_state_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_VPORT_STATE);
@@ -52,14 +53,9 @@ static int _mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod,
 	if (vport)
 		MLX5_SET(query_vport_state_in, in, other_vport, 1);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
-}
-
-u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
-{
-	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {0};
-
-	_mlx5_query_vport_state(mdev, opmod, vport, out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out);
+	if (err)
+		return 0;
 
 	return MLX5_GET(query_vport_state_out, out, state);
 }
@@ -67,8 +63,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 other_vport, u8 state)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
 
 	MLX5_SET(modify_vport_state_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
@@ -77,13 +72,13 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 	MLX5_SET(modify_vport_state_in, in, other_vport, other_vport);
 	MLX5_SET(modify_vport_state_in, in, admin_state, state);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, modify_vport_state, in);
 }
 
 static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
-					u32 *out, int outlen)
+					u32 *out)
 {
-	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {};
 
 	MLX5_SET(query_nic_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
@@ -91,26 +86,16 @@ static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
 	if (vport)
 		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
-}
-
-static int mlx5_modify_nic_vport_context(struct mlx5_core_dev *mdev, void *in,
-					 int inlen)
-{
-	u32 out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)] = {0};
-
-	MLX5_SET(modify_nic_vport_context_in, in, opcode,
-		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
-	return mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec_inout(mdev, query_nic_vport_context, in, out);
 }
 
 int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				    u16 vport, u8 *min_inline)
 {
-	u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {};
 	int err;
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out, sizeof(out));
+	err = mlx5_query_nic_vport_context(mdev, vport, out);
 	if (!err)
 		*min_inline = MLX5_GET(query_nic_vport_context_out, out,
 				       nic_vport_context.min_wqe_inline_mode);
@@ -139,8 +124,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_min_inline);
 int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 min_inline)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)] = {0};
-	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+	u32 in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)] = {};
 	void *nic_vport_ctx;
 
 	MLX5_SET(modify_nic_vport_context_in, in,
@@ -152,23 +136,20 @@ int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				     in, nic_vport_context);
 	MLX5_SET(nic_vport_context, nic_vport_ctx,
 		 min_wqe_inline_mode, min_inline);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	return mlx5_modify_nic_vport_context(mdev, in, inlen);
+	return mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 }
 
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				     u16 vport, bool other, u8 *addr)
 {
-	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {};
 	u8 *out_addr;
-	u32 *out;
 	int err;
 
-	out = kvzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
 	out_addr = MLX5_ADDR_OF(query_nic_vport_context_out, out,
 				nic_vport_context.permanent_address);
 
@@ -177,11 +158,10 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
 	MLX5_SET(query_nic_vport_context_in, in, other_vport, other);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
+	err = mlx5_cmd_exec_inout(mdev, query_nic_vport_context, in, out);
 	if (!err)
 		ether_addr_copy(addr, &out_addr[2]);
 
-	kvfree(out);
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mac_address);
@@ -216,8 +196,10 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				permanent_address);
 
 	ether_addr_copy(&perm_mac[2], addr);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	kvfree(in);
 
@@ -235,7 +217,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
 	if (!err)
 		*mtu = MLX5_GET(query_nic_vport_context_out, out,
 				nic_vport_context.mtu);
@@ -257,8 +239,10 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu)
 
 	MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, mtu);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	kvfree(in);
 	return err;
@@ -292,7 +276,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 		req_list_size = max_list_size;
 	}
 
-	out_sz = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in) +
+	out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) +
 			req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout);
 
 	out = kzalloc(out_sz, GFP_KERNEL);
@@ -332,7 +316,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 				   u8 addr_list[][ETH_ALEN],
 				   int list_size)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)];
+	u32 out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)] = {};
 	void *nic_vport_ctx;
 	int max_list_size;
 	int in_sz;
@@ -350,7 +334,6 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 	in_sz = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in) +
 		list_size * MLX5_ST_SZ_BYTES(mac_address_layout);
 
-	memset(out, 0, sizeof(out));
 	in = kzalloc(in_sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -442,7 +425,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	mlx5_query_nic_vport_context(mdev, 0, out);
 
 	*system_image_guid = MLX5_GET64(query_nic_vport_context_out, out,
 					nic_vport_context.system_image_guid);
@@ -462,7 +445,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	mlx5_query_nic_vport_context(mdev, 0, out);
 
 	*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
 				nic_vport_context.node_guid);
@@ -498,8 +481,10 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
 	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	kvfree(in);
 
@@ -516,7 +501,7 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	mlx5_query_nic_vport_context(mdev, 0, out);
 
 	*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
 				   nic_vport_context.qkey_violation_counter);
@@ -664,7 +649,7 @@ int mlx5_query_hca_vport_context(struct mlx5_core_dev *dev,
 				 struct mlx5_hca_vport_context *rep)
 {
 	int out_sz = MLX5_ST_SZ_BYTES(query_hca_vport_context_out);
-	int in[MLX5_ST_SZ_DW(query_hca_vport_context_in)] = {0};
+	int in[MLX5_ST_SZ_DW(query_hca_vport_context_in)] = {};
 	int is_group_manager;
 	void *out;
 	void *ctx;
@@ -691,7 +676,7 @@ int mlx5_query_hca_vport_context(struct mlx5_core_dev *dev,
 	if (MLX5_CAP_GEN(dev, num_ports) == 2)
 		MLX5_SET(query_hca_vport_context_in, in, port_num, port_num);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out,  out_sz);
+	err = mlx5_cmd_exec_inout(dev, query_hca_vport_context, in, out);
 	if (err)
 		goto ex;
 
@@ -788,7 +773,7 @@ int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out, outlen);
+	err = mlx5_query_nic_vport_context(mdev, vport, out);
 	if (err)
 		goto out;
 
@@ -825,8 +810,10 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev,
 		 nic_vport_context.promisc_mc, promisc_mc);
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 nic_vport_context.promisc_all, promisc_all);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	kvfree(in);
 
@@ -865,8 +852,10 @@ int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable)
 	if (MLX5_CAP_GEN(mdev, disable_local_lb_uc))
 		MLX5_SET(modify_nic_vport_context_in, in,
 			 field_select.disable_uc_local_lb, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	if (!err)
 		mlx5_core_dbg(mdev, "%s local_lb\n",
@@ -888,7 +877,7 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status)
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
 	if (err)
 		goto out;
 
@@ -925,8 +914,10 @@ static int mlx5_nic_vport_update_roce_state(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_nic_vport_context_in, in, field_select.roce_en, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.roce_en,
 		 state);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+	err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in);
 
 	kvfree(in);
 
@@ -965,16 +956,15 @@ int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev)
 	mutex_unlock(&mlx5_roce_en_lock);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_nic_vport_disable_roce);
+EXPORT_SYMBOL(mlx5_nic_vport_disable_roce);
 
 int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
-				  int vf, u8 port_num, void *out,
-				  size_t out_sz)
+				  int vf, u8 port_num, void *out)
 {
-	int	in_sz = MLX5_ST_SZ_BYTES(query_vport_counter_in);
-	int	is_group_manager;
-	void   *in;
-	int	err;
+	int in_sz = MLX5_ST_SZ_BYTES(query_vport_counter_in);
+	int is_group_manager;
+	void *in;
+	int err;
 
 	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
 	in = kvzalloc(in_sz, GFP_KERNEL);
@@ -997,7 +987,7 @@ int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
 	if (MLX5_CAP_GEN(dev, num_ports) == 2)
 		MLX5_SET(query_vport_counter_in, in, port_num, port_num);
 
-	err = mlx5_cmd_exec(dev, in, in_sz, out,  out_sz);
+	err = mlx5_cmd_exec_inout(dev, query_vport_counter, in, out);
 free:
 	kvfree(in);
 	return err;
@@ -1008,8 +998,8 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 				u8 other_vport, u64 *rx_discard_vport_down,
 				u64 *tx_discard_vport_down)
 {
-	u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {};
 	int err;
 
 	MLX5_SET(query_vnic_env_in, in, opcode,
@@ -1018,7 +1008,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 	MLX5_SET(query_vnic_env_in, in, vport_number, vport);
 	MLX5_SET(query_vnic_env_in, in, other_vport, other_vport);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, query_vnic_env, in, out);
 	if (err)
 		return err;
 
@@ -1035,11 +1025,10 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 				       struct mlx5_hca_vport_context *req)
 {
 	int in_sz = MLX5_ST_SZ_BYTES(modify_hca_vport_context_in);
-	u8 out[MLX5_ST_SZ_BYTES(modify_hca_vport_context_out)];
 	int is_group_manager;
+	void *ctx;
 	void *in;
 	int err;
-	void *ctx;
 
 	mlx5_core_dbg(dev, "vf %d\n", vf);
 	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
@@ -1047,7 +1036,6 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 	if (!in)
 		return -ENOMEM;
 
-	memset(out, 0, sizeof(out));
 	MLX5_SET(modify_hca_vport_context_in, in, opcode, MLX5_CMD_OP_MODIFY_HCA_VPORT_CONTEXT);
 	if (other_vport) {
 		if (is_group_manager) {
@@ -1074,7 +1062,7 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 	MLX5_SET(hca_vport_context, ctx, cap_mask1, req->cap_mask1);
 	MLX5_SET(hca_vport_context, ctx, cap_mask1_field_select,
 		 req->cap_mask1_perm);
-	err = mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out));
+	err = mlx5_cmd_exec_in(dev, modify_hca_vport_context, in);
 ex:
 	kfree(in);
 	return err;
@@ -1103,8 +1091,10 @@ int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev,
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 nic_vport_context.affiliation_criteria,
 		 MLX5_CAP_GEN(port_mdev, affiliate_nic_vport_criteria));
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(port_mdev, in, inlen);
+	err = mlx5_cmd_exec_in(port_mdev, modify_nic_vport_context, in);
 	if (err)
 		mlx5_nic_vport_disable_roce(port_mdev);
 
@@ -1129,8 +1119,10 @@ int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev)
 		 nic_vport_context.affiliated_vhca_id, 0);
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 nic_vport_context.affiliation_criteria, 0);
+	MLX5_SET(modify_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 
-	err = mlx5_modify_nic_vport_context(port_mdev, in, inlen);
+	err = mlx5_cmd_exec_in(port_mdev, modify_nic_vport_context, in);
 	if (!err)
 		mlx5_nic_vport_disable_roce(port_mdev);
 
@@ -1170,4 +1162,4 @@ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
 {
 	return MLX5_SPECIAL_VPORTS(dev) + mlx5_core_max_vfs(dev);
 }
-EXPORT_SYMBOL(mlx5_eswitch_get_total_vports);
+EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports);
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 16060fb9b5e5..8170da1e9f70 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -127,8 +127,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 				u8 other_vport, u64 *rx_discard_vport_down,
 				u64 *tx_discard_vport_down);
 int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport,
-				  int vf, u8 port_num, void *out,
-				  size_t out_sz);
+				  int vf, u8 port_num, void *out);
 int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 				       u8 other_vport, u8 port_num,
 				       int vf,
-- 
cgit v1.2.3


From d1f620500cde5c72c7b96a19474733c4c6c67f38 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 11:39:14 +0300
Subject: net/mlx5: Update cq.c to new cmd interface

Do mass update of cq.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cq.c       | 22 +++++++++-------------
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/health.c    |  2 +-
 include/linux/mlx5/cq.h                            |  2 +-
 4 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 4477a590b308..8379b24cb838 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -90,8 +90,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 			u32 *in, int inlen, u32 *out, int outlen)
 {
 	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn);
-	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
-	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
+	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)] = {};
 	struct mlx5_eq_comp *eq;
 	int err;
 
@@ -141,20 +140,17 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 err_cq_add:
 	mlx5_eq_del_cq(&eq->core, cq);
 err_cmd:
-	memset(din, 0, sizeof(din));
-	memset(dout, 0, sizeof(dout));
 	MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ);
 	MLX5_SET(destroy_cq_in, din, cqn, cq->cqn);
 	MLX5_SET(destroy_cq_in, din, uid, cq->uid);
-	mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
+	mlx5_cmd_exec_in(dev, destroy_cq, din);
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_create_cq);
 
 int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_cq_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {};
 	int err;
 
 	mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
@@ -163,7 +159,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	MLX5_SET(destroy_cq_in, in, opcode, MLX5_CMD_OP_DESTROY_CQ);
 	MLX5_SET(destroy_cq_in, in, cqn, cq->cqn);
 	MLX5_SET(destroy_cq_in, in, uid, cq->uid);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_in(dev, destroy_cq, in);
 	if (err)
 		return err;
 
@@ -178,20 +174,20 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 EXPORT_SYMBOL(mlx5_core_destroy_cq);
 
 int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-		       u32 *out, int outlen)
+		       u32 *out)
 {
-	u32 in[MLX5_ST_SZ_DW(query_cq_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_cq_in)] = {};
 
 	MLX5_SET(query_cq_in, in, opcode, MLX5_CMD_OP_QUERY_CQ);
 	MLX5_SET(query_cq_in, in, cqn, cq->cqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return mlx5_cmd_exec_inout(dev, query_cq, in, out);
 }
 EXPORT_SYMBOL(mlx5_core_query_cq);
 
 int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 			u32 *in, int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_cq_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(modify_cq_out)] = {};
 
 	MLX5_SET(modify_cq_in, in, opcode, MLX5_CMD_OP_MODIFY_CQ);
 	MLX5_SET(modify_cq_in, in, uid, cq->uid);
@@ -204,7 +200,7 @@ int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev,
 				   u16 cq_period,
 				   u16 cq_max_count)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_cq_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_cq_in)] = {};
 	void *cqc;
 
 	MLX5_SET(modify_cq_in, in, cqn, cq->cqn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 65fef5a86644..c05e6a2c9126 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -333,7 +333,7 @@ static u64 cq_read_field(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	if (!out)
 		return param;
 
-	err = mlx5_core_query_cq(dev, cq, out, outlen);
+	err = mlx5_core_query_cq(dev, cq, out);
 	if (err) {
 		mlx5_core_warn(dev, "failed to query cq\n");
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 3a199a03d929..7283443868f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -43,7 +43,7 @@ int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg)
 	void *cqc;
 	int err;
 
-	err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out, sizeof(out));
+	err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out);
 	if (err)
 		return err;
 
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 40748fc1b11b..b5a9399e07ee 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -188,7 +188,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 			u32 *in, int inlen, u32 *out, int outlen);
 int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq);
 int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-		       u32 *out, int outlen);
+		       u32 *out);
 int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 			u32 *in, int inlen);
 int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev,
-- 
cgit v1.2.3


From e36fb468d23967683c1f0de644da0928563e604d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 11:55:06 +0300
Subject: net/mlx5: Update debugfs.c to new cmd interface

Do mass update of debugfs.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index c05e6a2c9126..6409090b3ec5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -273,20 +273,11 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 	return param;
 }
 
-static int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-			      u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
-
-	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
-	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
 static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 			 int index)
 {
 	int outlen = MLX5_ST_SZ_BYTES(query_eq_out);
+	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
 	u64 param = 0;
 	void *ctx;
 	u32 *out;
@@ -296,7 +287,9 @@ static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	if (!out)
 		return param;
 
-	err = mlx5_core_eq_query(dev, eq, out, outlen);
+	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
+	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
+	err = mlx5_cmd_exec_inout(dev, query_eq, in, out);
 	if (err) {
 		mlx5_core_warn(dev, "failed to query eq\n");
 		goto out;
-- 
cgit v1.2.3


From 9aa536ad45ec390d32c563321b26ccd8de52a2d9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 11:56:42 +0300
Subject: net/mlx5: Update ecpf.c to new cmd interface

Do mass update of ecpf.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c | 30 ++++++--------------------
 1 file changed, 6 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index d2228e37450f..a894ea98c95a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -8,33 +8,13 @@ bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev)
 	return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
 }
 
-static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev)
-{
-	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {};
-
-	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
-	MLX5_SET(enable_hca_in, in, function_id, 0);
-	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
-	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
-}
-
-static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev)
-{
-	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {};
-
-	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
-	MLX5_SET(disable_hca_in, in, function_id, 0);
-	MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
 static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
 {
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
 	int err;
 
-	err = mlx5_peer_pf_enable_hca(dev);
+	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
+	err = mlx5_cmd_exec_in(dev, enable_hca, in);
 	if (err)
 		mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
 			      err);
@@ -44,9 +24,11 @@ static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
 
 static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
 {
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
 	int err;
 
-	err = mlx5_peer_pf_disable_hca(dev);
+	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+	err = mlx5_cmd_exec_in(dev, disable_hca, in);
 	if (err) {
 		mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
 			      err);
-- 
cgit v1.2.3


From 49d7fcd127c1ee011aee252985749eb33593488c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 12:25:08 +0300
Subject: net/mlx5: Update eq.c to new cmd interface

Do mass update of eq.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index bee419d01af2..4d974b5405b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -101,12 +101,11 @@ struct mlx5_eq_table {
 
 static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_eq_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_eq_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_eq_in)] = {};
 
 	MLX5_SET(destroy_eq_in, in, opcode, MLX5_CMD_OP_DESTROY_EQ);
 	MLX5_SET(destroy_eq_in, in, eq_number, eqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_eq, in);
 }
 
 /* caller must eventually call mlx5_cq_put on the returned cq */
-- 
cgit v1.2.3


From a184cda1bb31eb14720c5f09d9698ab1666aa371 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 12:26:41 +0300
Subject: net/mlx5: Update statistics to new cmd interface

Do mass update of statistics to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.c | 46 +++++++---------------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 17 +++-----
 2 files changed, 19 insertions(+), 44 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 7cd5b02e0f10..8fe8b4d6ad1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -38,12 +38,11 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
 
 void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
 {
-	u32  in[MLX5_ST_SZ_DW(arm_monitor_counter_in)]  = {};
-	u32 out[MLX5_ST_SZ_DW(arm_monitor_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {};
 
 	MLX5_SET(arm_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_ARM_MONITOR_COUNTER);
-	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in);
 }
 
 static void mlx5e_monitor_counters_work(struct work_struct *work)
@@ -66,19 +65,6 @@ static int mlx5e_monitor_event_handler(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static void mlx5e_monitor_counter_start(struct mlx5e_priv *priv)
-{
-	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
-		     MONITOR_COUNTER);
-	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
-}
-
-static void mlx5e_monitor_counter_stop(struct mlx5e_priv *priv)
-{
-	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
-	cancel_work_sync(&priv->monitor_counters_work);
-}
-
 static int fill_monitor_counter_ppcnt_set1(int cnt, u32 *in)
 {
 	enum mlx5_monitor_counter_ppcnt ppcnt_cnt;
@@ -118,8 +104,7 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
 	int num_q_counters      = MLX5_CAP_GEN(mdev, num_q_monitor_counters);
 	int num_ppcnt_counters  = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 :
 				  MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters);
-	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
-	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
 	int q_counter = priv->q_counter;
 	int cnt	= 0;
 
@@ -136,34 +121,31 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
 	MLX5_SET(set_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
 
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(mdev, set_monitor_counter, in);
 }
 
 /* check if mlx5e_monitor_counter_supported before calling this function*/
 void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 {
 	INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work);
-	mlx5e_monitor_counter_start(priv);
+	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
+		     MONITOR_COUNTER);
+	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
+
 	mlx5e_set_monitor_counter(priv);
 	mlx5e_monitor_counter_arm(priv);
 	queue_work(priv->wq, &priv->update_stats_work);
 }
 
-static void mlx5e_monitor_counter_disable(struct mlx5e_priv *priv)
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
 {
-	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
-	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
 
-	MLX5_SET(set_monitor_counter_in, in, num_of_counters, 0);
 	MLX5_SET(set_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
 
-	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
-}
-
-/* check if mlx5e_monitor_counter_supported before calling this function*/
-void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
-{
-	mlx5e_monitor_counter_disable(priv);
-	mlx5e_monitor_counter_stop(priv);
+	mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in);
+	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
+	cancel_work_sync(&priv->monitor_counters_work);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index ff4002ebad90..e91a8b22eba6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -491,18 +491,14 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vnic_env)
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env)
 {
 	u32 *out = (u32 *)priv->stats.vnic.query_vnic_env_out;
-	int outlen = MLX5_ST_SZ_BYTES(query_vnic_env_out);
-	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
 		return;
 
-	MLX5_SET(query_vnic_env_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_VNIC_ENV);
-	MLX5_SET(query_vnic_env_in, in, op_mod, 0);
-	MLX5_SET(query_vnic_env_in, in, other_vport, 0);
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
+	MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV);
+	mlx5_cmd_exec_inout(mdev, query_vnic_env, in, out);
 }
 
 #define VPORT_COUNTER_OFF(c) MLX5_BYTE_OFF(query_vport_counter_out, c)
@@ -577,15 +573,12 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vport)
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport)
 {
-	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
 	u32 *out = (u32 *)priv->stats.vport.query_vport_out;
-	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	MLX5_SET(query_vport_counter_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_COUNTER);
-	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
-	MLX5_SET(query_vport_counter_in, in, other_vport, 0);
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
+	mlx5_cmd_exec_inout(mdev, query_vport_counter, in, out);
 }
 
 #define PPORT_802_3_OFF(c) \
-- 
cgit v1.2.3


From e08a6832f9c19a1b514675ee53a34736647f918a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 12:30:08 +0300
Subject: net/mlx5: Update eswitch to new cmd interface

Do mass update of eswitch to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  | 38 ++++++----------------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  6 +---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 18 +++++-----
 3 files changed, 20 insertions(+), 42 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7f618a443bfd..c5eb4e7754a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -84,8 +84,7 @@ mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
-	int in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)]   = {0};
-	int out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)] = {};
 	void *nic_vport_ctx;
 
 	MLX5_SET(modify_nic_vport_context_in, in,
@@ -108,40 +107,24 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 		MLX5_SET(nic_vport_context, nic_vport_ctx,
 			 event_on_promisc_change, 1);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_nic_vport_context, in);
 }
 
 /* E-Switch vport context HW commands */
 int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
-					  bool other_vport,
-					  void *in, int inlen)
+					  bool other_vport, void *in)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_esw_vport_context_out)] = {0};
-
 	MLX5_SET(modify_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
 	MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-}
-
-int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
-					 bool other_vport,
-					 void *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
-
-	MLX5_SET(query_esw_vport_context_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
-	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return mlx5_cmd_exec_in(dev, modify_esw_vport_context, in);
 }
 
 static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 				  u16 vlan, u8 qos, u8 set_flags)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
 
 	if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) ||
 	    !MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
@@ -170,8 +153,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 	MLX5_SET(modify_esw_vport_context_in, in,
 		 field_select.vport_cvlan_insert, 1);
 
-	return mlx5_eswitch_modify_esw_vport_context(dev, vport, true,
-						     in, sizeof(in));
+	return mlx5_eswitch_modify_esw_vport_context(dev, vport, true, in);
 }
 
 /* E-Switch FDB */
@@ -1901,7 +1883,7 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 	MLX5_SET(query_esw_functions_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	err = mlx5_cmd_exec_inout(dev, query_esw_functions, in, out);
 	if (!err)
 		return out;
 
@@ -2783,8 +2765,8 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 {
 	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
-	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
-	struct mlx5_vport_drop_stats stats = {0};
+	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {};
+	struct mlx5_vport_drop_stats stats = {};
 	int err = 0;
 	u32 *out;
 
@@ -2801,7 +2783,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 	MLX5_SET(query_vport_counter_in, in, vport_number, vport->vport);
 	MLX5_SET(query_vport_counter_in, in, other_vport, 1);
 
-	err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
+	err = mlx5_cmd_exec_inout(esw->dev, query_vport_counter, in, out);
 	if (err)
 		goto free_out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 39f42f985fbd..fa2ad172f08c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -329,11 +329,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule);
 
 int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
-					  bool other_vport,
-					  void *in, int inlen);
-int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
-					 bool other_vport,
-					 void *out, int outlen);
+					  bool other_vport, void *in);
 
 struct mlx5_flow_spec;
 struct mlx5_esw_flow_attr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f171eb2234b0..dc098bb58973 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -790,7 +790,8 @@ static bool mlx5_eswitch_reg_c1_loopback_supported(struct mlx5_eswitch *esw)
 static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 {
 	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u32 min[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
 	u8 curr, wanted;
 	int err;
 
@@ -798,8 +799,9 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 	    !mlx5_eswitch_vport_match_metadata_enabled(esw))
 		return 0;
 
-	err = mlx5_eswitch_query_esw_vport_context(esw->dev, 0, false,
-						   out, sizeof(out));
+	MLX5_SET(query_esw_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+	err = mlx5_cmd_exec_inout(esw->dev, query_esw_vport_context, in, out);
 	if (err)
 		return err;
 
@@ -814,14 +816,12 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 	else
 		curr &= ~wanted;
 
-	MLX5_SET(modify_esw_vport_context_in, in,
+	MLX5_SET(modify_esw_vport_context_in, min,
 		 esw_vport_context.fdb_to_vport_reg_c_id, curr);
-
-	MLX5_SET(modify_esw_vport_context_in, in,
+	MLX5_SET(modify_esw_vport_context_in, min,
 		 field_select.fdb_to_vport_reg_c_id, 1);
 
-	err = mlx5_eswitch_modify_esw_vport_context(esw->dev, 0, false, in,
-						    sizeof(in));
+	err = mlx5_eswitch_modify_esw_vport_context(esw->dev, 0, false, min);
 	if (!err) {
 		if (enable && (curr & MLX5_FDB_TO_VPORT_REG_C_1))
 			esw->flags |= MLX5_ESWITCH_REG_C1_LOOPBACK_ENABLED;
@@ -1474,7 +1474,7 @@ query_vports:
 out:
 	*mode = mlx5_mode;
 	return 0;
-}       
+}
 
 static void esw_destroy_restore_table(struct mlx5_eswitch *esw)
 {
-- 
cgit v1.2.3


From b316e1866fa39aadc1888fc68b73729343cc4058 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 15:59:30 +0300
Subject: net/mlx5: Update FPGA to new cmd interface

Do mass update of FPGA to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c | 28 ++++++++++------------
 1 file changed, 13 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
index 09769401c313..9a37077152aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c
@@ -142,15 +142,15 @@ int mlx5_fpga_query(struct mlx5_core_dev *dev, struct mlx5_fpga_query *query)
 int mlx5_fpga_create_qp(struct mlx5_core_dev *dev, void *fpga_qpc,
 			u32 *fpga_qpn)
 {
-	u32 in[MLX5_ST_SZ_DW(fpga_create_qp_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(fpga_create_qp_out)];
+	u32 out[MLX5_ST_SZ_DW(fpga_create_qp_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(fpga_create_qp_in)] = {};
 	int ret;
 
 	MLX5_SET(fpga_create_qp_in, in, opcode, MLX5_CMD_OP_FPGA_CREATE_QP);
 	memcpy(MLX5_ADDR_OF(fpga_create_qp_in, in, fpga_qpc), fpga_qpc,
 	       MLX5_FLD_SZ_BYTES(fpga_create_qp_in, fpga_qpc));
 
-	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	ret = mlx5_cmd_exec_inout(dev, fpga_create_qp, in, out);
 	if (ret)
 		return ret;
 
@@ -164,8 +164,7 @@ int mlx5_fpga_modify_qp(struct mlx5_core_dev *dev, u32 fpga_qpn,
 			enum mlx5_fpga_qpc_field_select fields,
 			void *fpga_qpc)
 {
-	u32 in[MLX5_ST_SZ_DW(fpga_modify_qp_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(fpga_modify_qp_out)];
+	u32 in[MLX5_ST_SZ_DW(fpga_modify_qp_in)] = {};
 
 	MLX5_SET(fpga_modify_qp_in, in, opcode, MLX5_CMD_OP_FPGA_MODIFY_QP);
 	MLX5_SET(fpga_modify_qp_in, in, field_select, fields);
@@ -173,20 +172,20 @@ int mlx5_fpga_modify_qp(struct mlx5_core_dev *dev, u32 fpga_qpn,
 	memcpy(MLX5_ADDR_OF(fpga_modify_qp_in, in, fpga_qpc), fpga_qpc,
 	       MLX5_FLD_SZ_BYTES(fpga_modify_qp_in, fpga_qpc));
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, fpga_modify_qp, in);
 }
 
 int mlx5_fpga_query_qp(struct mlx5_core_dev *dev,
 		       u32 fpga_qpn, void *fpga_qpc)
 {
-	u32 in[MLX5_ST_SZ_DW(fpga_query_qp_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(fpga_query_qp_out)];
+	u32 out[MLX5_ST_SZ_DW(fpga_query_qp_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(fpga_query_qp_in)] = {};
 	int ret;
 
 	MLX5_SET(fpga_query_qp_in, in, opcode, MLX5_CMD_OP_FPGA_QUERY_QP);
 	MLX5_SET(fpga_query_qp_in, in, fpga_qpn, fpga_qpn);
 
-	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	ret = mlx5_cmd_exec_inout(dev, fpga_query_qp, in, out);
 	if (ret)
 		return ret;
 
@@ -197,20 +196,19 @@ int mlx5_fpga_query_qp(struct mlx5_core_dev *dev,
 
 int mlx5_fpga_destroy_qp(struct mlx5_core_dev *dev, u32 fpga_qpn)
 {
-	u32 in[MLX5_ST_SZ_DW(fpga_destroy_qp_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(fpga_destroy_qp_out)];
+	u32 in[MLX5_ST_SZ_DW(fpga_destroy_qp_in)] = {};
 
 	MLX5_SET(fpga_destroy_qp_in, in, opcode, MLX5_CMD_OP_FPGA_DESTROY_QP);
 	MLX5_SET(fpga_destroy_qp_in, in, fpga_qpn, fpga_qpn);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, fpga_destroy_qp, in);
 }
 
 int mlx5_fpga_query_qp_counters(struct mlx5_core_dev *dev, u32 fpga_qpn,
 				bool clear, struct mlx5_fpga_qp_counters *data)
 {
-	u32 in[MLX5_ST_SZ_DW(fpga_query_qp_counters_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(fpga_query_qp_counters_out)];
+	u32 out[MLX5_ST_SZ_DW(fpga_query_qp_counters_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(fpga_query_qp_counters_in)] = {};
 	int ret;
 
 	MLX5_SET(fpga_query_qp_counters_in, in, opcode,
@@ -218,7 +216,7 @@ int mlx5_fpga_query_qp_counters(struct mlx5_core_dev *dev, u32 fpga_qpn,
 	MLX5_SET(fpga_query_qp_counters_in, in, clear, clear);
 	MLX5_SET(fpga_query_qp_counters_in, in, fpga_qpn, fpga_qpn);
 
-	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	ret = mlx5_cmd_exec_inout(dev, fpga_query_qp_counters, in, out);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 31a0956ea91567b8f0e39d8420253646304b8571 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:01:30 +0300
Subject: net/mlx5: Update fs_core new cmd interface

Do mass update of fs_core to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 80 +++++++++---------------
 1 file changed, 31 insertions(+), 49 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 90048697b2ff..304d1e4f0541 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -155,8 +155,7 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 				   struct mlx5_flow_table *ft, u32 underlay_qpn,
 				   bool disconnect)
 {
-	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
 	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
@@ -167,13 +166,10 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
 	MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
 
-	if (disconnect) {
+	if (disconnect)
 		MLX5_SET(set_flow_table_root_in, in, op_mod, 1);
-		MLX5_SET(set_flow_table_root_in, in, table_id, 0);
-	} else {
-		MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
+	else
 		MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
-	}
 
 	MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn);
 	if (ft->vport) {
@@ -181,7 +177,7 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, set_flow_table_root, in);
 }
 
 static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
@@ -192,8 +188,8 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
 	int en_decap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 	int term = !!(ft->flags & MLX5_FLOW_TABLE_TERMINATION);
-	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 	int err;
 
@@ -239,7 +235,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 		break;
 	}
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, create_flow_table, in, out);
 	if (!err)
 		ft->id = MLX5_GET(create_flow_table_out, out,
 				  table_id);
@@ -249,8 +245,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 				       struct mlx5_flow_table *ft)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(destroy_flow_table_in, in, opcode,
@@ -262,15 +257,14 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(destroy_flow_table_in, in, other_vport, 1);
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_flow_table, in);
 }
 
 static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct mlx5_flow_table *next_ft)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_flow_table_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(modify_flow_table_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_flow_table_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(modify_flow_table_in, in, opcode,
@@ -310,7 +304,7 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_flow_table, in);
 }
 
 static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
@@ -318,8 +312,7 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
 				      u32 *in,
 				      struct mlx5_flow_group *fg)
 {
-	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {0};
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 	int err;
 
@@ -332,7 +325,7 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(create_flow_group_in, in, other_vport, 1);
 	}
 
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out);
 	if (!err)
 		fg->id = MLX5_GET(create_flow_group_out, out,
 				  group_id);
@@ -343,8 +336,7 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 				       struct mlx5_flow_table *ft,
 				       struct mlx5_flow_group *fg)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(destroy_flow_group_in, in, opcode,
@@ -357,7 +349,7 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(destroy_flow_group_in, in, other_vport, 1);
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_flow_group, in);
 }
 
 static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
@@ -600,8 +592,7 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 			       struct mlx5_flow_table *ft,
 			       struct fs_fte *fte)
 {
-	u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(delete_fte_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
@@ -613,22 +604,22 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(delete_fte_in, in, other_vport, 1);
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, delete_fte, in);
 }
 
 int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev,
 			   enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask,
 			   u32 *id)
 {
-	u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {};
 	int err;
 
 	MLX5_SET(alloc_flow_counter_in, in, opcode,
 		 MLX5_CMD_OP_ALLOC_FLOW_COUNTER);
 	MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, alloc_flow_counter, in, out);
 	if (!err)
 		*id = MLX5_GET(alloc_flow_counter_out, out, flow_counter_id);
 	return err;
@@ -641,21 +632,20 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id)
 
 int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id)
 {
-	u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(dealloc_flow_counter_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {};
 
 	MLX5_SET(dealloc_flow_counter_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_FLOW_COUNTER);
 	MLX5_SET(dealloc_flow_counter_in, in, flow_counter_id, id);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, dealloc_flow_counter, in);
 }
 
 int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id,
 		      u64 *packets, u64 *bytes)
 {
 	u32 out[MLX5_ST_SZ_BYTES(query_flow_counter_out) +
-		MLX5_ST_SZ_BYTES(traffic_counter)]   = {0};
-	u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0};
+		MLX5_ST_SZ_BYTES(traffic_counter)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {};
 	void *stats;
 	int err = 0;
 
@@ -683,11 +673,10 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
 			   u32 *out)
 {
 	int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len);
-	u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {};
 
 	MLX5_SET(query_flow_counter_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_FLOW_COUNTER);
-	MLX5_SET(query_flow_counter_in, in, op_mod, 0);
 	MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id);
 	MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
@@ -700,7 +689,7 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 					  enum mlx5_flow_namespace_type namespace,
 					  struct mlx5_pkt_reformat *pkt_reformat)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)];
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 	void *packet_reformat_context_in;
 	int max_encap_size;
@@ -732,7 +721,6 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 				reformat_data);
 	inlen = reformat - (void *)in  + size;
 
-	memset(in, 0, inlen);
 	MLX5_SET(alloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT);
 	MLX5_SET(packet_reformat_context_in, packet_reformat_context_in,
@@ -741,7 +729,6 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 		 reformat_type, reformat_type);
 	memcpy(reformat, reformat_data, size);
 
-	memset(out, 0, sizeof(out));
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 
 	pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out,
@@ -753,17 +740,15 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
 					     struct mlx5_pkt_reformat *pkt_reformat)
 {
-	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)];
-	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)];
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
-	memset(in, 0, sizeof(in));
 	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
 	MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
 		 pkt_reformat->id);
 
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, dealloc_packet_reformat_context, in);
 }
 
 static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
@@ -771,7 +756,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 					void *modify_actions,
 					struct mlx5_modify_hdr *modify_hdr)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
+	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)] = {};
 	int max_actions, actions_size, inlen, err;
 	struct mlx5_core_dev *dev = ns->dev;
 	void *actions_in;
@@ -821,7 +806,6 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 	actions_in = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
 	memcpy(actions_in, modify_actions, actions_size);
 
-	memset(out, 0, sizeof(out));
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 
 	modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
@@ -832,17 +816,15 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_modify_hdr *modify_hdr)
 {
-	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
-	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
 
-	memset(in, 0, sizeof(in));
 	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
 	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
 		 modify_hdr->id);
 
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, dealloc_modify_header_context, in);
 }
 
 static const struct mlx5_flow_cmds mlx5_flow_cmds = {
-- 
cgit v1.2.3


From 59ad21c21fc4025831fbd0c291e2db1247fddf4d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:08:35 +0300
Subject: net/mlx5: Update fw.c new cmd interface

Do mass update of fw.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c | 33 +++++++++++-----------------
 1 file changed, 13 insertions(+), 20 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 3040e0466681..a5fbe7343508 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -67,26 +67,19 @@ enum {
 	MCQI_FW_STORED_VERSION  = 1,
 };
 
-static int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev, u32 *out,
-				  int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_adapter_in)] = {0};
-
-	MLX5_SET(query_adapter_in, in, opcode, MLX5_CMD_OP_QUERY_ADAPTER);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
 int mlx5_query_board_id(struct mlx5_core_dev *dev)
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_adapter_out);
+	u32 in[MLX5_ST_SZ_DW(query_adapter_in)] = {};
 	int err;
 
 	out = kzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_cmd_query_adapter(dev, out, outlen);
+	MLX5_SET(query_adapter_in, in, opcode, MLX5_CMD_OP_QUERY_ADAPTER);
+	err = mlx5_cmd_exec_inout(dev, query_adapter, in, out);
 	if (err)
 		goto out;
 
@@ -105,13 +98,15 @@ int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id)
 {
 	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_adapter_out);
+	u32 in[MLX5_ST_SZ_DW(query_adapter_in)] = {};
 	int err;
 
 	out = kzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	err = mlx5_cmd_query_adapter(mdev, out, outlen);
+	MLX5_SET(query_adapter_in, in, opcode, MLX5_CMD_OP_QUERY_ADAPTER);
+	err = mlx5_cmd_exec_inout(mdev, query_adapter, in, out);
 	if (err)
 		goto out;
 
@@ -259,8 +254,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id)
 {
-	u32 out[MLX5_ST_SZ_DW(init_hca_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(init_hca_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(init_hca_in)] = {};
 	int i;
 
 	MLX5_SET(init_hca_in, in, opcode, MLX5_CMD_OP_INIT_HCA);
@@ -271,16 +265,15 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id)
 				       sw_owner_id[i]);
 	}
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, init_hca, in);
 }
 
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev)
 {
-	u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(teardown_hca_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {};
 
 	MLX5_SET(teardown_hca_in, in, opcode, MLX5_CMD_OP_TEARDOWN_HCA);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, teardown_hca, in);
 }
 
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev)
@@ -315,8 +308,8 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev)
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
 {
 	unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS;
-	u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {};
 	int state;
 	int ret;
 
@@ -329,7 +322,7 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
 	MLX5_SET(teardown_hca_in, in, profile,
 		 MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN);
 
-	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	ret = mlx5_cmd_exec_inout(dev, teardown_hca, in, out);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 5d19395f6988c057cb9461075f308a6c16a8c253 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:17:01 +0300
Subject: net/mlx5: Update lag.c new cmd interface

Do mass update of lag.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 52 +++++++++------------------
 1 file changed, 17 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 93052b07c76c..c6ad5ca46877 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -47,8 +47,7 @@ static DEFINE_MUTEX(lag_mutex);
 static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 			       u8 remap_port2)
 {
-	u32   in[MLX5_ST_SZ_DW(create_lag_in)]   = {0};
-	u32   out[MLX5_ST_SZ_DW(create_lag_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {};
 	void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);
 
 	MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG);
@@ -56,14 +55,13 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, create_lag, in);
 }
 
 static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 			       u8 remap_port2)
 {
-	u32   in[MLX5_ST_SZ_DW(modify_lag_in)]   = {0};
-	u32   out[MLX5_ST_SZ_DW(modify_lag_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_lag_in)] = {};
 	void *lag_ctx = MLX5_ADDR_OF(modify_lag_in, in, ctx);
 
 	MLX5_SET(modify_lag_in, in, opcode, MLX5_CMD_OP_MODIFY_LAG);
@@ -72,52 +70,29 @@ static int mlx5_cmd_modify_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1);
 	MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int mlx5_cmd_destroy_lag(struct mlx5_core_dev *dev)
-{
-	u32  in[MLX5_ST_SZ_DW(destroy_lag_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_lag_out)] = {0};
-
-	MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_lag, in);
 }
 
 int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev)
 {
-	u32  in[MLX5_ST_SZ_DW(create_vport_lag_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(create_vport_lag_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_vport_lag_in)] = {};
 
 	MLX5_SET(create_vport_lag_in, in, opcode, MLX5_CMD_OP_CREATE_VPORT_LAG);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, create_vport_lag, in);
 }
 EXPORT_SYMBOL(mlx5_cmd_create_vport_lag);
 
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 {
-	u32  in[MLX5_ST_SZ_DW(destroy_vport_lag_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_vport_lag_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_vport_lag_in)] = {};
 
 	MLX5_SET(destroy_vport_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_VPORT_LAG);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_vport_lag, in);
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
-static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
-				       bool reset, void *out, int out_size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
-
-	MLX5_SET(query_cong_statistics_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
-	MLX5_SET(query_cong_statistics_in, in, clear, reset);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
-}
-
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev)
 {
@@ -232,12 +207,14 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {};
 	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	int err;
 
 	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
 
-	err = mlx5_cmd_destroy_lag(dev0);
+	MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG);
+	err = mlx5_cmd_exec_in(dev0, destroy_lag, in);
 	if (err) {
 		if (roce_lag) {
 			mlx5_core_err(dev0,
@@ -758,7 +735,12 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	}
 
 	for (i = 0; i < num_ports; ++i) {
-		ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen);
+		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
+
+		MLX5_SET(query_cong_statistics_in, in, opcode,
+			 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
+		ret = mlx5_cmd_exec_inout(mdev[i], query_cong_statistics, in,
+					  out);
 		if (ret)
 			goto unlock;
 
-- 
cgit v1.2.3


From bb7664d369bfeb2754af8b972ddaa5734e2864a8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:30:39 +0300
Subject: net/mlx5: Update gid.c new cmd interface

Do mass update of gid.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
index 7722a3f9bb68..a68738c8f4bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
@@ -124,8 +124,7 @@ int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   const u8 *mac, bool vlan, u16 vlan_id, u8 port_num)
 {
 #define MLX5_SET_RA(p, f, v) MLX5_SET(roce_addr_layout, p, f, v)
-	u32  in[MLX5_ST_SZ_DW(set_roce_address_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(set_roce_address_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_roce_address_in)] = {};
 	void *in_addr = MLX5_ADDR_OF(set_roce_address_in, in, roce_address);
 	char *addr_l3_addr = MLX5_ADDR_OF(roce_addr_layout, in_addr,
 					  source_l3_address);
@@ -153,6 +152,6 @@ int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 
 	MLX5_SET(set_roce_address_in, in, roce_address_index, index);
 	MLX5_SET(set_roce_address_in, in, opcode, MLX5_CMD_OP_SET_ROCE_ADDRESS);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, set_roce_address, in);
 }
 EXPORT_SYMBOL(mlx5_core_roce_gid_set);
-- 
cgit v1.2.3


From 9d6ed27163163b3236f38f89e3968601f7de6a95 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:31:21 +0300
Subject: net/mlx5: Update mpfs.c new cmd interface

Do mass update of mpfs.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 3118e8d66407..fd8449ff9e17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -40,8 +40,7 @@
 /* HW L2 Table (MPFS) management */
 static int set_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index, u8 *mac)
 {
-	u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_l2_table_entry_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {};
 	u8 *in_mac_addr;
 
 	MLX5_SET(set_l2_table_entry_in, in, opcode, MLX5_CMD_OP_SET_L2_TABLE_ENTRY);
@@ -50,17 +49,16 @@ static int set_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index, u8 *mac)
 	in_mac_addr = MLX5_ADDR_OF(set_l2_table_entry_in, in, mac_address);
 	ether_addr_copy(&in_mac_addr[2], mac);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, set_l2_table_entry, in);
 }
 
 static int del_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index)
 {
-	u32 in[MLX5_ST_SZ_DW(delete_l2_table_entry_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(delete_l2_table_entry_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(delete_l2_table_entry_in)] = {};
 
 	MLX5_SET(delete_l2_table_entry_in, in, opcode, MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY);
 	MLX5_SET(delete_l2_table_entry_in, in, table_index, index);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, delete_l2_table_entry, in);
 }
 
 /* UC L2 table hash node */
-- 
cgit v1.2.3


From 253e790e204f90adf10797ccea58910518a2c77e Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:32:06 +0300
Subject: net/mlx5: Update vxlan.c new cmd interface

Do mass update of vxlan.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 148b55c3db7a..82c766a95165 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -60,24 +60,22 @@ static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
 
 static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 {
-	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)] = {};
 
 	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
 		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
 	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, add_vxlan_udp_dport, in);
 }
 
 static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 {
-	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)] = {};
 
 	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
 		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
 	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, delete_vxlan_udp_dport, in);
 }
 
 static struct mlx5_vxlan_port*
-- 
cgit v1.2.3


From 3ac0e69e69ad17fe792ec68e651c6535d74fcffd Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:33:38 +0300
Subject: net/mlx5: Update main.c new cmd interface

Do mass update of main.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 35 ++++++++++----------------
 1 file changed, 13 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0044aa5cc676..061b69ea9cc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -206,8 +206,7 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
 {
 	int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in,
 					      driver_version);
-	u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {0};
-	u8 out[MLX5_ST_SZ_BYTES(set_driver_version_out)] = {0};
+	u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {};
 	int remaining_size = driver_ver_sz;
 	char *string;
 
@@ -234,7 +233,7 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
 	MLX5_SET(set_driver_version_in, in, opcode,
 		 MLX5_CMD_OP_SET_DRIVER_VERSION);
 
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, set_driver_version, in);
 }
 
 static int set_dma_caps(struct pci_dev *pdev)
@@ -366,7 +365,7 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev,
 
 	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
 	MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
+	err = mlx5_cmd_exec_inout(dev, query_hca_cap, in, out);
 	if (err) {
 		mlx5_core_warn(dev,
 			       "QUERY_HCA_CAP : type(%x) opmode(%x) Failed(%d)\n",
@@ -409,12 +408,9 @@ int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type)
 
 static int set_caps(struct mlx5_core_dev *dev, void *in, int opmod)
 {
-	u32 out[MLX5_ST_SZ_DW(set_hca_cap_out)] = {};
-
 	MLX5_SET(set_hca_cap_in, in, opcode, MLX5_CMD_OP_SET_HCA_CAP);
 	MLX5_SET(set_hca_cap_in, in, op_mod, opmod << 1);
-	return mlx5_cmd_exec(dev, in, MLX5_ST_SZ_BYTES(set_hca_cap_in), out,
-			     sizeof(out));
+	return mlx5_cmd_exec_in(dev, set_hca_cap, in);
 }
 
 static int handle_hca_cap_atomic(struct mlx5_core_dev *dev, void *set_ctx)
@@ -653,26 +649,24 @@ static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev)
 
 int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
 {
-	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
 
 	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
 	MLX5_SET(enable_hca_in, in, function_id, func_id);
 	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
 		 dev->caps.embedded_cpu);
-	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, enable_hca, in);
 }
 
 int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 {
-	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
 
 	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
 	MLX5_SET(disable_hca_in, in, function_id, func_id);
 	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
 		 dev->caps.embedded_cpu);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, disable_hca, in);
 }
 
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
@@ -697,14 +691,13 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
 
 static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 {
-	u32 query_in[MLX5_ST_SZ_DW(query_issi_in)]   = {0};
-	u32 query_out[MLX5_ST_SZ_DW(query_issi_out)] = {0};
+	u32 query_out[MLX5_ST_SZ_DW(query_issi_out)] = {};
+	u32 query_in[MLX5_ST_SZ_DW(query_issi_in)] = {};
 	u32 sup_issi;
 	int err;
 
 	MLX5_SET(query_issi_in, query_in, opcode, MLX5_CMD_OP_QUERY_ISSI);
-	err = mlx5_cmd_exec(dev, query_in, sizeof(query_in),
-			    query_out, sizeof(query_out));
+	err = mlx5_cmd_exec_inout(dev, query_issi, query_in, query_out);
 	if (err) {
 		u32 syndrome;
 		u8 status;
@@ -724,13 +717,11 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 	sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0);
 
 	if (sup_issi & (1 << 1)) {
-		u32 set_in[MLX5_ST_SZ_DW(set_issi_in)]   = {0};
-		u32 set_out[MLX5_ST_SZ_DW(set_issi_out)] = {0};
+		u32 set_in[MLX5_ST_SZ_DW(set_issi_in)] = {};
 
 		MLX5_SET(set_issi_in, set_in, opcode, MLX5_CMD_OP_SET_ISSI);
 		MLX5_SET(set_issi_in, set_in, current_issi, 1);
-		err = mlx5_cmd_exec(dev, set_in, sizeof(set_in),
-				    set_out, sizeof(set_out));
+		err = mlx5_cmd_exec_in(dev, set_issi, set_in);
 		if (err) {
 			mlx5_core_err(dev, "Failed to set ISSI to 1 err(%d)\n",
 				      err);
-- 
cgit v1.2.3


From 62a9fec040831c84a79721ec288851a3fd6f8ec0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:43:58 +0300
Subject: net/mlx5: Update mcg.c new cmd interface

Do mass update of mcg.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/mcg.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
index 6789fe658037..e019d68062d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
@@ -38,28 +38,26 @@
 
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn)
 {
-	u32 out[MLX5_ST_SZ_DW(attach_to_mcg_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(attach_to_mcg_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(attach_to_mcg_in)] = {};
 	void *gid;
 
 	MLX5_SET(attach_to_mcg_in, in, opcode, MLX5_CMD_OP_ATTACH_TO_MCG);
 	MLX5_SET(attach_to_mcg_in, in, qpn, qpn);
 	gid = MLX5_ADDR_OF(attach_to_mcg_in, in, multicast_gid);
 	memcpy(gid, mgid, sizeof(*mgid));
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, attach_to_mcg, in);
 }
 EXPORT_SYMBOL(mlx5_core_attach_mcg);
 
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn)
 {
-	u32 out[MLX5_ST_SZ_DW(detach_from_mcg_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(detach_from_mcg_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(detach_from_mcg_in)] = {};
 	void *gid;
 
 	MLX5_SET(detach_from_mcg_in, in, opcode, MLX5_CMD_OP_DETACH_FROM_MCG);
 	MLX5_SET(detach_from_mcg_in, in, qpn, qpn);
 	gid = MLX5_ADDR_OF(detach_from_mcg_in, in, multicast_gid);
 	memcpy(gid, mgid, sizeof(*mgid));
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, detach_from_mcg, in);
 }
 EXPORT_SYMBOL(mlx5_core_detach_mcg);
-- 
cgit v1.2.3


From adda874c957c86c7407930142d944c1546c38260 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 16:50:37 +0300
Subject: net/mlx5: Update mr.c new cmd interface

Do mass update of mr.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/mr.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 1feedf335dea..9eb51f06d3ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -39,7 +39,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 			  struct mlx5_core_mkey *mkey,
 			  u32 *in, int inlen)
 {
-	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0};
+	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {};
 	u32 mkey_index;
 	void *mkc;
 	int err;
@@ -65,19 +65,18 @@ EXPORT_SYMBOL(mlx5_core_create_mkey);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
 			   struct mlx5_core_mkey *mkey)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {};
 
 	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
 	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_mkey, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
 
 int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
 			 u32 *out, int outlen)
 {
-	u32 in[MLX5_ST_SZ_DW(query_mkey_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_mkey_in)] = {};
 
 	memset(out, 0, outlen);
 	MLX5_SET(query_mkey_in, in, opcode, MLX5_CMD_OP_QUERY_MKEY);
@@ -99,8 +98,8 @@ static inline u32 mlx5_get_psv(u32 *out, int psv_index)
 int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 			 int npsvs, u32 *sig_index)
 {
-	u32 out[MLX5_ST_SZ_DW(create_psv_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_psv_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(create_psv_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_psv_in)] = {};
 	int i, err;
 
 	if (npsvs > MLX5_MAX_PSVS)
@@ -110,7 +109,7 @@ int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 	MLX5_SET(create_psv_in, in, pd, pdn);
 	MLX5_SET(create_psv_in, in, num_psv, npsvs);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, create_psv, in, out);
 	if (err)
 		return err;
 
@@ -123,11 +122,10 @@ EXPORT_SYMBOL(mlx5_core_create_psv);
 
 int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_psv_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_psv_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_psv_in)] = {};
 
 	MLX5_SET(destroy_psv_in, in, opcode, MLX5_CMD_OP_DESTROY_PSV);
 	MLX5_SET(destroy_psv_in, in, psvn, psv_num);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_psv, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_psv);
-- 
cgit v1.2.3


From 86d41641ddd66fc9b2cc0aef0909cee68493a78a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 17:02:07 +0300
Subject: net/mlx5: Update pagealloc.c new cmd interface

Do mass update of pagealloc.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index a3959754b927..3d6f617abb7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -135,8 +135,8 @@ static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr)
 static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 				s32 *npages, int boot)
 {
-	u32 out[MLX5_ST_SZ_DW(query_pages_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(query_pages_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(query_pages_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_pages_in)] = {};
 	int err;
 
 	MLX5_SET(query_pages_in, in, opcode, MLX5_CMD_OP_QUERY_PAGES);
@@ -145,7 +145,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 		 MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
 	MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, query_pages, in, out);
 	if (err)
 		return err;
 
@@ -256,8 +256,7 @@ err_mapping:
 static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
 			     bool ec_function)
 {
-	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(manage_pages_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
 	int err;
 
 	MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
@@ -265,7 +264,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_in(dev, manage_pages, in);
 	if (err)
 		mlx5_core_warn(dev, "page notify failed func_id(%d) err(%d)\n",
 			       func_id, err);
@@ -373,7 +372,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 			 int *nclaimed, bool ec_function)
 {
 	int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
-	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
 	int num_claimed;
 	u32 *out;
 	int err;
-- 
cgit v1.2.3


From 9b3ca3ec03169e895c414c4e98a49c0cd0cd95ec Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 17:04:30 +0300
Subject: net/mlx5: Update pd.c new cmd interface

Do mass update of pd.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pd.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pd.c b/drivers/net/ethernet/mellanox/mlx5/core/pd.c
index b92d6f621c83..aabc53ad8bdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pd.c
@@ -37,12 +37,12 @@
 
 int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(alloc_pd_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_pd_in)] = {};
 	int err;
 
 	MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, alloc_pd, in, out);
 	if (!err)
 		*pdn = MLX5_GET(alloc_pd_out, out, pd);
 	return err;
@@ -51,11 +51,10 @@ EXPORT_SYMBOL(mlx5_core_alloc_pd);
 
 int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_pd_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)] = {};
 
 	MLX5_SET(dealloc_pd_in, in, opcode, MLX5_CMD_OP_DEALLOC_PD);
 	MLX5_SET(dealloc_pd_in, in, pd, pdn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, dealloc_pd, in);
 }
 EXPORT_SYMBOL(mlx5_core_dealloc_pd);
-- 
cgit v1.2.3


From 1fb5193434555df68eb065705baf223bca80ad0a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 17:05:05 +0300
Subject: net/mlx5: Update uar.c new cmd interface

Do mass update of uar.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/uar.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 816f9c434359..da481a7c12f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -38,12 +38,12 @@
 
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(alloc_uar_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {};
 	int err;
 
 	MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out);
 	if (!err)
 		*uarn = MLX5_GET(alloc_uar_out, out, uar);
 	return err;
@@ -52,12 +52,11 @@ EXPORT_SYMBOL(mlx5_cmd_alloc_uar);
 
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_uar_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)]   = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {};
 
 	MLX5_SET(dealloc_uar_in, in, opcode, MLX5_CMD_OP_DEALLOC_UAR);
 	MLX5_SET(dealloc_uar_in, in, uar, uarn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, dealloc_uar, in);
 }
 EXPORT_SYMBOL(mlx5_cmd_free_uar);
 
-- 
cgit v1.2.3


From fa8110f4451c189b1efd4de6bef02ac6efb1244f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 17:05:31 +0300
Subject: net/mlx5: Update rl.c new cmd interface

Do mass update of rl.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/rl.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index c9599f7c5696..99039c47ef33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -39,8 +39,8 @@
 int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 				       void *ctx, u32 *element_id)
 {
-	u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {};
 	void *schedc;
 	int err;
 
@@ -52,7 +52,7 @@ int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 		 hierarchy);
 	memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, create_scheduling_element, in, out);
 	if (err)
 		return err;
 
@@ -65,8 +65,7 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 				       void *ctx, u32 element_id,
 				       u32 modify_bitmask)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {};
 	void *schedc;
 
 	schedc = MLX5_ADDR_OF(modify_scheduling_element_in, in,
@@ -81,14 +80,13 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 		 hierarchy);
 	memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_scheduling_element, in);
 }
 
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)]  = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {};
 
 	MLX5_SET(destroy_scheduling_element_in, in, opcode,
 		 MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT);
@@ -97,7 +95,7 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 	MLX5_SET(destroy_scheduling_element_in, in, scheduling_hierarchy,
 		 hierarchy);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, destroy_scheduling_element, in);
 }
 
 static bool mlx5_rl_are_equal_raw(struct mlx5_rl_entry *entry, void *rl_in,
@@ -144,8 +142,7 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
 static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
 				      struct mlx5_rl_entry *entry, bool set)
 {
-	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {};
 	void *pp_context;
 
 	pp_context = MLX5_ADDR_OF(set_pp_rate_limit_in, in, ctx);
@@ -155,7 +152,7 @@ static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
 	MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, entry->index);
 	if (set)
 		memcpy(pp_context, entry->rl_raw, sizeof(entry->rl_raw));
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, set_pp_rate_limit, in);
 }
 
 bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate)
-- 
cgit v1.2.3


From 2276a0dfc17be2cd89cfb8ed0a7ef6fad417aa3e Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 21:00:23 +0300
Subject: net/mlx5: Update port.c new cmd interface

Do mass update of port.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/port.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index cc262b30aed5..9f829e68fc73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -763,24 +763,23 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit);
 
 int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 {
-	u32 in[MLX5_ST_SZ_DW(set_wol_rol_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_wol_rol_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_wol_rol_in)] = {};
 
 	MLX5_SET(set_wol_rol_in, in, opcode, MLX5_CMD_OP_SET_WOL_ROL);
 	MLX5_SET(set_wol_rol_in, in, wol_mode_valid, 1);
 	MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, set_wol_rol, in);
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_wol);
 
 int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 {
-	u32 in[MLX5_ST_SZ_DW(query_wol_rol_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(query_wol_rol_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(query_wol_rol_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_wol_rol_in)] = {};
 	int err;
 
 	MLX5_SET(query_wol_rol_in, in, opcode, MLX5_CMD_OP_QUERY_WOL_ROL);
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, query_wol_rol, in, out);
 	if (!err)
 		*wol_mode = MLX5_GET(query_wol_rol_out, out, wol_mode);
 
-- 
cgit v1.2.3


From 7ba294e43595ab728adf2baf0aab378095768bfe Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 21:02:08 +0300
Subject: net/mlx5: Update SW steering new cmd interface

Do mass update of SW steering to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_cmd.c  | 33 +++++++++-------------
 1 file changed, 14 insertions(+), 19 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 461b39376daf..6bd34b293007 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -18,7 +18,7 @@ int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev,
 	MLX5_SET(query_esw_vport_context_in, in, other_vport, other_vport);
 	MLX5_SET(query_esw_vport_context_in, in, vport_number, vport_number);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, query_esw_vport_context, in, out);
 	if (err)
 		return err;
 
@@ -51,7 +51,7 @@ int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport,
 		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 |
 		 HCA_CAP_OPMOD_GET_CUR);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	err = mlx5_cmd_exec_inout(mdev, query_hca_cap, in, out);
 	if (err) {
 		kfree(out);
 		return err;
@@ -141,7 +141,7 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
 	MLX5_SET(query_flow_table_in, in, table_type, type);
 	MLX5_SET(query_flow_table_in, in, table_id, table_id);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, query_flow_table, in, out);
 	if (err)
 		return err;
 
@@ -158,12 +158,11 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
 
 int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev)
 {
-	u32 out[MLX5_ST_SZ_DW(sync_steering_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {};
 
 	MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, sync_steering, in);
 }
 
 int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev,
@@ -214,14 +213,13 @@ int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev,
 				    u32 table_type,
 				    u32 table_id)
 {
-	u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {};
 
 	MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
 	MLX5_SET(delete_fte_in, in, table_type, table_type);
 	MLX5_SET(delete_fte_in, in, table_id, table_id);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, delete_fte, in);
 }
 
 int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev,
@@ -263,7 +261,6 @@ out:
 int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev,
 				     u32 modify_header_id)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {};
 
 	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
@@ -271,7 +268,7 @@ int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev,
 	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
 		 modify_header_id);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, dealloc_modify_header_context, in);
 }
 
 int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev,
@@ -292,7 +289,7 @@ int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev,
 	MLX5_SET(create_flow_group_in, in, table_type, table_type);
 	MLX5_SET(create_flow_group_in, in, table_id, table_id);
 
-	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, create_flow_group, in, out);
 	if (err)
 		goto out;
 
@@ -309,14 +306,14 @@ int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev,
 				  u32 group_id)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {};
-	u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {};
 
-	MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP);
+	MLX5_SET(destroy_flow_group_in, in, opcode,
+		 MLX5_CMD_OP_DESTROY_FLOW_GROUP);
 	MLX5_SET(destroy_flow_group_in, in, table_type, table_type);
 	MLX5_SET(destroy_flow_group_in, in, table_id, table_id);
 	MLX5_SET(destroy_flow_group_in, in, group_id, group_id);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, destroy_flow_group, in);
 }
 
 int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
@@ -360,7 +357,7 @@ int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
 	MLX5_SET(create_flow_table_in, in, flow_table_context.reformat_en,
 		 attr->reformat_en);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, create_flow_table, in, out);
 	if (err)
 		return err;
 
@@ -379,7 +376,6 @@ int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
 				  u32 table_id,
 				  u32 table_type)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {};
 
 	MLX5_SET(destroy_flow_table_in, in, opcode,
@@ -387,7 +383,7 @@ int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
 	MLX5_SET(destroy_flow_table_in, in, table_type, table_type);
 	MLX5_SET(destroy_flow_table_in, in, table_id, table_id);
 
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	return mlx5_cmd_exec_in(mdev, destroy_flow_table, in);
 }
 
 int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
@@ -434,7 +430,6 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
 void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev,
 				     u32 reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {};
 
 	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
@@ -442,7 +437,7 @@ void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev,
 	MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
 		 reformat_id);
 
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(mdev, dealloc_packet_reformat_context, in);
 }
 
 int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num,
@@ -458,7 +453,7 @@ int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num,
 	MLX5_SET(query_roce_address_in, in, roce_address_index, index);
 	MLX5_SET(query_roce_address_in, in, vhca_port_num, vhca_port_num);
 
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(mdev, query_roce_address, in, out);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From e0b4b4722dfac09658d1519b296cf8dc349a2451 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 9 Apr 2020 21:03:33 +0300
Subject: net/mlx5: Update transobj.c new cmd interface

Do mass update of transobj.c to reuse newly introduced
mlx5_cmd_exec_in*() interfaces.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c                    |  32 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |   7 +-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |   2 +-
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  29 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 113 ++++++++-------------
 include/linux/mlx5/transobj.h                      |  19 ++--
 9 files changed, 85 insertions(+), 131 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 3ecd1864b3c8..af599c8b88aa 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1255,7 +1255,7 @@ static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_sq *sq, u32 tdn,
 				    struct ib_pd *pd)
 {
-	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
 
 	MLX5_SET(create_tis_in, in, uid, to_mpd(pd)->uid);
@@ -1263,7 +1263,7 @@ static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
 	if (qp->flags & MLX5_IB_QP_UNDERLAY)
 		MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn);
 
-	return mlx5_core_create_tis(dev->mdev, in, sizeof(in), &sq->tisn);
+	return mlx5_core_create_tis(dev->mdev, in, &sq->tisn);
 }
 
 static void destroy_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
@@ -1460,9 +1460,8 @@ static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_rq *rq, u32 tdn,
-				    u32 *qp_flags_en,
-				    struct ib_pd *pd,
-				    u32 *out, int outlen)
+				    u32 *qp_flags_en, struct ib_pd *pd,
+				    u32 *out)
 {
 	u8 lb_flag = 0;
 	u32 *in;
@@ -1495,9 +1494,8 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 	}
 
 	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
-
-	err = mlx5_core_create_tir_out(dev->mdev, in, inlen, out, outlen);
-
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+	err = mlx5_cmd_exec_inout(dev->mdev, create_tir, in, out);
 	rq->tirn = MLX5_GET(create_tir_out, out, tirn);
 	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
 		err = mlx5_ib_enable_lb(dev, false, true);
@@ -1557,9 +1555,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		if (err)
 			goto err_destroy_sq;
 
-		err = create_raw_packet_qp_tir(
-			dev, rq, tdn, &qp->flags_en, pd, out,
-			MLX5_ST_SZ_BYTES(create_tir_out));
+		err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en, pd,
+					       out);
 		if (err)
 			goto err_destroy_rq;
 
@@ -1854,7 +1851,8 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
 
 create_tir:
-	err = mlx5_core_create_tir_out(dev->mdev, in, inlen, out, outlen);
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+	err = mlx5_cmd_exec_inout(dev->mdev, create_tir, in, out);
 
 	qp->rss_qp.tirn = MLX5_GET(create_tir_out, out, tirn);
 	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
@@ -2933,7 +2931,7 @@ static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
 	tisc = MLX5_ADDR_OF(modify_tis_in, in, ctx);
 	MLX5_SET(tisc, tisc, prio, ((sl & 0x7) << 1));
 
-	err = mlx5_core_modify_tis(dev, sq->tisn, in, inlen);
+	err = mlx5_core_modify_tis(dev, sq->tisn, in);
 
 	kvfree(in);
 
@@ -2960,7 +2958,7 @@ static int modify_raw_packet_tx_affinity(struct mlx5_core_dev *dev,
 	tisc = MLX5_ADDR_OF(modify_tis_in, in, ctx);
 	MLX5_SET(tisc, tisc, lag_tx_port_affinity, tx_affinity);
 
-	err = mlx5_core_modify_tis(dev, sq->tisn, in, inlen);
+	err = mlx5_core_modify_tis(dev, sq->tisn, in);
 
 	kvfree(in);
 
@@ -3240,7 +3238,7 @@ static int modify_raw_packet_qp_rq(
 				"RAW PACKET QP counters are not supported on current FW\n");
 	}
 
-	err = mlx5_core_modify_rq(dev->mdev, rq->base.mqp.qpn, in, inlen);
+	err = mlx5_core_modify_rq(dev->mdev, rq->base.mqp.qpn, in);
 	if (err)
 		goto out;
 
@@ -3303,7 +3301,7 @@ static int modify_raw_packet_qp_sq(
 		MLX5_SET(sqc, sqc, packet_pacing_rate_limit_index, rl_index);
 	}
 
-	err = mlx5_core_modify_sq(dev, sq->base.mqp.qpn, in, inlen);
+	err = mlx5_core_modify_sq(dev, sq->base.mqp.qpn, in);
 	if (err) {
 		/* Remove new rate from table if failed */
 		if (new_rate_added)
@@ -6444,7 +6442,7 @@ int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 				"Receive WQ counters are not supported on current FW\n");
 	}
 
-	err = mlx5_core_modify_rq(dev->mdev, rwq->core_qp.qpn, in, inlen);
+	err = mlx5_core_modify_rq(dev->mdev, rwq->core_qp.qpn, in);
 	if (!err)
 		rwq->ibwq.state = (wq_state == MLX5_RQC_STATE_ERR) ? IB_WQS_ERR : wq_state;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 12a61bf82c14..1599b05f3c5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1012,7 +1012,7 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner);
-void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in);
 struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
 
 struct mlx5e_xsk_param;
@@ -1102,8 +1102,8 @@ void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
 void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
 #endif
 
-int mlx5e_create_tir(struct mlx5_core_dev *mdev,
-		     struct mlx5e_tir *tir, u32 *in, int inlen);
+int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir,
+		     u32 *in);
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index f7890e0ce96c..af3228b3f303 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -36,12 +36,11 @@
  * Global resources are common to all the netdevices crated on the same nic.
  */
 
-int mlx5e_create_tir(struct mlx5_core_dev *mdev,
-		     struct mlx5e_tir *tir, u32 *in, int inlen)
+int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 *in)
 {
 	int err;
 
-	err = mlx5_core_create_tir(mdev, in, inlen, &tir->tirn);
+	err = mlx5_core_create_tir(mdev, in, &tir->tirn);
 	if (err)
 		return err;
 
@@ -167,7 +166,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
-		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
+		err = mlx5_core_modify_tir(mdev, tirn, in);
 		if (err)
 			goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6d703ddee4e2..de8250820b06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1204,7 +1204,7 @@ int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	}
 
 	if (hash_changed)
-		mlx5e_modify_tirs_hash(priv, in, inlen);
+		mlx5e_modify_tirs_hash(priv, in);
 
 	mutex_unlock(&priv->state_lock);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 3bc2ac3d53fc..83c9b2bbc4af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -858,7 +858,7 @@ static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
 		goto out;
 
 	priv->rss_params.rx_hash_fields[tt] = rx_hash_field;
-	mlx5e_modify_tirs_hash(priv, in, inlen);
+	mlx5e_modify_tirs_hash(priv, in);
 
 out:
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 30970b405040..05dbe8b9caac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -721,7 +721,7 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);
 	MLX5_SET(rqc, rqc, state, next_state);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -752,7 +752,7 @@ static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable)
 	MLX5_SET(rqc, rqc, scatter_fcs, enable);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -781,7 +781,7 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
 	MLX5_SET(rqc, rqc, vsd, vsd);
 	MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
 
-	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in);
 
 	kvfree(in);
 
@@ -1259,7 +1259,7 @@ int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
 		MLX5_SET(sqc,  sqc, packet_pacing_rate_limit_index, p->rl_index);
 	}
 
-	err = mlx5_core_modify_sq(mdev, sqn, in, inlen);
+	err = mlx5_core_modify_sq(mdev, sqn, in);
 
 	kvfree(in);
 
@@ -2698,7 +2698,7 @@ static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig,
 	ttconfig->rx_hash_fields = rx_hash_fields;
 }
 
-void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in)
 {
 	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
 	struct mlx5e_rss_params *rss = &priv->rss_params;
@@ -2714,7 +2714,7 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5e_update_rx_hash_fields(&ttconfig, tt,
 					    rss->rx_hash_fields[tt]);
 		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false);
-		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
 	}
 
 	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
@@ -2725,8 +2725,7 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5e_update_rx_hash_fields(&ttconfig, tt,
 					    rss->rx_hash_fields[tt]);
 		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true);
-		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
-				     inlen);
+		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in);
 	}
 }
 
@@ -2752,15 +2751,13 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
-					   inlen);
+		err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in);
 		if (err)
 			goto free_in;
 	}
 
 	for (ix = 0; ix < priv->max_nch; ix++) {
-		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn,
-					   in, inlen);
+		err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in);
 		if (err)
 			goto free_in;
 	}
@@ -3214,7 +3211,7 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
 	if (mlx5_lag_is_lacp_owner(mdev))
 		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
 
-	return mlx5_core_create_tis(mdev, in, MLX5_ST_SZ_BYTES(create_tis_in), tisn);
+	return mlx5_core_create_tis(mdev, in, tisn);
 }
 
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
@@ -3332,7 +3329,7 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
 		tir = &priv->indir_tir[tt];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_indir_tir_ctx(priv, tt, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err);
 			goto err_destroy_inner_tirs;
@@ -3347,7 +3344,7 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
 		tir = &priv->inner_indir_tir[i];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_inner_indir_tir_ctx(priv, i, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
 		if (err) {
 			mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err);
 			goto err_destroy_inner_tirs;
@@ -3390,7 +3387,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 		tir = &tirs[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 		mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc);
-		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
+		err = mlx5e_create_tir(priv->mdev, tir, in);
 		if (unlikely(err))
 			goto err_destroy_ch_tirs;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 438128dde187..88c0e460e995 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -568,7 +568,7 @@ struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex)
 
 static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp)
 {
-	u32 in[MLX5_ST_SZ_DW(create_tir_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_tir_in)] = {};
 	void *tirc;
 	int err;
 
@@ -582,7 +582,7 @@ static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp)
 	MLX5_SET(tirc, tirc, inline_rqn, hp->pair->rqn[0]);
 	MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
 
-	err = mlx5_core_create_tir(hp->func_mdev, in, MLX5_ST_SZ_BYTES(create_tir_in), &hp->tirn);
+	err = mlx5_core_create_tir(hp->func_mdev, in, &hp->tirn);
 	if (err)
 		goto create_tir_err;
 
@@ -666,7 +666,7 @@ static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp)
 		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false);
 
 		err = mlx5_core_create_tir(hp->func_mdev, in,
-					   MLX5_ST_SZ_BYTES(create_tir_in), &hp->indir_tirn[tt]);
+					   &hp->indir_tirn[tt]);
 		if (err) {
 			mlx5_core_warn(hp->func_mdev, "create indirect tirs failed, %d\n", err);
 			goto err_destroy_tirs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index b1068500f1df..01cc00ad8acf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -36,14 +36,14 @@
 
 int mlx5_core_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn)
 {
-	u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)] = {};
 	int err;
 
 	MLX5_SET(alloc_transport_domain_in, in, opcode,
 		 MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN);
 
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, alloc_transport_domain, in, out);
 	if (!err)
 		*tdn = MLX5_GET(alloc_transport_domain_out, out,
 				transport_domain);
@@ -54,19 +54,18 @@ EXPORT_SYMBOL(mlx5_core_alloc_transport_domain);
 
 void mlx5_core_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn)
 {
-	u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(dealloc_transport_domain_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)] = {};
 
 	MLX5_SET(dealloc_transport_domain_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN);
 	MLX5_SET(dealloc_transport_domain_in, in, transport_domain, tdn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, dealloc_transport_domain, in);
 }
 EXPORT_SYMBOL(mlx5_core_dealloc_transport_domain);
 
 int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_rq_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_rq_out)] = {};
 	int err;
 
 	MLX5_SET(create_rq_in, in, opcode, MLX5_CMD_OP_CREATE_RQ);
@@ -78,44 +77,39 @@ int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn)
 }
 EXPORT_SYMBOL(mlx5_core_create_rq);
 
-int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen)
+int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_rq_out)];
-
 	MLX5_SET(modify_rq_in, in, rqn, rqn);
 	MLX5_SET(modify_rq_in, in, opcode, MLX5_CMD_OP_MODIFY_RQ);
 
-	memset(out, 0, sizeof(out));
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_rq, in);
 }
 EXPORT_SYMBOL(mlx5_core_modify_rq);
 
 void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_rq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_rq_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_rq_in)] = {};
 
 	MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ);
 	MLX5_SET(destroy_rq_in, in, rqn, rqn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, destroy_rq, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_rq);
 
 int mlx5_core_query_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *out)
 {
-	u32 in[MLX5_ST_SZ_DW(query_rq_in)] = {0};
-	int outlen = MLX5_ST_SZ_BYTES(query_rq_out);
+	u32 in[MLX5_ST_SZ_DW(query_rq_in)] = {};
 
 	MLX5_SET(query_rq_in, in, opcode, MLX5_CMD_OP_QUERY_RQ);
 	MLX5_SET(query_rq_in, in, rqn, rqn);
 
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return mlx5_cmd_exec_inout(dev, query_rq, in, out);
 }
 EXPORT_SYMBOL(mlx5_core_query_rq);
 
 int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_sq_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_sq_out)] = {};
 	int err;
 
 	MLX5_SET(create_sq_in, in, opcode, MLX5_CMD_OP_CREATE_SQ);
@@ -126,34 +120,30 @@ int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn)
 	return err;
 }
 
-int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen)
+int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_sq_out)] = {0};
-
 	MLX5_SET(modify_sq_in, in, sqn, sqn);
 	MLX5_SET(modify_sq_in, in, opcode, MLX5_CMD_OP_MODIFY_SQ);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_sq, in);
 }
 EXPORT_SYMBOL(mlx5_core_modify_sq);
 
 void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_sq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_sq_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_sq_in)] = {};
 
 	MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ);
 	MLX5_SET(destroy_sq_in, in, sqn, sqn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, destroy_sq, in);
 }
 
 int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out)
 {
-	u32 in[MLX5_ST_SZ_DW(query_sq_in)] = {0};
-	int outlen = MLX5_ST_SZ_BYTES(query_sq_out);
+	u32 in[MLX5_ST_SZ_DW(query_sq_in)] = {};
 
 	MLX5_SET(query_sq_in, in, opcode, MLX5_CMD_OP_QUERY_SQ);
 	MLX5_SET(query_sq_in, in, sqn, sqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return mlx5_cmd_exec_inout(dev, query_sq, in, out);
 }
 EXPORT_SYMBOL(mlx5_core_query_sq);
 
@@ -182,24 +172,13 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_sq_state);
 
-int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
-			     u32 *in, int inlen,
-			     u32 *out, int outlen)
-{
-	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
-
-	return mlx5_cmd_exec(dev, in, inlen, out, outlen);
-}
-EXPORT_SYMBOL(mlx5_core_create_tir_out);
-
-int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *tirn)
+int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, u32 *tirn)
 {
 	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 	int err;
 
-	err = mlx5_core_create_tir_out(dev, in, inlen,
-				       out, sizeof(out));
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+	err = mlx5_cmd_exec_inout(dev, create_tir, in, out);
 	if (!err)
 		*tirn = MLX5_GET(create_tir_out, out, tirn);
 
@@ -207,35 +186,30 @@ int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 }
 EXPORT_SYMBOL(mlx5_core_create_tir);
 
-int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in,
-			 int inlen)
+int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_tir_out)] = {0};
-
 	MLX5_SET(modify_tir_in, in, tirn, tirn);
 	MLX5_SET(modify_tir_in, in, opcode, MLX5_CMD_OP_MODIFY_TIR);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_tir, in);
 }
 
 void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_tir_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_tir_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_tir_in)] = {};
 
 	MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR);
 	MLX5_SET(destroy_tir_in, in, tirn, tirn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, destroy_tir, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_tir);
 
-int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *tisn)
+int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, u32 *tisn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_tis_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_tis_out)] = {};
 	int err;
 
 	MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec_inout(dev, create_tis, in, out);
 	if (!err)
 		*tisn = MLX5_GET(create_tis_out, out, tisn);
 
@@ -243,33 +217,29 @@ int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
 }
 EXPORT_SYMBOL(mlx5_core_create_tis);
 
-int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in,
-			 int inlen)
+int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_tis_out)] = {0};
-
 	MLX5_SET(modify_tis_in, in, tisn, tisn);
 	MLX5_SET(modify_tis_in, in, opcode, MLX5_CMD_OP_MODIFY_TIS);
 
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	return mlx5_cmd_exec_in(dev, modify_tis, in);
 }
 EXPORT_SYMBOL(mlx5_core_modify_tis);
 
 void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_tis_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_tis_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_tis_in)] = {};
 
 	MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS);
 	MLX5_SET(destroy_tis_in, in, tisn, tisn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, destroy_tis, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_tis);
 
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {};
 	int err;
 
 	MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT);
@@ -284,7 +254,7 @@ EXPORT_SYMBOL(mlx5_core_create_rqt);
 int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in,
 			 int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(modify_rqt_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(modify_rqt_out)] = {};
 
 	MLX5_SET(modify_rqt_in, in, rqtn, rqtn);
 	MLX5_SET(modify_rqt_in, in, opcode, MLX5_CMD_OP_MODIFY_RQT);
@@ -293,12 +263,11 @@ int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in,
 
 void mlx5_core_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn)
 {
-	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_rqt_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {};
 
 	MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT);
 	MLX5_SET(destroy_rqt_in, in, rqtn, rqtn);
-	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	mlx5_cmd_exec_in(dev, destroy_rqt, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_rqt);
 
@@ -383,7 +352,7 @@ static int mlx5_hairpin_modify_rq(struct mlx5_core_dev *func_mdev, u32 rqn,
 				  int curr_state, int next_state,
 				  u16 peer_vhca, u32 peer_sq)
 {
-	u32 in[MLX5_ST_SZ_DW(modify_rq_in)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_rq_in)] = {};
 	void *rqc;
 
 	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
@@ -396,8 +365,7 @@ static int mlx5_hairpin_modify_rq(struct mlx5_core_dev *func_mdev, u32 rqn,
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);
 	MLX5_SET(rqc, rqc, state, next_state);
 
-	return mlx5_core_modify_rq(func_mdev, rqn,
-				   in, MLX5_ST_SZ_BYTES(modify_rq_in));
+	return mlx5_core_modify_rq(func_mdev, rqn, in);
 }
 
 static int mlx5_hairpin_modify_sq(struct mlx5_core_dev *peer_mdev, u32 sqn,
@@ -417,8 +385,7 @@ static int mlx5_hairpin_modify_sq(struct mlx5_core_dev *peer_mdev, u32 sqn,
 	MLX5_SET(modify_sq_in, in, sq_state, curr_state);
 	MLX5_SET(sqc, sqc, state, next_state);
 
-	return mlx5_core_modify_sq(peer_mdev, sqn,
-				   in, MLX5_ST_SZ_BYTES(modify_sq_in));
+	return mlx5_core_modify_sq(peer_mdev, sqn, in);
 }
 
 static int mlx5_hairpin_pair_queues(struct mlx5_hairpin *hp)
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index dc6b1e7cb8c4..028f442530cf 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -39,27 +39,20 @@ int mlx5_core_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn);
 void mlx5_core_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn);
 int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			u32 *rqn);
-int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen);
+int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in);
 void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn);
 int mlx5_core_query_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *out);
 int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			u32 *sqn);
-int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen);
+int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in);
 void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn);
 int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out);
 int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state);
-int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *tirn);
-int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
-			     u32 *in, int inlen,
-			     u32 *out, int outlen);
-int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in,
-			 int inlen);
+int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, u32 *tirn);
+int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in);
 void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn);
-int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *tisn);
-int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in,
-			 int inlen);
+int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, u32 *tisn);
+int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in);
 void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn);
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn);
-- 
cgit v1.2.3


From 2196d831205bad6bc5cd328baf0ae02234629695 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Wed, 22 Apr 2020 06:16:06 -0700
Subject: qed: Enable device error reporting capability.

The patch enables the device to send error messages to root port when
an error is detected.

Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 96356e897c80..38a1d26ca9db 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -49,6 +49,7 @@
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_ll2_if.h>
 #include <net/devlink.h>
+#include <linux/aer.h>
 
 #include "qed.h"
 #include "qed_sriov.h"
@@ -129,6 +130,8 @@ static void qed_free_pci(struct qed_dev *cdev)
 {
 	struct pci_dev *pdev = cdev->pdev;
 
+	pci_disable_pcie_error_reporting(pdev);
+
 	if (cdev->doorbells && cdev->db_size)
 		iounmap(cdev->doorbells);
 	if (cdev->regview)
@@ -231,6 +234,12 @@ static int qed_init_pci(struct qed_dev *cdev, struct pci_dev *pdev)
 		return -ENOMEM;
 	}
 
+	/* AER (Advanced Error reporting) configuration */
+	rc = pci_enable_pcie_error_reporting(pdev);
+	if (rc)
+		DP_VERBOSE(cdev, NETIF_MSG_DRV,
+			   "Failed to configure PCIe AER [%d]\n", rc);
+
 	return 0;
 
 err2:
-- 
cgit v1.2.3


From 731815e720ae7e47a19753e00ea80651b2d52b3b Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Wed, 22 Apr 2020 06:16:07 -0700
Subject: qede: Add support for handling the pcie errors.

The error recovery is handled by management firmware (MFW) with the help of
qed/qede drivers. Upon detecting the errors, driver informs MFW about this
event which in turn starts a recovery process. MFW sends ERROR_RECOVERY
notification to the driver which performs the required cleanup/recovery
from the driver side.

Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      |  1 +
 drivers/net/ethernet/qlogic/qede/qede_main.c | 68 +++++++++++++++++++++++++++-
 2 files changed, 68 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 234c6f30effb..1a708f95ce94 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -485,6 +485,7 @@ struct qede_fastpath {
 
 #define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
+#define QEDE_SP_AER			7
 
 #ifdef CONFIG_RFS_ACCEL
 int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 34fa3917eb33..9b456198cb50 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -60,6 +60,7 @@
 #include <net/ip6_checksum.h>
 #include <linux/bitops.h>
 #include <linux/vmalloc.h>
+#include <linux/aer.h>
 #include "qede.h"
 #include "qede_ptp.h"
 
@@ -124,6 +125,8 @@ static const struct pci_device_id qede_pci_tbl[] = {
 MODULE_DEVICE_TABLE(pci, qede_pci_tbl);
 
 static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id);
+static pci_ers_result_t
+qede_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state);
 
 #define TX_TIMEOUT		(5 * HZ)
 
@@ -203,6 +206,10 @@ static int qede_sriov_configure(struct pci_dev *pdev, int num_vfs_param)
 }
 #endif
 
+static const struct pci_error_handlers qede_err_handler = {
+	.error_detected = qede_io_error_detected,
+};
+
 static struct pci_driver qede_pci_driver = {
 	.name = "qede",
 	.id_table = qede_pci_tbl,
@@ -212,6 +219,7 @@ static struct pci_driver qede_pci_driver = {
 #ifdef CONFIG_QED_SRIOV
 	.sriov_configure = qede_sriov_configure,
 #endif
+	.err_handler = &qede_err_handler,
 };
 
 static struct qed_eth_cb_ops qede_ll_ops = {
@@ -974,7 +982,8 @@ static void qede_sp_task(struct work_struct *work)
 		/* SRIOV must be disabled outside the lock to avoid a deadlock.
 		 * The recovery of the active VFs is currently not supported.
 		 */
-		qede_sriov_configure(edev->pdev, 0);
+		if (pci_num_vf(edev->pdev))
+			qede_sriov_configure(edev->pdev, 0);
 #endif
 		qede_lock(edev);
 		qede_recovery_handler(edev);
@@ -994,6 +1003,17 @@ static void qede_sp_task(struct work_struct *work)
 	}
 #endif
 	__qede_unlock(edev);
+
+	if (test_and_clear_bit(QEDE_SP_AER, &edev->sp_flags)) {
+#ifdef CONFIG_QED_SRIOV
+		/* SRIOV must be disabled outside the lock to avoid a deadlock.
+		 * The recovery of the active VFs is currently not supported.
+		 */
+		if (pci_num_vf(edev->pdev))
+			qede_sriov_configure(edev->pdev, 0);
+#endif
+		edev->ops->common->recovery_process(edev->cdev);
+	}
 }
 
 static void qede_update_pf_params(struct qed_dev *cdev)
@@ -2579,3 +2599,49 @@ static void qede_get_eth_tlv_data(void *dev, void *data)
 	etlv->num_txqs_full_set = true;
 	etlv->num_rxqs_full_set = true;
 }
+
+/**
+ * qede_io_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
+ *
+ * This function is called after a PCI bus error affecting
+ * this device has been detected.
+ */
+static pci_ers_result_t
+qede_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct qede_dev *edev = netdev_priv(dev);
+
+	if (!edev)
+		return PCI_ERS_RESULT_NONE;
+
+	DP_NOTICE(edev, "IO error detected [%d]\n", state);
+
+	__qede_lock(edev);
+	if (edev->state == QEDE_STATE_RECOVERY) {
+		DP_NOTICE(edev, "Device already in the recovery state\n");
+		__qede_unlock(edev);
+		return PCI_ERS_RESULT_NONE;
+	}
+
+	/* PF handles the recovery of its VFs */
+	if (IS_VF(edev)) {
+		DP_VERBOSE(edev, QED_MSG_IOV,
+			   "VF recovery is handled by its PF\n");
+		__qede_unlock(edev);
+		return PCI_ERS_RESULT_RECOVERED;
+	}
+
+	/* Close OS Tx */
+	netif_tx_disable(edev->ndev);
+	netif_carrier_off(edev->ndev);
+
+	set_bit(QEDE_SP_AER, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+
+	__qede_unlock(edev);
+
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
-- 
cgit v1.2.3


From cf4058dbaa18bf8e55b7cb8c04e1c313298cd5b1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2020 09:13:29 -0700
Subject: net/mlx4_en: use napi_complete_done() in TX completion

In order to benefit from the new napi_defer_hard_irqs feature,
we need to use napi_complete_done() variant in this driver.

RX path is already using it, this patch implements TX completion side.

mlx4_en_process_tx_cq() now returns the amount of retired packets,
instead of a boolean, so that mlx4_en_poll_tx_cq() can pass
this value to napi_complete_done().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 20 ++++++++++----------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  4 ++--
 3 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index db3552f2d087..787139219813 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -946,7 +946,7 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 		xdp_tx_cq = priv->tx_cq[TX_XDP][cq->ring];
 		if (xdp_tx_cq->xdp_busy) {
 			clean_complete = mlx4_en_process_tx_cq(dev, xdp_tx_cq,
-							       budget);
+							       budget) < budget;
 			xdp_tx_cq->xdp_busy = !clean_complete;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4d5ca302c067..a99d3ed49ed6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -382,8 +382,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-bool mlx4_en_process_tx_cq(struct net_device *dev,
-			   struct mlx4_en_cq *cq, int napi_budget)
+int mlx4_en_process_tx_cq(struct net_device *dev,
+			  struct mlx4_en_cq *cq, int napi_budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
@@ -405,7 +405,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 ring_cons;
 
 	if (unlikely(!priv->port_up))
-		return true;
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 
@@ -480,7 +480,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 	WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped);
 
 	if (cq->type == TX_XDP)
-		return done < budget;
+		return done;
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
@@ -492,7 +492,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 		ring->wake_queue++;
 	}
 
-	return done < budget;
+	return done;
 }
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@@ -512,14 +512,14 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
 	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
 	struct net_device *dev = cq->dev;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	bool clean_complete;
+	int work_done;
 
-	clean_complete = mlx4_en_process_tx_cq(dev, cq, budget);
-	if (!clean_complete)
+	work_done = mlx4_en_process_tx_cq(dev, cq, budget);
+	if (work_done >= budget)
 		return budget;
 
-	napi_complete(napi);
-	mlx4_en_arm_cq(priv, cq);
+	if (napi_complete_done(napi, work_done))
+		mlx4_en_arm_cq(priv, cq);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 630f15977f09..9f5603612960 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -737,8 +737,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
 			  int budget);
 int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget);
 int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget);
-bool mlx4_en_process_tx_cq(struct net_device *dev,
-			   struct mlx4_en_cq *cq, int napi_budget);
+int mlx4_en_process_tx_cq(struct net_device *dev,
+			  struct mlx4_en_cq *cq, int napi_budget);
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
 			 int index, u64 timestamp,
-- 
cgit v1.2.3


From 79d6e755a45486ffb14bf0ed752e6ace20334cda Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:13 +0300
Subject: net: ethernet: ti: cpts: use dev_yy() api for logs

Use dev_yy() API instead of pr_yy() for log outputs.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 729ce09dded9..445f445185df 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -71,7 +71,7 @@ static int cpts_purge_events(struct cpts *cpts)
 	}
 
 	if (removed)
-		pr_debug("cpts: event pool cleaned up %d\n", removed);
+		dev_dbg(cpts->dev, "cpts: event pool cleaned up %d\n", removed);
 	return removed ? 0 : -1;
 }
 
@@ -150,7 +150,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 			break;
 
 		if (list_empty(&cpts->pool) && cpts_purge_events(cpts)) {
-			pr_err("cpts: event pool empty\n");
+			dev_warn(cpts->dev, "cpts: event pool empty\n");
 			return -1;
 		}
 
@@ -178,7 +178,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		case CPTS_EV_HW:
 			break;
 		default:
-			pr_err("cpts: unknown event type\n");
+			dev_err(cpts->dev, "cpts: unknown event type\n");
 			break;
 		}
 		if (type == match)
@@ -196,7 +196,7 @@ static u64 cpts_systim_read(const struct cyclecounter *cc)
 
 	cpts_write32(cpts, TS_PUSH, ts_push);
 	if (cpts_fifo_read(cpts, CPTS_EV_PUSH))
-		pr_err("cpts: unable to obtain a time stamp\n");
+		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
 
 	list_for_each_safe(this, next, &cpts->events) {
 		event = list_entry(this, struct cpts_event, list);
@@ -307,8 +307,8 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
-	pr_debug("cpts overflow check at %lld.%09ld\n",
-		 (long long)ts.tv_sec, ts.tv_nsec);
+	dev_dbg(cpts->dev, "cpts overflow check at %lld.%09ld\n",
+		(long long)ts.tv_sec, ts.tv_nsec);
 	return (long)delay;
 }
 
-- 
cgit v1.2.3


From e66dccced0cfd59a4dc4c16409b713332b882fa6 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:14 +0300
Subject: net: ethernet: ti: cpts: separate hw counter read from timecounter

Now CPTS HW time reading code is implemented in timecounter->cyclecounter
.read() callback and performs following operations:
timecounter_read() ->cc.read() -> cpts_systim_read()
 - request current CPTS HW time CPTS_TS_PUSH.TS_PUSH = 1
 - poll CPTS FIFO for CPTS_EV_PUSH event with current HW timestamp

This approach need to be changed for the future switch to PTP PHC
.gettimex64() callback, which require to separate requesting current CPTS
HW time and processing CPTS FIFO. And for the follow up patch, which
improves .adjfreq() implementation.

This patch moves code accessing CPTS HW out of timecounter code as
following:
- convert HW timestamp of every CPTS event to PTP time (us) and store it as
part struct cpts_event;
- add CPTS context field to store current CPTS HW time (counter) value and
update it on CPTS_EV_PUSH reception;
- move code accessing CPTS HW out of timecounter code and use current CPTS
HW time (counter) from CPTS context instead;
- ensure timecounter->cycle_last is updated on CPTS_EV_PUSH reception.

After this change CPTS timecounter will only perform timekeeper role
without actually accessing CPTS HW.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 53 +++++++++++++++++++++---------------------
 drivers/net/ethernet/ti/cpts.h |  2 ++
 2 files changed, 29 insertions(+), 26 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 445f445185df..f40a864d8c36 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -112,10 +112,8 @@ static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 					(struct cpts_skb_cb_data *)skb->cb;
 
 		if (cpts_match(skb, class, seqid, mtype)) {
-			u64 ns = timecounter_cyc2time(&cpts->tc, event->low);
-
 			memset(&ssh, 0, sizeof(ssh));
-			ssh.hwtstamp = ns_to_ktime(ns);
+			ssh.hwtstamp = ns_to_ktime(event->timestamp);
 			skb_tstamp_tx(skb, &ssh);
 			found = true;
 			__skb_unlink(skb, &cpts->txq);
@@ -158,8 +156,16 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		event->tmo = jiffies + 2;
 		event->high = hi;
 		event->low = lo;
+		event->timestamp = timecounter_cyc2time(&cpts->tc, event->low);
 		type = event_type(event);
+
+		dev_dbg(cpts->dev, "CPTS_EV: %d high:%08X low:%08x\n",
+			type, event->high, event->low);
 		switch (type) {
+		case CPTS_EV_PUSH:
+			WRITE_ONCE(cpts->cur_timestamp, lo);
+			timecounter_read(&cpts->tc);
+			break;
 		case CPTS_EV_TX:
 			if (cpts_match_tx_ts(cpts, event)) {
 				/* if the new event matches an existing skb,
@@ -168,7 +174,6 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 				break;
 			}
 			/* fall through */
-		case CPTS_EV_PUSH:
 		case CPTS_EV_RX:
 			list_del_init(&event->list);
 			list_add_tail(&event->list, &cpts->events);
@@ -189,26 +194,17 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 
 static u64 cpts_systim_read(const struct cyclecounter *cc)
 {
-	u64 val = 0;
-	struct cpts_event *event;
-	struct list_head *this, *next;
 	struct cpts *cpts = container_of(cc, struct cpts, cc);
 
-	cpts_write32(cpts, TS_PUSH, ts_push);
-	if (cpts_fifo_read(cpts, CPTS_EV_PUSH))
-		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
+	return READ_ONCE(cpts->cur_timestamp);
+}
 
-	list_for_each_safe(this, next, &cpts->events) {
-		event = list_entry(this, struct cpts_event, list);
-		if (event_type(event) == CPTS_EV_PUSH) {
-			list_del_init(&event->list);
-			list_add(&event->list, &cpts->pool);
-			val = event->low;
-			break;
-		}
-	}
+static void cpts_update_cur_time(struct cpts *cpts, int match)
+{
+	cpts_write32(cpts, TS_PUSH, ts_push);
 
-	return val;
+	if (cpts_fifo_read(cpts, match) && match != -1)
+		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
 }
 
 /* PTP clock operations */
@@ -232,7 +228,7 @@ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 
 	spin_lock_irqsave(&cpts->lock, flags);
 
-	timecounter_read(&cpts->tc);
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
 
 	cpts->cc.mult = neg_adj ? mult - diff : mult + diff;
 
@@ -260,6 +256,9 @@ static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
 
 	spin_lock_irqsave(&cpts->lock, flags);
+
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
+
 	ns = timecounter_read(&cpts->tc);
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
@@ -294,11 +293,14 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 {
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
 	unsigned long delay = cpts->ov_check_period;
-	struct timespec64 ts;
 	unsigned long flags;
+	u64 ns;
 
 	spin_lock_irqsave(&cpts->lock, flags);
-	ts = ns_to_timespec64(timecounter_read(&cpts->tc));
+
+	cpts_update_cur_time(cpts, -1);
+
+	ns = timecounter_read(&cpts->tc);
 
 	if (!skb_queue_empty(&cpts->txq)) {
 		cpts_purge_txq(cpts);
@@ -307,8 +309,7 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
-	dev_dbg(cpts->dev, "cpts overflow check at %lld.%09ld\n",
-		(long long)ts.tv_sec, ts.tv_nsec);
+	dev_dbg(cpts->dev, "cpts overflow check at %lld\n", ns);
 	return (long)delay;
 }
 
@@ -390,7 +391,7 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 		seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
 		if (ev_type == event_type(event) &&
 		    cpts_match(skb, class, seqid, mtype)) {
-			ns = timecounter_cyc2time(&cpts->tc, event->low);
+			ns = event->timestamp;
 			list_del_init(&event->list);
 			list_add(&event->list, &cpts->pool);
 			break;
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index bb997c11ee15..32ecd1ce4d3b 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -94,6 +94,7 @@ struct cpts_event {
 	unsigned long tmo;
 	u32 high;
 	u32 low;
+	u64 timestamp;
 };
 
 struct cpts {
@@ -114,6 +115,7 @@ struct cpts {
 	struct cpts_event pool_data[CPTS_MAX_EVENTS];
 	unsigned long ov_check_period;
 	struct sk_buff_head txq;
+	u64 cur_timestamp;
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
-- 
cgit v1.2.3


From 0d6df3e613b74fe1a88de89cda63a0352e1dc4eb Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:15 +0300
Subject: net: ethernet: ti: cpts: move tc mult update in cpts_fifo_read()

Now CPTS driver .adjfreq() generates request to read CPTS current time
(CPTS_EV_PUSH) with intention to process all pending event using previous
frequency adjustment values before switching to the new ones. So
CPTS_EV_PUSH works as a marker to switch to the new frequency adjustment
values. Current code assumes that all job is done in .adjfreq(), but after
enabling IRQ this will not be true any more.

Hence save new frequency adjustment values (mult) and perform actual freq
adjustment in cpts_fifo_read() immediately after CPTS_EV_PUSH is received.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 8 ++++++--
 drivers/net/ethernet/ti/cpts.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index f40a864d8c36..a2974b542bed 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -165,6 +165,10 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		case CPTS_EV_PUSH:
 			WRITE_ONCE(cpts->cur_timestamp, lo);
 			timecounter_read(&cpts->tc);
+			if (cpts->mult_new) {
+				cpts->cc.mult = cpts->mult_new;
+				cpts->mult_new = 0;
+			}
 			break;
 		case CPTS_EV_TX:
 			if (cpts_match_tx_ts(cpts, event)) {
@@ -228,9 +232,9 @@ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 
 	spin_lock_irqsave(&cpts->lock, flags);
 
-	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
+	cpts->mult_new = neg_adj ? mult - diff : mult + diff;
 
-	cpts->cc.mult = neg_adj ? mult - diff : mult + diff;
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
 
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 32ecd1ce4d3b..421630049ee7 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -116,6 +116,7 @@ struct cpts {
 	unsigned long ov_check_period;
 	struct sk_buff_head txq;
 	u64 cur_timestamp;
+	u32 mult_new;
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
-- 
cgit v1.2.3


From 856e59ab7e6d3c85ee739f3f53341d47c88d454e Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:16 +0300
Subject: net: ethernet: ti: cpts: switch to use new .gettimex64() interface

The CPTS HW latches and saves CPTS counter value in CPTS fifo immediately
after writing to CPSW_CPTS_PUSH.TS_PUSH (bit 0), so the total time that the
driver needs to read the CPTS timestamp is the time required CPSW_CPTS_PUSH
write to actually reach HW.

Hence switch CPTS driver to implement new .gettimex64() callback for more
precise measurement of the offset between a PHC and the system clock which
is measured as time between
  write(CPSW_CPTS_PUSH)
  read(CPSW_CPTS_PUSH)

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index a2974b542bed..1f738bb3df74 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -203,9 +203,13 @@ static u64 cpts_systim_read(const struct cyclecounter *cc)
 	return READ_ONCE(cpts->cur_timestamp);
 }
 
-static void cpts_update_cur_time(struct cpts *cpts, int match)
+static void cpts_update_cur_time(struct cpts *cpts, int match,
+				 struct ptp_system_timestamp *sts)
 {
+	ptp_read_system_prets(sts);
 	cpts_write32(cpts, TS_PUSH, ts_push);
+	cpts_read32(cpts, ts_push);
+	ptp_read_system_postts(sts);
 
 	if (cpts_fifo_read(cpts, match) && match != -1)
 		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
@@ -234,7 +238,7 @@ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 
 	cpts->mult_new = neg_adj ? mult - diff : mult + diff;
 
-	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL);
 
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
@@ -253,15 +257,17 @@ static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int cpts_ptp_gettimeex(struct ptp_clock_info *ptp,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
 {
-	u64 ns;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	unsigned long flags;
+	u64 ns;
 
 	spin_lock_irqsave(&cpts->lock, flags);
 
-	cpts_update_cur_time(cpts, CPTS_EV_PUSH);
+	cpts_update_cur_time(cpts, CPTS_EV_PUSH, sts);
 
 	ns = timecounter_read(&cpts->tc);
 	spin_unlock_irqrestore(&cpts->lock, flags);
@@ -302,7 +308,7 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 
 	spin_lock_irqsave(&cpts->lock, flags);
 
-	cpts_update_cur_time(cpts, -1);
+	cpts_update_cur_time(cpts, -1, NULL);
 
 	ns = timecounter_read(&cpts->tc);
 
@@ -326,7 +332,7 @@ static const struct ptp_clock_info cpts_info = {
 	.pps		= 0,
 	.adjfreq	= cpts_ptp_adjfreq,
 	.adjtime	= cpts_ptp_adjtime,
-	.gettime64	= cpts_ptp_gettime,
+	.gettimex64	= cpts_ptp_gettimeex,
 	.settime64	= cpts_ptp_settime,
 	.enable		= cpts_ptp_enable,
 	.do_aux_work	= cpts_overflow_check,
-- 
cgit v1.2.3


From 3bfd41b57811d76412af57f4884e28ad78c2ab2f Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:17 +0300
Subject: net: ethernet: ti: cpts: optimize packet to event matching

Now the CPTS driver performs packet (skb) parsing every time when it needs
to match packet to CPTS event (including ptp_classify_raw() calls).

This patch optimizes matching process by parsing packet only once upon
arrival and stores PTP specific data in skb->cb using the same fromat as in
CPTS HW event. As result, all future matching reduces to comparing two u32
values.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 91 +++++++++++++++++++++++++++---------------
 1 file changed, 58 insertions(+), 33 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 1f738bb3df74..6efb809d58ed 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -23,15 +23,13 @@
 #define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */
 
 struct cpts_skb_cb_data {
+	u32 skb_mtype_seqid;
 	unsigned long tmo;
 };
 
 #define cpts_read32(c, r)	readl_relaxed(&c->reg->r)
 #define cpts_write32(c, v, r)	writel_relaxed(v, &c->reg->r)
 
-static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
-		      u16 ts_seqid, u8 ts_msgtype);
-
 static int event_expired(struct cpts_event *event)
 {
 	return time_after(jiffies, event->tmo);
@@ -97,29 +95,29 @@ static void cpts_purge_txq(struct cpts *cpts)
 static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 {
 	struct sk_buff *skb, *tmp;
-	u16 seqid;
-	u8 mtype;
 	bool found = false;
+	u32 mtype_seqid;
 
-	mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK;
-	seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
+	mtype_seqid = event->high &
+		      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
+		       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
+		       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
 
 	/* no need to grab txq.lock as access is always done under cpts->lock */
 	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
 		struct skb_shared_hwtstamps ssh;
-		unsigned int class = ptp_classify_raw(skb);
 		struct cpts_skb_cb_data *skb_cb =
 					(struct cpts_skb_cb_data *)skb->cb;
 
-		if (cpts_match(skb, class, seqid, mtype)) {
+		if (mtype_seqid == skb_cb->skb_mtype_seqid) {
 			memset(&ssh, 0, sizeof(ssh));
 			ssh.hwtstamp = ns_to_ktime(event->timestamp);
 			skb_tstamp_tx(skb, &ssh);
 			found = true;
 			__skb_unlink(skb, &cpts->txq);
 			dev_consume_skb_any(skb);
-			dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n",
-				mtype, seqid);
+			dev_dbg(cpts->dev, "match tx timestamp mtype_seqid %08x\n",
+				mtype_seqid);
 			break;
 		}
 
@@ -338,12 +336,15 @@ static const struct ptp_clock_info cpts_info = {
 	.do_aux_work	= cpts_overflow_check,
 };
 
-static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
-		      u16 ts_seqid, u8 ts_msgtype)
+static int cpts_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid)
 {
-	u16 *seqid;
-	unsigned int offset = 0;
+	unsigned int ptp_class = ptp_classify_raw(skb);
 	u8 *msgtype, *data = skb->data;
+	unsigned int offset = 0;
+	u16 *seqid;
+
+	if (ptp_class == PTP_CLASS_NONE)
+		return 0;
 
 	if (ptp_class & PTP_CLASS_VLAN)
 		offset += VLAN_HLEN;
@@ -371,22 +372,20 @@ static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
 		msgtype = data + offset;
 
 	seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+	*mtype_seqid = (*msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT;
+	*mtype_seqid |= (ntohs(*seqid) & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT;
 
-	return (ts_msgtype == (*msgtype & 0xf) && ts_seqid == ntohs(*seqid));
+	return 1;
 }
 
-static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
+static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb,
+			int ev_type, u32 skb_mtype_seqid)
 {
-	u64 ns = 0;
-	struct cpts_event *event;
 	struct list_head *this, *next;
-	unsigned int class = ptp_classify_raw(skb);
+	struct cpts_event *event;
 	unsigned long flags;
-	u16 seqid;
-	u8 mtype;
-
-	if (class == PTP_CLASS_NONE)
-		return 0;
+	u32 mtype_seqid;
+	u64 ns = 0;
 
 	spin_lock_irqsave(&cpts->lock, flags);
 	cpts_fifo_read(cpts, -1);
@@ -397,10 +396,13 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 			list_add(&event->list, &cpts->pool);
 			continue;
 		}
-		mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK;
-		seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
-		if (ev_type == event_type(event) &&
-		    cpts_match(skb, class, seqid, mtype)) {
+
+		mtype_seqid = event->high &
+			      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
+			       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
+			       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
+
+		if (mtype_seqid == skb_mtype_seqid) {
 			ns = event->timestamp;
 			list_del_init(&event->list);
 			list_add(&event->list, &cpts->pool);
@@ -427,10 +429,21 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
-	u64 ns;
+	struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb;
 	struct skb_shared_hwtstamps *ssh;
+	int ret;
+	u64 ns;
+
+	ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
+		return;
+
+	skb_cb->skb_mtype_seqid |= (CPTS_EV_RX << EVENT_TYPE_SHIFT);
 
-	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX);
+	dev_dbg(cpts->dev, "%s mtype seqid %08x\n",
+		__func__, skb_cb->skb_mtype_seqid);
+
+	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX, skb_cb->skb_mtype_seqid);
 	if (!ns)
 		return;
 	ssh = skb_hwtstamps(skb);
@@ -441,12 +454,24 @@ EXPORT_SYMBOL_GPL(cpts_rx_timestamp);
 
 void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
-	u64 ns;
+	struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb;
 	struct skb_shared_hwtstamps ssh;
+	int ret;
+	u64 ns;
 
 	if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
 		return;
-	ns = cpts_find_ts(cpts, skb, CPTS_EV_TX);
+
+	ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
+		return;
+
+	skb_cb->skb_mtype_seqid |= (CPTS_EV_TX << EVENT_TYPE_SHIFT);
+
+	dev_dbg(cpts->dev, "%s mtype seqid %08x\n",
+		__func__, skb_cb->skb_mtype_seqid);
+
+	ns = cpts_find_ts(cpts, skb, CPTS_EV_TX, skb_cb->skb_mtype_seqid);
 	if (!ns)
 		return;
 	memset(&ssh, 0, sizeof(ssh));
-- 
cgit v1.2.3


From c8f8e47efe66dae775b617982e47a4564d7c4dda Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:18 +0300
Subject: net: ethernet: ti: cpts: move tx timestamp processing to ptp worker
 only

Now the tx timestamp processing happens from different contexts - softirq
and thread/PTP worker. Enabling IRQ will add one more hard_irq context.
This makes over all defered TX timestamp processing and locking
overcomplicated. Move tx timestamp processing to PTP worker always instead.

napi_rx->cpts_tx_timestamp
 if ptp_packet then
    push to txq
    ptp_schedule_worker()

do_aux_work->cpts_overflow_check
 cpts_process_events()

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 165 +++++++++++++++++++++++------------------
 1 file changed, 94 insertions(+), 71 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 6efb809d58ed..55ba6b425fb5 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -21,6 +21,8 @@
 #include "cpts.h"
 
 #define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */
+#define CPTS_SKB_RX_TX_TMO 100 /*ms */
+#define CPTS_EVENT_RX_TX_TIMEOUT (100) /* ms */
 
 struct cpts_skb_cb_data {
 	u32 skb_mtype_seqid;
@@ -92,46 +94,6 @@ static void cpts_purge_txq(struct cpts *cpts)
 		dev_dbg(cpts->dev, "txq cleaned up %d\n", removed);
 }
 
-static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
-{
-	struct sk_buff *skb, *tmp;
-	bool found = false;
-	u32 mtype_seqid;
-
-	mtype_seqid = event->high &
-		      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
-		       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
-		       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
-
-	/* no need to grab txq.lock as access is always done under cpts->lock */
-	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
-		struct skb_shared_hwtstamps ssh;
-		struct cpts_skb_cb_data *skb_cb =
-					(struct cpts_skb_cb_data *)skb->cb;
-
-		if (mtype_seqid == skb_cb->skb_mtype_seqid) {
-			memset(&ssh, 0, sizeof(ssh));
-			ssh.hwtstamp = ns_to_ktime(event->timestamp);
-			skb_tstamp_tx(skb, &ssh);
-			found = true;
-			__skb_unlink(skb, &cpts->txq);
-			dev_consume_skb_any(skb);
-			dev_dbg(cpts->dev, "match tx timestamp mtype_seqid %08x\n",
-				mtype_seqid);
-			break;
-		}
-
-		if (time_after(jiffies, skb_cb->tmo)) {
-			/* timeout any expired skbs over 1s */
-			dev_dbg(cpts->dev, "expiring tx timestamp from txq\n");
-			__skb_unlink(skb, &cpts->txq);
-			dev_consume_skb_any(skb);
-		}
-	}
-
-	return found;
-}
-
 /*
  * Returns zero if matching event type was found.
  */
@@ -151,7 +113,6 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		}
 
 		event = list_first_entry(&cpts->pool, struct cpts_event, list);
-		event->tmo = jiffies + 2;
 		event->high = hi;
 		event->low = lo;
 		event->timestamp = timecounter_cyc2time(&cpts->tc, event->low);
@@ -169,14 +130,10 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 			}
 			break;
 		case CPTS_EV_TX:
-			if (cpts_match_tx_ts(cpts, event)) {
-				/* if the new event matches an existing skb,
-				 * then don't queue it
-				 */
-				break;
-			}
-			/* fall through */
 		case CPTS_EV_RX:
+			event->tmo = jiffies +
+				msecs_to_jiffies(CPTS_EVENT_RX_TX_TIMEOUT);
+
 			list_del_init(&event->list);
 			list_add_tail(&event->list, &cpts->events);
 			break;
@@ -297,6 +254,84 @@ static int cpts_ptp_enable(struct ptp_clock_info *ptp,
 	return -EOPNOTSUPP;
 }
 
+static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
+{
+	struct sk_buff_head txq_list;
+	struct sk_buff *skb, *tmp;
+	unsigned long flags;
+	bool found = false;
+	u32 mtype_seqid;
+
+	mtype_seqid = event->high &
+		      ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) |
+		       (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) |
+		       (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT));
+
+	__skb_queue_head_init(&txq_list);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice_init(&cpts->txq, &txq_list);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	skb_queue_walk_safe(&txq_list, skb, tmp) {
+		struct skb_shared_hwtstamps ssh;
+		struct cpts_skb_cb_data *skb_cb =
+					(struct cpts_skb_cb_data *)skb->cb;
+
+		if (mtype_seqid == skb_cb->skb_mtype_seqid) {
+			memset(&ssh, 0, sizeof(ssh));
+			ssh.hwtstamp = ns_to_ktime(event->timestamp);
+			skb_tstamp_tx(skb, &ssh);
+			found = true;
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+			dev_dbg(cpts->dev, "match tx timestamp mtype_seqid %08x\n",
+				mtype_seqid);
+			break;
+		}
+
+		if (time_after(jiffies, skb_cb->tmo)) {
+			/* timeout any expired skbs over 1s */
+			dev_dbg(cpts->dev, "expiring tx timestamp from txq\n");
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+		}
+	}
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice(&txq_list, &cpts->txq);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	return found;
+}
+
+static void cpts_process_events(struct cpts *cpts)
+{
+	struct list_head *this, *next;
+	struct cpts_event *event;
+	LIST_HEAD(events_free);
+	unsigned long flags;
+	LIST_HEAD(events);
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_init(&cpts->events, &events);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	list_for_each_safe(this, next, &events) {
+		event = list_entry(this, struct cpts_event, list);
+		if (cpts_match_tx_ts(cpts, event) ||
+		    time_after(jiffies, event->tmo)) {
+			list_del_init(&event->list);
+			list_add(&event->list, &events_free);
+		}
+	}
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_tail(&events, &cpts->events);
+	list_splice_tail(&events_free, &cpts->pool);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+}
+
 static long cpts_overflow_check(struct ptp_clock_info *ptp)
 {
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
@@ -305,17 +340,20 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	u64 ns;
 
 	spin_lock_irqsave(&cpts->lock, flags);
-
 	cpts_update_cur_time(cpts, -1, NULL);
+	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	ns = timecounter_read(&cpts->tc);
 
+	cpts_process_events(cpts);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
 	if (!skb_queue_empty(&cpts->txq)) {
 		cpts_purge_txq(cpts);
 		if (!skb_queue_empty(&cpts->txq))
 			delay = CPTS_SKB_TX_WORK_TIMEOUT;
 	}
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
 
 	dev_dbg(cpts->dev, "cpts overflow check at %lld\n", ns);
 	return (long)delay;
@@ -409,19 +447,6 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb,
 			break;
 		}
 	}
-
-	if (ev_type == CPTS_EV_TX && !ns) {
-		struct cpts_skb_cb_data *skb_cb =
-				(struct cpts_skb_cb_data *)skb->cb;
-		/* Not found, add frame to queue for processing later.
-		 * The periodic FIFO check will handle this.
-		 */
-		skb_get(skb);
-		/* get the timestamp for timeouts */
-		skb_cb->tmo = jiffies + msecs_to_jiffies(100);
-		__skb_queue_tail(&cpts->txq, skb);
-		ptp_schedule_worker(cpts->clock, 0);
-	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	return ns;
@@ -455,9 +480,7 @@ EXPORT_SYMBOL_GPL(cpts_rx_timestamp);
 void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb;
-	struct skb_shared_hwtstamps ssh;
 	int ret;
-	u64 ns;
 
 	if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
 		return;
@@ -471,12 +494,12 @@ void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 	dev_dbg(cpts->dev, "%s mtype seqid %08x\n",
 		__func__, skb_cb->skb_mtype_seqid);
 
-	ns = cpts_find_ts(cpts, skb, CPTS_EV_TX, skb_cb->skb_mtype_seqid);
-	if (!ns)
-		return;
-	memset(&ssh, 0, sizeof(ssh));
-	ssh.hwtstamp = ns_to_ktime(ns);
-	skb_tstamp_tx(skb, &ssh);
+	/* Always defer TX TS processing to PTP worker */
+	skb_get(skb);
+	/* get the timestamp for timeouts */
+	skb_cb->tmo = jiffies + msecs_to_jiffies(CPTS_SKB_RX_TX_TMO);
+	skb_queue_tail(&cpts->txq, skb);
+	ptp_schedule_worker(cpts->clock, 0);
 }
 EXPORT_SYMBOL_GPL(cpts_tx_timestamp);
 
-- 
cgit v1.2.3


From ba10742840fbc6e475dc05c7515fd91b7c88e1b2 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:19 +0300
Subject: net: ethernet: ti: cpts: rework locking

Now spinlock is used to synchronize everything which is not required. Add
mutex and use to sync access to PTP interface and PTP worker and use
spinlock only to sync FIFO/events processing.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 53 ++++++++++++++++++++++++------------------
 drivers/net/ethernet/ti/cpts.h |  3 ++-
 2 files changed, 32 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 55ba6b425fb5..8db9efdf1708 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -99,9 +99,12 @@ static void cpts_purge_txq(struct cpts *cpts)
  */
 static int cpts_fifo_read(struct cpts *cpts, int match)
 {
+	struct cpts_event *event;
+	unsigned long flags;
 	int i, type = -1;
 	u32 hi, lo;
-	struct cpts_event *event;
+
+	spin_lock_irqsave(&cpts->lock, flags);
 
 	for (i = 0; i < CPTS_FIFO_DEPTH; i++) {
 		if (cpts_fifo_pop(cpts, &hi, &lo))
@@ -109,7 +112,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 
 		if (list_empty(&cpts->pool) && cpts_purge_events(cpts)) {
 			dev_warn(cpts->dev, "cpts: event pool empty\n");
-			return -1;
+			break;
 		}
 
 		event = list_first_entry(&cpts->pool, struct cpts_event, list);
@@ -148,6 +151,9 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		if (type == match)
 			break;
 	}
+
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
 	return type == match ? 0 : -1;
 }
 
@@ -161,10 +167,15 @@ static u64 cpts_systim_read(const struct cyclecounter *cc)
 static void cpts_update_cur_time(struct cpts *cpts, int match,
 				 struct ptp_system_timestamp *sts)
 {
+	unsigned long flags;
+
+	/* use spin_lock_irqsave() here as it has to run very fast */
+	spin_lock_irqsave(&cpts->lock, flags);
 	ptp_read_system_prets(sts);
 	cpts_write32(cpts, TS_PUSH, ts_push);
 	cpts_read32(cpts, ts_push);
 	ptp_read_system_postts(sts);
+	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	if (cpts_fifo_read(cpts, match) && match != -1)
 		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
@@ -174,11 +185,10 @@ static void cpts_update_cur_time(struct cpts *cpts, int match,
 
 static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 {
-	u64 adj;
-	u32 diff, mult;
-	int neg_adj = 0;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	int neg_adj = 0;
+	u32 diff, mult;
+	u64 adj;
 
 	if (ppb < 0) {
 		neg_adj = 1;
@@ -189,25 +199,23 @@ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	adj *= ppb;
 	diff = div_u64(adj, 1000000000ULL);
 
-	spin_lock_irqsave(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 
 	cpts->mult_new = neg_adj ? mult - diff : mult + diff;
 
 	cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL);
 
-	spin_unlock_irqrestore(&cpts->lock, flags);
-
+	mutex_unlock(&cpts->ptp_clk_mutex);
 	return 0;
 }
 
 static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
 
-	spin_lock_irqsave(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 	timecounter_adjtime(&cpts->tc, delta);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
 	return 0;
 }
@@ -217,15 +225,14 @@ static int cpts_ptp_gettimeex(struct ptp_clock_info *ptp,
 			      struct ptp_system_timestamp *sts)
 {
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
-	unsigned long flags;
 	u64 ns;
 
-	spin_lock_irqsave(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 
 	cpts_update_cur_time(cpts, CPTS_EV_PUSH, sts);
 
 	ns = timecounter_read(&cpts->tc);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
 	*ts = ns_to_timespec64(ns);
 
@@ -235,15 +242,14 @@ static int cpts_ptp_gettimeex(struct ptp_clock_info *ptp,
 static int cpts_ptp_settime(struct ptp_clock_info *ptp,
 			    const struct timespec64 *ts)
 {
-	u64 ns;
-	unsigned long flags;
 	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	u64 ns;
 
 	ns = timespec64_to_ns(ts);
 
-	spin_lock_irqsave(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 	timecounter_init(&cpts->tc, &cpts->cc, ns);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 
 	return 0;
 }
@@ -339,10 +345,9 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	unsigned long flags;
 	u64 ns;
 
-	spin_lock_irqsave(&cpts->lock, flags);
-	cpts_update_cur_time(cpts, -1, NULL);
-	spin_unlock_irqrestore(&cpts->lock, flags);
+	mutex_lock(&cpts->ptp_clk_mutex);
 
+	cpts_update_cur_time(cpts, -1, NULL);
 	ns = timecounter_read(&cpts->tc);
 
 	cpts_process_events(cpts);
@@ -356,6 +361,7 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	spin_unlock_irqrestore(&cpts->txq.lock, flags);
 
 	dev_dbg(cpts->dev, "cpts overflow check at %lld\n", ns);
+	mutex_unlock(&cpts->ptp_clk_mutex);
 	return (long)delay;
 }
 
@@ -425,8 +431,8 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb,
 	u32 mtype_seqid;
 	u64 ns = 0;
 
-	spin_lock_irqsave(&cpts->lock, flags);
 	cpts_fifo_read(cpts, -1);
+	spin_lock_irqsave(&cpts->lock, flags);
 	list_for_each_safe(this, next, &cpts->events) {
 		event = list_entry(this, struct cpts_event, list);
 		if (event_expired(event)) {
@@ -703,6 +709,7 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 	cpts->dev = dev;
 	cpts->reg = (struct cpsw_cpts __iomem *)regs;
 	spin_lock_init(&cpts->lock);
+	mutex_init(&cpts->ptp_clk_mutex);
 
 	ret = cpts_of_parse(cpts, node);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 421630049ee7..f16e14d67f5f 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -104,7 +104,7 @@ struct cpts {
 	int rx_enable;
 	struct ptp_clock_info info;
 	struct ptp_clock *clock;
-	spinlock_t lock; /* protects time registers */
+	spinlock_t lock; /* protects fifo/events */
 	u32 cc_mult; /* for the nominal frequency */
 	struct cyclecounter cc;
 	struct timecounter tc;
@@ -117,6 +117,7 @@ struct cpts {
 	struct sk_buff_head txq;
 	u64 cur_timestamp;
 	u32 mult_new;
+	struct mutex ptp_clk_mutex; /* sync PTP interface and worker */
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
-- 
cgit v1.2.3


From 85624412a03dc61eabddeb1cfbbc8325e3544694 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:20 +0300
Subject: net: ethernet: ti: cpts: add irq support

Add CPTS IRQ support, but do not enable it. By default, the CPTS driver
will continue working using polling mode which is required for CPTS to
continue working on platforms other than CPSW, like Keystone 2.

The CPTS IRQ support is required to enable support for HW_TS_PUSH events.
The CPSW CPTS IRQ and HW_TS_PUSH events support will be enabled in follow
up patches.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 23 ++++++++++++++++++++++-
 drivers/net/ethernet/ti/cpts.h | 16 ++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 8db9efdf1708..339796c87bf6 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -99,6 +99,7 @@ static void cpts_purge_txq(struct cpts *cpts)
  */
 static int cpts_fifo_read(struct cpts *cpts, int match)
 {
+	bool need_schedule = false;
 	struct cpts_event *event;
 	unsigned long flags;
 	int i, type = -1;
@@ -131,6 +132,8 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 				cpts->cc.mult = cpts->mult_new;
 				cpts->mult_new = 0;
 			}
+			if (!cpts->irq_poll)
+				complete(&cpts->ts_push_complete);
 			break;
 		case CPTS_EV_TX:
 		case CPTS_EV_RX:
@@ -139,6 +142,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 
 			list_del_init(&event->list);
 			list_add_tail(&event->list, &cpts->events);
+			need_schedule = true;
 			break;
 		case CPTS_EV_ROLL:
 		case CPTS_EV_HALF:
@@ -154,9 +158,18 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
+	if (!cpts->irq_poll && need_schedule)
+		ptp_schedule_worker(cpts->clock, 0);
+
 	return type == match ? 0 : -1;
 }
 
+void cpts_misc_interrupt(struct cpts *cpts)
+{
+	cpts_fifo_read(cpts, -1);
+}
+EXPORT_SYMBOL_GPL(cpts_misc_interrupt);
+
 static u64 cpts_systim_read(const struct cyclecounter *cc)
 {
 	struct cpts *cpts = container_of(cc, struct cpts, cc);
@@ -169,6 +182,8 @@ static void cpts_update_cur_time(struct cpts *cpts, int match,
 {
 	unsigned long flags;
 
+	reinit_completion(&cpts->ts_push_complete);
+
 	/* use spin_lock_irqsave() here as it has to run very fast */
 	spin_lock_irqsave(&cpts->lock, flags);
 	ptp_read_system_prets(sts);
@@ -177,8 +192,12 @@ static void cpts_update_cur_time(struct cpts *cpts, int match,
 	ptp_read_system_postts(sts);
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
-	if (cpts_fifo_read(cpts, match) && match != -1)
+	if (cpts->irq_poll && cpts_fifo_read(cpts, match) && match != -1)
 		dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n");
+
+	if (!cpts->irq_poll &&
+	    !wait_for_completion_timeout(&cpts->ts_push_complete, HZ))
+		dev_err(cpts->dev, "cpts: obtain a time stamp timeout\n");
 }
 
 /* PTP clock operations */
@@ -708,8 +727,10 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 
 	cpts->dev = dev;
 	cpts->reg = (struct cpsw_cpts __iomem *)regs;
+	cpts->irq_poll = true;
 	spin_lock_init(&cpts->lock);
 	mutex_init(&cpts->ptp_clk_mutex);
+	init_completion(&cpts->ts_push_complete);
 
 	ret = cpts_of_parse(cpts, node);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index f16e14d67f5f..473d0622e861 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -118,6 +118,8 @@ struct cpts {
 	u64 cur_timestamp;
 	u32 mult_new;
 	struct mutex ptp_clk_mutex; /* sync PTP interface and worker */
+	bool irq_poll;
+	struct completion	ts_push_complete;
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
@@ -127,6 +129,7 @@ void cpts_unregister(struct cpts *cpts);
 struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 			 struct device_node *node);
 void cpts_release(struct cpts *cpts);
+void cpts_misc_interrupt(struct cpts *cpts);
 
 static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
@@ -138,6 +141,11 @@ static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 	return true;
 }
 
+static inline void cpts_set_irqpoll(struct cpts *cpts, bool en)
+{
+	cpts->irq_poll = en;
+}
+
 #else
 struct cpts;
 
@@ -173,6 +181,14 @@ static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	return false;
 }
+
+static inline void cpts_misc_interrupt(struct cpts *cpts)
+{
+}
+
+static inline void cpts_set_irqpoll(struct cpts *cpts, bool en)
+{
+}
 #endif
 
 
-- 
cgit v1.2.3


From b78aba495df0eaee4f4a779b2354d6e2a43a3d70 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:21 +0300
Subject: net: ethernet: ti: cpts: add support for HW_TS_PUSH events

Hence CPTS IRQ support is in place the W_TS_PUSH events can be added.
PWM capable DmTimers can be used to generete input signals for CPTS on TI
AM335x/AM437x/DRA7 SoCs to be timestamped:
AM335x/AM437x: timer4 - timer7
DRA7/AM57xx: timer13 - timer16

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_priv.c   |  5 +++-
 drivers/net/ethernet/ti/cpts.c        | 49 ++++++++++++++++++++++++++++++++++-
 drivers/net/ethernet/ti/cpts.h        |  5 ++--
 drivers/net/ethernet/ti/netcp_ethss.c |  3 ++-
 4 files changed, 57 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 97a058ca60ac..099208927400 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -28,6 +28,8 @@
 #include "cpsw_sl.h"
 #include "davinci_cpdma.h"
 
+#define CPTS_N_ETX_TS 4
+
 int (*cpsw_slave_index)(struct cpsw_common *cpsw, struct cpsw_priv *priv);
 
 void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -522,7 +524,8 @@ int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs,
 	if (!cpts_node)
 		cpts_node = cpsw->dev->of_node;
 
-	cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpts_node);
+	cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpts_node,
+				 CPTS_N_ETX_TS);
 	if (IS_ERR(cpsw->cpts)) {
 		ret = PTR_ERR(cpsw->cpts);
 		cpdma_ctlr_destroy(cpsw->dma);
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 339796c87bf6..7c55d395de2c 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -32,6 +32,11 @@ struct cpts_skb_cb_data {
 #define cpts_read32(c, r)	readl_relaxed(&c->reg->r)
 #define cpts_write32(c, v, r)	writel_relaxed(v, &c->reg->r)
 
+static int cpts_event_port(struct cpts_event *event)
+{
+	return (event->high >> PORT_NUMBER_SHIFT) & PORT_NUMBER_MASK;
+}
+
 static int event_expired(struct cpts_event *event)
 {
 	return time_after(jiffies, event->tmo);
@@ -99,6 +104,7 @@ static void cpts_purge_txq(struct cpts *cpts)
  */
 static int cpts_fifo_read(struct cpts *cpts, int match)
 {
+	struct ptp_clock_event pevent;
 	bool need_schedule = false;
 	struct cpts_event *event;
 	unsigned long flags;
@@ -146,7 +152,12 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 			break;
 		case CPTS_EV_ROLL:
 		case CPTS_EV_HALF:
+			break;
 		case CPTS_EV_HW:
+			pevent.timestamp = event->timestamp;
+			pevent.type = PTP_CLOCK_EXTTS;
+			pevent.index = cpts_event_port(event) - 1;
+			ptp_clock_event(cpts->clock, &pevent);
 			break;
 		default:
 			dev_err(cpts->dev, "cpts: unknown event type\n");
@@ -273,9 +284,42 @@ static int cpts_ptp_settime(struct ptp_clock_info *ptp,
 	return 0;
 }
 
+static int cpts_extts_enable(struct cpts *cpts, u32 index, int on)
+{
+	u32 v;
+
+	if (((cpts->hw_ts_enable & BIT(index)) >> index) == on)
+		return 0;
+
+	mutex_lock(&cpts->ptp_clk_mutex);
+
+	v = cpts_read32(cpts, control);
+	if (on) {
+		v |= BIT(8 + index);
+		cpts->hw_ts_enable |= BIT(index);
+	} else {
+		v &= ~BIT(8 + index);
+		cpts->hw_ts_enable &= ~BIT(index);
+	}
+	cpts_write32(cpts, v, control);
+
+	mutex_unlock(&cpts->ptp_clk_mutex);
+
+	return 0;
+}
+
 static int cpts_ptp_enable(struct ptp_clock_info *ptp,
 			   struct ptp_clock_request *rq, int on)
 {
+	struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return cpts_extts_enable(cpts, rq->extts.index, on);
+	default:
+		break;
+	}
+
 	return -EOPNOTSUPP;
 }
 
@@ -716,7 +760,7 @@ of_error:
 }
 
 struct cpts *cpts_create(struct device *dev, void __iomem *regs,
-			 struct device_node *node)
+			 struct device_node *node, u32 n_ext_ts)
 {
 	struct cpts *cpts;
 	int ret;
@@ -755,6 +799,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 	cpts->cc.mask = CLOCKSOURCE_MASK(32);
 	cpts->info = cpts_info;
 
+	if (n_ext_ts)
+		cpts->info.n_ext_ts = n_ext_ts;
+
 	cpts_calc_mult_shift(cpts);
 	/* save cc.mult original value as it can be modified
 	 * by cpts_ptp_adjfreq().
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 473d0622e861..07222f651d2e 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -120,6 +120,7 @@ struct cpts {
 	struct mutex ptp_clk_mutex; /* sync PTP interface and worker */
 	bool irq_poll;
 	struct completion	ts_push_complete;
+	u32 hw_ts_enable;
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
@@ -127,7 +128,7 @@ void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb);
 int cpts_register(struct cpts *cpts);
 void cpts_unregister(struct cpts *cpts);
 struct cpts *cpts_create(struct device *dev, void __iomem *regs,
-			 struct device_node *node);
+			 struct device_node *node, u32 n_ext_ts);
 void cpts_release(struct cpts *cpts);
 void cpts_misc_interrupt(struct cpts *cpts);
 
@@ -158,7 +159,7 @@ static inline void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 
 static inline
 struct cpts *cpts_create(struct device *dev, void __iomem *regs,
-			 struct device_node *node)
+			 struct device_node *node, u32 n_ext_ts)
 {
 	return NULL;
 }
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index fb36115e9c51..9d6e27fb710e 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3716,7 +3716,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	if (!cpts_node)
 		cpts_node = of_node_get(node);
 
-	gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg, cpts_node);
+	gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg,
+				    cpts_node, 0);
 	of_node_put(cpts_node);
 	if (IS_ENABLED(CONFIG_TI_CPTS) && IS_ERR(gbe_dev->cpts)) {
 		ret = PTR_ERR(gbe_dev->cpts);
-- 
cgit v1.2.3


From 84ea9c0a95d7b3e554d6c3d7d719cc57be22e7ad Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 23 Apr 2020 17:20:22 +0300
Subject: net: ethernet: ti: cpsw: enable cpts irq

The CPSW misc IRQ need be enabled for CPTS event_pend IRQs processing. This
patch adds corresponding support to CPSW driver.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c      | 21 +++++++++++++++++++++
 drivers/net/ethernet/ti/cpsw_new.c  | 20 ++++++++++++++++++++
 drivers/net/ethernet/ti/cpsw_priv.c | 12 ++++++++++++
 drivers/net/ethernet/ti/cpsw_priv.h |  2 ++
 4 files changed, 55 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c2c5bf87da01..09f98fa2fb4e 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1569,6 +1569,12 @@ static int cpsw_probe(struct platform_device *pdev)
 		return irq;
 	cpsw->irqs_table[1] = irq;
 
+	/* get misc irq*/
+	irq = platform_get_irq(pdev, 3);
+	if (irq <= 0)
+		return irq;
+	cpsw->misc_irq = irq;
+
 	/*
 	 * This may be required here for child devices.
 	 */
@@ -1703,6 +1709,21 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_unregister_netdev_ret;
 	}
 
+	if (!cpsw->cpts)
+		goto skip_cpts;
+
+	ret = devm_request_irq(&pdev->dev, cpsw->misc_irq, cpsw_misc_interrupt,
+			       0, dev_name(&pdev->dev), cpsw);
+	if (ret < 0) {
+		dev_err(dev, "error attaching misc irq (%d)\n", ret);
+		goto clean_unregister_netdev_ret;
+	}
+
+	/* Enable misc CPTS evnt_pend IRQ */
+	cpts_set_irqpoll(cpsw->cpts, false);
+	writel(0x10, &cpsw->wr_regs->misc_en);
+
+skip_cpts:
 	cpsw_notice(priv, probe,
 		    "initialized device (regs %pa, irq %d, pool size %d)\n",
 		    &ss_res->start, cpsw->irqs_table[0], descs_pool_size);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 9209e613257d..33c8dd686206 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1896,6 +1896,11 @@ static int cpsw_probe(struct platform_device *pdev)
 		return irq;
 	cpsw->irqs_table[1] = irq;
 
+	irq = platform_get_irq_byname(pdev, "misc");
+	if (irq <= 0)
+		return irq;
+	cpsw->misc_irq = irq;
+
 	platform_set_drvdata(pdev, cpsw);
 	/* This may be required here for child devices. */
 	pm_runtime_enable(dev);
@@ -1975,6 +1980,21 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_unregister_netdev;
 	}
 
+	if (!cpsw->cpts)
+		goto skip_cpts;
+
+	ret = devm_request_irq(dev, cpsw->misc_irq, cpsw_misc_interrupt,
+			       0, dev_name(&pdev->dev), cpsw);
+	if (ret < 0) {
+		dev_err(dev, "error attaching misc irq (%d)\n", ret);
+		goto clean_unregister_netdev;
+	}
+
+	/* Enable misc CPTS evnt_pend IRQ */
+	cpts_set_irqpoll(cpsw->cpts, false);
+	writel(0x10, &cpsw->wr_regs->misc_en);
+
+skip_cpts:
 	ret = cpsw_register_notifiers(cpsw);
 	if (ret)
 		goto clean_unregister_netdev;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 099208927400..9d098c802c6d 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -114,6 +114,18 @@ irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id)
+{
+	struct cpsw_common *cpsw = dev_id;
+
+	writel(0, &cpsw->wr_regs->misc_en);
+	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_MISC);
+	cpts_misc_interrupt(cpsw->cpts);
+	writel(0x10, &cpsw->wr_regs->misc_en);
+
+	return IRQ_HANDLED;
+}
+
 int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
 {
 	struct cpsw_common	*cpsw = napi_to_cpsw(napi_tx);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index b8d7b924ee3d..bf4e179b4ca4 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -350,6 +350,7 @@ struct cpsw_common {
 	bool				rx_irq_disabled;
 	bool				tx_irq_disabled;
 	u32 irqs_table[IRQ_NUM];
+	int misc_irq;
 	struct cpts			*cpts;
 	struct devlink *devlink;
 	int				rx_ch_num, tx_ch_num;
@@ -442,6 +443,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
 		 struct page *page, int port);
 irqreturn_t cpsw_tx_interrupt(int irq, void *dev_id);
 irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id);
+irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id);
 int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget);
 int cpsw_tx_poll(struct napi_struct *napi_tx, int budget);
 int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget);
-- 
cgit v1.2.3


From 8ffe2df6426f874659a3aa1654f45ba83fa91f87 Mon Sep 17 00:00:00 2001
From: Zou Wei <zou_wei@huawei.com>
Date: Thu, 23 Apr 2020 15:27:40 +0800
Subject: qed: Make ll2_cbs static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following sparse warning:

drivers/net/ethernet/qlogic/qed/qed_ll2.c:2334:20: warning: symbol 'll2_cbs'
was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_ll2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 037e5978787e..4afd8572ada6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -2331,7 +2331,7 @@ static void qed_ll2_register_cb_ops(struct qed_dev *cdev,
 	cdev->ll2->cb_cookie = cookie;
 }
 
-struct qed_ll2_cbs ll2_cbs = {
+static struct qed_ll2_cbs ll2_cbs = {
 	.rx_comp_cb = &qed_ll2b_complete_rx_packet,
 	.rx_release_cb = &qed_ll2b_release_rx_packet,
 	.tx_comp_cb = &qed_ll2b_complete_tx_packet,
-- 
cgit v1.2.3


From 8146458fcd7942861c754b85b5464ef2a8cfacbb Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Fri, 24 Apr 2020 18:43:41 +0300
Subject: mlxsw: spectrum_span: Reduce nesting in
 mlxsw_sp_span_entry_configure()

Use early return to avoid unnecessary nesting.

Signed-off-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 29 ++++++++++++++--------
 1 file changed, 19 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 9fb2e9d93929..e7be1bfe7f75 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -622,18 +622,27 @@ mlxsw_sp_span_entry_configure(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_span_entry *span_entry,
 			      struct mlxsw_sp_span_parms sparms)
 {
-	if (sparms.dest_port) {
-		if (sparms.dest_port->mlxsw_sp != mlxsw_sp) {
-			netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance",
-				   sparms.dest_port->dev->name);
-			sparms.dest_port = NULL;
-		} else if (span_entry->ops->configure(span_entry, sparms)) {
-			netdev_err(span_entry->to_dev, "Failed to offload mirror to %s",
-				   sparms.dest_port->dev->name);
-			sparms.dest_port = NULL;
-		}
+	int err;
+
+	if (!sparms.dest_port)
+		goto set_parms;
+
+	if (sparms.dest_port->mlxsw_sp != mlxsw_sp) {
+		netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance",
+			   sparms.dest_port->dev->name);
+		sparms.dest_port = NULL;
+		goto set_parms;
+	}
+
+	err = span_entry->ops->configure(span_entry, sparms);
+	if (err) {
+		netdev_err(span_entry->to_dev, "Failed to offload mirror to %s",
+			   sparms.dest_port->dev->name);
+		sparms.dest_port = NULL;
+		goto set_parms;
 	}
 
+set_parms:
 	span_entry->parms = sparms;
 }
 
-- 
cgit v1.2.3


From 7f9b099bd9d3143d3c1a0ea74b586c5189e58750 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Fri, 24 Apr 2020 18:43:42 +0300
Subject: mlxsw: spectrum_span: Rename parms() to parms_set()

Use a more meaningful name for parms() function.

Signed-off-by: Amit Cohen <amitc@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 14 +++++++-------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h |  4 ++--
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index e7be1bfe7f75..eb4a1c0f2788 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -130,7 +130,7 @@ mlxsw_sp_span_entry_phys_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 static const
 struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = {
 	.can_handle = mlxsw_sp_port_dev_check,
-	.parms = mlxsw_sp_span_entry_phys_parms,
+	.parms_set = mlxsw_sp_span_entry_phys_parms,
 	.configure = mlxsw_sp_span_entry_phys_configure,
 	.deconfigure = mlxsw_sp_span_entry_phys_deconfigure,
 };
@@ -418,7 +418,7 @@ mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 
 static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = {
 	.can_handle = netif_is_gretap,
-	.parms = mlxsw_sp_span_entry_gretap4_parms,
+	.parms_set = mlxsw_sp_span_entry_gretap4_parms,
 	.configure = mlxsw_sp_span_entry_gretap4_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure,
 };
@@ -519,7 +519,7 @@ mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 static const
 struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = {
 	.can_handle = netif_is_ip6gretap,
-	.parms = mlxsw_sp_span_entry_gretap6_parms,
+	.parms_set = mlxsw_sp_span_entry_gretap6_parms,
 	.configure = mlxsw_sp_span_entry_gretap6_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure,
 };
@@ -575,7 +575,7 @@ mlxsw_sp_span_entry_vlan_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 static const
 struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_vlan = {
 	.can_handle = mlxsw_sp_span_vlan_can_handle,
-	.parms = mlxsw_sp_span_entry_vlan_parms,
+	.parms_set = mlxsw_sp_span_entry_vlan_parms,
 	.configure = mlxsw_sp_span_entry_vlan_configure,
 	.deconfigure = mlxsw_sp_span_entry_vlan_deconfigure,
 };
@@ -612,7 +612,7 @@ mlxsw_sp_span_entry_nop_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 }
 
 static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_nop = {
-	.parms = mlxsw_sp_span_entry_nop_parms,
+	.parms_set = mlxsw_sp_span_entry_nop_parms,
 	.configure = mlxsw_sp_span_entry_nop_configure,
 	.deconfigure = mlxsw_sp_span_entry_nop_deconfigure,
 };
@@ -970,7 +970,7 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
 		return -EOPNOTSUPP;
 	}
 
-	err = ops->parms(to_dev, &sparms);
+	err = ops->parms_set(to_dev, &sparms);
 	if (err)
 		return err;
 
@@ -1026,7 +1026,7 @@ static void mlxsw_sp_span_respin_work(struct work_struct *work)
 		if (!curr->ref_count)
 			continue;
 
-		err = curr->ops->parms(curr->to_dev, &sparms);
+		err = curr->ops->parms_set(curr->to_dev, &sparms);
 		if (err)
 			continue;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 59724335525f..01273e54ba20 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -49,8 +49,8 @@ struct mlxsw_sp_span_entry {
 
 struct mlxsw_sp_span_entry_ops {
 	bool (*can_handle)(const struct net_device *to_dev);
-	int (*parms)(const struct net_device *to_dev,
-		     struct mlxsw_sp_span_parms *sparmsp);
+	int (*parms_set)(const struct net_device *to_dev,
+			 struct mlxsw_sp_span_parms *sparmsp);
 	int (*configure)(struct mlxsw_sp_span_entry *span_entry,
 			 struct mlxsw_sp_span_parms sparms);
 	void (*deconfigure)(struct mlxsw_sp_span_entry *span_entry);
-- 
cgit v1.2.3


From c0c2899cf66ee7a68e5b3a7a135089622e005008 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 24 Apr 2020 18:43:43 +0300
Subject: mlxsw: spectrum_span: Remove unnecessary debug prints

To the best of my knowledge, these debug prints were never used. Remove
them.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index eb4a1c0f2788..14c5edc71239 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -978,9 +978,6 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
 	if (!span_entry)
 		return -ENOBUFS;
 
-	netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n",
-		   span_entry->id);
-
 	err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind);
 	if (err)
 		goto err_port_bind;
@@ -1004,8 +1001,6 @@ void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id,
 		return;
 	}
 
-	netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n",
-		   span_entry->id);
 	mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind);
 }
 
-- 
cgit v1.2.3


From 4c00dafc59c7cc25a381abf7671b203a2fcfca71 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 24 Apr 2020 18:43:44 +0300
Subject: mlxsw: spectrum_span: Use 'refcount_t' for reference counting

'refcount_t' is very useful for catching over/under flows. Convert the
SPAN agent objects to use it instead of 'int' for their reference count.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 16 ++++++++--------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h |  3 ++-
 2 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 14c5edc71239..235556be58f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -3,6 +3,7 @@
 
 #include <linux/if_bridge.h>
 #include <linux/list.h>
+#include <linux/refcount.h>
 #include <linux/rtnetlink.h>
 #include <linux/workqueue.h>
 #include <net/arp.h>
@@ -664,7 +665,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp,
 
 	/* find a free entry to use */
 	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
-		if (!mlxsw_sp->span->entries[i].ref_count) {
+		if (!refcount_read(&mlxsw_sp->span->entries[i].ref_count)) {
 			span_entry = &mlxsw_sp->span->entries[i];
 			break;
 		}
@@ -674,7 +675,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp,
 
 	atomic_inc(&mlxsw_sp->span->active_entries_count);
 	span_entry->ops = ops;
-	span_entry->ref_count = 1;
+	refcount_set(&span_entry->ref_count, 1);
 	span_entry->to_dev = to_dev;
 	mlxsw_sp_span_entry_configure(mlxsw_sp, span_entry, sparms);
 
@@ -697,7 +698,7 @@ mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp,
 	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
 
-		if (curr->ref_count && curr->to_dev == to_dev)
+		if (refcount_read(&curr->ref_count) && curr->to_dev == to_dev)
 			return curr;
 	}
 	return NULL;
@@ -718,7 +719,7 @@ mlxsw_sp_span_entry_find_by_id(struct mlxsw_sp *mlxsw_sp, int span_id)
 	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
 
-		if (curr->ref_count && curr->id == span_id)
+		if (refcount_read(&curr->ref_count) && curr->id == span_id)
 			return curr;
 	}
 	return NULL;
@@ -735,7 +736,7 @@ mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp,
 	span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, to_dev);
 	if (span_entry) {
 		/* Already exists, just take a reference */
-		span_entry->ref_count++;
+		refcount_inc(&span_entry->ref_count);
 		return span_entry;
 	}
 
@@ -745,8 +746,7 @@ mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_span_entry *span_entry)
 {
-	WARN_ON(!span_entry->ref_count);
-	if (--span_entry->ref_count == 0)
+	if (refcount_dec_and_test(&span_entry->ref_count))
 		mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry);
 	return 0;
 }
@@ -1018,7 +1018,7 @@ static void mlxsw_sp_span_respin_work(struct work_struct *work)
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
 		struct mlxsw_sp_span_parms sparms = {NULL};
 
-		if (!curr->ref_count)
+		if (!refcount_read(&curr->ref_count))
 			continue;
 
 		err = curr->ops->parms_set(curr->to_dev, &sparms);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 01273e54ba20..d23abdf957fa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <linux/if_ether.h>
+#include <linux/refcount.h>
 
 #include "spectrum_router.h"
 
@@ -43,7 +44,7 @@ struct mlxsw_sp_span_entry {
 	const struct mlxsw_sp_span_entry_ops *ops;
 	struct mlxsw_sp_span_parms parms;
 	struct list_head bound_ports_list;
-	int ref_count;
+	refcount_t ref_count;
 	int id;
 };
 
-- 
cgit v1.2.3


From 4780dbdbd957c204b62680161f39bb0bc4daf3a0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 24 Apr 2020 18:43:45 +0300
Subject: mlxsw: spectrum_span: Replace zero-length array with flexible-array
 member

In a similar fashion to commit e99f8e7f88b5 ("mlxsw: Replace zero-length
array with flexible-array member"), use a flexible-array member to get a
compiler warning in case the flexible array does not occur last in the
structure.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 235556be58f5..ae3c8a1e9a43 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -22,7 +22,7 @@ struct mlxsw_sp_span {
 	struct mlxsw_sp *mlxsw_sp;
 	atomic_t active_entries_count;
 	int entries_count;
-	struct mlxsw_sp_span_entry entries[0];
+	struct mlxsw_sp_span_entry entries[];
 };
 
 static void mlxsw_sp_span_respin_work(struct work_struct *work);
-- 
cgit v1.2.3


From b89c1e6bdc73f5775e118eb2ab778e75b262b30c Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 23 Apr 2020 16:57:50 +0200
Subject: dpaa2-eth: fix return codes used in ndo_setup_tc

Drivers ndo_setup_tc call should return -EOPNOTSUPP, when it cannot
support the qdisc type. Other return values will result in failing the
qdisc setup.  This lead to qdisc noop getting assigned, which will
drop all TX packets on the interface.

Fixes: ab1e6de2bd49 ("dpaa2-eth: Add mqprio support")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 9d4061bba0b8..d271c016229d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2021,7 +2021,7 @@ static int dpaa2_eth_setup_tc(struct net_device *net_dev,
 	int i;
 
 	if (type != TC_SETUP_QDISC_MQPRIO)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 	num_queues = dpaa2_eth_queue_count(priv);
@@ -2033,7 +2033,7 @@ static int dpaa2_eth_setup_tc(struct net_device *net_dev,
 	if (num_tc  > dpaa2_eth_tc_count(priv)) {
 		netdev_err(net_dev, "Max %d traffic classes supported\n",
 			   dpaa2_eth_tc_count(priv));
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	if (!num_tc) {
-- 
cgit v1.2.3


From 10395e99f4a6f67d53b89f143f610ee954c24531 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Fri, 24 Apr 2020 17:00:15 +0800
Subject: net/mlxfw: Remove unneeded semicolon

Fixes coccicheck warning:

drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c:79:2-3: Unneeded semicolon
drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c:162:2-3: Unneeded semicolon

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 046a0cb82ed8..7a04c626a2aa 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -76,7 +76,7 @@ static int mlxfw_fsm_state_err(struct mlxfw_dev *mlxfw_dev,
 	case MLXFW_FSM_STATE_ERR_MAX:
 		MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown error", err);
 		break;
-	};
+	}
 
 	return mlxfw_fsm_state_errno[fsm_state_err];
 };
@@ -159,7 +159,7 @@ mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev,
 	case MLXFW_FSM_REACTIVATE_STATUS_MAX:
 		MLXFW_REACT_ERR("unexpected error", err);
 		break;
-	};
+	}
 	return -EREMOTEIO;
 };
 
-- 
cgit v1.2.3


From d9e4171a4a2cf20e803eb31a92d6854ea7002c38 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Fri, 24 Apr 2020 17:04:28 +0800
Subject: net: atlantic: Remove unneeded semicolon

Fixes coccicheck warning:

drivers/net/ethernet/aquantia/atlantic/aq_macsec.c:404:2-3: Unneeded semicolon
drivers/net/ethernet/aquantia/atlantic/aq_macsec.c:420:2-3: Unneeded semicolon

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Acked-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_macsec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
index 0b3e234a54aa..91870ceaf3fe 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
@@ -401,7 +401,7 @@ static u32 aq_sc_idx_max(const enum aq_macsec_sc_sa sc_sa)
 		break;
 	default:
 		break;
-	};
+	}
 
 	return result;
 }
@@ -417,7 +417,7 @@ static u32 aq_to_hw_sc_idx(const u32 sc_idx, const enum aq_macsec_sc_sa sc_sa)
 		return sc_idx;
 	default:
 		WARN_ONCE(true, "Invalid sc_sa");
-	};
+	}
 
 	return sc_idx;
 }
-- 
cgit v1.2.3


From 1ac0e6c292983c2665383ae9efcfe1f8b53271e0 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:06 +0800
Subject: net: hns3: refine for unicast MAC VLAN space management

Currently, firmware helps manage the unicast MAC VLAN table
space for each PF. PF just needs to tell firmware its wanted
space when initializing, and unnecessary to free it when
un-intializing. So this patch removes the umv space free handle,
and removes the forward statement of hclge_set_umv_space()
by defining hclge_init_umv_space() after it.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 72 ++++++++--------------
 1 file changed, 24 insertions(+), 48 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0618f22e6f14..ccf269a9a3b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -62,8 +62,6 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev);
 static void hclge_sync_vlan_filter(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
 static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle);
-static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
-			       u16 *allocated_size, bool is_alloc);
 static void hclge_rfs_filter_expire(struct hclge_dev *hdev);
 static void hclge_clear_arfs_rules(struct hnae3_handle *handle);
 static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
@@ -7196,50 +7194,6 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport,
 	return cfg_status;
 }
 
-static int hclge_init_umv_space(struct hclge_dev *hdev)
-{
-	u16 allocated_size = 0;
-	int ret;
-
-	ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size,
-				  true);
-	if (ret)
-		return ret;
-
-	if (allocated_size < hdev->wanted_umv_size)
-		dev_warn(&hdev->pdev->dev,
-			 "Alloc umv space failed, want %u, get %u\n",
-			 hdev->wanted_umv_size, allocated_size);
-
-	mutex_init(&hdev->umv_mutex);
-	hdev->max_umv_size = allocated_size;
-	/* divide max_umv_size by (hdev->num_req_vfs + 2), in order to
-	 * preserve some unicast mac vlan table entries shared by pf
-	 * and its vfs.
-	 */
-	hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_req_vfs + 2);
-	hdev->share_umv_size = hdev->priv_umv_size +
-			hdev->max_umv_size % (hdev->num_req_vfs + 2);
-
-	return 0;
-}
-
-static int hclge_uninit_umv_space(struct hclge_dev *hdev)
-{
-	int ret;
-
-	if (hdev->max_umv_size > 0) {
-		ret = hclge_set_umv_space(hdev, hdev->max_umv_size, NULL,
-					  false);
-		if (ret)
-			return ret;
-		hdev->max_umv_size = 0;
-	}
-	mutex_destroy(&hdev->umv_mutex);
-
-	return 0;
-}
-
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 			       u16 *allocated_size, bool is_alloc)
 {
@@ -7268,6 +7222,30 @@ static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 	return 0;
 }
 
+static int hclge_init_umv_space(struct hclge_dev *hdev)
+{
+	u16 allocated_size = 0;
+	int ret;
+
+	ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size,
+				  true);
+	if (ret)
+		return ret;
+
+	if (allocated_size < hdev->wanted_umv_size)
+		dev_warn(&hdev->pdev->dev,
+			 "failed to alloc umv space, want %u, get %u\n",
+			 hdev->wanted_umv_size, allocated_size);
+
+	mutex_init(&hdev->umv_mutex);
+	hdev->max_umv_size = allocated_size;
+	hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_alloc_vport + 1);
+	hdev->share_umv_size = hdev->priv_umv_size +
+			hdev->max_umv_size % (hdev->num_alloc_vport + 1);
+
+	return 0;
+}
+
 static void hclge_reset_umv_space(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport;
@@ -10041,8 +10019,6 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (mac->phydev)
 		mdiobus_unregister(mac->mdio_bus);
 
-	hclge_uninit_umv_space(hdev);
-
 	/* Disable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, false);
 	synchronize_irq(hdev->misc_vector.vector_irq);
-- 
cgit v1.2.3


From c1c5f66ee0dea782de9c95e6d63f19c355389ee8 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:07 +0800
Subject: net: hns3: remove unnecessary parameter 'is_alloc' in
 hclge_set_umv_space()

Since hclge_set_umv_space() is only called by hclge_init_umv_space(),
so parameter 'is_alloc' is redundant.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ccf269a9a3b1..fe6e60a41925 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7195,7 +7195,7 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport,
 }
 
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
-			       u16 *allocated_size, bool is_alloc)
+			       u16 *allocated_size)
 {
 	struct hclge_umv_spc_alc_cmd *req;
 	struct hclge_desc desc;
@@ -7203,20 +7203,17 @@ static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 
 	req = (struct hclge_umv_spc_alc_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ALLOCATE, false);
-	if (!is_alloc)
-		hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, 1);
 
 	req->space_size = cpu_to_le32(space_size);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"%s umv space failed for cmd_send, ret =%d\n",
-			is_alloc ? "allocate" : "free", ret);
+		dev_err(&hdev->pdev->dev, "failed to set umv space, ret = %d\n",
+			ret);
 		return ret;
 	}
 
-	if (is_alloc && allocated_size)
+	if (allocated_size)
 		*allocated_size = le32_to_cpu(desc.data[1]);
 
 	return 0;
@@ -7227,8 +7224,7 @@ static int hclge_init_umv_space(struct hclge_dev *hdev)
 	u16 allocated_size = 0;
 	int ret;
 
-	ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size,
-				  true);
+	ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 4c58f592470192d2b5ce4cfd2f7ff0ea2624c073 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:08 +0800
Subject: net: hns3: replace num_req_vfs with num_alloc_vport in
 hclge_reset_umv_space()

Like the calculation elsewhere, replaces num_req_vfs with
num_alloc_vport in hclge_reset_umv_space().

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fe6e60a41925..a268004c8e0e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7254,7 +7254,7 @@ static void hclge_reset_umv_space(struct hclge_dev *hdev)
 
 	mutex_lock(&hdev->umv_mutex);
 	hdev->share_umv_size = hdev->priv_umv_size +
-			hdev->max_umv_size % (hdev->num_req_vfs + 2);
+			hdev->max_umv_size % (hdev->num_alloc_vport + 1);
 	mutex_unlock(&hdev->umv_mutex);
 }
 
-- 
cgit v1.2.3


From ee4bcd3b7ae40bd77732eb1ba14aa26d6c514525 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:09 +0800
Subject: net: hns3: refactor the MAC address configure

Currently, the HNS3 driver sync and unsync MAC address in function
hns3_set_rx_mode(). For PF, it adds and deletes MAC address directly
in the path of dev_set_rx_mode(). If failed, it won't retry until
next calling of hns3_set_rx_mode(). On the other hand, if request
add and remove a same address many times at a short interval, each
request must be done one by one, can't be merged. For VF, it sends
mailbox messages to PF to request adding or deleting MAC address in
the path of function hns3_set_rx_mode(), no matter the address is
configured success.

This patch refines it by recording the MAC address in function
hns3_set_rx_mode(), and updating MAC address in the service task.
If failed, it will retry by the next calling of periodical service
task. It also uses some state to mark the state of each MAC address
in the MAC list, which can help merge configure request for a same
address. With these changes, when global reset or IMP reset occurs,
we can restore the MAC table with the MAC list.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  79 +--
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 592 +++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  27 +-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c |  42 +-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 313 ++++++++++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  25 +
 6 files changed, 860 insertions(+), 218 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index ac3a48a24d86..341e8b5cd219 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -40,7 +40,6 @@
 	} while (0)
 
 static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
-static void hns3_remove_hw_addr(struct net_device *netdev);
 
 static const char hns3_driver_name[] = "hns3";
 static const char hns3_driver_string[] =
@@ -548,6 +547,13 @@ static int hns3_nic_uc_unsync(struct net_device *netdev,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
+	/* need ignore the request of removing device address, because
+	 * we store the device address and other addresses of uc list
+	 * in the function's mac filter list.
+	 */
+	if (ether_addr_equal(addr, netdev->dev_addr))
+		return 0;
+
 	if (h->ae_algo->ops->rm_uc_addr)
 		return h->ae_algo->ops->rm_uc_addr(h, addr);
 
@@ -3907,9 +3913,11 @@ static int hns3_init_mac_addr(struct net_device *netdev)
 		eth_hw_addr_random(netdev);
 		dev_warn(priv->dev, "using random MAC address %pM\n",
 			 netdev->dev_addr);
-	} else {
+	} else if (!ether_addr_equal(netdev->dev_addr, mac_addr_temp)) {
 		ether_addr_copy(netdev->dev_addr, mac_addr_temp);
 		ether_addr_copy(netdev->perm_addr, mac_addr_temp);
+	} else {
+		return 0;
 	}
 
 	if (h->ae_algo->ops->set_mac_addr)
@@ -4119,8 +4127,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
-	hns3_remove_hw_addr(netdev);
-
 	if (netdev->reg_state != NETREG_UNINITIALIZED)
 		unregister_netdev(netdev);
 
@@ -4191,56 +4197,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	return hns3_nic_set_real_num_queue(ndev);
 }
 
-static int hns3_recover_hw_addr(struct net_device *ndev)
-{
-	struct netdev_hw_addr_list *list;
-	struct netdev_hw_addr *ha, *tmp;
-	int ret = 0;
-
-	netif_addr_lock_bh(ndev);
-	/* go through and sync uc_addr entries to the device */
-	list = &ndev->uc;
-	list_for_each_entry_safe(ha, tmp, &list->list, list) {
-		ret = hns3_nic_uc_sync(ndev, ha->addr);
-		if (ret)
-			goto out;
-	}
-
-	/* go through and sync mc_addr entries to the device */
-	list = &ndev->mc;
-	list_for_each_entry_safe(ha, tmp, &list->list, list) {
-		ret = hns3_nic_mc_sync(ndev, ha->addr);
-		if (ret)
-			goto out;
-	}
-
-out:
-	netif_addr_unlock_bh(ndev);
-	return ret;
-}
-
-static void hns3_remove_hw_addr(struct net_device *netdev)
-{
-	struct netdev_hw_addr_list *list;
-	struct netdev_hw_addr *ha, *tmp;
-
-	hns3_nic_uc_unsync(netdev, netdev->dev_addr);
-
-	netif_addr_lock_bh(netdev);
-	/* go through and unsync uc_addr entries to the device */
-	list = &netdev->uc;
-	list_for_each_entry_safe(ha, tmp, &list->list, list)
-		hns3_nic_uc_unsync(netdev, ha->addr);
-
-	/* go through and unsync mc_addr entries to the device */
-	list = &netdev->mc;
-	list_for_each_entry_safe(ha, tmp, &list->list, list)
-		if (ha->refcount > 1)
-			hns3_nic_mc_unsync(netdev, ha->addr);
-
-	netif_addr_unlock_bh(netdev);
-}
-
 static void hns3_clear_tx_ring(struct hns3_enet_ring *ring)
 {
 	while (ring->next_to_clean != ring->next_to_use) {
@@ -4411,10 +4367,8 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 	 * from table space. Hence, for function reset software intervention is
 	 * required to delete the entries
 	 */
-	if (hns3_dev_ongoing_func_reset(ae_dev)) {
-		hns3_remove_hw_addr(ndev);
+	if (hns3_dev_ongoing_func_reset(ae_dev))
 		hns3_del_all_fd_rules(ndev, false);
-	}
 
 	if (!netif_running(ndev))
 		return 0;
@@ -4482,6 +4436,9 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 		goto err_init_irq_fail;
 	}
 
+	if (!hns3_is_phys_func(handle->pdev))
+		hns3_init_mac_addr(netdev);
+
 	ret = hns3_client_start(handle);
 	if (ret) {
 		dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
@@ -4513,14 +4470,6 @@ static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle)
 	bool vlan_filter_enable;
 	int ret;
 
-	ret = hns3_init_mac_addr(netdev);
-	if (ret)
-		return ret;
-
-	ret = hns3_recover_hw_addr(netdev);
-	if (ret)
-		return ret;
-
 	ret = hns3_update_promisc_mode(netdev, handle->netdev_flags);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a268004c8e0e..c3205ae620ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -68,6 +68,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 						   unsigned long *addr);
 static int hclge_set_default_loopback(struct hclge_dev *hdev);
 
+static void hclge_sync_mac_table(struct hclge_dev *hdev);
+
 static struct hnae3_ae_algo ae_algo;
 
 static struct workqueue_struct *hclge_wq;
@@ -1685,6 +1687,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 		INIT_LIST_HEAD(&vport->vlan_list);
 		INIT_LIST_HEAD(&vport->uc_mac_list);
 		INIT_LIST_HEAD(&vport->mc_mac_list);
+		spin_lock_init(&vport->mac_list_lock);
 
 		if (i == 0)
 			ret = hclge_vport_setup(vport, tqp_main_vport);
@@ -3971,6 +3974,7 @@ static void hclge_periodic_service_task(struct hclge_dev *hdev)
 	 * updated when it is triggered by mbx.
 	 */
 	hclge_update_link_status(hdev);
+	hclge_sync_mac_table(hdev);
 
 	if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) {
 		delta = jiffies - hdev->last_serv_processed;
@@ -6922,8 +6926,16 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 int hclge_vport_start(struct hclge_vport *vport)
 {
+	struct hclge_dev *hdev = vport->back;
+
 	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
 	vport->last_active_jiffies = jiffies;
+
+	if (test_bit(vport->vport_id, hdev->vport_config_block))
+		hclge_restore_mac_table_common(vport);
+
+	clear_bit(vport->vport_id, hdev->vport_config_block);
+
 	return 0;
 }
 
@@ -7291,12 +7303,106 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free)
 	mutex_unlock(&hdev->umv_mutex);
 }
 
+static struct hclge_mac_node *hclge_find_mac_node(struct list_head *list,
+						  const u8 *mac_addr)
+{
+	struct hclge_mac_node *mac_node, *tmp;
+
+	list_for_each_entry_safe(mac_node, tmp, list, node)
+		if (ether_addr_equal(mac_addr, mac_node->mac_addr))
+			return mac_node;
+
+	return NULL;
+}
+
+static void hclge_update_mac_node(struct hclge_mac_node *mac_node,
+				  enum HCLGE_MAC_NODE_STATE state)
+{
+	switch (state) {
+	/* from set_rx_mode or tmp_add_list */
+	case HCLGE_MAC_TO_ADD:
+		if (mac_node->state == HCLGE_MAC_TO_DEL)
+			mac_node->state = HCLGE_MAC_ACTIVE;
+		break;
+	/* only from set_rx_mode */
+	case HCLGE_MAC_TO_DEL:
+		if (mac_node->state == HCLGE_MAC_TO_ADD) {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else {
+			mac_node->state = HCLGE_MAC_TO_DEL;
+		}
+		break;
+	/* only from tmp_add_list, the mac_node->state won't be
+	 * ACTIVE.
+	 */
+	case HCLGE_MAC_ACTIVE:
+		if (mac_node->state == HCLGE_MAC_TO_ADD)
+			mac_node->state = HCLGE_MAC_ACTIVE;
+
+		break;
+	}
+}
+
+int hclge_update_mac_list(struct hclge_vport *vport,
+			  enum HCLGE_MAC_NODE_STATE state,
+			  enum HCLGE_MAC_ADDR_TYPE mac_type,
+			  const unsigned char *addr)
+{
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_mac_node *mac_node;
+	struct list_head *list;
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+		&vport->uc_mac_list : &vport->mc_mac_list;
+
+	spin_lock_bh(&vport->mac_list_lock);
+
+	/* if the mac addr is already in the mac list, no need to add a new
+	 * one into it, just check the mac addr state, convert it to a new
+	 * new state, or just remove it, or do nothing.
+	 */
+	mac_node = hclge_find_mac_node(list, addr);
+	if (mac_node) {
+		hclge_update_mac_node(mac_node, state);
+		spin_unlock_bh(&vport->mac_list_lock);
+		set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state);
+		return 0;
+	}
+
+	/* if this address is never added, unnecessary to delete */
+	if (state == HCLGE_MAC_TO_DEL) {
+		spin_unlock_bh(&vport->mac_list_lock);
+		dev_err(&hdev->pdev->dev,
+			"failed to delete address %pM from mac list\n",
+			addr);
+		return -ENOENT;
+	}
+
+	mac_node = kzalloc(sizeof(*mac_node), GFP_ATOMIC);
+	if (!mac_node) {
+		spin_unlock_bh(&vport->mac_list_lock);
+		return -ENOMEM;
+	}
+
+	set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state);
+
+	mac_node->state = state;
+	ether_addr_copy(mac_node->mac_addr, addr);
+	list_add_tail(&mac_node->node, list);
+
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	return 0;
+}
+
 static int hclge_add_uc_addr(struct hnae3_handle *handle,
 			     const unsigned char *addr)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return hclge_add_uc_addr_common(vport, addr);
+	return hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, HCLGE_MAC_ADDR_UC,
+				     addr);
 }
 
 int hclge_add_uc_addr_common(struct hclge_vport *vport,
@@ -7367,7 +7473,8 @@ static int hclge_rm_uc_addr(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return hclge_rm_uc_addr_common(vport, addr);
+	return hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, HCLGE_MAC_ADDR_UC,
+				     addr);
 }
 
 int hclge_rm_uc_addr_common(struct hclge_vport *vport,
@@ -7392,6 +7499,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
 	if (!ret)
 		hclge_update_umv_space(vport, true);
+	else if (ret == -ENOENT)
+		ret = 0;
 
 	return ret;
 }
@@ -7401,7 +7510,8 @@ static int hclge_add_mc_addr(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return hclge_add_mc_addr_common(vport, addr);
+	return hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, HCLGE_MAC_ADDR_MC,
+				     addr);
 }
 
 int hclge_add_mc_addr_common(struct hclge_vport *vport,
@@ -7444,7 +7554,8 @@ static int hclge_rm_mc_addr(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return hclge_rm_mc_addr_common(vport, addr);
+	return hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, HCLGE_MAC_ADDR_MC,
+				     addr);
 }
 
 int hclge_rm_mc_addr_common(struct hclge_vport *vport,
@@ -7479,111 +7590,328 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 			/* Not all the vfid is zero, update the vfid */
 			status = hclge_add_mac_vlan_tbl(vport, &req, desc);
 
-	} else {
-		/* Maybe this mac address is in mta table, but it cannot be
-		 * deleted here because an entry of mta represents an address
-		 * range rather than a specific address. the delete action to
-		 * all entries will take effect in update_mta_status called by
-		 * hns3_nic_set_rx_mode.
-		 */
+	} else if (status == -ENOENT) {
 		status = 0;
 	}
 
 	return status;
 }
 
-void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
-			       enum HCLGE_MAC_ADDR_TYPE mac_type)
+static void hclge_sync_vport_mac_list(struct hclge_vport *vport,
+				      struct list_head *list,
+				      int (*sync)(struct hclge_vport *,
+						  const unsigned char *))
 {
-	struct hclge_vport_mac_addr_cfg *mac_cfg;
-	struct list_head *list;
+	struct hclge_mac_node *mac_node, *tmp;
+	int ret;
 
-	if (!vport->vport_id)
-		return;
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		ret = sync(vport, mac_node->mac_addr);
+		if (!ret) {
+			mac_node->state = HCLGE_MAC_ACTIVE;
+		} else {
+			set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
+				&vport->state);
+			break;
+		}
+	}
+}
 
-	mac_cfg = kzalloc(sizeof(*mac_cfg), GFP_KERNEL);
-	if (!mac_cfg)
-		return;
+static void hclge_unsync_vport_mac_list(struct hclge_vport *vport,
+					struct list_head *list,
+					int (*unsync)(struct hclge_vport *,
+						      const unsigned char *))
+{
+	struct hclge_mac_node *mac_node, *tmp;
+	int ret;
 
-	mac_cfg->hd_tbl_status = true;
-	memcpy(mac_cfg->mac_addr, mac_addr, ETH_ALEN);
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		ret = unsync(vport, mac_node->mac_addr);
+		if (!ret || ret == -ENOENT) {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else {
+			set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
+				&vport->state);
+			break;
+		}
+	}
+}
 
-	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
-	       &vport->uc_mac_list : &vport->mc_mac_list;
+static void hclge_sync_from_add_list(struct list_head *add_list,
+				     struct list_head *mac_list)
+{
+	struct hclge_mac_node *mac_node, *tmp, *new_node;
 
-	list_add_tail(&mac_cfg->node, list);
+	list_for_each_entry_safe(mac_node, tmp, add_list, node) {
+		/* if the mac address from tmp_add_list is not in the
+		 * uc/mc_mac_list, it means have received a TO_DEL request
+		 * during the time window of adding the mac address into mac
+		 * table. if mac_node state is ACTIVE, then change it to TO_DEL,
+		 * then it will be removed at next time. else it must be TO_ADD,
+		 * this address hasn't been added into mac table,
+		 * so just remove the mac node.
+		 */
+		new_node = hclge_find_mac_node(mac_list, mac_node->mac_addr);
+		if (new_node) {
+			hclge_update_mac_node(new_node, mac_node->state);
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else if (mac_node->state == HCLGE_MAC_ACTIVE) {
+			mac_node->state = HCLGE_MAC_TO_DEL;
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, mac_list);
+		} else {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		}
+	}
 }
 
-void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
-			      bool is_write_tbl,
-			      enum HCLGE_MAC_ADDR_TYPE mac_type)
+static void hclge_sync_from_del_list(struct list_head *del_list,
+				     struct list_head *mac_list)
 {
-	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
-	struct list_head *list;
-	bool uc_flag, mc_flag;
+	struct hclge_mac_node *mac_node, *tmp, *new_node;
 
-	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
-	       &vport->uc_mac_list : &vport->mc_mac_list;
+	list_for_each_entry_safe(mac_node, tmp, del_list, node) {
+		new_node = hclge_find_mac_node(mac_list, mac_node->mac_addr);
+		if (new_node) {
+			/* If the mac addr exists in the mac list, it means
+			 * received a new TO_ADD request during the time window
+			 * of configuring the mac address. For the mac node
+			 * state is TO_ADD, and the address is already in the
+			 * in the hardware(due to delete fail), so we just need
+			 * to change the mac node state to ACTIVE.
+			 */
+			new_node->state = HCLGE_MAC_ACTIVE;
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else {
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, mac_list);
+		}
+	}
+}
 
-	uc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_UC;
-	mc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_MC;
+static void hclge_sync_vport_mac_table(struct hclge_vport *vport,
+				       enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_mac_node *mac_node, *tmp, *new_node;
+	struct list_head tmp_add_list, tmp_del_list;
+	struct list_head *list;
 
-	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
-		if (ether_addr_equal(mac_cfg->mac_addr, mac_addr)) {
-			if (uc_flag && mac_cfg->hd_tbl_status)
-				hclge_rm_uc_addr_common(vport, mac_addr);
+	INIT_LIST_HEAD(&tmp_add_list);
+	INIT_LIST_HEAD(&tmp_del_list);
 
-			if (mc_flag && mac_cfg->hd_tbl_status)
-				hclge_rm_mc_addr_common(vport, mac_addr);
+	/* move the mac addr to the tmp_add_list and tmp_del_list, then
+	 * we can add/delete these mac addr outside the spin lock
+	 */
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+		&vport->uc_mac_list : &vport->mc_mac_list;
 
-			list_del(&mac_cfg->node);
-			kfree(mac_cfg);
+	spin_lock_bh(&vport->mac_list_lock);
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		switch (mac_node->state) {
+		case HCLGE_MAC_TO_DEL:
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, &tmp_del_list);
+			break;
+		case HCLGE_MAC_TO_ADD:
+			new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
+			if (!new_node)
+				goto stop_traverse;
+			ether_addr_copy(new_node->mac_addr, mac_node->mac_addr);
+			new_node->state = mac_node->state;
+			list_add_tail(&new_node->node, &tmp_add_list);
+			break;
+		default:
 			break;
 		}
 	}
+
+stop_traverse:
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	/* delete first, in order to get max mac table space for adding */
+	if (mac_type == HCLGE_MAC_ADDR_UC) {
+		hclge_unsync_vport_mac_list(vport, &tmp_del_list,
+					    hclge_rm_uc_addr_common);
+		hclge_sync_vport_mac_list(vport, &tmp_add_list,
+					  hclge_add_uc_addr_common);
+	} else {
+		hclge_unsync_vport_mac_list(vport, &tmp_del_list,
+					    hclge_rm_mc_addr_common);
+		hclge_sync_vport_mac_list(vport, &tmp_add_list,
+					  hclge_add_mc_addr_common);
+	}
+
+	/* if some mac addresses were added/deleted fail, move back to the
+	 * mac_list, and retry at next time.
+	 */
+	spin_lock_bh(&vport->mac_list_lock);
+
+	hclge_sync_from_del_list(&tmp_del_list, list);
+	hclge_sync_from_add_list(&tmp_add_list, list);
+
+	spin_unlock_bh(&vport->mac_list_lock);
+}
+
+static bool hclge_need_sync_mac_table(struct hclge_vport *vport)
+{
+	struct hclge_dev *hdev = vport->back;
+
+	if (test_bit(vport->vport_id, hdev->vport_config_block))
+		return false;
+
+	if (test_and_clear_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state))
+		return true;
+
+	return false;
+}
+
+static void hclge_sync_mac_table(struct hclge_dev *hdev)
+{
+	int i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+
+		if (!hclge_need_sync_mac_table(vport))
+			continue;
+
+		hclge_sync_vport_mac_table(vport, HCLGE_MAC_ADDR_UC);
+		hclge_sync_vport_mac_table(vport, HCLGE_MAC_ADDR_MC);
+	}
 }
 
 void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
 				  enum HCLGE_MAC_ADDR_TYPE mac_type)
 {
-	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
-	struct list_head *list;
+	int (*unsync)(struct hclge_vport *vport, const unsigned char *addr);
+	struct hclge_mac_node *mac_cfg, *tmp;
+	struct hclge_dev *hdev = vport->back;
+	struct list_head tmp_del_list, *list;
+	int ret;
 
-	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
-	       &vport->uc_mac_list : &vport->mc_mac_list;
+	if (mac_type == HCLGE_MAC_ADDR_UC) {
+		list = &vport->uc_mac_list;
+		unsync = hclge_rm_uc_addr_common;
+	} else {
+		list = &vport->mc_mac_list;
+		unsync = hclge_rm_mc_addr_common;
+	}
 
-	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
-		if (mac_type == HCLGE_MAC_ADDR_UC && mac_cfg->hd_tbl_status)
-			hclge_rm_uc_addr_common(vport, mac_cfg->mac_addr);
+	INIT_LIST_HEAD(&tmp_del_list);
 
-		if (mac_type == HCLGE_MAC_ADDR_MC && mac_cfg->hd_tbl_status)
-			hclge_rm_mc_addr_common(vport, mac_cfg->mac_addr);
+	if (!is_del_list)
+		set_bit(vport->vport_id, hdev->vport_config_block);
 
-		mac_cfg->hd_tbl_status = false;
-		if (is_del_list) {
+	spin_lock_bh(&vport->mac_list_lock);
+
+	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
+		switch (mac_cfg->state) {
+		case HCLGE_MAC_TO_DEL:
+		case HCLGE_MAC_ACTIVE:
 			list_del(&mac_cfg->node);
-			kfree(mac_cfg);
+			list_add_tail(&mac_cfg->node, &tmp_del_list);
+			break;
+		case HCLGE_MAC_TO_ADD:
+			if (is_del_list) {
+				list_del(&mac_cfg->node);
+				kfree(mac_cfg);
+			}
+			break;
 		}
 	}
+
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	list_for_each_entry_safe(mac_cfg, tmp, &tmp_del_list, node) {
+		ret = unsync(vport, mac_cfg->mac_addr);
+		if (!ret || ret == -ENOENT) {
+			/* clear all mac addr from hardware, but remain these
+			 * mac addr in the mac list, and restore them after
+			 * vf reset finished.
+			 */
+			if (!is_del_list &&
+			    mac_cfg->state == HCLGE_MAC_ACTIVE) {
+				mac_cfg->state = HCLGE_MAC_TO_ADD;
+			} else {
+				list_del(&mac_cfg->node);
+				kfree(mac_cfg);
+			}
+		} else if (is_del_list) {
+			mac_cfg->state = HCLGE_MAC_TO_DEL;
+		}
+	}
+
+	spin_lock_bh(&vport->mac_list_lock);
+
+	hclge_sync_from_del_list(&tmp_del_list, list);
+
+	spin_unlock_bh(&vport->mac_list_lock);
+}
+
+/* remove all mac address when uninitailize */
+static void hclge_uninit_vport_mac_list(struct hclge_vport *vport,
+					enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_mac_node *mac_node, *tmp;
+	struct hclge_dev *hdev = vport->back;
+	struct list_head tmp_del_list, *list;
+
+	INIT_LIST_HEAD(&tmp_del_list);
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+		&vport->uc_mac_list : &vport->mc_mac_list;
+
+	spin_lock_bh(&vport->mac_list_lock);
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		switch (mac_node->state) {
+		case HCLGE_MAC_TO_DEL:
+		case HCLGE_MAC_ACTIVE:
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, &tmp_del_list);
+			break;
+		case HCLGE_MAC_TO_ADD:
+			list_del(&mac_node->node);
+			kfree(mac_node);
+			break;
+		}
+	}
+
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	if (mac_type == HCLGE_MAC_ADDR_UC)
+		hclge_unsync_vport_mac_list(vport, &tmp_del_list,
+					    hclge_rm_uc_addr_common);
+	else
+		hclge_unsync_vport_mac_list(vport, &tmp_del_list,
+					    hclge_rm_mc_addr_common);
+
+	if (!list_empty(&tmp_del_list))
+		dev_warn(&hdev->pdev->dev,
+			 "uninit %s mac list for vport %u not completely.\n",
+			 mac_type == HCLGE_MAC_ADDR_UC ? "uc" : "mc",
+			 vport->vport_id);
+
+	list_for_each_entry_safe(mac_node, tmp, &tmp_del_list, node) {
+		list_del(&mac_node->node);
+		kfree(mac_node);
+	}
 }
 
-void hclge_uninit_vport_mac_table(struct hclge_dev *hdev)
+static void hclge_uninit_mac_table(struct hclge_dev *hdev)
 {
-	struct hclge_vport_mac_addr_cfg *mac, *tmp;
 	struct hclge_vport *vport;
 	int i;
 
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
 		vport = &hdev->vport[i];
-		list_for_each_entry_safe(mac, tmp, &vport->uc_mac_list, node) {
-			list_del(&mac->node);
-			kfree(mac);
-		}
-
-		list_for_each_entry_safe(mac, tmp, &vport->mc_mac_list, node) {
-			list_del(&mac->node);
-			kfree(mac);
-		}
+		hclge_uninit_vport_mac_list(vport, HCLGE_MAC_ADDR_UC);
+		hclge_uninit_vport_mac_list(vport, HCLGE_MAC_ADDR_MC);
 	}
 }
 
@@ -7747,12 +8075,57 @@ static void hclge_get_mac_addr(struct hnae3_handle *handle, u8 *p)
 	ether_addr_copy(p, hdev->hw.mac.mac_addr);
 }
 
+int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport,
+				       const u8 *old_addr, const u8 *new_addr)
+{
+	struct list_head *list = &vport->uc_mac_list;
+	struct hclge_mac_node *old_node, *new_node;
+
+	new_node = hclge_find_mac_node(list, new_addr);
+	if (!new_node) {
+		new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
+		if (!new_node)
+			return -ENOMEM;
+
+		new_node->state = HCLGE_MAC_TO_ADD;
+		ether_addr_copy(new_node->mac_addr, new_addr);
+		list_add(&new_node->node, list);
+	} else {
+		if (new_node->state == HCLGE_MAC_TO_DEL)
+			new_node->state = HCLGE_MAC_ACTIVE;
+
+		/* make sure the new addr is in the list head, avoid dev
+		 * addr may be not re-added into mac table for the umv space
+		 * limitation after global/imp reset which will clear mac
+		 * table by hardware.
+		 */
+		list_move(&new_node->node, list);
+	}
+
+	if (old_addr && !ether_addr_equal(old_addr, new_addr)) {
+		old_node = hclge_find_mac_node(list, old_addr);
+		if (old_node) {
+			if (old_node->state == HCLGE_MAC_TO_ADD) {
+				list_del(&old_node->node);
+				kfree(old_node);
+			} else {
+				old_node->state = HCLGE_MAC_TO_DEL;
+			}
+		}
+	}
+
+	set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state);
+
+	return 0;
+}
+
 static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p,
 			      bool is_first)
 {
 	const unsigned char *new_addr = (const unsigned char *)p;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	unsigned char *old_addr = NULL;
 	int ret;
 
 	/* mac addr check */
@@ -7760,39 +8133,42 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p,
 	    is_broadcast_ether_addr(new_addr) ||
 	    is_multicast_ether_addr(new_addr)) {
 		dev_err(&hdev->pdev->dev,
-			"Change uc mac err! invalid mac:%pM.\n",
+			"change uc mac err! invalid mac: %pM.\n",
 			 new_addr);
 		return -EINVAL;
 	}
 
-	if ((!is_first || is_kdump_kernel()) &&
-	    hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr))
-		dev_warn(&hdev->pdev->dev,
-			 "remove old uc mac address fail.\n");
-
-	ret = hclge_add_uc_addr(handle, new_addr);
+	ret = hclge_pause_addr_cfg(hdev, new_addr);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"add uc mac address fail, ret =%d.\n",
+			"failed to configure mac pause address, ret = %d\n",
 			ret);
-
-		if (!is_first &&
-		    hclge_add_uc_addr(handle, hdev->hw.mac.mac_addr))
-			dev_err(&hdev->pdev->dev,
-				"restore uc mac address fail.\n");
-
-		return -EIO;
+		return ret;
 	}
 
-	ret = hclge_pause_addr_cfg(hdev, new_addr);
+	if (!is_first)
+		old_addr = hdev->hw.mac.mac_addr;
+
+	spin_lock_bh(&vport->mac_list_lock);
+	ret = hclge_update_mac_node_for_dev_addr(vport, old_addr, new_addr);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"configure mac pause address fail, ret =%d.\n",
-			ret);
-		return -EIO;
-	}
+			"failed to change the mac addr:%pM, ret = %d\n",
+			new_addr, ret);
+		spin_unlock_bh(&vport->mac_list_lock);
+
+		if (!is_first)
+			hclge_pause_addr_cfg(hdev, old_addr);
 
+		return ret;
+	}
+	/* we must update dev addr with spin lock protect, preventing dev addr
+	 * being removed by set_rx_mode path.
+	 */
 	ether_addr_copy(hdev->hw.mac.mac_addr, new_addr);
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	hclge_task_schedule(hdev, 0);
 
 	return 0;
 }
@@ -8408,6 +8784,37 @@ static void hclge_restore_vlan_table(struct hnae3_handle *handle)
 	}
 }
 
+/* For global reset and imp reset, hardware will clear the mac table,
+ * so we change the mac address state from ACTIVE to TO_ADD, then they
+ * can be restored in the service task after reset complete. Furtherly,
+ * the mac addresses with state TO_DEL or DEL_FAIL are unnecessary to
+ * be restored after reset, so just remove these mac nodes from mac_list.
+ */
+static void hclge_mac_node_convert_for_reset(struct list_head *list)
+{
+	struct hclge_mac_node *mac_node, *tmp;
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		if (mac_node->state == HCLGE_MAC_ACTIVE) {
+			mac_node->state = HCLGE_MAC_TO_ADD;
+		} else if (mac_node->state == HCLGE_MAC_TO_DEL) {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		}
+	}
+}
+
+void hclge_restore_mac_table_common(struct hclge_vport *vport)
+{
+	spin_lock_bh(&vport->mac_list_lock);
+
+	hclge_mac_node_convert_for_reset(&vport->uc_mac_list);
+	hclge_mac_node_convert_for_reset(&vport->mc_mac_list);
+	set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state);
+
+	spin_unlock_bh(&vport->mac_list_lock);
+}
+
 int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -9899,6 +10306,15 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
 	hclge_stats_clear(hdev);
+	/* NOTE: pf reset needn't to clear or restore pf and vf table entry.
+	 * so here should not clean table in memory.
+	 */
+	if (hdev->reset_type == HNAE3_IMP_RESET ||
+	    hdev->reset_type == HNAE3_GLOBAL_RESET) {
+		bitmap_set(hdev->vport_config_block, 0, hdev->num_alloc_vport);
+		hclge_reset_umv_space(hdev);
+	}
+
 	memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table));
 	memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full));
 
@@ -9914,8 +10330,6 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	hclge_reset_umv_space(hdev);
-
 	ret = hclge_mac_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret);
@@ -10011,6 +10425,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_clear_vf_vlan(hdev);
 	hclge_misc_affinity_teardown(hdev);
 	hclge_state_uninit(hdev);
+	hclge_uninit_mac_table(hdev);
 
 	if (mac->phydev)
 		mdiobus_unregister(mac->mdio_bus);
@@ -10028,7 +10443,6 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_misc_irq_uninit(hdev);
 	hclge_pci_uninit(hdev);
 	mutex_destroy(&hdev->vport_lock);
-	hclge_uninit_vport_mac_table(hdev);
 	hclge_uninit_vport_vlan_table(hdev);
 	ae_dev->priv = NULL;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index a58c26200ea0..5fcbc3d23f21 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -630,9 +630,15 @@ struct hclge_fd_ad_data {
 	u16 rule_id;
 };
 
-struct hclge_vport_mac_addr_cfg {
+enum HCLGE_MAC_NODE_STATE {
+	HCLGE_MAC_TO_ADD,
+	HCLGE_MAC_TO_DEL,
+	HCLGE_MAC_ACTIVE
+};
+
+struct hclge_mac_node {
 	struct list_head node;
-	int hd_tbl_status;
+	enum HCLGE_MAC_NODE_STATE state;
 	u8 mac_addr[ETH_ALEN];
 };
 
@@ -805,6 +811,8 @@ struct hclge_dev {
 	unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)];
 	unsigned long vf_vlan_full[BITS_TO_LONGS(HCLGE_VPORT_NUM)];
 
+	unsigned long vport_config_block[BITS_TO_LONGS(HCLGE_VPORT_NUM)];
+
 	struct hclge_fd_cfg fd_cfg;
 	struct hlist_head fd_rule_list;
 	spinlock_t fd_rule_lock; /* protect fd_rule_list and fd_bmap */
@@ -866,6 +874,7 @@ struct hclge_rss_tuple_cfg {
 
 enum HCLGE_VPORT_STATE {
 	HCLGE_VPORT_STATE_ALIVE,
+	HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
 	HCLGE_VPORT_STATE_MAX
 };
 
@@ -922,6 +931,7 @@ struct hclge_vport {
 	u32 mps; /* Max packet size */
 	struct hclge_vf_info vf_info;
 
+	spinlock_t mac_list_lock; /* protect mac address need to add/detele */
 	struct list_head uc_mac_list;   /* Store VF unicast table */
 	struct list_head mc_mac_list;   /* Store VF multicast table */
 	struct list_head vlan_list;     /* Store VF vlan table */
@@ -977,16 +987,17 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf);
 u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
 int hclge_notify_client(struct hclge_dev *hdev,
 			enum hnae3_reset_notify_type type);
-void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
-			       enum HCLGE_MAC_ADDR_TYPE mac_type);
-void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
-			      bool is_write_tbl,
-			      enum HCLGE_MAC_ADDR_TYPE mac_type);
+int hclge_update_mac_list(struct hclge_vport *vport,
+			  enum HCLGE_MAC_NODE_STATE state,
+			  enum HCLGE_MAC_ADDR_TYPE mac_type,
+			  const unsigned char *addr);
+int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport,
+				       const u8 *old_addr, const u8 *new_addr);
 void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
 				  enum HCLGE_MAC_ADDR_TYPE mac_type);
-void hclge_uninit_vport_mac_table(struct hclge_dev *hdev);
 void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list);
 void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev);
+void hclge_restore_mac_table_common(struct hclge_vport *vport);
 int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 				    struct hclge_vlan_info *vlan_info);
 int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 103c2ec777b0..0efc04562ba6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -275,26 +275,17 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
 		if (!is_valid_ether_addr(mac_addr))
 			return -EINVAL;
 
-		hclge_rm_uc_addr_common(vport, old_addr);
-		status = hclge_add_uc_addr_common(vport, mac_addr);
-		if (status) {
-			hclge_add_uc_addr_common(vport, old_addr);
-		} else {
-			hclge_rm_vport_mac_table(vport, mac_addr,
-						 false, HCLGE_MAC_ADDR_UC);
-			hclge_add_vport_mac_table(vport, mac_addr,
-						  HCLGE_MAC_ADDR_UC);
-		}
+		spin_lock_bh(&vport->mac_list_lock);
+		status = hclge_update_mac_node_for_dev_addr(vport, old_addr,
+							    mac_addr);
+		spin_unlock_bh(&vport->mac_list_lock);
+		hclge_task_schedule(hdev, 0);
 	} else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_UC_ADD) {
-		status = hclge_add_uc_addr_common(vport, mac_addr);
-		if (!status)
-			hclge_add_vport_mac_table(vport, mac_addr,
-						  HCLGE_MAC_ADDR_UC);
+		status = hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD,
+					       HCLGE_MAC_ADDR_UC, mac_addr);
 	} else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_UC_REMOVE) {
-		status = hclge_rm_uc_addr_common(vport, mac_addr);
-		if (!status)
-			hclge_rm_vport_mac_table(vport, mac_addr,
-						 false, HCLGE_MAC_ADDR_UC);
+		status = hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL,
+					       HCLGE_MAC_ADDR_UC, mac_addr);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set unicast mac addr, unknown subcode %u\n",
@@ -310,18 +301,13 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 {
 	const u8 *mac_addr = (const u8 *)(mbx_req->msg.data);
 	struct hclge_dev *hdev = vport->back;
-	int status;
 
 	if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_MC_ADD) {
-		status = hclge_add_mc_addr_common(vport, mac_addr);
-		if (!status)
-			hclge_add_vport_mac_table(vport, mac_addr,
-						  HCLGE_MAC_ADDR_MC);
+		hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD,
+				      HCLGE_MAC_ADDR_MC, mac_addr);
 	} else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_MC_REMOVE) {
-		status = hclge_rm_mc_addr_common(vport, mac_addr);
-		if (!status)
-			hclge_rm_vport_mac_table(vport, mac_addr,
-						 false, HCLGE_MAC_ADDR_MC);
+		hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL,
+				      HCLGE_MAC_ADDR_MC, mac_addr);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set mcast mac addr, unknown subcode %u\n",
@@ -329,7 +315,7 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 		return -EIO;
 	}
 
-	return status;
+	return 0;
 }
 
 int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index e02d427131ee..05d485a48706 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1245,10 +1245,12 @@ static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p,
 	int status;
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST, 0);
-	send_msg.subcode = is_first ? HCLGE_MBX_MAC_VLAN_UC_ADD :
-			HCLGE_MBX_MAC_VLAN_UC_MODIFY;
+	send_msg.subcode = HCLGE_MBX_MAC_VLAN_UC_MODIFY;
 	ether_addr_copy(send_msg.data, new_mac_addr);
-	ether_addr_copy(&send_msg.data[ETH_ALEN], old_mac_addr);
+	if (is_first && !hdev->has_pf_mac)
+		eth_zero_addr(&send_msg.data[ETH_ALEN]);
+	else
+		ether_addr_copy(&send_msg.data[ETH_ALEN], old_mac_addr);
 	status = hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0);
 	if (!status)
 		ether_addr_copy(hdev->hw.mac.mac_addr, new_mac_addr);
@@ -1256,54 +1258,302 @@ static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p,
 	return status;
 }
 
-static int hclgevf_add_uc_addr(struct hnae3_handle *handle,
-			       const unsigned char *addr)
+static struct hclgevf_mac_addr_node *
+hclgevf_find_mac_node(struct list_head *list, const u8 *mac_addr)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp;
+
+	list_for_each_entry_safe(mac_node, tmp, list, node)
+		if (ether_addr_equal(mac_addr, mac_node->mac_addr))
+			return mac_node;
+
+	return NULL;
+}
+
+static void hclgevf_update_mac_node(struct hclgevf_mac_addr_node *mac_node,
+				    enum HCLGEVF_MAC_NODE_STATE state)
+{
+	switch (state) {
+	/* from set_rx_mode or tmp_add_list */
+	case HCLGEVF_MAC_TO_ADD:
+		if (mac_node->state == HCLGEVF_MAC_TO_DEL)
+			mac_node->state = HCLGEVF_MAC_ACTIVE;
+		break;
+	/* only from set_rx_mode */
+	case HCLGEVF_MAC_TO_DEL:
+		if (mac_node->state == HCLGEVF_MAC_TO_ADD) {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else {
+			mac_node->state = HCLGEVF_MAC_TO_DEL;
+		}
+		break;
+	/* only from tmp_add_list, the mac_node->state won't be
+	 * HCLGEVF_MAC_ACTIVE
+	 */
+	case HCLGEVF_MAC_ACTIVE:
+		if (mac_node->state == HCLGEVF_MAC_TO_ADD)
+			mac_node->state = HCLGEVF_MAC_ACTIVE;
+		break;
+	}
+}
+
+static int hclgevf_update_mac_list(struct hnae3_handle *handle,
+				   enum HCLGEVF_MAC_NODE_STATE state,
+				   enum HCLGEVF_MAC_ADDR_TYPE mac_type,
+				   const unsigned char *addr)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	struct hclge_vf_to_pf_msg send_msg;
+	struct hclgevf_mac_addr_node *mac_node;
+	struct list_head *list;
 
-	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST,
-			       HCLGE_MBX_MAC_VLAN_UC_ADD);
-	ether_addr_copy(send_msg.data, addr);
-	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
+	list = (mac_type == HCLGEVF_MAC_ADDR_UC) ?
+	       &hdev->mac_table.uc_mac_list : &hdev->mac_table.mc_mac_list;
+
+	spin_lock_bh(&hdev->mac_table.mac_list_lock);
+
+	/* if the mac addr is already in the mac list, no need to add a new
+	 * one into it, just check the mac addr state, convert it to a new
+	 * new state, or just remove it, or do nothing.
+	 */
+	mac_node = hclgevf_find_mac_node(list, addr);
+	if (mac_node) {
+		hclgevf_update_mac_node(mac_node, state);
+		spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+		return 0;
+	}
+	/* if this address is never added, unnecessary to delete */
+	if (state == HCLGEVF_MAC_TO_DEL) {
+		spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+		return -ENOENT;
+	}
+
+	mac_node = kzalloc(sizeof(*mac_node), GFP_ATOMIC);
+	if (!mac_node) {
+		spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+		return -ENOMEM;
+	}
+
+	mac_node->state = state;
+	ether_addr_copy(mac_node->mac_addr, addr);
+	list_add_tail(&mac_node->node, list);
+
+	spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+	return 0;
+}
+
+static int hclgevf_add_uc_addr(struct hnae3_handle *handle,
+			       const unsigned char *addr)
+{
+	return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_ADD,
+				       HCLGEVF_MAC_ADDR_UC, addr);
 }
 
 static int hclgevf_rm_uc_addr(struct hnae3_handle *handle,
 			      const unsigned char *addr)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	struct hclge_vf_to_pf_msg send_msg;
-
-	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST,
-			       HCLGE_MBX_MAC_VLAN_UC_REMOVE);
-	ether_addr_copy(send_msg.data, addr);
-	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
+	return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_DEL,
+				       HCLGEVF_MAC_ADDR_UC, addr);
 }
 
 static int hclgevf_add_mc_addr(struct hnae3_handle *handle,
 			       const unsigned char *addr)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	struct hclge_vf_to_pf_msg send_msg;
-
-	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_MULTICAST,
-			       HCLGE_MBX_MAC_VLAN_MC_ADD);
-	ether_addr_copy(send_msg.data, addr);
-	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
+	return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_ADD,
+				       HCLGEVF_MAC_ADDR_MC, addr);
 }
 
 static int hclgevf_rm_mc_addr(struct hnae3_handle *handle,
 			      const unsigned char *addr)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_DEL,
+				       HCLGEVF_MAC_ADDR_MC, addr);
+}
+
+static int hclgevf_add_del_mac_addr(struct hclgevf_dev *hdev,
+				    struct hclgevf_mac_addr_node *mac_node,
+				    enum HCLGEVF_MAC_ADDR_TYPE mac_type)
+{
 	struct hclge_vf_to_pf_msg send_msg;
+	u8 code, subcode;
 
-	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_MULTICAST,
-			       HCLGE_MBX_MAC_VLAN_MC_REMOVE);
-	ether_addr_copy(send_msg.data, addr);
+	if (mac_type == HCLGEVF_MAC_ADDR_UC) {
+		code = HCLGE_MBX_SET_UNICAST;
+		if (mac_node->state == HCLGEVF_MAC_TO_ADD)
+			subcode = HCLGE_MBX_MAC_VLAN_UC_ADD;
+		else
+			subcode = HCLGE_MBX_MAC_VLAN_UC_REMOVE;
+	} else {
+		code = HCLGE_MBX_SET_MULTICAST;
+		if (mac_node->state == HCLGEVF_MAC_TO_ADD)
+			subcode = HCLGE_MBX_MAC_VLAN_MC_ADD;
+		else
+			subcode = HCLGE_MBX_MAC_VLAN_MC_REMOVE;
+	}
+
+	hclgevf_build_send_msg(&send_msg, code, subcode);
+	ether_addr_copy(send_msg.data, mac_node->mac_addr);
 	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
 }
 
+static void hclgevf_config_mac_list(struct hclgevf_dev *hdev,
+				    struct list_head *list,
+				    enum HCLGEVF_MAC_ADDR_TYPE mac_type)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp;
+	int ret;
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		ret = hclgevf_add_del_mac_addr(hdev, mac_node, mac_type);
+		if  (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to configure mac %pM, state = %d, ret = %d\n",
+				mac_node->mac_addr, mac_node->state, ret);
+			return;
+		}
+		if (mac_node->state == HCLGEVF_MAC_TO_ADD) {
+			mac_node->state = HCLGEVF_MAC_ACTIVE;
+		} else {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		}
+	}
+}
+
+static void hclgevf_sync_from_add_list(struct list_head *add_list,
+				       struct list_head *mac_list)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node;
+
+	list_for_each_entry_safe(mac_node, tmp, add_list, node) {
+		/* if the mac address from tmp_add_list is not in the
+		 * uc/mc_mac_list, it means have received a TO_DEL request
+		 * during the time window of sending mac config request to PF
+		 * If mac_node state is ACTIVE, then change its state to TO_DEL,
+		 * then it will be removed at next time. If is TO_ADD, it means
+		 * send TO_ADD request failed, so just remove the mac node.
+		 */
+		new_node = hclgevf_find_mac_node(mac_list, mac_node->mac_addr);
+		if (new_node) {
+			hclgevf_update_mac_node(new_node, mac_node->state);
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else if (mac_node->state == HCLGEVF_MAC_ACTIVE) {
+			mac_node->state = HCLGEVF_MAC_TO_DEL;
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, mac_list);
+		} else {
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		}
+	}
+}
+
+static void hclgevf_sync_from_del_list(struct list_head *del_list,
+				       struct list_head *mac_list)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node;
+
+	list_for_each_entry_safe(mac_node, tmp, del_list, node) {
+		new_node = hclgevf_find_mac_node(mac_list, mac_node->mac_addr);
+		if (new_node) {
+			/* If the mac addr is exist in the mac list, it means
+			 * received a new request TO_ADD during the time window
+			 * of sending mac addr configurrequest to PF, so just
+			 * change the mac state to ACTIVE.
+			 */
+			new_node->state = HCLGEVF_MAC_ACTIVE;
+			list_del(&mac_node->node);
+			kfree(mac_node);
+		} else {
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, mac_list);
+		}
+	}
+}
+
+static void hclgevf_clear_list(struct list_head *list)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp;
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		list_del(&mac_node->node);
+		kfree(mac_node);
+	}
+}
+
+static void hclgevf_sync_mac_list(struct hclgevf_dev *hdev,
+				  enum HCLGEVF_MAC_ADDR_TYPE mac_type)
+{
+	struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node;
+	struct list_head tmp_add_list, tmp_del_list;
+	struct list_head *list;
+
+	INIT_LIST_HEAD(&tmp_add_list);
+	INIT_LIST_HEAD(&tmp_del_list);
+
+	/* move the mac addr to the tmp_add_list and tmp_del_list, then
+	 * we can add/delete these mac addr outside the spin lock
+	 */
+	list = (mac_type == HCLGEVF_MAC_ADDR_UC) ?
+		&hdev->mac_table.uc_mac_list : &hdev->mac_table.mc_mac_list;
+
+	spin_lock_bh(&hdev->mac_table.mac_list_lock);
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		switch (mac_node->state) {
+		case HCLGEVF_MAC_TO_DEL:
+			list_del(&mac_node->node);
+			list_add_tail(&mac_node->node, &tmp_del_list);
+			break;
+		case HCLGEVF_MAC_TO_ADD:
+			new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
+			if (!new_node)
+				goto stop_traverse;
+
+			ether_addr_copy(new_node->mac_addr, mac_node->mac_addr);
+			new_node->state = mac_node->state;
+			list_add_tail(&new_node->node, &tmp_add_list);
+			break;
+		default:
+			break;
+		}
+	}
+
+stop_traverse:
+	spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+
+	/* delete first, in order to get max mac table space for adding */
+	hclgevf_config_mac_list(hdev, &tmp_del_list, mac_type);
+	hclgevf_config_mac_list(hdev, &tmp_add_list, mac_type);
+
+	/* if some mac addresses were added/deleted fail, move back to the
+	 * mac_list, and retry at next time.
+	 */
+	spin_lock_bh(&hdev->mac_table.mac_list_lock);
+
+	hclgevf_sync_from_del_list(&tmp_del_list, list);
+	hclgevf_sync_from_add_list(&tmp_add_list, list);
+
+	spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+}
+
+static void hclgevf_sync_mac_table(struct hclgevf_dev *hdev)
+{
+	hclgevf_sync_mac_list(hdev, HCLGEVF_MAC_ADDR_UC);
+	hclgevf_sync_mac_list(hdev, HCLGEVF_MAC_ADDR_MC);
+}
+
+static void hclgevf_uninit_mac_list(struct hclgevf_dev *hdev)
+{
+	spin_lock_bh(&hdev->mac_table.mac_list_lock);
+
+	hclgevf_clear_list(&hdev->mac_table.uc_mac_list);
+	hclgevf_clear_list(&hdev->mac_table.mc_mac_list);
+
+	spin_unlock_bh(&hdev->mac_table.mac_list_lock);
+}
+
 static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 				   __be16 proto, u16 vlan_id,
 				   bool is_kill)
@@ -1951,6 +2201,8 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev)
 
 	hclgevf_sync_vlan_filter(hdev);
 
+	hclgevf_sync_mac_table(hdev);
+
 	hdev->last_serv_processed = jiffies;
 
 out:
@@ -2313,6 +2565,10 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
 	mutex_init(&hdev->mbx_resp.mbx_mutex);
 	sema_init(&hdev->reset_sem, 1);
 
+	spin_lock_init(&hdev->mac_table.mac_list_lock);
+	INIT_LIST_HEAD(&hdev->mac_table.uc_mac_list);
+	INIT_LIST_HEAD(&hdev->mac_table.mc_mac_list);
+
 	/* bring the device down */
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 }
@@ -2846,6 +3102,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 
 	hclgevf_pci_uninit(hdev);
 	hclgevf_cmd_uninit(hdev);
+	hclgevf_uninit_mac_list(hdev);
 }
 
 static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 3b88d866facc..0222d9b87a42 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -234,6 +234,29 @@ struct hclgevf_rst_stats {
 	u32 rst_fail_cnt;		/* the number of VF reset fail */
 };
 
+enum HCLGEVF_MAC_ADDR_TYPE {
+	HCLGEVF_MAC_ADDR_UC,
+	HCLGEVF_MAC_ADDR_MC
+};
+
+enum HCLGEVF_MAC_NODE_STATE {
+	HCLGEVF_MAC_TO_ADD,
+	HCLGEVF_MAC_TO_DEL,
+	HCLGEVF_MAC_ACTIVE
+};
+
+struct hclgevf_mac_addr_node {
+	struct list_head node;
+	enum HCLGEVF_MAC_NODE_STATE state;
+	u8 mac_addr[ETH_ALEN];
+};
+
+struct hclgevf_mac_table_cfg {
+	spinlock_t mac_list_lock; /* protect mac address need to add/detele */
+	struct list_head uc_mac_list;
+	struct list_head mc_mac_list;
+};
+
 struct hclgevf_dev {
 	struct pci_dev *pdev;
 	struct hnae3_ae_dev *ae_dev;
@@ -282,6 +305,8 @@ struct hclgevf_dev {
 
 	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 
+	struct hclgevf_mac_table_cfg mac_table;
+
 	bool mbx_event_pending;
 	struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
-- 
cgit v1.2.3


From f671237a4b4521dfde5f96c2b088287712e72f4b Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:10 +0800
Subject: net: hns3: add support for dumping UC and MC MAC list

This patch adds support for dumping entries of UC and MC MAC list,
which help checking whether a MAC address being added into hardware
or not.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c |  2 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 51 ++++++++++++++++++++++
 2 files changed, 53 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index c934f328c040..fe7fb565da19 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -262,6 +262,8 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump mac tnl status\n");
 	dev_info(&h->pdev->dev, "dump loopback\n");
 	dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n");
+	dev_info(&h->pdev->dev, "dump uc mac list <func id>\n");
+	dev_info(&h->pdev->dev, "dump mc mac list <func id>\n");
 
 	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
 	strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 66c1ad3a156b..6cfa8253eefc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -1441,6 +1441,49 @@ static void hclge_dbg_dump_qs_shaper(struct hclge_dev *hdev,
 	hclge_dbg_dump_qs_shaper_single(hdev, qsid);
 }
 
+static int hclge_dbg_dump_mac_list(struct hclge_dev *hdev, const char *cmd_buf,
+				   bool is_unicast)
+{
+	struct hclge_mac_node *mac_node, *tmp;
+	struct hclge_vport *vport;
+	struct list_head *list;
+	u32 func_id;
+	int ret;
+
+	ret = kstrtouint(cmd_buf, 0, &func_id);
+	if (ret < 0) {
+		dev_err(&hdev->pdev->dev,
+			"dump mac list: bad command string, ret = %d\n", ret);
+		return -EINVAL;
+	}
+
+	if (func_id >= hdev->num_alloc_vport) {
+		dev_err(&hdev->pdev->dev,
+			"function id(%u) is out of range(0-%u)\n", func_id,
+			hdev->num_alloc_vport - 1);
+		return -EINVAL;
+	}
+
+	vport = &hdev->vport[func_id];
+
+	list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list;
+
+	dev_info(&hdev->pdev->dev, "vport %u %s mac list:\n",
+		 func_id, is_unicast ? "uc" : "mc");
+	dev_info(&hdev->pdev->dev, "mac address              state\n");
+
+	spin_lock_bh(&vport->mac_list_lock);
+
+	list_for_each_entry_safe(mac_node, tmp, list, node) {
+		dev_info(&hdev->pdev->dev, "%pM         %d\n",
+			 mac_node->mac_addr, mac_node->state);
+	}
+
+	spin_unlock_bh(&vport->mac_list_lock);
+
+	return 0;
+}
+
 int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
 {
 #define DUMP_REG	"dump reg"
@@ -1485,6 +1528,14 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
 	} else if (strncmp(cmd_buf, "dump qs shaper", 14) == 0) {
 		hclge_dbg_dump_qs_shaper(hdev,
 					 &cmd_buf[sizeof("dump qs shaper")]);
+	} else if (strncmp(cmd_buf, "dump uc mac list", 16) == 0) {
+		hclge_dbg_dump_mac_list(hdev,
+					&cmd_buf[sizeof("dump uc mac list")],
+					true);
+	} else if (strncmp(cmd_buf, "dump mc mac list", 16) == 0) {
+		hclge_dbg_dump_mac_list(hdev,
+					&cmd_buf[sizeof("dump mc mac list")],
+					false);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From c631c696823cdddbf3c683c3b78812ecba31c350 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:11 +0800
Subject: net: hns3: refactor the promisc mode setting

As the HNS3 driver doesn't update the MAC address directly in
function hns3_set_rx_mode() now, it can't know whether the
MAC table is full from __dev_uc_sync() and __dev_mc_sync(),
so it's senseless to handle the overflow promisc here.

This patch removes the handle of overflow promisc from function
hns3_set_rx_mode(), and updates the promisc mode in the service
task.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  3 +
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 42 +++-------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c |  2 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 89 ++++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  4 +
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 26 +++++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 8 files changed, 122 insertions(+), 46 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 5587605d6deb..a56f8d623349 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -270,6 +270,8 @@ struct hnae3_ae_dev {
  *   Set loopback
  * set_promisc_mode
  *   Set promisc mode
+ * request_update_promisc_mode
+ *   request to hclge(vf) to update promisc mode
  * set_mtu()
  *   set mtu
  * get_pauseparam()
@@ -408,6 +410,7 @@ struct hnae3_ae_ops {
 
 	int (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc,
 				bool en_mc_pmc);
+	void (*request_update_promisc_mode)(struct hnae3_handle *handle);
 	int (*set_mtu)(struct hnae3_handle *handle, int new_mtu);
 
 	void (*get_pauseparam)(struct hnae3_handle *handle,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 341e8b5cd219..6b9535c17647 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -601,34 +601,25 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	u8 new_flags;
-	int ret;
 
 	new_flags = hns3_get_netdev_flags(netdev);
 
-	ret = __dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync);
-	if (ret) {
-		netdev_err(netdev, "sync uc address fail\n");
-		if (ret == -ENOSPC)
-			new_flags |= HNAE3_OVERFLOW_UPE;
-	}
-
-	if (netdev->flags & IFF_MULTICAST) {
-		ret = __dev_mc_sync(netdev, hns3_nic_mc_sync,
-				    hns3_nic_mc_unsync);
-		if (ret) {
-			netdev_err(netdev, "sync mc address fail\n");
-			if (ret == -ENOSPC)
-				new_flags |= HNAE3_OVERFLOW_MPE;
-		}
-	}
+	__dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync);
+	__dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync);
 
 	/* User mode Promisc mode enable and vlan filtering is disabled to
-	 * let all packets in. MAC-VLAN Table overflow Promisc enabled and
-	 * vlan fitering is enabled
+	 * let all packets in.
 	 */
-	hns3_enable_vlan_filter(netdev, new_flags & HNAE3_VLAN_FLTR);
 	h->netdev_flags = new_flags;
-	hns3_update_promisc_mode(netdev, new_flags);
+	hns3_request_update_promisc_mode(h);
+}
+
+void hns3_request_update_promisc_mode(struct hnae3_handle *handle)
+{
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+
+	if (ops->request_update_promisc_mode)
+		ops->request_update_promisc_mode(handle);
 }
 
 int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
@@ -4467,15 +4458,6 @@ err_put_ring:
 static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle)
 {
 	struct net_device *netdev = handle->kinfo.netdev;
-	bool vlan_filter_enable;
-	int ret;
-
-	ret = hns3_update_promisc_mode(netdev, handle->netdev_flags);
-	if (ret)
-		return ret;
-
-	vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true;
-	hns3_enable_vlan_filter(netdev, vlan_filter_enable);
 
 	if (handle->ae_algo->ops->restore_vlan_table)
 		handle->ae_algo->ops->restore_vlan_table(handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 4b3f0abf0715..53bc0edf9b6f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -658,6 +658,7 @@ void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector,
 
 void hns3_enable_vlan_filter(struct net_device *netdev, bool enable);
 int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags);
+void hns3_request_update_promisc_mode(struct hnae3_handle *handle);
 
 #ifdef CONFIG_HNS3_DCB
 void hns3_dcbnl_setup(struct hnae3_handle *handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 6a0734be4a1a..4d9c85f049dc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -99,7 +99,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 		h->ae_algo->ops->set_promisc_mode(h, true, true);
 	} else {
 		/* recover promisc mode before loopback test */
-		hns3_update_promisc_mode(ndev, h->netdev_flags);
+		hns3_request_update_promisc_mode(h);
 		vlan_filter_enable = ndev->flags & IFF_PROMISC ? false : true;
 		hns3_enable_vlan_filter(ndev, vlan_filter_enable);
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c3205ae620ce..71ff0fa64f46 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -69,6 +69,7 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 static int hclge_set_default_loopback(struct hclge_dev *hdev);
 
 static void hclge_sync_mac_table(struct hclge_dev *hdev);
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -3975,6 +3976,7 @@ static void hclge_periodic_service_task(struct hclge_dev *hdev)
 	 */
 	hclge_update_link_status(hdev);
 	hclge_sync_mac_table(hdev);
+	hclge_sync_promisc_mode(hdev);
 
 	if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) {
 		delta = jiffies - hdev->last_serv_processed;
@@ -4724,7 +4726,8 @@ static int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev,
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
-			"Set promisc mode fail, status is %d.\n", ret);
+			"failed to set vport %d promisc mode, ret = %d.\n",
+			param->vf_id, ret);
 
 	return ret;
 }
@@ -4774,6 +4777,14 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 					    en_bc_pmc);
 }
 
+static void hclge_request_update_promisc_mode(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+}
+
 static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode)
 {
 	struct hclge_get_fd_mode_cmd *req;
@@ -6972,17 +6983,11 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport,
 	}
 
 	if (op == HCLGE_MAC_VLAN_ADD) {
-		if ((!resp_code) || (resp_code == 1)) {
+		if (!resp_code || resp_code == 1)
 			return 0;
-		} else if (resp_code == HCLGE_ADD_UC_OVERFLOW) {
-			dev_err(&hdev->pdev->dev,
-				"add mac addr failed for uc_overflow.\n");
-			return -ENOSPC;
-		} else if (resp_code == HCLGE_ADD_MC_OVERFLOW) {
-			dev_err(&hdev->pdev->dev,
-				"add mac addr failed for mc_overflow.\n");
+		else if (resp_code == HCLGE_ADD_UC_OVERFLOW ||
+			 resp_code == HCLGE_ADD_MC_OVERFLOW)
 			return -ENOSPC;
-		}
 
 		dev_err(&hdev->pdev->dev,
 			"add mac addr failed for undefined, code=%u.\n",
@@ -7448,8 +7453,9 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 			return ret;
 		}
 
-		dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n",
-			hdev->priv_umv_size);
+		if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE))
+			dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n",
+				hdev->priv_umv_size);
 
 		return -ENOSPC;
 	}
@@ -7543,7 +7549,9 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 		return status;
 	status = hclge_add_mac_vlan_tbl(vport, &req, desc);
 
-	if (status == -ENOSPC)
+	/* if already overflow, not to print each time */
+	if (status == -ENOSPC &&
+	    !(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE))
 		dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n");
 
 	return status;
@@ -7638,12 +7646,16 @@ static void hclge_unsync_vport_mac_list(struct hclge_vport *vport,
 	}
 }
 
-static void hclge_sync_from_add_list(struct list_head *add_list,
+static bool hclge_sync_from_add_list(struct list_head *add_list,
 				     struct list_head *mac_list)
 {
 	struct hclge_mac_node *mac_node, *tmp, *new_node;
+	bool all_added = true;
 
 	list_for_each_entry_safe(mac_node, tmp, add_list, node) {
+		if (mac_node->state == HCLGE_MAC_TO_ADD)
+			all_added = false;
+
 		/* if the mac address from tmp_add_list is not in the
 		 * uc/mc_mac_list, it means have received a TO_DEL request
 		 * during the time window of adding the mac address into mac
@@ -7666,6 +7678,8 @@ static void hclge_sync_from_add_list(struct list_head *add_list,
 			kfree(mac_node);
 		}
 	}
+
+	return all_added;
 }
 
 static void hclge_sync_from_del_list(struct list_head *del_list,
@@ -7693,12 +7707,30 @@ static void hclge_sync_from_del_list(struct list_head *del_list,
 	}
 }
 
+static void hclge_update_overflow_flags(struct hclge_vport *vport,
+					enum HCLGE_MAC_ADDR_TYPE mac_type,
+					bool is_all_added)
+{
+	if (mac_type == HCLGE_MAC_ADDR_UC) {
+		if (is_all_added)
+			vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE;
+		else
+			vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE;
+	} else {
+		if (is_all_added)
+			vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_MPE;
+		else
+			vport->overflow_promisc_flags |= HNAE3_OVERFLOW_MPE;
+	}
+}
+
 static void hclge_sync_vport_mac_table(struct hclge_vport *vport,
 				       enum HCLGE_MAC_ADDR_TYPE mac_type)
 {
 	struct hclge_mac_node *mac_node, *tmp, *new_node;
 	struct list_head tmp_add_list, tmp_del_list;
 	struct list_head *list;
+	bool all_added;
 
 	INIT_LIST_HEAD(&tmp_add_list);
 	INIT_LIST_HEAD(&tmp_del_list);
@@ -7752,9 +7784,11 @@ stop_traverse:
 	spin_lock_bh(&vport->mac_list_lock);
 
 	hclge_sync_from_del_list(&tmp_del_list, list);
-	hclge_sync_from_add_list(&tmp_add_list, list);
+	all_added = hclge_sync_from_add_list(&tmp_add_list, list);
 
 	spin_unlock_bh(&vport->mac_list_lock);
+
+	hclge_update_overflow_flags(vport, mac_type, all_added);
 }
 
 static bool hclge_need_sync_mac_table(struct hclge_vport *vport)
@@ -11052,6 +11086,30 @@ static int hclge_gro_en(struct hnae3_handle *handle, bool enable)
 	return hclge_config_gro(hdev, enable);
 }
 
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = &hdev->vport[0];
+	struct hnae3_handle *handle = &vport->nic;
+	u8 tmp_flags = 0;
+	int ret;
+
+	if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
+		set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+		vport->last_promisc_flags = vport->overflow_promisc_flags;
+	}
+
+	if (test_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state)) {
+		tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
+		ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
+					     tmp_flags & HNAE3_MPE);
+		if (!ret) {
+			clear_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+			hclge_enable_vlan_filter(handle,
+						 tmp_flags & HNAE3_VLAN_FLTR);
+		}
+	}
+}
+
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
@@ -11064,6 +11122,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_vector = hclge_get_vector,
 	.put_vector = hclge_put_vector,
 	.set_promisc_mode = hclge_set_promisc_mode,
+	.request_update_promisc_mode = hclge_request_update_promisc_mode,
 	.set_loopback = hclge_set_loopback,
 	.start = hclge_ae_start,
 	.stop = hclge_ae_stop,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 5fcbc3d23f21..85180f4a9b4d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -217,6 +217,7 @@ enum HCLGE_DEV_STATE {
 	HCLGE_STATE_STATISTICS_UPDATING,
 	HCLGE_STATE_CMD_DISABLE,
 	HCLGE_STATE_LINK_UPDATING,
+	HCLGE_STATE_PROMISC_CHANGED,
 	HCLGE_STATE_RST_FAIL,
 	HCLGE_STATE_MAX
 };
@@ -931,6 +932,9 @@ struct hclge_vport {
 	u32 mps; /* Max packet size */
 	struct hclge_vf_info vf_info;
 
+	u8 overflow_promisc_flags;
+	u8 last_promisc_flags;
+
 	spinlock_t mac_list_lock; /* protect mac address need to add/detele */
 	struct list_head uc_mac_list;   /* Store VF unicast table */
 	struct list_head mc_mac_list;   /* Store VF multicast table */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 05d485a48706..fea197fd77cb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1164,6 +1164,27 @@ static int hclgevf_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 					    en_bc_pmc);
 }
 
+static void hclgevf_request_update_promisc_mode(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state);
+}
+
+static void hclgevf_sync_promisc_mode(struct hclgevf_dev *hdev)
+{
+	struct hnae3_handle *handle = &hdev->nic;
+	bool en_uc_pmc = handle->netdev_flags & HNAE3_UPE;
+	bool en_mc_pmc = handle->netdev_flags & HNAE3_MPE;
+	int ret;
+
+	if (test_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state)) {
+		ret = hclgevf_set_promisc_mode(handle, en_uc_pmc, en_mc_pmc);
+		if (!ret)
+			clear_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state);
+	}
+}
+
 static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, unsigned int tqp_id,
 			      int stream_id, bool enable)
 {
@@ -2203,6 +2224,8 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev)
 
 	hclgevf_sync_mac_table(hdev);
 
+	hclgevf_sync_promisc_mode(hdev);
+
 	hdev->last_serv_processed = jiffies;
 
 out:
@@ -2986,6 +3009,8 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state);
+
 	dev_info(&hdev->pdev->dev, "Reset done\n");
 
 	return 0;
@@ -3470,6 +3495,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_timer_task = hclgevf_set_timer_task,
 	.get_link_mode = hclgevf_get_link_mode,
 	.set_promisc_mode = hclgevf_set_promisc_mode,
+	.request_update_promisc_mode = hclgevf_request_update_promisc_mode,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 0222d9b87a42..f19583c4bc9b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -148,6 +148,7 @@ enum hclgevf_states {
 	HCLGEVF_STATE_MBX_HANDLING,
 	HCLGEVF_STATE_CMD_DISABLE,
 	HCLGEVF_STATE_LINK_UPDATING,
+	HCLGEVF_STATE_PROMISC_CHANGED,
 	HCLGEVF_STATE_RST_FAIL,
 };
 
-- 
cgit v1.2.3


From 7d0b345156d0678fbbbf885f991c6d83f23d70f1 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:12 +0800
Subject: net: hns3: use mutex vport_lock instead of mutex umv_lock

Currently, the driver use mutex umv_lock to protect the variable
vport->share_umv_size. And there is already a mutex vport_lock
being defined in the driver, which is designed to protect the
resource of vport. So we can use vport_lock instead of umv_lock.

Furthermore, there is a time window for protect share_umv_size
between checking UMV space and doing MAC configuration in the
lin function hclge_add_uc_addr_common(). It should be extended.

This patch uses mutex vport_lock intead of spin lock umv_lock to
protect share_umv_size, and adjusts the mutex's range.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 31 +++++++++++++---------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 -
 2 files changed, 19 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 71ff0fa64f46..177ef5e93d06 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7250,7 +7250,6 @@ static int hclge_init_umv_space(struct hclge_dev *hdev)
 			 "failed to alloc umv space, want %u, get %u\n",
 			 hdev->wanted_umv_size, allocated_size);
 
-	mutex_init(&hdev->umv_mutex);
 	hdev->max_umv_size = allocated_size;
 	hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_alloc_vport + 1);
 	hdev->share_umv_size = hdev->priv_umv_size +
@@ -7269,21 +7268,25 @@ static void hclge_reset_umv_space(struct hclge_dev *hdev)
 		vport->used_umv_num = 0;
 	}
 
-	mutex_lock(&hdev->umv_mutex);
+	mutex_lock(&hdev->vport_lock);
 	hdev->share_umv_size = hdev->priv_umv_size +
 			hdev->max_umv_size % (hdev->num_alloc_vport + 1);
-	mutex_unlock(&hdev->umv_mutex);
+	mutex_unlock(&hdev->vport_lock);
 }
 
-static bool hclge_is_umv_space_full(struct hclge_vport *vport)
+static bool hclge_is_umv_space_full(struct hclge_vport *vport, bool need_lock)
 {
 	struct hclge_dev *hdev = vport->back;
 	bool is_full;
 
-	mutex_lock(&hdev->umv_mutex);
+	if (need_lock)
+		mutex_lock(&hdev->vport_lock);
+
 	is_full = (vport->used_umv_num >= hdev->priv_umv_size &&
 		   hdev->share_umv_size == 0);
-	mutex_unlock(&hdev->umv_mutex);
+
+	if (need_lock)
+		mutex_unlock(&hdev->vport_lock);
 
 	return is_full;
 }
@@ -7292,7 +7295,6 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free)
 {
 	struct hclge_dev *hdev = vport->back;
 
-	mutex_lock(&hdev->umv_mutex);
 	if (is_free) {
 		if (vport->used_umv_num > hdev->priv_umv_size)
 			hdev->share_umv_size++;
@@ -7305,7 +7307,6 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free)
 			hdev->share_umv_size--;
 		vport->used_umv_num++;
 	}
-	mutex_unlock(&hdev->umv_mutex);
 }
 
 static struct hclge_mac_node *hclge_find_mac_node(struct list_head *list,
@@ -7446,12 +7447,15 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	 */
 	ret = hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false);
 	if (ret == -ENOENT) {
-		if (!hclge_is_umv_space_full(vport)) {
+		mutex_lock(&hdev->vport_lock);
+		if (!hclge_is_umv_space_full(vport, false)) {
 			ret = hclge_add_mac_vlan_tbl(vport, &req, NULL);
 			if (!ret)
 				hclge_update_umv_space(vport, false);
+			mutex_unlock(&hdev->vport_lock);
 			return ret;
 		}
+		mutex_unlock(&hdev->vport_lock);
 
 		if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE))
 			dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n",
@@ -7503,10 +7507,13 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr, false);
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
-	if (!ret)
+	if (!ret) {
+		mutex_lock(&hdev->vport_lock);
 		hclge_update_umv_space(vport, true);
-	else if (ret == -ENOENT)
+		mutex_unlock(&hdev->vport_lock);
+	} else if (ret == -ENOENT) {
 		ret = 0;
+	}
 
 	return ret;
 }
@@ -10163,7 +10170,7 @@ static int hclge_set_vf_spoofchk(struct hnae3_handle *handle, int vf,
 		dev_warn(&hdev->pdev->dev,
 			 "vf %d vlan table is full, enable spoof check may cause its packet send fail\n",
 			 vf);
-	else if (enable && hclge_is_umv_space_full(vport))
+	else if (enable && hclge_is_umv_space_full(vport, true))
 		dev_warn(&hdev->pdev->dev,
 			 "vf %d mac table is full, enable spoof check may cause its packet send fail\n",
 			 vf);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 85180f4a9b4d..8e69651f8bf1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -831,7 +831,6 @@ struct hclge_dev {
 	u16 priv_umv_size;
 	/* unicast mac vlan space shared by PF and its VFs */
 	u16 share_umv_size;
-	struct mutex umv_mutex; /* protect share_umv_size */
 
 	DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats,
 		      HCLGE_MAC_TNL_LOG_SIZE);
-- 
cgit v1.2.3


From 039ba863e8d71c52b1f5faf26b0f458eec33d5e7 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 24 Apr 2020 10:23:13 +0800
Subject: net: hns3: optimize the filter table entries handling when resetting

Currently, the PF driver removes all (including its VFs') MAC/VLAN
flow director table entries when resetting, and restores them after
reset completed.

In fact, the hardware will clear all table entries only in IMP
reset and global reset. So driver only needs to restore the table
entries in these cases, and needs do nothing when PF reset, FLR
or other function level reset.

This patch optimizes it by removing unnecessary table entries clear
and restoring handling in the reset flow, and doing the restoring
after reset completed.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h    |  5 ++
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  5 --
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 33 --------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |  9 ---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 89 +++++++++++-----------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 28 ++++++-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 29 ++++---
 8 files changed, 94 insertions(+), 105 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 948e67ef30fd..21a736174fda 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -45,6 +45,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_GET_MEDIA_TYPE,       /* (VF -> PF) get media type */
 	HCLGE_MBX_PUSH_PROMISC_INFO,	/* (PF -> VF) push vf promisc info */
 	HCLGE_MBX_VF_UNINIT,            /* (VF -> PF) vf is unintializing */
+	HCLGE_MBX_HANDLE_VF_TBL,	/* (VF -> PF) store/clear hw table */
 
 	HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf flr status */
 	HCLGE_MBX_PUSH_LINK_STATUS,	/* (M7 -> PF) get port link status */
@@ -70,6 +71,10 @@ enum hclge_mbx_vlan_cfg_subcode {
 	HCLGE_MBX_GET_PORT_BASE_VLAN_STATE,	/* get port based vlan state */
 };
 
+enum hclge_mbx_tbl_cfg_subcode {
+	HCLGE_MBX_VPORT_LIST_CLEAR,
+};
+
 #define HCLGE_MBX_MAX_MSG_SIZE	14
 #define HCLGE_MBX_MAX_RESP_DATA_SIZE	8U
 #define HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM	4
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a56f8d623349..6291aa9f06b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -233,7 +233,6 @@ struct hnae3_ae_dev {
 	struct list_head node;
 	u32 flag;
 	unsigned long hw_err_reset_req;
-	enum hnae3_reset_type reset_type;
 	void *priv;
 };
 
@@ -356,8 +355,6 @@ struct hnae3_ae_dev {
  *   Set vlan filter config of Ports
  * set_vf_vlan_filter()
  *   Set vlan filter config of vf
- * restore_vlan_table()
- *   Restore vlan filter entries after reset
  * enable_hw_strip_rxvtag()
  *   Enable/disable hardware strip vlan tag of packets received
  * set_gro_en
@@ -528,7 +525,6 @@ struct hnae3_ae_ops {
 				struct ethtool_rxnfc *cmd);
 	int (*get_fd_all_rules)(struct hnae3_handle *handle,
 				struct ethtool_rxnfc *cmd, u32 *rule_locs);
-	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
 	int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id,
 			      u16 flow_id, struct flow_keys *fkeys);
@@ -542,7 +538,6 @@ struct hnae3_ae_ops {
 	void (*set_timer_task)(struct hnae3_handle *handle, bool enable);
 	int (*mac_connect_phy)(struct hnae3_handle *handle);
 	void (*mac_disconnect_phy)(struct hnae3_handle *handle);
-	void (*restore_vlan_table)(struct hnae3_handle *handle);
 	int (*get_vf_config)(struct hnae3_handle *handle, int vf,
 			     struct ifla_vf_info *ivf);
 	int (*set_vf_link_state)(struct hnae3_handle *handle, int vf,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 6b9535c17647..c79d6a391105 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2102,7 +2102,6 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ae_dev->pdev = pdev;
 	ae_dev->flag = ent->driver_data;
-	ae_dev->reset_type = HNAE3_NONE_RESET;
 	hns3_get_dev_capability(pdev, ae_dev);
 	pci_set_drvdata(pdev, ae_dev);
 
@@ -3936,17 +3935,6 @@ static void hns3_uninit_phy(struct net_device *netdev)
 		h->ae_algo->ops->mac_disconnect_phy(h);
 }
 
-static int hns3_restore_fd_rules(struct net_device *netdev)
-{
-	struct hnae3_handle *h = hns3_get_handle(netdev);
-	int ret = 0;
-
-	if (h->ae_algo->ops->restore_fd_rules)
-		ret = h->ae_algo->ops->restore_fd_rules(h);
-
-	return ret;
-}
-
 static void hns3_del_all_fd_rules(struct net_device *netdev, bool clear_list)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
@@ -4346,7 +4334,6 @@ static void hns3_restore_coal(struct hns3_nic_priv *priv)
 
 static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
@@ -4354,13 +4341,6 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 	if (test_and_set_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
 		return 0;
 
-	/* it is cumbersome for hardware to pick-and-choose entries for deletion
-	 * from table space. Hence, for function reset software intervention is
-	 * required to delete the entries
-	 */
-	if (hns3_dev_ongoing_func_reset(ae_dev))
-		hns3_del_all_fd_rules(ndev, false);
-
 	if (!netif_running(ndev))
 		return 0;
 
@@ -4455,16 +4435,6 @@ err_put_ring:
 	return ret;
 }
 
-static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle)
-{
-	struct net_device *netdev = handle->kinfo.netdev;
-
-	if (handle->ae_algo->ops->restore_vlan_table)
-		handle->ae_algo->ops->restore_vlan_table(handle);
-
-	return hns3_restore_fd_rules(netdev);
-}
-
 static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 {
 	struct net_device *netdev = handle->kinfo.netdev;
@@ -4514,9 +4484,6 @@ static int hns3_reset_notify(struct hnae3_handle *handle,
 	case HNAE3_UNINIT_CLIENT:
 		ret = hns3_reset_notify_uninit_enet(handle);
 		break;
-	case HNAE3_RESTORE_CLIENT:
-		ret = hns3_reset_notify_restore_enet(handle);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 53bc0edf9b6f..240ba06cd0eb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -576,15 +576,6 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 	writel(value, reg_addr + reg);
 }
 
-static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
-{
-	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET ||
-			   ae_dev->reset_type == HNAE3_FLR_RESET ||
-			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET ||
-			   ae_dev->reset_type == HNAE3_VF_FULL_RESET ||
-			   ae_dev->reset_type == HNAE3_VF_PF_FUNC_RESET));
-}
-
 #define hns3_read_dev(a, reg) \
 	hns3_read_reg((a)->io_base, (reg))
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 177ef5e93d06..c74990a59e10 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -69,6 +69,7 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 static int hclge_set_default_loopback(struct hclge_dev *hdev);
 
 static void hclge_sync_mac_table(struct hclge_dev *hdev);
+static void hclge_restore_hw_table(struct hclge_dev *hdev);
 static void hclge_sync_promisc_mode(struct hclge_dev *hdev);
 
 static struct hnae3_ae_algo ae_algo;
@@ -3731,22 +3732,13 @@ static int hclge_reset_stack(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
-	if (ret)
-		return ret;
-
-	return hclge_notify_client(hdev, HNAE3_RESTORE_CLIENT);
+	return hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
 }
 
 static int hclge_reset_prepare(struct hclge_dev *hdev)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int ret;
 
-	/* Initialize ae_dev reset status as well, in case enet layer wants to
-	 * know if device is undergoing reset
-	 */
-	ae_dev->reset_type = hdev->reset_type;
 	hdev->rst_stats.reset_cnt++;
 	/* perform reset of the stack & ae device for a client */
 	ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
@@ -3808,7 +3800,6 @@ static int hclge_reset_rebuild(struct hclge_dev *hdev)
 	hdev->last_reset_time = jiffies;
 	hdev->rst_stats.reset_fail_cnt = 0;
 	hdev->rst_stats.reset_done_cnt++;
-	ae_dev->reset_type = HNAE3_NONE_RESET;
 	clear_bit(HCLGE_STATE_RST_FAIL, &hdev->state);
 
 	/* if default_reset_request has a higher level reset request,
@@ -6942,8 +6933,14 @@ int hclge_vport_start(struct hclge_vport *vport)
 	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
 	vport->last_active_jiffies = jiffies;
 
-	if (test_bit(vport->vport_id, hdev->vport_config_block))
-		hclge_restore_mac_table_common(vport);
+	if (test_bit(vport->vport_id, hdev->vport_config_block)) {
+		if (vport->vport_id) {
+			hclge_restore_mac_table_common(vport);
+			hclge_restore_vport_vlan_table(vport);
+		} else {
+			hclge_restore_hw_table(hdev);
+		}
+	}
 
 	clear_bit(vport->vport_id, hdev->vport_config_block);
 
@@ -8789,39 +8786,34 @@ void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev)
 	}
 }
 
-static void hclge_restore_vlan_table(struct hnae3_handle *handle)
+void hclge_restore_vport_vlan_table(struct hclge_vport *vport)
 {
-	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_vport_vlan_cfg *vlan, *tmp;
 	struct hclge_dev *hdev = vport->back;
 	u16 vlan_proto;
-	u16 state, vlan_id;
-	int i;
+	u16 vlan_id;
+	u16 state;
+	int ret;
 
-	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		vport = &hdev->vport[i];
-		vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto;
-		vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
-		state = vport->port_base_vlan_cfg.state;
+	vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto;
+	vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
+	state = vport->port_base_vlan_cfg.state;
 
-		if (state != HNAE3_PORT_BASE_VLAN_DISABLE) {
-			hclge_set_vlan_filter_hw(hdev, htons(vlan_proto),
-						 vport->vport_id, vlan_id,
-						 false);
-			continue;
-		}
-
-		list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
-			int ret;
+	if (state != HNAE3_PORT_BASE_VLAN_DISABLE) {
+		clear_bit(vport->vport_id, hdev->vlan_table[vlan_id]);
+		hclge_set_vlan_filter_hw(hdev, htons(vlan_proto),
+					 vport->vport_id, vlan_id,
+					 false);
+		return;
+	}
 
-			if (!vlan->hd_tbl_status)
-				continue;
-			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
-						       vport->vport_id,
-						       vlan->vlan_id, false);
-			if (ret)
-				break;
-		}
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+					       vport->vport_id,
+					       vlan->vlan_id, false);
+		if (ret)
+			break;
+		vlan->hd_tbl_status = true;
 	}
 }
 
@@ -8856,6 +8848,18 @@ void hclge_restore_mac_table_common(struct hclge_vport *vport)
 	spin_unlock_bh(&vport->mac_list_lock);
 }
 
+static void hclge_restore_hw_table(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = &hdev->vport[0];
+	struct hnae3_handle *handle = &vport->nic;
+
+	hclge_restore_mac_table_common(vport);
+	hclge_restore_vport_vlan_table(vport);
+	set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state);
+
+	hclge_restore_fd_entries(handle);
+}
+
 int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -10352,13 +10356,12 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 	 */
 	if (hdev->reset_type == HNAE3_IMP_RESET ||
 	    hdev->reset_type == HNAE3_GLOBAL_RESET) {
+		memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table));
+		memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full));
 		bitmap_set(hdev->vport_config_block, 0, hdev->num_alloc_vport);
 		hclge_reset_umv_space(hdev);
 	}
 
-	memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table));
-	memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full));
-
 	ret = hclge_cmd_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Cmd queue init failed\n");
@@ -11191,7 +11194,6 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_rule_cnt = hclge_get_fd_rule_cnt,
 	.get_fd_rule_info = hclge_get_fd_rule_info,
 	.get_fd_all_rules = hclge_get_all_rules,
-	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
 	.add_arfs_entry = hclge_add_fd_entry_by_arfs,
 	.dbg_run_cmd = hclge_dbg_run_cmd,
@@ -11204,7 +11206,6 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_timer_task = hclge_set_timer_task,
 	.mac_connect_phy = hclge_mac_connect_phy,
 	.mac_disconnect_phy = hclge_mac_disconnect_phy,
-	.restore_vlan_table = hclge_restore_vlan_table,
 	.get_vf_config = hclge_get_vf_config,
 	.set_vf_link_state = hclge_set_vf_link_state,
 	.set_vf_spoofchk = hclge_set_vf_spoofchk,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 8e69651f8bf1..913c4f677404 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1001,6 +1001,7 @@ void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
 void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list);
 void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev);
 void hclge_restore_mac_table_common(struct hclge_vport *vport);
+void hclge_restore_vport_vlan_table(struct hclge_vport *vport);
 int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
 				    struct hclge_vlan_info *vlan_info);
 int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 0efc04562ba6..ac70fafd15d5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -629,6 +629,23 @@ static void hclge_handle_ncsi_error(struct hclge_dev *hdev)
 	ae_dev->ops->reset_event(hdev->pdev, NULL);
 }
 
+static void hclge_handle_vf_tbl(struct hclge_vport *vport,
+				struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_vf_vlan_cfg *msg_cmd;
+
+	msg_cmd = (struct hclge_vf_vlan_cfg *)&mbx_req->msg;
+	if (msg_cmd->subcode == HCLGE_MBX_VPORT_LIST_CLEAR) {
+		hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_UC);
+		hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_MC);
+		hclge_rm_vport_all_vlan_table(vport, true);
+	} else {
+		dev_warn(&hdev->pdev->dev, "Invalid cmd(%u)\n",
+			 msg_cmd->subcode);
+	}
+}
+
 void hclge_mbx_handler(struct hclge_dev *hdev)
 {
 	struct hclge_cmq_ring *crq = &hdev->hw.cmq.crq;
@@ -636,6 +653,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclge_vport *vport;
 	struct hclge_desc *desc;
+	bool is_del = false;
 	unsigned int flag;
 	int ret = 0;
 
@@ -753,11 +771,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 			break;
 		case HCLGE_MBX_GET_VF_FLR_STATUS:
 		case HCLGE_MBX_VF_UNINIT:
-			hclge_rm_vport_all_mac_table(vport, true,
+			is_del = req->msg.code == HCLGE_MBX_VF_UNINIT;
+			hclge_rm_vport_all_mac_table(vport, is_del,
 						     HCLGE_MAC_ADDR_UC);
-			hclge_rm_vport_all_mac_table(vport, true,
+			hclge_rm_vport_all_mac_table(vport, is_del,
 						     HCLGE_MAC_ADDR_MC);
-			hclge_rm_vport_all_vlan_table(vport, true);
+			hclge_rm_vport_all_vlan_table(vport, is_del);
 			break;
 		case HCLGE_MBX_GET_MEDIA_TYPE:
 			hclge_get_vf_media_type(vport, &resp_msg);
@@ -771,6 +790,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		case HCLGE_MBX_NCSI_ERROR:
 			hclge_handle_ncsi_error(hdev);
 			break;
+		case HCLGE_MBX_HANDLE_VF_TBL:
+			hclge_handle_vf_tbl(vport, req);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %u\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index fea197fd77cb..32341dcaa6c1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1777,10 +1777,6 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT);
-	if (ret)
-		return ret;
-
 	/* clear handshake status with IMP */
 	hclgevf_reset_handshake(hdev, false);
 
@@ -1860,13 +1856,8 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
 
 static int hclgevf_reset_prepare(struct hclgevf_dev *hdev)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int ret;
 
-	/* Initialize ae_dev reset status as well, in case enet layer wants to
-	 * know if device is undergoing reset
-	 */
-	ae_dev->reset_type = hdev->reset_type;
 	hdev->rst_stats.rst_cnt++;
 
 	rtnl_lock();
@@ -1881,7 +1872,6 @@ static int hclgevf_reset_prepare(struct hclgevf_dev *hdev)
 
 static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int ret;
 
 	hdev->rst_stats.hw_rst_done_cnt++;
@@ -1896,7 +1886,6 @@ static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev)
 	}
 
 	hdev->last_reset_time = jiffies;
-	ae_dev->reset_type = HNAE3_NONE_RESET;
 	hdev->rst_stats.rst_done_cnt++;
 	hdev->rst_stats.rst_fail_cnt = 0;
 	clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state);
@@ -2974,6 +2963,15 @@ static int hclgevf_pci_reset(struct hclgevf_dev *hdev)
 	return ret;
 }
 
+static int hclgevf_clear_vport_list(struct hclgevf_dev *hdev)
+{
+	struct hclge_vf_to_pf_msg send_msg;
+
+	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_HANDLE_VF_TBL,
+			       HCLGE_MBX_VPORT_LIST_CLEAR);
+	return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
+}
+
 static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -3083,6 +3081,15 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	/* ensure vf tbl list as empty before init*/
+	ret = hclgevf_clear_vport_list(hdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to clear tbl list configuration, ret = %d.\n",
+			ret);
+		goto err_config;
+	}
+
 	ret = hclgevf_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-- 
cgit v1.2.3


From ae23aae229b8a253a3d5d51acf3bd6103a519d85 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Fri, 24 Apr 2020 17:13:35 +0800
Subject: octeontx2-pf: Remove unneeded semicolon

Fixes coccicheck warning:

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h:312:2-3: Unneeded semicolon

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 018c283a0ac4..0b1c653b3449 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -309,7 +309,7 @@ static inline void __iomem *otx2_get_regaddr(struct otx2_nic *nic, u64 offset)
 	default:
 		blkaddr = BLKADDR_RVUM;
 		break;
-	};
+	}
 
 	offset &= ~(RVU_FUNC_BLKADDR_MASK << RVU_FUNC_BLKADDR_SHIFT);
 	offset |= (blkaddr << RVU_FUNC_BLKADDR_SHIFT);
-- 
cgit v1.2.3


From 460fd830dd9d68e07c4d15363fd764944090e1f8 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 24 Apr 2020 12:33:18 +0300
Subject: dpaa2-eth: add channel stat to debugfs

Compute the average number of frames processed for each CDAN (Channel
Data Availability Notification) and export it to debugfs detailed
channel stats.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c | 9 ++++++---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c         | 1 +
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h         | 2 ++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c     | 2 +-
 4 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
index a9afe46b837f..80291afff3ea 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -127,16 +127,19 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
 	int i;
 
 	seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name);
-	seq_printf(file, "%s%16s%16s%16s%16s\n",
-		   "CHID", "CPU", "Deq busy", "CDANs", "Buf count");
+	seq_printf(file, "%s%16s%16s%16s%16s%16s%16s\n",
+		   "CHID", "CPU", "Deq busy", "Frames", "CDANs",
+		   "Avg Frm/CDAN", "Buf count");
 
 	for (i = 0; i < priv->num_channels; i++) {
 		ch = priv->channel[i];
-		seq_printf(file, "%4d%16d%16llu%16llu%16d\n",
+		seq_printf(file, "%4d%16d%16llu%16llu%16llu%16llu%16d\n",
 			   ch->ch_id,
 			   ch->nctx.desired_cpu,
 			   ch->stats.dequeue_portal_busy,
+			   ch->stats.frames,
 			   ch->stats.cdan,
+			   ch->stats.frames / ch->stats.cdan,
 			   ch->buf_count);
 	}
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index d271c016229d..8ec435ba7d27 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -493,6 +493,7 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 		return 0;
 
 	fq->stats.frames += cleaned;
+	ch->stats.frames += cleaned;
 
 	/* A dequeue operation only pulls frames from a single queue
 	 * into the store. Return the frame queue as an out param.
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 289053099974..43cd8409f2e9 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -288,6 +288,8 @@ struct dpaa2_eth_ch_stats {
 	__u64 xdp_tx;
 	__u64 xdp_tx_err;
 	__u64 xdp_redirect;
+	/* Must be last, does not show up in ethtool stats */
+	__u64 frames;
 };
 
 /* Maximum number of queues associated with a DPNI */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 94347c695233..bd13ee48d623 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -277,7 +277,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	/* Per-channel stats */
 	for (k = 0; k < priv->num_channels; k++) {
 		ch_stats = &priv->channel[k]->stats;
-		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64); j++)
+		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++)
 			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
 	i += j;
-- 
cgit v1.2.3


From 308de89fedf4240d2270d00a36b90a1394fef6a7 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 24 Apr 2020 21:11:34 +0800
Subject: liquidio: remove unused inline functions

commit b6334be64d6f ("net/liquidio: Delete driver version assignment")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/octeon_device.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 3d01d3602d8f..fb380b4f3e02 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -712,18 +712,6 @@ struct octeon_device *lio_get_device(u32 octeon_id);
  */
 int lio_get_device_id(void *dev);
 
-static inline u16 OCTEON_MAJOR_REV(struct octeon_device *oct)
-{
-	u16 rev = (oct->rev_id & 0xC) >> 2;
-
-	return (rev == 0) ? 1 : rev;
-}
-
-static inline u16 OCTEON_MINOR_REV(struct octeon_device *oct)
-{
-	return oct->rev_id & 0x3;
-}
-
 /** Read windowed register.
  *  @param  oct   -  pointer to the Octeon device.
  *  @param  addr  -  Address of the register to read.
-- 
cgit v1.2.3


From 163749ad8436b3206709172406d68869c40bc176 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 24 Apr 2020 21:12:56 +0800
Subject: qlcnic: remove unused inline function qlcnic_hw_write_wx_2M

There's no callers in-tree anymore.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 134611aa2c9a..d838774af5a6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1880,12 +1880,6 @@ static inline void qlcnic_write_crb(struct qlcnic_adapter *adapter, char *buf,
 	adapter->ahw->hw_ops->write_crb(adapter, buf, offset, size);
 }
 
-static inline int qlcnic_hw_write_wx_2M(struct qlcnic_adapter *adapter,
-					ulong off, u32 data)
-{
-	return adapter->ahw->hw_ops->write_reg(adapter, off, data);
-}
-
 static inline int qlcnic_get_mac_address(struct qlcnic_adapter *adapter,
 					 u8 *mac, u8 function)
 {
-- 
cgit v1.2.3


From c90af587a9eee697e2d89683113707cada70116a Mon Sep 17 00:00:00 2001
From: Zou Wei <zou_wei@huawei.com>
Date: Fri, 24 Apr 2020 21:53:14 +0800
Subject: net/mlx4_core: Add missing iounmap() in error path

This fixes the following coccicheck warning:

drivers/net/ethernet/mellanox/mlx4/crdump.c:200:2-8: ERROR: missing iounmap;
ioremap on line 190 and execution via conditional on line 198

Fixes: 7ef19d3b1d5e ("devlink: report error once U32_MAX snapshot ids have been used")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/crdump.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
index 73eae80e1cb7..ac5468b77488 100644
--- a/drivers/net/ethernet/mellanox/mlx4/crdump.c
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -197,6 +197,7 @@ int mlx4_crdump_collect(struct mlx4_dev *dev)
 	err = devlink_region_snapshot_id_get(devlink, &id);
 	if (err) {
 		mlx4_err(dev, "crdump: devlink get snapshot id err %d\n", err);
+		iounmap(cr_space);
 		return err;
 	}
 
-- 
cgit v1.2.3


From a425b6e1c69ba907b72b737a4d44f8cfbc43ce3c Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Sat, 25 Apr 2020 01:21:09 +0000
Subject: hinic: add mailbox function support

virtual function and physical function can communicate with each
other through mailbox channel supported by hw

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/Makefile        |    2 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h  |    2 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c  |   25 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h  |    2 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h  |    3 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_if.c   |   46 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h   |   18 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c | 1213 +++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h |  154 +++
 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h |    1 +
 10 files changed, 1456 insertions(+), 10 deletions(-)
 create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
 create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index fe88ab88cacc..a73862a64690 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -4,4 +4,4 @@ obj-$(CONFIG_HINIC) += hinic.o
 hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \
 	   hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \
 	   hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \
-	   hinic_common.o hinic_ethtool.o
+	   hinic_common.o hinic_ethtool.o hinic_hw_mbox.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index cdec1d0a3962..7e84e4e33fff 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -10,7 +10,7 @@
 /* HW interface registers */
 #define HINIC_CSR_FUNC_ATTR0_ADDR                       0x0
 #define HINIC_CSR_FUNC_ATTR1_ADDR                       0x4
-
+#define HINIC_CSR_FUNC_ATTR2_ADDR			0x8
 #define HINIC_CSR_FUNC_ATTR4_ADDR                       0x10
 #define HINIC_CSR_FUNC_ATTR5_ADDR                       0x14
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index c7c75b772a86..f2cf6f7ffc34 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -676,10 +676,23 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev)
 		return err;
 	}
 
-	hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC,
-				   pfhwdev, nic_mgmt_msg_handler);
+	err = hinic_func_to_func_init(hwdev);
+	if (err) {
+		dev_err(&hwif->pdev->dev, "Failed to init mailbox\n");
+		hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt);
+		return err;
+	}
+
+	if (!HINIC_IS_VF(hwif))
+		hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt,
+					   HINIC_MOD_L2NIC, pfhwdev,
+					   nic_mgmt_msg_handler);
+	else
+		hinic_register_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC,
+					  nic_mgmt_msg_handler);
 
 	hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE);
+
 	return 0;
 }
 
@@ -693,7 +706,13 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev)
 
 	hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT);
 
-	hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC);
+	if (!HINIC_IS_VF(hwdev->hwif))
+		hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt,
+					     HINIC_MOD_L2NIC);
+	else
+		hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC);
+
+	hinic_func_to_func_free(hwdev);
 
 	hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 66fd2340d447..2574086aa314 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -16,6 +16,7 @@
 #include "hinic_hw_mgmt.h"
 #include "hinic_hw_qp.h"
 #include "hinic_hw_io.h"
+#include "hinic_hw_mbox.h"
 
 #define HINIC_MAX_QPS   32
 
@@ -225,6 +226,7 @@ struct hinic_hwdev {
 
 	struct hinic_aeqs               aeqs;
 	struct hinic_func_to_io         func_to_io;
+	struct hinic_mbox_func_to_func  *func_to_func;
 
 	struct hinic_cap                nic_cap;
 };
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
index d35f2068ee0c..d73256da4b80 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
@@ -143,8 +143,9 @@ enum hinic_eq_type {
 };
 
 enum hinic_aeq_type {
+	HINIC_MBX_FROM_FUNC = 1,
 	HINIC_MSG_FROM_MGMT_CPU = 2,
-
+	HINIC_MBX_SEND_RSLT = 5,
 	HINIC_MAX_AEQ_EVENTS,
 };
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index 07bbfbf68577..3fbd2eb80582 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -115,8 +115,12 @@ int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index)
  **/
 void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action)
 {
-	u32 attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR);
+	u32 attr5;
 
+	if (HINIC_IS_VF(hwif))
+		return;
+
+	attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR);
 	attr5 = HINIC_FA5_CLEAR(attr5, PF_ACTION);
 	attr5 |= HINIC_FA5_SET(action, PF_ACTION);
 
@@ -203,7 +207,8 @@ static int hwif_ready(struct hinic_hwif *hwif)
  * @attr0: the first attribute that was read from the hw
  * @attr1: the second attribute that was read from the hw
  **/
-static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1)
+static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1,
+			  u32 attr2)
 {
 	hwif->attr.func_idx     = HINIC_FA0_GET(attr0, FUNC_IDX);
 	hwif->attr.pf_idx       = HINIC_FA0_GET(attr0, PF_IDX);
@@ -214,6 +219,8 @@ static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1)
 	hwif->attr.num_ceqs = BIT(HINIC_FA1_GET(attr1, CEQS_PER_FUNC));
 	hwif->attr.num_irqs = BIT(HINIC_FA1_GET(attr1, IRQS_PER_FUNC));
 	hwif->attr.num_dma_attr = BIT(HINIC_FA1_GET(attr1, DMA_ATTR_PER_FUNC));
+	hwif->attr.global_vf_id_of_pf = HINIC_FA2_GET(attr2,
+						      GLOBAL_VF_ID_OF_PF);
 }
 
 /**
@@ -222,7 +229,7 @@ static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1)
  **/
 static void read_hwif_attr(struct hinic_hwif *hwif)
 {
-	u32 addr, attr0, attr1;
+	u32 addr, attr0, attr1, attr2;
 
 	addr   = HINIC_CSR_FUNC_ATTR0_ADDR;
 	attr0  = hinic_hwif_read_reg(hwif, addr);
@@ -230,7 +237,10 @@ static void read_hwif_attr(struct hinic_hwif *hwif)
 	addr   = HINIC_CSR_FUNC_ATTR1_ADDR;
 	attr1  = hinic_hwif_read_reg(hwif, addr);
 
-	set_hwif_attr(hwif, attr0, attr1);
+	addr   = HINIC_CSR_FUNC_ATTR2_ADDR;
+	attr2  = hinic_hwif_read_reg(hwif, addr);
+
+	set_hwif_attr(hwif, attr0, attr1, attr2);
 }
 
 /**
@@ -309,6 +319,34 @@ static void dma_attr_init(struct hinic_hwif *hwif)
 		     HINIC_PCIE_SNOOP, HINIC_PCIE_TPH_DISABLE);
 }
 
+u16 hinic_glb_pf_vf_offset(struct hinic_hwif *hwif)
+{
+	if (!hwif)
+		return 0;
+
+	return hwif->attr.global_vf_id_of_pf;
+}
+
+u16 hinic_global_func_id_hw(struct hinic_hwif *hwif)
+{
+	u32 addr, attr0;
+
+	addr   = HINIC_CSR_FUNC_ATTR0_ADDR;
+	attr0  = hinic_hwif_read_reg(hwif, addr);
+
+	return HINIC_FA0_GET(attr0, FUNC_IDX);
+}
+
+u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif)
+{
+	u32 addr, attr0;
+
+	addr   = HINIC_CSR_FUNC_ATTR0_ADDR;
+	attr0  = hinic_hwif_read_reg(hwif, addr);
+
+	return HINIC_FA0_GET(attr0, PF_IDX);
+}
+
 /**
  * hinic_init_hwif - initialize the hw interface
  * @hwif: the HW interface of a pci function device
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index c7bb9ceca72c..53bb89c1dd26 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -35,6 +35,7 @@
 #define HINIC_FA0_FUNC_IDX_SHIFT                                0
 #define HINIC_FA0_PF_IDX_SHIFT                                  10
 #define HINIC_FA0_PCI_INTF_IDX_SHIFT                            14
+#define HINIC_FA0_VF_IN_PF_SHIFT				16
 /* reserved members - off 16 */
 #define HINIC_FA0_FUNC_TYPE_SHIFT                               24
 
@@ -42,6 +43,7 @@
 #define HINIC_FA0_PF_IDX_MASK                                   0xF
 #define HINIC_FA0_PCI_INTF_IDX_MASK                             0x3
 #define HINIC_FA0_FUNC_TYPE_MASK                                0x1
+#define HINIC_FA0_VF_IN_PF_MASK					0xFF
 
 #define HINIC_FA0_GET(val, member)                              \
 	(((val) >> HINIC_FA0_##member##_SHIFT) & HINIC_FA0_##member##_MASK)
@@ -64,6 +66,12 @@
 #define HINIC_FA1_GET(val, member)                              \
 	(((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK)
 
+#define HINIC_FA2_GLOBAL_VF_ID_OF_PF_SHIFT	16
+#define HINIC_FA2_GLOBAL_VF_ID_OF_PF_MASK	0x3FF
+
+#define HINIC_FA2_GET(val, member)				\
+	(((val) >> HINIC_FA2_##member##_SHIFT) & HINIC_FA2_##member##_MASK)
+
 #define HINIC_FA4_OUTBOUND_STATE_SHIFT                          0
 #define HINIC_FA4_DB_STATE_SHIFT                                1
 
@@ -140,6 +148,7 @@
 #define HINIC_HWIF_PPF_IDX(hwif)        ((hwif)->attr.ppf_idx)
 
 #define HINIC_FUNC_TYPE(hwif)           ((hwif)->attr.func_type)
+#define HINIC_IS_VF(hwif)               (HINIC_FUNC_TYPE(hwif) == HINIC_VF)
 #define HINIC_IS_PF(hwif)               (HINIC_FUNC_TYPE(hwif) == HINIC_PF)
 #define HINIC_IS_PPF(hwif)              (HINIC_FUNC_TYPE(hwif) == HINIC_PPF)
 
@@ -173,6 +182,7 @@ enum hinic_pcie_tph {
 
 enum hinic_func_type {
 	HINIC_PF        = 0,
+	HINIC_VF	    = 1,
 	HINIC_PPF       = 2,
 };
 
@@ -223,6 +233,8 @@ struct hinic_func_attr {
 	u8                      num_ceqs;
 
 	u8                      num_dma_attr;
+
+	u16						global_vf_id_of_pf;
 };
 
 struct hinic_hwif {
@@ -271,6 +283,12 @@ enum hinic_db_state hinic_db_state_get(struct hinic_hwif *hwif);
 void hinic_db_state_set(struct hinic_hwif *hwif,
 			enum hinic_db_state db_state);
 
+u16 hinic_glb_pf_vf_offset(struct hinic_hwif *hwif);
+
+u16 hinic_global_func_id_hw(struct hinic_hwif *hwif);
+
+u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif);
+
 int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev);
 
 void hinic_free_hwif(struct hinic_hwif *hwif);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
new file mode 100644
index 000000000000..f8626dfd192e
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -0,0 +1,1213 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ */
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/types.h>
+#include <linux/completion.h>
+#include <linux/semaphore.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+
+#include "hinic_hw_if.h"
+#include "hinic_hw_mgmt.h"
+#include "hinic_hw_csr.h"
+#include "hinic_hw_dev.h"
+#include "hinic_hw_mbox.h"
+
+#define HINIC_MBOX_INT_DST_FUNC_SHIFT				0
+#define HINIC_MBOX_INT_DST_AEQN_SHIFT				10
+#define HINIC_MBOX_INT_SRC_RESP_AEQN_SHIFT			12
+#define HINIC_MBOX_INT_STAT_DMA_SHIFT				14
+/* The size of data to be sended (unit of 4 bytes) */
+#define HINIC_MBOX_INT_TX_SIZE_SHIFT				20
+/* SO_RO(strong order, relax order) */
+#define HINIC_MBOX_INT_STAT_DMA_SO_RO_SHIFT			25
+#define HINIC_MBOX_INT_WB_EN_SHIFT				28
+
+#define HINIC_MBOX_INT_DST_FUNC_MASK				0x3FF
+#define HINIC_MBOX_INT_DST_AEQN_MASK				0x3
+#define HINIC_MBOX_INT_SRC_RESP_AEQN_MASK			0x3
+#define HINIC_MBOX_INT_STAT_DMA_MASK				0x3F
+#define HINIC_MBOX_INT_TX_SIZE_MASK				0x1F
+#define HINIC_MBOX_INT_STAT_DMA_SO_RO_MASK			0x3
+#define HINIC_MBOX_INT_WB_EN_MASK				0x1
+
+#define HINIC_MBOX_INT_SET(val, field)	\
+			(((val) & HINIC_MBOX_INT_##field##_MASK) << \
+			HINIC_MBOX_INT_##field##_SHIFT)
+
+enum hinic_mbox_tx_status {
+	TX_NOT_DONE = 1,
+};
+
+#define HINIC_MBOX_CTRL_TRIGGER_AEQE_SHIFT			0
+
+/* specifies the issue request for the message data.
+ * 0 - Tx request is done;
+ * 1 - Tx request is in process.
+ */
+#define HINIC_MBOX_CTRL_TX_STATUS_SHIFT				1
+
+#define HINIC_MBOX_CTRL_TRIGGER_AEQE_MASK			0x1
+#define HINIC_MBOX_CTRL_TX_STATUS_MASK				0x1
+
+#define HINIC_MBOX_CTRL_SET(val, field)	\
+			(((val) & HINIC_MBOX_CTRL_##field##_MASK) << \
+			HINIC_MBOX_CTRL_##field##_SHIFT)
+
+#define HINIC_MBOX_HEADER_MSG_LEN_SHIFT				0
+#define HINIC_MBOX_HEADER_MODULE_SHIFT				11
+#define HINIC_MBOX_HEADER_SEG_LEN_SHIFT				16
+#define HINIC_MBOX_HEADER_NO_ACK_SHIFT				22
+#define HINIC_MBOX_HEADER_SEQID_SHIFT				24
+#define HINIC_MBOX_HEADER_LAST_SHIFT				30
+
+/* specifies the mailbox message direction
+ * 0 - send
+ * 1 - receive
+ */
+#define HINIC_MBOX_HEADER_DIRECTION_SHIFT			31
+#define HINIC_MBOX_HEADER_CMD_SHIFT				32
+#define HINIC_MBOX_HEADER_MSG_ID_SHIFT				40
+#define HINIC_MBOX_HEADER_STATUS_SHIFT				48
+#define HINIC_MBOX_HEADER_SRC_GLB_FUNC_IDX_SHIFT		54
+
+#define HINIC_MBOX_HEADER_MSG_LEN_MASK				0x7FF
+#define HINIC_MBOX_HEADER_MODULE_MASK				0x1F
+#define HINIC_MBOX_HEADER_SEG_LEN_MASK				0x3F
+#define HINIC_MBOX_HEADER_NO_ACK_MASK				0x1
+#define HINIC_MBOX_HEADER_SEQID_MASK				0x3F
+#define HINIC_MBOX_HEADER_LAST_MASK				0x1
+#define HINIC_MBOX_HEADER_DIRECTION_MASK			0x1
+#define HINIC_MBOX_HEADER_CMD_MASK				0xFF
+#define HINIC_MBOX_HEADER_MSG_ID_MASK				0xFF
+#define HINIC_MBOX_HEADER_STATUS_MASK				0x3F
+#define HINIC_MBOX_HEADER_SRC_GLB_FUNC_IDX_MASK			0x3FF
+
+#define HINIC_MBOX_HEADER_GET(val, field)	\
+			(((val) >> HINIC_MBOX_HEADER_##field##_SHIFT) & \
+			HINIC_MBOX_HEADER_##field##_MASK)
+#define HINIC_MBOX_HEADER_SET(val, field)	\
+			((u64)((val) & HINIC_MBOX_HEADER_##field##_MASK) << \
+			HINIC_MBOX_HEADER_##field##_SHIFT)
+
+#define MBOX_SEGLEN_MASK			\
+		HINIC_MBOX_HEADER_SET(HINIC_MBOX_HEADER_SEG_LEN_MASK, SEG_LEN)
+
+#define HINIC_MBOX_SEG_LEN			48
+#define HINIC_MBOX_COMP_TIME			8000U
+#define MBOX_MSG_POLLING_TIMEOUT		8000
+
+#define HINIC_MBOX_DATA_SIZE			2040
+
+#define MBOX_MAX_BUF_SZ				2048UL
+#define MBOX_HEADER_SZ				8
+
+#define MBOX_INFO_SZ				4
+
+/* MBOX size is 64B, 8B for mbox_header, 4B reserved */
+#define MBOX_SEG_LEN				48
+#define MBOX_SEG_LEN_ALIGN			4
+#define MBOX_WB_STATUS_LEN			16UL
+
+/* mbox write back status is 16B, only first 4B is used */
+#define MBOX_WB_STATUS_ERRCODE_MASK		0xFFFF
+#define MBOX_WB_STATUS_MASK			0xFF
+#define MBOX_WB_ERROR_CODE_MASK			0xFF00
+#define MBOX_WB_STATUS_FINISHED_SUCCESS		0xFF
+#define MBOX_WB_STATUS_FINISHED_WITH_ERR	0xFE
+#define MBOX_WB_STATUS_NOT_FINISHED		0x00
+
+#define MBOX_STATUS_FINISHED(wb)	\
+	(((wb) & MBOX_WB_STATUS_MASK) != MBOX_WB_STATUS_NOT_FINISHED)
+#define MBOX_STATUS_SUCCESS(wb)		\
+	(((wb) & MBOX_WB_STATUS_MASK) == MBOX_WB_STATUS_FINISHED_SUCCESS)
+#define MBOX_STATUS_ERRCODE(wb)		\
+	((wb) & MBOX_WB_ERROR_CODE_MASK)
+
+#define SEQ_ID_START_VAL			0
+#define SEQ_ID_MAX_VAL				42
+
+#define DST_AEQ_IDX_DEFAULT_VAL			0
+#define SRC_AEQ_IDX_DEFAULT_VAL			0
+#define NO_DMA_ATTRIBUTE_VAL			0
+
+#define HINIC_MGMT_RSP_AEQN			0
+#define HINIC_MBOX_RSP_AEQN			2
+#define HINIC_MBOX_RECV_AEQN			0
+
+#define MBOX_MSG_NO_DATA_LEN			1
+
+#define MBOX_BODY_FROM_HDR(header)	((u8 *)(header) + MBOX_HEADER_SZ)
+#define MBOX_AREA(hwif)			\
+	((hwif)->cfg_regs_bar + HINIC_FUNC_CSR_MAILBOX_DATA_OFF)
+
+#define IS_PF_OR_PPF_SRC(src_func_idx)	((src_func_idx) < HINIC_MAX_PF_FUNCS)
+
+#define MBOX_RESPONSE_ERROR		0x1
+#define MBOX_MSG_ID_MASK		0xFF
+#define MBOX_MSG_ID(func_to_func)	((func_to_func)->send_msg_id)
+#define MBOX_MSG_ID_INC(func_to_func_mbox) (MBOX_MSG_ID(func_to_func_mbox) = \
+			(MBOX_MSG_ID(func_to_func_mbox) + 1) & MBOX_MSG_ID_MASK)
+
+#define FUNC_ID_OFF_SET_8B		8
+#define FUNC_ID_OFF_SET_10B		10
+
+/* max message counter wait to process for one function */
+#define HINIC_MAX_MSG_CNT_TO_PROCESS	10
+
+#define HINIC_QUEUE_MIN_DEPTH		6
+#define HINIC_QUEUE_MAX_DEPTH		12
+#define HINIC_MAX_RX_BUFFER_SIZE		15
+
+enum hinic_hwif_direction_type {
+	HINIC_HWIF_DIRECT_SEND	= 0,
+	HINIC_HWIF_RESPONSE	= 1,
+};
+
+enum mbox_send_mod {
+	MBOX_SEND_MSG_INT,
+};
+
+enum mbox_seg_type {
+	NOT_LAST_SEG,
+	LAST_SEG,
+};
+
+enum mbox_ordering_type {
+	STRONG_ORDER,
+};
+
+enum mbox_write_back_type {
+	WRITE_BACK = 1,
+};
+
+enum mbox_aeq_trig_type {
+	NOT_TRIGGER,
+	TRIGGER,
+};
+
+/**
+ * hinic_register_pf_mbox_cb - register mbox callback for pf
+ * @hwdev: the pointer to hw device
+ * @mod:	specific mod that the callback will handle
+ * @callback:	callback function
+ * Return: 0 - success, negative - failure
+ */
+int hinic_register_pf_mbox_cb(struct hinic_hwdev *hwdev,
+			      enum hinic_mod_type mod,
+			      hinic_pf_mbox_cb callback)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+
+	if (mod >= HINIC_MOD_MAX)
+		return -EFAULT;
+
+	func_to_func->pf_mbox_cb[mod] = callback;
+
+	set_bit(HINIC_PF_MBOX_CB_REG, &func_to_func->pf_mbox_cb_state[mod]);
+
+	return 0;
+}
+
+/**
+ * hinic_register_vf_mbox_cb - register mbox callback for vf
+ * @hwdev: the pointer to hw device
+ * @mod:	specific mod that the callback will handle
+ * @callback:	callback function
+ * Return: 0 - success, negative - failure
+ */
+int hinic_register_vf_mbox_cb(struct hinic_hwdev *hwdev,
+			      enum hinic_mod_type mod,
+			      hinic_vf_mbox_cb callback)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+
+	if (mod >= HINIC_MOD_MAX)
+		return -EFAULT;
+
+	func_to_func->vf_mbox_cb[mod] = callback;
+
+	set_bit(HINIC_VF_MBOX_CB_REG, &func_to_func->vf_mbox_cb_state[mod]);
+
+	return 0;
+}
+
+/**
+ * hinic_unregister_pf_mbox_cb - unregister the mbox callback for pf
+ * @hwdev:	the pointer to hw device
+ * @mod:	specific mod that the callback will handle
+ */
+void hinic_unregister_pf_mbox_cb(struct hinic_hwdev *hwdev,
+				 enum hinic_mod_type mod)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+
+	clear_bit(HINIC_PF_MBOX_CB_REG, &func_to_func->pf_mbox_cb_state[mod]);
+
+	while (test_bit(HINIC_PF_MBOX_CB_RUNNING,
+			&func_to_func->pf_mbox_cb_state[mod]))
+		usleep_range(900, 1000);
+
+	func_to_func->pf_mbox_cb[mod] = NULL;
+}
+
+/**
+ * hinic_unregister_vf_mbox_cb - unregister the mbox callback for vf
+ * @hwdev:	the pointer to hw device
+ * @mod:	specific mod that the callback will handle
+ */
+void hinic_unregister_vf_mbox_cb(struct hinic_hwdev *hwdev,
+				 enum hinic_mod_type mod)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+
+	clear_bit(HINIC_VF_MBOX_CB_REG, &func_to_func->vf_mbox_cb_state[mod]);
+
+	while (test_bit(HINIC_VF_MBOX_CB_RUNNING,
+			&func_to_func->vf_mbox_cb_state[mod]))
+		usleep_range(900, 1000);
+
+	func_to_func->vf_mbox_cb[mod] = NULL;
+}
+
+static int recv_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+				struct hinic_recv_mbox *recv_mbox,
+				void *buf_out, u16 *out_size)
+{
+	hinic_vf_mbox_cb cb;
+	int ret = 0;
+
+	if (recv_mbox->mod >= HINIC_MOD_MAX) {
+		dev_err(&func_to_func->hwif->pdev->dev, "Receive illegal mbox message, mod = %d\n",
+			recv_mbox->mod);
+		return -EINVAL;
+	}
+
+	set_bit(HINIC_VF_MBOX_CB_RUNNING,
+		&func_to_func->vf_mbox_cb_state[recv_mbox->mod]);
+
+	cb = func_to_func->vf_mbox_cb[recv_mbox->mod];
+	if (cb && test_bit(HINIC_VF_MBOX_CB_REG,
+			   &func_to_func->vf_mbox_cb_state[recv_mbox->mod])) {
+		cb(func_to_func->hwdev, recv_mbox->cmd, recv_mbox->mbox,
+		   recv_mbox->mbox_len, buf_out, out_size);
+	} else {
+		dev_err(&func_to_func->hwif->pdev->dev, "VF mbox cb is not registered\n");
+		ret = -EINVAL;
+	}
+
+	clear_bit(HINIC_VF_MBOX_CB_RUNNING,
+		  &func_to_func->vf_mbox_cb_state[recv_mbox->mod]);
+
+	return ret;
+}
+
+static int
+recv_pf_from_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+			     struct hinic_recv_mbox *recv_mbox,
+			     u16 src_func_idx, void *buf_out,
+			     u16 *out_size)
+{
+	hinic_pf_mbox_cb cb;
+	u16 vf_id = 0;
+	int ret;
+
+	if (recv_mbox->mod >= HINIC_MOD_MAX) {
+		dev_err(&func_to_func->hwif->pdev->dev, "Receive illegal mbox message, mod = %d\n",
+			recv_mbox->mod);
+		return -EINVAL;
+	}
+
+	set_bit(HINIC_PF_MBOX_CB_RUNNING,
+		&func_to_func->pf_mbox_cb_state[recv_mbox->mod]);
+
+	cb = func_to_func->pf_mbox_cb[recv_mbox->mod];
+	if (cb && test_bit(HINIC_PF_MBOX_CB_REG,
+			   &func_to_func->pf_mbox_cb_state[recv_mbox->mod])) {
+		vf_id = src_func_idx -
+			hinic_glb_pf_vf_offset(func_to_func->hwif);
+		ret = cb(func_to_func->hwdev, vf_id, recv_mbox->cmd,
+			 recv_mbox->mbox, recv_mbox->mbox_len,
+			 buf_out, out_size);
+	} else {
+		dev_err(&func_to_func->hwif->pdev->dev, "PF mbox mod(0x%x) cb is not registered\n",
+			recv_mbox->mod);
+		ret = -EINVAL;
+	}
+
+	clear_bit(HINIC_PF_MBOX_CB_RUNNING,
+		  &func_to_func->pf_mbox_cb_state[recv_mbox->mod]);
+
+	return ret;
+}
+
+static bool check_mbox_seq_id_and_seg_len(struct hinic_recv_mbox *recv_mbox,
+					  u8 seq_id, u8 seg_len)
+{
+	if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN)
+		return false;
+
+	if (seq_id == 0) {
+		recv_mbox->seq_id = seq_id;
+	} else {
+		if (seq_id != recv_mbox->seq_id + 1)
+			return false;
+
+		recv_mbox->seq_id = seq_id;
+	}
+
+	return true;
+}
+
+static void resp_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+			      struct hinic_recv_mbox *recv_mbox)
+{
+	spin_lock(&func_to_func->mbox_lock);
+	if (recv_mbox->msg_info.msg_id == func_to_func->send_msg_id &&
+	    func_to_func->event_flag == EVENT_START)
+		complete(&recv_mbox->recv_done);
+	else
+		dev_err(&func_to_func->hwif->pdev->dev,
+			"Mbox response timeout, current send msg id(0x%x), recv msg id(0x%x), status(0x%x)\n",
+			func_to_func->send_msg_id, recv_mbox->msg_info.msg_id,
+			recv_mbox->msg_info.status);
+	spin_unlock(&func_to_func->mbox_lock);
+}
+
+static void recv_func_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+				   struct hinic_recv_mbox *recv_mbox,
+				   u16 src_func_idx);
+
+static void recv_func_mbox_work_handler(struct work_struct *work)
+{
+	struct hinic_mbox_work *mbox_work =
+			container_of(work, struct hinic_mbox_work, work);
+	struct hinic_recv_mbox *recv_mbox;
+
+	recv_func_mbox_handler(mbox_work->func_to_func, mbox_work->recv_mbox,
+			       mbox_work->src_func_idx);
+
+	recv_mbox =
+		&mbox_work->func_to_func->mbox_send[mbox_work->src_func_idx];
+
+	atomic_dec(&recv_mbox->msg_cnt);
+
+	kfree(mbox_work);
+}
+
+static void recv_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+			      void *header, struct hinic_recv_mbox *recv_mbox)
+{
+	void *mbox_body = MBOX_BODY_FROM_HDR(header);
+	struct hinic_recv_mbox *rcv_mbox_temp = NULL;
+	u64 mbox_header = *((u64 *)header);
+	struct hinic_mbox_work *mbox_work;
+	u8 seq_id, seg_len;
+	u16 src_func_idx;
+	int pos;
+
+	seq_id = HINIC_MBOX_HEADER_GET(mbox_header, SEQID);
+	seg_len = HINIC_MBOX_HEADER_GET(mbox_header, SEG_LEN);
+	src_func_idx = HINIC_MBOX_HEADER_GET(mbox_header, SRC_GLB_FUNC_IDX);
+
+	if (!check_mbox_seq_id_and_seg_len(recv_mbox, seq_id, seg_len)) {
+		dev_err(&func_to_func->hwif->pdev->dev,
+			"Mailbox sequence and segment check fail, src func id: 0x%x, front id: 0x%x, current id: 0x%x, seg len: 0x%x\n",
+			src_func_idx, recv_mbox->seq_id, seq_id, seg_len);
+		recv_mbox->seq_id = SEQ_ID_MAX_VAL;
+		return;
+	}
+
+	pos = seq_id * MBOX_SEG_LEN;
+	memcpy((u8 *)recv_mbox->mbox + pos, mbox_body,
+	       HINIC_MBOX_HEADER_GET(mbox_header, SEG_LEN));
+
+	if (!HINIC_MBOX_HEADER_GET(mbox_header, LAST))
+		return;
+
+	recv_mbox->cmd = HINIC_MBOX_HEADER_GET(mbox_header, CMD);
+	recv_mbox->mod = HINIC_MBOX_HEADER_GET(mbox_header, MODULE);
+	recv_mbox->mbox_len = HINIC_MBOX_HEADER_GET(mbox_header, MSG_LEN);
+	recv_mbox->ack_type = HINIC_MBOX_HEADER_GET(mbox_header, NO_ACK);
+	recv_mbox->msg_info.msg_id = HINIC_MBOX_HEADER_GET(mbox_header, MSG_ID);
+	recv_mbox->msg_info.status = HINIC_MBOX_HEADER_GET(mbox_header, STATUS);
+	recv_mbox->seq_id = SEQ_ID_MAX_VAL;
+
+	if (HINIC_MBOX_HEADER_GET(mbox_header, DIRECTION) ==
+	    HINIC_HWIF_RESPONSE) {
+		resp_mbox_handler(func_to_func, recv_mbox);
+		return;
+	}
+
+	if (atomic_read(&recv_mbox->msg_cnt) > HINIC_MAX_MSG_CNT_TO_PROCESS) {
+		dev_warn(&func_to_func->hwif->pdev->dev,
+			 "This function(%u) have %d message wait to process,can't add to work queue\n",
+			 src_func_idx, atomic_read(&recv_mbox->msg_cnt));
+		return;
+	}
+
+	rcv_mbox_temp = kzalloc(sizeof(*rcv_mbox_temp), GFP_KERNEL);
+	if (!rcv_mbox_temp)
+		return;
+
+	memcpy(rcv_mbox_temp, recv_mbox, sizeof(*rcv_mbox_temp));
+
+	rcv_mbox_temp->mbox = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!rcv_mbox_temp->mbox)
+		goto err_alloc_rcv_mbox_msg;
+
+	memcpy(rcv_mbox_temp->mbox, recv_mbox->mbox, MBOX_MAX_BUF_SZ);
+
+	rcv_mbox_temp->buf_out = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!rcv_mbox_temp->buf_out)
+		goto err_alloc_rcv_mbox_buf;
+
+	mbox_work = kzalloc(sizeof(*mbox_work), GFP_KERNEL);
+	if (!mbox_work)
+		goto err_alloc_mbox_work;
+
+	mbox_work->func_to_func = func_to_func;
+	mbox_work->recv_mbox = rcv_mbox_temp;
+	mbox_work->src_func_idx = src_func_idx;
+
+	atomic_inc(&recv_mbox->msg_cnt);
+	INIT_WORK(&mbox_work->work, recv_func_mbox_work_handler);
+	queue_work(func_to_func->workq, &mbox_work->work);
+
+	return;
+
+err_alloc_mbox_work:
+	kfree(rcv_mbox_temp->buf_out);
+
+err_alloc_rcv_mbox_buf:
+	kfree(rcv_mbox_temp->mbox);
+
+err_alloc_rcv_mbox_msg:
+	kfree(rcv_mbox_temp);
+}
+
+void hinic_mbox_func_aeqe_handler(void *handle, void *header, u8 size)
+{
+	struct hinic_mbox_func_to_func *func_to_func;
+	u64 mbox_header = *((u64 *)header);
+	struct hinic_recv_mbox *recv_mbox;
+	u64 src, dir;
+
+	func_to_func = ((struct hinic_hwdev *)handle)->func_to_func;
+
+	dir = HINIC_MBOX_HEADER_GET(mbox_header, DIRECTION);
+	src = HINIC_MBOX_HEADER_GET(mbox_header, SRC_GLB_FUNC_IDX);
+
+	if (src >= HINIC_MAX_FUNCTIONS) {
+		dev_err(&func_to_func->hwif->pdev->dev,
+			"Mailbox source function id:%u is invalid\n", (u32)src);
+		return;
+	}
+
+	recv_mbox = (dir == HINIC_HWIF_DIRECT_SEND) ?
+		    &func_to_func->mbox_send[src] :
+		    &func_to_func->mbox_resp[src];
+
+	recv_mbox_handler(func_to_func, (u64 *)header, recv_mbox);
+}
+
+void hinic_mbox_self_aeqe_handler(void *handle, void *header, u8 size)
+{
+	struct hinic_mbox_func_to_func *func_to_func;
+	struct hinic_send_mbox *send_mbox;
+
+	func_to_func = ((struct hinic_hwdev *)handle)->func_to_func;
+	send_mbox = &func_to_func->send_mbox;
+
+	complete(&send_mbox->send_done);
+}
+
+static void clear_mbox_status(struct hinic_send_mbox *mbox)
+{
+	*mbox->wb_status = 0;
+
+	/* clear mailbox write back status */
+	wmb();
+}
+
+static void mbox_copy_header(struct hinic_hwdev *hwdev,
+			     struct hinic_send_mbox *mbox, u64 *header)
+{
+	u32 i, idx_max = MBOX_HEADER_SZ / sizeof(u32);
+	u32 *data = (u32 *)header;
+
+	for (i = 0; i < idx_max; i++)
+		__raw_writel(*(data + i), mbox->data + i * sizeof(u32));
+}
+
+static void mbox_copy_send_data(struct hinic_hwdev *hwdev,
+				struct hinic_send_mbox *mbox, void *seg,
+				u16 seg_len)
+{
+	u8 mbox_max_buf[MBOX_SEG_LEN] = {0};
+	u32 data_len, chk_sz = sizeof(u32);
+	u32 *data = seg;
+	u32 i, idx_max;
+
+	/* The mbox message should be aligned in 4 bytes. */
+	if (seg_len % chk_sz) {
+		memcpy(mbox_max_buf, seg, seg_len);
+		data = (u32 *)mbox_max_buf;
+	}
+
+	data_len = seg_len;
+	idx_max = ALIGN(data_len, chk_sz) / chk_sz;
+
+	for (i = 0; i < idx_max; i++)
+		__raw_writel(*(data + i),
+			     mbox->data + MBOX_HEADER_SZ + i * sizeof(u32));
+}
+
+static void write_mbox_msg_attr(struct hinic_mbox_func_to_func *func_to_func,
+				u16 dst_func, u16 dst_aeqn, u16 seg_len,
+				int poll)
+{
+	u16 rsp_aeq = (dst_aeqn == 0) ? 0 : HINIC_MBOX_RSP_AEQN;
+	u32 mbox_int, mbox_ctrl;
+
+	mbox_int = HINIC_MBOX_INT_SET(dst_func, DST_FUNC) |
+		   HINIC_MBOX_INT_SET(dst_aeqn, DST_AEQN) |
+		   HINIC_MBOX_INT_SET(rsp_aeq, SRC_RESP_AEQN) |
+		   HINIC_MBOX_INT_SET(NO_DMA_ATTRIBUTE_VAL, STAT_DMA) |
+		   HINIC_MBOX_INT_SET(ALIGN(MBOX_SEG_LEN + MBOX_HEADER_SZ +
+				      MBOX_INFO_SZ, MBOX_SEG_LEN_ALIGN) >> 2,
+				      TX_SIZE) |
+		   HINIC_MBOX_INT_SET(STRONG_ORDER, STAT_DMA_SO_RO) |
+		   HINIC_MBOX_INT_SET(WRITE_BACK, WB_EN);
+
+	hinic_hwif_write_reg(func_to_func->hwif,
+			     HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF, mbox_int);
+
+	wmb(); /* writing the mbox int attributes */
+	mbox_ctrl = HINIC_MBOX_CTRL_SET(TX_NOT_DONE, TX_STATUS);
+
+	if (poll)
+		mbox_ctrl |= HINIC_MBOX_CTRL_SET(NOT_TRIGGER, TRIGGER_AEQE);
+	else
+		mbox_ctrl |= HINIC_MBOX_CTRL_SET(TRIGGER, TRIGGER_AEQE);
+
+	hinic_hwif_write_reg(func_to_func->hwif,
+			     HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF, mbox_ctrl);
+}
+
+void dump_mox_reg(struct hinic_hwdev *hwdev)
+{
+	u32 val;
+
+	val = hinic_hwif_read_reg(hwdev->hwif,
+				  HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF);
+	dev_err(&hwdev->hwif->pdev->dev, "Mailbox control reg: 0x%x\n", val);
+
+	val = hinic_hwif_read_reg(hwdev->hwif,
+				  HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF);
+	dev_err(&hwdev->hwif->pdev->dev, "Mailbox interrupt offset: 0x%x\n",
+		val);
+}
+
+static u16 get_mbox_status(struct hinic_send_mbox *mbox)
+{
+	/* write back is 16B, but only use first 4B */
+	u64 wb_val = be64_to_cpu(*mbox->wb_status);
+
+	rmb(); /* verify reading before check */
+
+	return (u16)(wb_val & MBOX_WB_STATUS_ERRCODE_MASK);
+}
+
+static int
+wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func,
+			     int poll, u16 *wb_status)
+{
+	struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox;
+	struct hinic_hwdev *hwdev = func_to_func->hwdev;
+	struct completion *done = &send_mbox->send_done;
+	u32 cnt = 0;
+	ulong jif;
+
+	if (poll) {
+		while (cnt < MBOX_MSG_POLLING_TIMEOUT) {
+			*wb_status = get_mbox_status(send_mbox);
+			if (MBOX_STATUS_FINISHED(*wb_status))
+				break;
+
+			usleep_range(900, 1000);
+			cnt++;
+		}
+
+		if (cnt == MBOX_MSG_POLLING_TIMEOUT) {
+			dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout, wb status: 0x%x\n",
+				*wb_status);
+			dump_mox_reg(hwdev);
+			return -ETIMEDOUT;
+		}
+	} else {
+		jif = msecs_to_jiffies(HINIC_MBOX_COMP_TIME);
+		if (!wait_for_completion_timeout(done, jif)) {
+			dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout\n");
+			dump_mox_reg(hwdev);
+			return -ETIMEDOUT;
+		}
+
+		*wb_status = get_mbox_status(send_mbox);
+	}
+
+	return 0;
+}
+
+static int send_mbox_seg(struct hinic_mbox_func_to_func *func_to_func,
+			 u64 header, u16 dst_func, void *seg, u16 seg_len,
+			 int poll, void *msg_info)
+{
+	struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox;
+	u16 seq_dir = HINIC_MBOX_HEADER_GET(header, DIRECTION);
+	struct hinic_hwdev *hwdev = func_to_func->hwdev;
+	struct completion *done = &send_mbox->send_done;
+	u8 num_aeqs = hwdev->hwif->attr.num_aeqs;
+	u16 dst_aeqn, wb_status = 0, errcode;
+
+	if (num_aeqs >= 4)
+		dst_aeqn = (seq_dir == HINIC_HWIF_DIRECT_SEND) ?
+			   HINIC_MBOX_RECV_AEQN : HINIC_MBOX_RSP_AEQN;
+	else
+		dst_aeqn = 0;
+
+	if (!poll)
+		init_completion(done);
+
+	clear_mbox_status(send_mbox);
+
+	mbox_copy_header(hwdev, send_mbox, &header);
+
+	mbox_copy_send_data(hwdev, send_mbox, seg, seg_len);
+
+	write_mbox_msg_attr(func_to_func, dst_func, dst_aeqn, seg_len, poll);
+
+	wmb(); /* writing the mbox msg attributes */
+
+	if (wait_for_mbox_seg_completion(func_to_func, poll, &wb_status))
+		return -ETIMEDOUT;
+
+	if (!MBOX_STATUS_SUCCESS(wb_status)) {
+		dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment to function %d error, wb status: 0x%x\n",
+			dst_func, wb_status);
+		errcode = MBOX_STATUS_ERRCODE(wb_status);
+		return errcode ? errcode : -EFAULT;
+	}
+
+	return 0;
+}
+
+static int send_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
+			     enum hinic_mod_type mod, u16 cmd, void *msg,
+			     u16 msg_len, u16 dst_func,
+			     enum hinic_hwif_direction_type direction,
+			     enum hinic_mbox_ack_type ack_type,
+			     struct mbox_msg_info *msg_info)
+{
+	struct hinic_hwdev *hwdev = func_to_func->hwdev;
+	u16 seg_len = MBOX_SEG_LEN;
+	u8 *msg_seg = (u8 *)msg;
+	u16 left = msg_len;
+	u32 seq_id = 0;
+	u64 header = 0;
+	int err = 0;
+
+	down(&func_to_func->msg_send_sem);
+
+	header = HINIC_MBOX_HEADER_SET(msg_len, MSG_LEN) |
+		 HINIC_MBOX_HEADER_SET(mod, MODULE) |
+		 HINIC_MBOX_HEADER_SET(seg_len, SEG_LEN) |
+		 HINIC_MBOX_HEADER_SET(ack_type, NO_ACK) |
+		 HINIC_MBOX_HEADER_SET(SEQ_ID_START_VAL, SEQID) |
+		 HINIC_MBOX_HEADER_SET(NOT_LAST_SEG, LAST) |
+		 HINIC_MBOX_HEADER_SET(direction, DIRECTION) |
+		 HINIC_MBOX_HEADER_SET(cmd, CMD) |
+		 /* The vf's offset to it's associated pf */
+		 HINIC_MBOX_HEADER_SET(msg_info->msg_id, MSG_ID) |
+		 HINIC_MBOX_HEADER_SET(msg_info->status, STATUS) |
+		 HINIC_MBOX_HEADER_SET(hinic_global_func_id_hw(hwdev->hwif),
+				       SRC_GLB_FUNC_IDX);
+
+	while (!(HINIC_MBOX_HEADER_GET(header, LAST))) {
+		if (left <= HINIC_MBOX_SEG_LEN) {
+			header &= ~MBOX_SEGLEN_MASK;
+			header |= HINIC_MBOX_HEADER_SET(left, SEG_LEN);
+			header |= HINIC_MBOX_HEADER_SET(LAST_SEG, LAST);
+
+			seg_len = left;
+		}
+
+		err = send_mbox_seg(func_to_func, header, dst_func, msg_seg,
+				    seg_len, MBOX_SEND_MSG_INT, msg_info);
+		if (err) {
+			dev_err(&hwdev->hwif->pdev->dev, "Failed to send mbox seg, seq_id=0x%llx\n",
+				HINIC_MBOX_HEADER_GET(header, SEQID));
+			goto err_send_mbox_seg;
+		}
+
+		left -= HINIC_MBOX_SEG_LEN;
+		msg_seg += HINIC_MBOX_SEG_LEN;
+
+		seq_id++;
+		header &= ~(HINIC_MBOX_HEADER_SET(HINIC_MBOX_HEADER_SEQID_MASK,
+						  SEQID));
+		header |= HINIC_MBOX_HEADER_SET(seq_id, SEQID);
+	}
+
+err_send_mbox_seg:
+	up(&func_to_func->msg_send_sem);
+
+	return err;
+}
+
+static void
+response_for_recv_func_mbox(struct hinic_mbox_func_to_func *func_to_func,
+			    struct hinic_recv_mbox *recv_mbox, int err,
+			    u16 out_size, u16 src_func_idx)
+{
+	struct mbox_msg_info msg_info = {0};
+
+	if (recv_mbox->ack_type == MBOX_ACK) {
+		msg_info.msg_id = recv_mbox->msg_info.msg_id;
+		if (err == HINIC_MBOX_PF_BUSY_ACTIVE_FW)
+			msg_info.status = HINIC_MBOX_PF_BUSY_ACTIVE_FW;
+		else if (err == HINIC_MBOX_VF_CMD_ERROR)
+			msg_info.status = HINIC_MBOX_VF_CMD_ERROR;
+		else if (err)
+			msg_info.status = HINIC_MBOX_PF_SEND_ERR;
+
+		/* if no data needs to response, set out_size to 1 */
+		if (!out_size || err)
+			out_size = MBOX_MSG_NO_DATA_LEN;
+
+		send_mbox_to_func(func_to_func, recv_mbox->mod, recv_mbox->cmd,
+				  recv_mbox->buf_out, out_size, src_func_idx,
+				  HINIC_HWIF_RESPONSE, MBOX_ACK,
+				  &msg_info);
+	}
+}
+
+static void recv_func_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
+				   struct hinic_recv_mbox *recv_mbox,
+				   u16 src_func_idx)
+{
+	void *buf_out = recv_mbox->buf_out;
+	u16 out_size = MBOX_MAX_BUF_SZ;
+	int err = 0;
+
+	if (HINIC_IS_VF(func_to_func->hwif)) {
+		err = recv_vf_mbox_handler(func_to_func, recv_mbox, buf_out,
+					   &out_size);
+	} else {
+		if (IS_PF_OR_PPF_SRC(src_func_idx))
+			dev_warn(&func_to_func->hwif->pdev->dev,
+				 "Unsupported pf2pf mbox msg\n");
+		else
+			err = recv_pf_from_vf_mbox_handler(func_to_func,
+							   recv_mbox,
+							   src_func_idx,
+							   buf_out, &out_size);
+	}
+
+	response_for_recv_func_mbox(func_to_func, recv_mbox, err, out_size,
+				    src_func_idx);
+	kfree(recv_mbox->buf_out);
+	kfree(recv_mbox->mbox);
+	kfree(recv_mbox);
+}
+
+static void set_mbox_to_func_event(struct hinic_mbox_func_to_func *func_to_func,
+				   enum mbox_event_state event_flag)
+{
+	spin_lock(&func_to_func->mbox_lock);
+	func_to_func->event_flag = event_flag;
+	spin_unlock(&func_to_func->mbox_lock);
+}
+
+static int mbox_resp_info_handler(struct hinic_mbox_func_to_func *func_to_func,
+				  struct hinic_recv_mbox *mbox_for_resp,
+				  enum hinic_mod_type mod, u16 cmd,
+				  void *buf_out, u16 *out_size)
+{
+	int err;
+
+	if (mbox_for_resp->msg_info.status) {
+		err = mbox_for_resp->msg_info.status;
+		if (err != HINIC_MBOX_PF_BUSY_ACTIVE_FW)
+			dev_err(&func_to_func->hwif->pdev->dev, "Mbox response error(0x%x)\n",
+				mbox_for_resp->msg_info.status);
+		return err;
+	}
+
+	if (buf_out && out_size) {
+		if (*out_size < mbox_for_resp->mbox_len) {
+			dev_err(&func_to_func->hwif->pdev->dev,
+				"Invalid response mbox message length: %d for mod %d cmd %d, should less than: %d\n",
+				mbox_for_resp->mbox_len, mod, cmd, *out_size);
+			return -EFAULT;
+		}
+
+		if (mbox_for_resp->mbox_len)
+			memcpy(buf_out, mbox_for_resp->mbox,
+			       mbox_for_resp->mbox_len);
+
+		*out_size = mbox_for_resp->mbox_len;
+	}
+
+	return 0;
+}
+
+int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
+		       enum hinic_mod_type mod, u16 cmd, u16 dst_func,
+		       void *buf_in, u16 in_size, void *buf_out,
+		       u16 *out_size, u32 timeout)
+{
+	struct hinic_recv_mbox *mbox_for_resp;
+	struct mbox_msg_info msg_info = {0};
+	ulong timeo;
+	int err;
+
+	mbox_for_resp = &func_to_func->mbox_resp[dst_func];
+
+	down(&func_to_func->mbox_send_sem);
+
+	init_completion(&mbox_for_resp->recv_done);
+
+	msg_info.msg_id = MBOX_MSG_ID_INC(func_to_func);
+
+	set_mbox_to_func_event(func_to_func, EVENT_START);
+
+	err = send_mbox_to_func(func_to_func, mod, cmd, buf_in, in_size,
+				dst_func, HINIC_HWIF_DIRECT_SEND, MBOX_ACK,
+				&msg_info);
+	if (err) {
+		dev_err(&func_to_func->hwif->pdev->dev, "Send mailbox failed, msg_id: %d\n",
+			msg_info.msg_id);
+		set_mbox_to_func_event(func_to_func, EVENT_FAIL);
+		goto err_send_mbox;
+	}
+
+	timeo = msecs_to_jiffies(timeout ? timeout : HINIC_MBOX_COMP_TIME);
+	if (!wait_for_completion_timeout(&mbox_for_resp->recv_done, timeo)) {
+		set_mbox_to_func_event(func_to_func, EVENT_TIMEOUT);
+		dev_err(&func_to_func->hwif->pdev->dev,
+			"Send mbox msg timeout, msg_id: %d\n", msg_info.msg_id);
+		err = -ETIMEDOUT;
+		goto err_send_mbox;
+	}
+
+	set_mbox_to_func_event(func_to_func, EVENT_END);
+
+	err = mbox_resp_info_handler(func_to_func, mbox_for_resp, mod, cmd,
+				     buf_out, out_size);
+
+err_send_mbox:
+	up(&func_to_func->mbox_send_sem);
+
+	return err;
+}
+
+static int mbox_func_params_valid(struct hinic_mbox_func_to_func *func_to_func,
+				  void *buf_in, u16 in_size)
+{
+	if (in_size > HINIC_MBOX_DATA_SIZE) {
+		dev_err(&func_to_func->hwif->pdev->dev,
+			"Mbox msg len(%d) exceed limit(%d)\n",
+			in_size, HINIC_MBOX_DATA_SIZE);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_mbox_to_pf(struct hinic_hwdev *hwdev,
+		     enum hinic_mod_type mod, u8 cmd, void *buf_in,
+		     u16 in_size, void *buf_out, u16 *out_size, u32 timeout)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+	int err = mbox_func_params_valid(func_to_func, buf_in, in_size);
+
+	if (err)
+		return err;
+
+	if (!HINIC_IS_VF(hwdev->hwif)) {
+		dev_err(&hwdev->hwif->pdev->dev, "Params error, func_type: %d\n",
+			HINIC_FUNC_TYPE(hwdev->hwif));
+		return -EINVAL;
+	}
+
+	return hinic_mbox_to_func(func_to_func, mod, cmd,
+				  hinic_pf_id_of_vf_hw(hwdev->hwif), buf_in,
+				  in_size, buf_out, out_size, timeout);
+}
+
+int hinic_mbox_to_vf(struct hinic_hwdev *hwdev,
+		     enum hinic_mod_type mod, u16 vf_id, u8 cmd, void *buf_in,
+		     u16 in_size, void *buf_out, u16 *out_size, u32 timeout)
+{
+	struct hinic_mbox_func_to_func *func_to_func;
+	u16 dst_func_idx;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	func_to_func = hwdev->func_to_func;
+	err = mbox_func_params_valid(func_to_func, buf_in, in_size);
+	if (err)
+		return err;
+
+	if (HINIC_IS_VF(hwdev->hwif)) {
+		dev_err(&hwdev->hwif->pdev->dev, "Params error, func_type: %d\n",
+			HINIC_FUNC_TYPE(hwdev->hwif));
+		return -EINVAL;
+	}
+
+	if (!vf_id) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"VF id(%d) error!\n", vf_id);
+		return -EINVAL;
+	}
+
+	/* vf_offset_to_pf + vf_id is the vf's global function id of vf in
+	 * this pf
+	 */
+	dst_func_idx = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+
+	return hinic_mbox_to_func(func_to_func, mod, cmd, dst_func_idx, buf_in,
+				  in_size, buf_out, out_size, timeout);
+}
+
+static int init_mbox_info(struct hinic_recv_mbox *mbox_info)
+{
+	int err;
+
+	mbox_info->seq_id = SEQ_ID_MAX_VAL;
+
+	mbox_info->mbox = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!mbox_info->mbox)
+		return -ENOMEM;
+
+	mbox_info->buf_out = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	if (!mbox_info->buf_out) {
+		err = -ENOMEM;
+		goto err_alloc_buf_out;
+	}
+
+	atomic_set(&mbox_info->msg_cnt, 0);
+
+	return 0;
+
+err_alloc_buf_out:
+	kfree(mbox_info->mbox);
+
+	return err;
+}
+
+static void clean_mbox_info(struct hinic_recv_mbox *mbox_info)
+{
+	kfree(mbox_info->buf_out);
+	kfree(mbox_info->mbox);
+}
+
+static int alloc_mbox_info(struct hinic_hwdev *hwdev,
+			   struct hinic_recv_mbox *mbox_info)
+{
+	u16 func_idx, i;
+	int err;
+
+	for (func_idx = 0; func_idx < HINIC_MAX_FUNCTIONS; func_idx++) {
+		err = init_mbox_info(&mbox_info[func_idx]);
+		if (err) {
+			dev_err(&hwdev->hwif->pdev->dev, "Failed to init function %d mbox info\n",
+				func_idx);
+			goto err_init_mbox_info;
+		}
+	}
+
+	return 0;
+
+err_init_mbox_info:
+	for (i = 0; i < func_idx; i++)
+		clean_mbox_info(&mbox_info[i]);
+
+	return err;
+}
+
+static void free_mbox_info(struct hinic_recv_mbox *mbox_info)
+{
+	u16 func_idx;
+
+	for (func_idx = 0; func_idx < HINIC_MAX_FUNCTIONS; func_idx++)
+		clean_mbox_info(&mbox_info[func_idx]);
+}
+
+static void prepare_send_mbox(struct hinic_mbox_func_to_func *func_to_func)
+{
+	struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox;
+
+	send_mbox->data = MBOX_AREA(func_to_func->hwif);
+}
+
+static int alloc_mbox_wb_status(struct hinic_mbox_func_to_func *func_to_func)
+{
+	struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox;
+	struct hinic_hwdev *hwdev = func_to_func->hwdev;
+	u32 addr_h, addr_l;
+
+	send_mbox->wb_vaddr = dma_alloc_coherent(&hwdev->hwif->pdev->dev,
+						 MBOX_WB_STATUS_LEN,
+						 &send_mbox->wb_paddr,
+						 GFP_KERNEL);
+	if (!send_mbox->wb_vaddr)
+		return -ENOMEM;
+
+	send_mbox->wb_status = send_mbox->wb_vaddr;
+
+	addr_h = upper_32_bits(send_mbox->wb_paddr);
+	addr_l = lower_32_bits(send_mbox->wb_paddr);
+
+	hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF,
+			     addr_h);
+	hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF,
+			     addr_l);
+
+	return 0;
+}
+
+static void free_mbox_wb_status(struct hinic_mbox_func_to_func *func_to_func)
+{
+	struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox;
+	struct hinic_hwdev *hwdev = func_to_func->hwdev;
+
+	hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF,
+			     0);
+	hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF,
+			     0);
+
+	dma_free_coherent(&hwdev->hwif->pdev->dev, MBOX_WB_STATUS_LEN,
+			  send_mbox->wb_vaddr,
+			  send_mbox->wb_paddr);
+}
+
+static int comm_pf_mbox_handler(void *handle, u16 vf_id, u8 cmd, void *buf_in,
+				u16 in_size, void *buf_out, u16 *out_size)
+{
+	struct hinic_hwdev *hwdev = handle;
+	struct hinic_pfhwdev *pfhwdev;
+	int err = 0;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	if (cmd == HINIC_COMM_CMD_START_FLR) {
+		*out_size = 0;
+	} else {
+		err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
+					cmd, buf_in, in_size, buf_out, out_size,
+					HINIC_MGMT_MSG_SYNC);
+		if (err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW)
+			dev_err(&hwdev->hwif->pdev->dev,
+				"PF mbox common callback handler err: %d\n",
+				err);
+	}
+
+	return err;
+}
+
+int hinic_func_to_func_init(struct hinic_hwdev *hwdev)
+{
+	struct hinic_mbox_func_to_func *func_to_func;
+	struct hinic_pfhwdev *pfhwdev;
+	int err;
+
+	pfhwdev =  container_of(hwdev, struct hinic_pfhwdev, hwdev);
+	func_to_func = kzalloc(sizeof(*func_to_func), GFP_KERNEL);
+	if (!func_to_func)
+		return -ENOMEM;
+
+	hwdev->func_to_func = func_to_func;
+	func_to_func->hwdev = hwdev;
+	func_to_func->hwif = hwdev->hwif;
+	sema_init(&func_to_func->mbox_send_sem, 1);
+	sema_init(&func_to_func->msg_send_sem, 1);
+	spin_lock_init(&func_to_func->mbox_lock);
+	func_to_func->workq = create_singlethread_workqueue(HINIC_MBOX_WQ_NAME);
+	if (!func_to_func->workq) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to initialize MBOX workqueue\n");
+		err = -ENOMEM;
+		goto err_create_mbox_workq;
+	}
+
+	err = alloc_mbox_info(hwdev, func_to_func->mbox_send);
+	if (err) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mem for mbox_active\n");
+		goto err_alloc_mbox_for_send;
+	}
+
+	err = alloc_mbox_info(hwdev, func_to_func->mbox_resp);
+	if (err) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mem for mbox_passive\n");
+		goto err_alloc_mbox_for_resp;
+	}
+
+	err = alloc_mbox_wb_status(func_to_func);
+	if (err) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mbox write back status\n");
+		goto err_alloc_wb_status;
+	}
+
+	prepare_send_mbox(func_to_func);
+
+	hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MBX_FROM_FUNC,
+				 &pfhwdev->hwdev, hinic_mbox_func_aeqe_handler);
+	hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MBX_SEND_RSLT,
+				 &pfhwdev->hwdev, hinic_mbox_self_aeqe_handler);
+
+	if (!HINIC_IS_VF(hwdev->hwif))
+		hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_COMM,
+					  comm_pf_mbox_handler);
+
+	return 0;
+
+err_alloc_wb_status:
+	free_mbox_info(func_to_func->mbox_resp);
+
+err_alloc_mbox_for_resp:
+	free_mbox_info(func_to_func->mbox_send);
+
+err_alloc_mbox_for_send:
+	destroy_workqueue(func_to_func->workq);
+
+err_create_mbox_workq:
+	kfree(func_to_func);
+
+	return err;
+}
+
+void hinic_func_to_func_free(struct hinic_hwdev *hwdev)
+{
+	struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func;
+
+	hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MBX_FROM_FUNC);
+	hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MBX_SEND_RSLT);
+
+	hinic_unregister_pf_mbox_cb(hwdev, HINIC_MOD_COMM);
+	/* destroy workqueue before free related mbox resources in case of
+	 * illegal resource access
+	 */
+	destroy_workqueue(func_to_func->workq);
+
+	free_mbox_wb_status(func_to_func);
+	free_mbox_info(func_to_func->mbox_resp);
+	free_mbox_info(func_to_func->mbox_send);
+
+	kfree(func_to_func);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h
new file mode 100644
index 000000000000..7b18559bfe80
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ */
+
+#ifndef HINIC_MBOX_H_
+#define HINIC_MBOX_H_
+
+#define HINIC_MBOX_PF_SEND_ERR		0x1
+#define HINIC_MBOX_PF_BUSY_ACTIVE_FW	0x2
+#define HINIC_MBOX_VF_CMD_ERROR		0x3
+
+#define HINIC_MAX_FUNCTIONS		512
+
+#define HINIC_MAX_PF_FUNCS		16
+
+#define HINIC_MBOX_WQ_NAME		"hinic_mbox"
+
+#define HINIC_FUNC_CSR_MAILBOX_DATA_OFF			0x80
+#define HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF		0x0100
+#define HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF		0x0104
+#define HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF		0x0108
+#define HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF		0x010C
+
+enum hinic_mbox_ack_type {
+	MBOX_ACK,
+	MBOX_NO_ACK,
+};
+
+struct mbox_msg_info {
+	u8 msg_id;
+	u8 status;
+};
+
+struct hinic_recv_mbox {
+	struct completion	recv_done;
+	void			*mbox;
+	u8			cmd;
+	enum hinic_mod_type	mod;
+	u16			mbox_len;
+	void			*buf_out;
+	enum hinic_mbox_ack_type ack_type;
+	struct mbox_msg_info	msg_info;
+	u8			seq_id;
+	atomic_t		msg_cnt;
+};
+
+struct hinic_send_mbox {
+	struct completion	send_done;
+	u8			*data;
+
+	u64			*wb_status;
+	void			*wb_vaddr;
+	dma_addr_t		wb_paddr;
+};
+
+typedef void (*hinic_vf_mbox_cb)(void *handle, u8 cmd, void *buf_in,
+				u16 in_size, void *buf_out, u16 *out_size);
+typedef int (*hinic_pf_mbox_cb)(void *handle, u16 vf_id, u8 cmd, void *buf_in,
+				u16 in_size, void *buf_out, u16 *out_size);
+
+enum mbox_event_state {
+	EVENT_START = 0,
+	EVENT_FAIL,
+	EVENT_TIMEOUT,
+	EVENT_END,
+};
+
+enum hinic_mbox_cb_state {
+	HINIC_VF_MBOX_CB_REG = 0,
+	HINIC_VF_MBOX_CB_RUNNING,
+	HINIC_PF_MBOX_CB_REG,
+	HINIC_PF_MBOX_CB_RUNNING,
+	HINIC_PPF_MBOX_CB_REG,
+	HINIC_PPF_MBOX_CB_RUNNING,
+	HINIC_PPF_TO_PF_MBOX_CB_REG,
+	HINIC_PPF_TO_PF_MBOX_CB_RUNNIG,
+};
+
+struct hinic_mbox_func_to_func {
+	struct hinic_hwdev	*hwdev;
+	struct hinic_hwif		*hwif;
+
+	struct semaphore	mbox_send_sem;
+	struct semaphore	msg_send_sem;
+	struct hinic_send_mbox	send_mbox;
+
+	struct workqueue_struct *workq;
+
+	struct hinic_recv_mbox	mbox_resp[HINIC_MAX_FUNCTIONS];
+	struct hinic_recv_mbox	mbox_send[HINIC_MAX_FUNCTIONS];
+
+	hinic_vf_mbox_cb	vf_mbox_cb[HINIC_MOD_MAX];
+	hinic_pf_mbox_cb	pf_mbox_cb[HINIC_MOD_MAX];
+	unsigned long		pf_mbox_cb_state[HINIC_MOD_MAX];
+	unsigned long		vf_mbox_cb_state[HINIC_MOD_MAX];
+
+	u8 send_msg_id;
+	enum mbox_event_state event_flag;
+
+	/* lock for mbox event flag */
+	spinlock_t mbox_lock;
+};
+
+struct hinic_mbox_work {
+	struct work_struct work;
+	u16 src_func_idx;
+	struct hinic_mbox_func_to_func *func_to_func;
+	struct hinic_recv_mbox *recv_mbox;
+};
+
+struct vf_cmd_msg_handle {
+	u8 cmd;
+	int (*cmd_msg_handler)(void *hwdev, u16 vf_id,
+			       void *buf_in, u16 in_size,
+			       void *buf_out, u16 *out_size);
+};
+
+int hinic_register_pf_mbox_cb(struct hinic_hwdev *hwdev,
+			      enum hinic_mod_type mod,
+			      hinic_pf_mbox_cb callback);
+
+int hinic_register_vf_mbox_cb(struct hinic_hwdev *hwdev,
+			      enum hinic_mod_type mod,
+			      hinic_vf_mbox_cb callback);
+
+void hinic_unregister_pf_mbox_cb(struct hinic_hwdev *hwdev,
+				 enum hinic_mod_type mod);
+
+void hinic_unregister_vf_mbox_cb(struct hinic_hwdev *hwdev,
+				 enum hinic_mod_type mod);
+
+void hinic_mbox_func_aeqe_handler(void *handle, void *header, u8 size);
+
+void hinic_mbox_self_aeqe_handler(void *handle, void *header, u8 size);
+
+int hinic_func_to_func_init(struct hinic_hwdev *hwdev);
+
+void hinic_func_to_func_free(struct hinic_hwdev *hwdev);
+
+int hinic_mbox_to_pf(struct hinic_hwdev *hwdev, enum hinic_mod_type mod,
+		     u8 cmd, void *buf_in, u16 in_size, void *buf_out,
+		     u16 *out_size, u32 timeout);
+
+int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
+		       enum hinic_mod_type mod, u16 cmd, u16 dst_func,
+		       void *buf_in, u16 in_size, void *buf_out,
+		       u16 *out_size, u32 timeout);
+
+int hinic_mbox_to_vf(struct hinic_hwdev *hwdev,
+		     enum hinic_mod_type mod, u16 vf_id, u8 cmd, void *buf_in,
+		     u16 in_size, void *buf_out, u16 *out_size, u32 timeout);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index 182fba17b643..a5ab044f98cc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -60,6 +60,7 @@ enum hinic_cfg_cmd {
 };
 
 enum hinic_comm_cmd {
+	HINIC_COMM_CMD_START_FLR          = 0x1,
 	HINIC_COMM_CMD_IO_STATUS_GET    = 0x3,
 
 	HINIC_COMM_CMD_CMDQ_CTXT_SET    = 0x10,
-- 
cgit v1.2.3


From 7dd29ee128654702bd493ecec0bb22c2c5f0f395 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Sat, 25 Apr 2020 01:21:10 +0000
Subject: hinic: add sriov feature support

adds support of basic sriov feature including initialization and
tx/rx capabilities of virtual function

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/Makefile        |   2 +-
 drivers/net/ethernet/huawei/hinic/hinic_dev.h     |   3 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c |  18 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h |   2 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c  | 123 ++--
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h  |  46 ++
 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c  |  98 ++-
 drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h  |   4 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_io.c   |  49 ++
 drivers/net/ethernet/huawei/hinic/hinic_hw_io.h   |  23 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c |  17 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h |  11 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c   |   7 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h   |   4 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c   |   9 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h   |   6 +-
 drivers/net/ethernet/huawei/hinic/hinic_main.c    |  77 ++-
 drivers/net/ethernet/huawei/hinic/hinic_port.c    |  76 +--
 drivers/net/ethernet/huawei/hinic/hinic_port.h    |   4 +-
 drivers/net/ethernet/huawei/hinic/hinic_rx.c      |  15 +-
 drivers/net/ethernet/huawei/hinic/hinic_sriov.c   | 698 ++++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_sriov.h   |  79 +++
 drivers/net/ethernet/huawei/hinic/hinic_tx.c      |  17 +-
 23 files changed, 1195 insertions(+), 193 deletions(-)
 create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_sriov.c
 create mode 100644 drivers/net/ethernet/huawei/hinic/hinic_sriov.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index a73862a64690..32a011ca44c3 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -4,4 +4,4 @@ obj-$(CONFIG_HINIC) += hinic.o
 hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \
 	   hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \
 	   hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \
-	   hinic_common.o hinic_ethtool.o hinic_hw_mbox.o
+	   hinic_common.o hinic_ethtool.o hinic_hw_mbox.o hinic_sriov.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index a209b14160cc..a621ebbf7610 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -16,6 +16,7 @@
 #include "hinic_hw_dev.h"
 #include "hinic_tx.h"
 #include "hinic_rx.h"
+#include "hinic_sriov.h"
 
 #define HINIC_DRV_NAME          "hinic"
 
@@ -23,6 +24,7 @@ enum hinic_flags {
 	HINIC_LINK_UP = BIT(0),
 	HINIC_INTF_UP = BIT(1),
 	HINIC_RSS_ENABLE = BIT(2),
+	HINIC_LINK_DOWN = BIT(3),
 };
 
 struct hinic_rx_mode_work {
@@ -78,6 +80,7 @@ struct hinic_dev {
 	struct hinic_rss_type		rss_type;
 	u8				*rss_hkey_user;
 	s32				*rss_indir_user;
+	struct hinic_sriov_info sriov_info;
 };
 
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index 5f2d57d1b2d3..33c5333657c1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -64,7 +64,7 @@
 #define CMDQ_WQE_SIZE                   64
 #define CMDQ_DEPTH                      SZ_4K
 
-#define CMDQ_WQ_PAGE_SIZE               SZ_4K
+#define CMDQ_WQ_PAGE_SIZE               SZ_256K
 
 #define WQE_LCMD_SIZE                   64
 #define WQE_SCMD_SIZE                   64
@@ -705,7 +705,7 @@ static void cmdq_init_queue_ctxt(struct hinic_cmdq_ctxt *cmdq_ctxt,
 	/* The data in the HW is in Big Endian Format */
 	wq_first_page_paddr = be64_to_cpu(*wq->block_vaddr);
 
-	pfn = CMDQ_PFN(wq_first_page_paddr, wq->wq_page_size);
+	pfn = CMDQ_PFN(wq_first_page_paddr, SZ_4K);
 
 	ctxt_info->curr_wqe_page_pfn =
 		HINIC_CMDQ_CTXT_PAGE_INFO_SET(pfn, CURR_WQE_PAGE_PFN)   |
@@ -714,16 +714,19 @@ static void cmdq_init_queue_ctxt(struct hinic_cmdq_ctxt *cmdq_ctxt,
 		HINIC_CMDQ_CTXT_PAGE_INFO_SET(1, CEQ_EN)                |
 		HINIC_CMDQ_CTXT_PAGE_INFO_SET(cmdq->wrapped, WRAPPED);
 
-	/* block PFN - Read Modify Write */
-	cmdq_first_block_paddr = cmdq_pages->page_paddr;
+	if (wq->num_q_pages != 1) {
+		/* block PFN - Read Modify Write */
+		cmdq_first_block_paddr = cmdq_pages->page_paddr;
 
-	pfn = CMDQ_PFN(cmdq_first_block_paddr, wq->wq_page_size);
+		pfn = CMDQ_PFN(cmdq_first_block_paddr, wq->wq_page_size);
+	}
 
 	ctxt_info->wq_block_pfn =
 		HINIC_CMDQ_CTXT_BLOCK_INFO_SET(pfn, WQ_BLOCK_PFN) |
 		HINIC_CMDQ_CTXT_BLOCK_INFO_SET(atomic_read(&wq->cons_idx), CI);
 
 	cmdq_ctxt->func_idx = HINIC_HWIF_FUNC_IDX(cmdqs->hwif);
+	cmdq_ctxt->ppf_idx = HINIC_HWIF_PPF_IDX(cmdqs->hwif);
 	cmdq_ctxt->cmdq_type  = cmdq->cmdq_type;
 }
 
@@ -795,11 +798,6 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev,
 	size_t cmdq_ctxts_size;
 	int err;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI function type\n");
-		return -EINVAL;
-	}
-
 	cmdq_ctxts_size = HINIC_MAX_CMDQ_TYPES * sizeof(*cmdq_ctxts);
 	cmdq_ctxts = devm_kzalloc(&pdev->dev, cmdq_ctxts_size, GFP_KERNEL);
 	if (!cmdq_ctxts)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
index 7a434b653faa..3e4b0aef9fe6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
@@ -122,7 +122,7 @@ struct hinic_cmdq_ctxt {
 
 	u16     func_idx;
 	u8      cmdq_type;
-	u8      rsvd1[1];
+	u8      ppf_idx;
 
 	u8      rsvd2[4];
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index f2cf6f7ffc34..e5cab58e4ddd 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -15,7 +15,9 @@
 #include <linux/jiffies.h>
 #include <linux/log2.h>
 #include <linux/err.h>
+#include <linux/netdevice.h>
 
+#include "hinic_sriov.h"
 #include "hinic_hw_if.h"
 #include "hinic_hw_eqs.h"
 #include "hinic_hw_mgmt.h"
@@ -46,20 +48,6 @@ enum hw_ioctxt_set_cmdq_depth {
 	HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT,
 };
 
-/* HW struct */
-struct hinic_dev_cap {
-	u8      status;
-	u8      version;
-	u8      rsvd0[6];
-
-	u8      rsvd1[5];
-	u8      intr_type;
-	u8      rsvd2[66];
-	u16     max_sqs;
-	u16     max_rqs;
-	u8      rsvd3[208];
-};
-
 /**
  * get_capability - convert device capabilities to NIC capabilities
  * @hwdev: the HW device to set and convert device capabilities for
@@ -67,16 +55,13 @@ struct hinic_dev_cap {
  *
  * Return 0 - Success, negative - Failure
  **/
-static int get_capability(struct hinic_hwdev *hwdev,
-			  struct hinic_dev_cap *dev_cap)
+static int parse_capability(struct hinic_hwdev *hwdev,
+			    struct hinic_dev_cap *dev_cap)
 {
 	struct hinic_cap *nic_cap = &hwdev->nic_cap;
 	int num_aeqs, num_ceqs, num_irqs;
 
-	if (!HINIC_IS_PF(hwdev->hwif) && !HINIC_IS_PPF(hwdev->hwif))
-		return -EINVAL;
-
-	if (dev_cap->intr_type != INTR_MSIX_TYPE)
+	if (!HINIC_IS_VF(hwdev->hwif) && dev_cap->intr_type != INTR_MSIX_TYPE)
 		return -EFAULT;
 
 	num_aeqs = HINIC_HWIF_NUM_AEQS(hwdev->hwif);
@@ -89,13 +74,19 @@ static int get_capability(struct hinic_hwdev *hwdev,
 	if (nic_cap->num_qps > HINIC_Q_CTXT_MAX)
 		nic_cap->num_qps = HINIC_Q_CTXT_MAX;
 
-	nic_cap->max_qps = dev_cap->max_sqs + 1;
-	if (nic_cap->max_qps != (dev_cap->max_rqs + 1))
-		return -EFAULT;
+	if (!HINIC_IS_VF(hwdev->hwif))
+		nic_cap->max_qps = dev_cap->max_sqs + 1;
+	else
+		nic_cap->max_qps = dev_cap->max_sqs;
 
 	if (nic_cap->num_qps > nic_cap->max_qps)
 		nic_cap->num_qps = nic_cap->max_qps;
 
+	if (!HINIC_IS_VF(hwdev->hwif)) {
+		nic_cap->max_vf = dev_cap->max_vf;
+		nic_cap->max_vf_qps = dev_cap->max_vf_sqs + 1;
+	}
+
 	return 0;
 }
 
@@ -105,27 +96,26 @@ static int get_capability(struct hinic_hwdev *hwdev,
  *
  * Return 0 - Success, negative - Failure
  **/
-static int get_cap_from_fw(struct hinic_pfhwdev *pfhwdev)
+static int get_capability(struct hinic_pfhwdev *pfhwdev)
 {
 	struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_dev_cap dev_cap;
-	u16 in_len, out_len;
+	u16 out_len;
 	int err;
 
-	in_len = 0;
 	out_len = sizeof(dev_cap);
 
 	err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_CFGM,
-				HINIC_CFG_NIC_CAP, &dev_cap, in_len, &dev_cap,
-				&out_len, HINIC_MGMT_MSG_SYNC);
+				HINIC_CFG_NIC_CAP, &dev_cap, sizeof(dev_cap),
+				&dev_cap, &out_len, HINIC_MGMT_MSG_SYNC);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to get capability from FW\n");
 		return err;
 	}
 
-	return get_capability(hwdev, &dev_cap);
+	return parse_capability(hwdev, &dev_cap);
 }
 
 /**
@@ -144,15 +134,14 @@ static int get_dev_cap(struct hinic_hwdev *hwdev)
 	switch (HINIC_FUNC_TYPE(hwif)) {
 	case HINIC_PPF:
 	case HINIC_PF:
+	case HINIC_VF:
 		pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
-
-		err = get_cap_from_fw(pfhwdev);
+		err = get_capability(pfhwdev);
 		if (err) {
-			dev_err(&pdev->dev, "Failed to get capability from FW\n");
+			dev_err(&pdev->dev, "Failed to get capability\n");
 			return err;
 		}
 		break;
-
 	default:
 		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
 		return -EINVAL;
@@ -225,15 +214,8 @@ static void disable_msix(struct hinic_hwdev *hwdev)
 int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
 		       void *buf_in, u16 in_size, void *buf_out, u16 *out_size)
 {
-	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
 
 	return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, cmd,
@@ -252,14 +234,9 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_cmd_fw_ctxt fw_ctxt;
-	u16 out_size;
+	u16 out_size = sizeof(fw_ctxt);
 	int err;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ;
 
@@ -288,14 +265,8 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth,
 {
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_cmd_hw_ioctxt hw_ioctxt;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif);
 
@@ -374,11 +345,6 @@ static int clear_io_resources(struct hinic_hwdev *hwdev)
 	struct hinic_pfhwdev *pfhwdev;
 	int err;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	/* sleep 100ms to wait for firmware stopping I/O */
 	msleep(100);
 
@@ -410,14 +376,8 @@ static int set_resources_state(struct hinic_hwdev *hwdev,
 {
 	struct hinic_cmd_set_res_state res_state;
 	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	res_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	res_state.state = state;
 
@@ -441,8 +401,8 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
 {
 	struct hinic_cmd_base_qpn cmd_base_qpn;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(cmd_base_qpn);
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
 	int err;
 
 	cmd_base_qpn.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
@@ -488,7 +448,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev)
 	num_ceqs = HINIC_HWIF_NUM_CEQS(hwif);
 
 	ceq_msix_entries = &hwdev->msix_entries[num_aeqs];
-
+	func_to_io->hwdev = hwdev;
 	err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs,
 			    ceq_msix_entries);
 	if (err) {
@@ -558,17 +518,10 @@ void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev,
 					     u16 in_size, void *buf_out,
 					     u16 *out_size))
 {
-	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 	struct hinic_nic_cb *nic_cb;
 	u8 cmd_cb;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "unsupported PCI Function type\n");
-		return;
-	}
-
 	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
 
 	cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE;
@@ -588,15 +541,12 @@ void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev,
 			       enum hinic_mgmt_msg_cmd cmd)
 {
 	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 	struct hinic_nic_cb *nic_cb;
 	u8 cmd_cb;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "unsupported PCI Function type\n");
+	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif))
 		return;
-	}
 
 	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
 
@@ -742,12 +692,6 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev)
 		return ERR_PTR(err);
 	}
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		err = -EFAULT;
-		goto err_func_type;
-	}
-
 	pfhwdev = devm_kzalloc(&pdev->dev, sizeof(*pfhwdev), GFP_KERNEL);
 	if (!pfhwdev) {
 		err = -ENOMEM;
@@ -791,6 +735,12 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev)
 		goto err_dev_cap;
 	}
 
+	err = hinic_vf_func_init(hwdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init nic mbox\n");
+		goto err_vf_func_init;
+	}
+
 	err = init_fw_ctxt(hwdev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init function table\n");
@@ -807,6 +757,8 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev)
 
 err_resources_state:
 err_init_fw_ctxt:
+	hinic_vf_func_free(hwdev);
+err_vf_func_init:
 err_dev_cap:
 	free_pfhwdev(pfhwdev);
 
@@ -818,7 +770,6 @@ err_aeqs_init:
 
 err_init_msix:
 err_pfhwdev_alloc:
-err_func_type:
 	hinic_free_hwif(hwif);
 	return ERR_PTR(err);
 }
@@ -949,15 +900,9 @@ int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq,
 {
 	struct hinic_qp *qp = container_of(sq, struct hinic_qp, sq);
 	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_pfhwdev *pfhwdev;
 	struct hinic_cmd_hw_ci hw_ci;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	hw_ci.dma_attr_off  = 0;
 	hw_ci.pending_limit = pending_limit;
 	hw_ci.coalesc_timer = coalesc_timer;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 2574086aa314..531d1072e0df 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -23,12 +23,20 @@
 #define HINIC_MGMT_NUM_MSG_CMD  (HINIC_MGMT_MSG_CMD_MAX - \
 				 HINIC_MGMT_MSG_CMD_BASE)
 
+#define HINIC_PF_SET_VF_ALREADY				0x4
+#define HINIC_MGMT_STATUS_EXIST				0x6
+
 struct hinic_cap {
 	u16     max_qps;
 	u16     num_qps;
+	u8		max_vf;
+	u16     max_vf_qps;
 };
 
 enum hinic_port_cmd {
+	HINIC_PORT_CMD_VF_REGISTER = 0x0,
+	HINIC_PORT_CMD_VF_UNREGISTER = 0x1,
+
 	HINIC_PORT_CMD_CHANGE_MTU       = 2,
 
 	HINIC_PORT_CMD_ADD_VLAN         = 3,
@@ -84,10 +92,18 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_GLOBAL_QPN   = 102,
 
+	HINIC_PORT_CMD_SET_VF_VLAN	= 106,
+
+	HINIC_PORT_CMD_CLR_VF_VLAN,
+
 	HINIC_PORT_CMD_SET_TSO          = 112,
 
 	HINIC_PORT_CMD_SET_RQ_IQ_MAP	= 115,
 
+	HINIC_PORT_CMD_LINK_STATUS_REPORT = 160,
+
+	HINIC_PORT_CMD_UPDATE_MAC = 164,
+
 	HINIC_PORT_CMD_GET_CAP          = 170,
 
 	HINIC_PORT_CMD_SET_LRO_TIMER	= 244,
@@ -192,6 +208,17 @@ struct hinic_cmd_set_res_state {
 	u32     rsvd2;
 };
 
+struct hinic_ceq_ctrl_reg {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+
+	u16 func_id;
+	u16 q_id;
+	u32 ctrl0;
+	u32 ctrl1;
+};
+
 struct hinic_cmd_base_qpn {
 	u8      status;
 	u8      version;
@@ -248,6 +275,25 @@ struct hinic_pfhwdev {
 	struct hinic_nic_cb             nic_cb[HINIC_MGMT_NUM_MSG_CMD];
 };
 
+struct hinic_dev_cap {
+	u8      status;
+	u8      version;
+	u8      rsvd0[6];
+
+	u8      rsvd1[5];
+	u8      intr_type;
+	u8	max_cos_id;
+	u8	er_id;
+	u8	port_id;
+	u8      max_vf;
+	u8      rsvd2[62];
+	u16     max_sqs;
+	u16	max_rqs;
+	u16	max_vf_sqs;
+	u16     max_vf_rqs;
+	u8      rsvd3[204];
+};
+
 void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev,
 			     enum hinic_mgmt_msg_cmd cmd, void *handle,
 			     void (*handler)(void *handle, void *buf_in,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index c0b6bcb067cd..397936cac304 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -17,6 +17,7 @@
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 
+#include "hinic_hw_dev.h"
 #include "hinic_hw_csr.h"
 #include "hinic_hw_if.h"
 #include "hinic_hw_eqs.h"
@@ -416,11 +417,11 @@ static irqreturn_t ceq_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void set_ctrl0(struct hinic_eq *eq)
+static u32 get_ctrl0_val(struct hinic_eq *eq, u32 addr)
 {
 	struct msix_entry *msix_entry = &eq->msix_entry;
 	enum hinic_eq_type type = eq->type;
-	u32 addr, val, ctrl0;
+	u32 val, ctrl0;
 
 	if (type == HINIC_AEQ) {
 		/* RMW Ctrl0 */
@@ -440,9 +441,7 @@ static void set_ctrl0(struct hinic_eq *eq)
 			HINIC_AEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INT_MODE);
 
 		val |= ctrl0;
-
-		hinic_hwif_write_reg(eq->hwif, addr, val);
-	} else if (type == HINIC_CEQ) {
+	} else {
 		/* RMW Ctrl0 */
 		addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id);
 
@@ -462,16 +461,28 @@ static void set_ctrl0(struct hinic_eq *eq)
 			HINIC_CEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INTR_MODE);
 
 		val |= ctrl0;
-
-		hinic_hwif_write_reg(eq->hwif, addr, val);
 	}
+	return val;
 }
 
-static void set_ctrl1(struct hinic_eq *eq)
+static void set_ctrl0(struct hinic_eq *eq)
 {
+	u32 val, addr;
+
+	if (eq->type == HINIC_AEQ)
+		addr = HINIC_CSR_AEQ_CTRL_0_ADDR(eq->q_id);
+	else
+		addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id);
+
+	val = get_ctrl0_val(eq, addr);
+
+	hinic_hwif_write_reg(eq->hwif, addr, val);
+}
+
+static u32 get_ctrl1_val(struct hinic_eq *eq, u32 addr)
+{
+	u32 page_size_val, elem_size, val, ctrl1;
 	enum hinic_eq_type type = eq->type;
-	u32 page_size_val, elem_size;
-	u32 addr, val, ctrl1;
 
 	if (type == HINIC_AEQ) {
 		/* RMW Ctrl1 */
@@ -491,9 +502,7 @@ static void set_ctrl1(struct hinic_eq *eq)
 			HINIC_AEQ_CTRL_1_SET(page_size_val, PAGE_SIZE);
 
 		val |= ctrl1;
-
-		hinic_hwif_write_reg(eq->hwif, addr, val);
-	} else if (type == HINIC_CEQ) {
+	} else {
 		/* RMW Ctrl1 */
 		addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id);
 
@@ -508,19 +517,70 @@ static void set_ctrl1(struct hinic_eq *eq)
 			HINIC_CEQ_CTRL_1_SET(page_size_val, PAGE_SIZE);
 
 		val |= ctrl1;
+	}
+	return val;
+}
 
-		hinic_hwif_write_reg(eq->hwif, addr, val);
+static void set_ctrl1(struct hinic_eq *eq)
+{
+	u32 addr, val;
+
+	if (eq->type == HINIC_AEQ)
+		addr = HINIC_CSR_AEQ_CTRL_1_ADDR(eq->q_id);
+	else
+		addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id);
+
+	val = get_ctrl1_val(eq, addr);
+
+	hinic_hwif_write_reg(eq->hwif, addr, val);
+}
+
+static int set_ceq_ctrl_reg(struct hinic_eq *eq)
+{
+	struct hinic_ceq_ctrl_reg ceq_ctrl = {0};
+	struct hinic_hwdev *hwdev = eq->hwdev;
+	u16 out_size = sizeof(ceq_ctrl);
+	u16 in_size = sizeof(ceq_ctrl);
+	struct hinic_pfhwdev *pfhwdev;
+	u32 addr;
+	int err;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id);
+	ceq_ctrl.ctrl0 = get_ctrl0_val(eq, addr);
+	addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id);
+	ceq_ctrl.ctrl1 = get_ctrl1_val(eq, addr);
+
+	ceq_ctrl.func_id = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+	ceq_ctrl.q_id = eq->q_id;
+
+	err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
+				HINIC_COMM_CMD_CEQ_CTRL_REG_WR_BY_UP,
+				&ceq_ctrl, in_size,
+				&ceq_ctrl, &out_size, HINIC_MGMT_MSG_SYNC);
+	if (err || !out_size || ceq_ctrl.status) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"Failed to set ceq %d ctrl reg, err: %d status: 0x%x, out_size: 0x%x\n",
+			eq->q_id, err, ceq_ctrl.status, out_size);
+		return -EFAULT;
 	}
+
+	return 0;
 }
 
 /**
  * set_eq_ctrls - setting eq's ctrl registers
  * @eq: the Event Queue for setting
  **/
-static void set_eq_ctrls(struct hinic_eq *eq)
+static int set_eq_ctrls(struct hinic_eq *eq)
 {
+	if (HINIC_IS_VF(eq->hwif) && eq->type == HINIC_CEQ)
+		return set_ceq_ctrl_reg(eq);
+
 	set_ctrl0(eq);
 	set_ctrl1(eq);
+	return 0;
 }
 
 /**
@@ -703,7 +763,12 @@ static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif,
 		return -EINVAL;
 	}
 
-	set_eq_ctrls(eq);
+	err = set_eq_ctrls(eq);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set eq ctrls\n");
+		return err;
+	}
+
 	eq_update_ci(eq, EQ_ARMED);
 
 	err = alloc_eq_pages(eq);
@@ -859,6 +924,7 @@ int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif,
 	ceqs->num_ceqs = num_ceqs;
 
 	for (q_id = 0; q_id < num_ceqs; q_id++) {
+		ceqs->ceq[q_id].hwdev = ceqs->hwdev;
 		err = init_eq(&ceqs->ceq[q_id], hwif, HINIC_CEQ, q_id, q_len,
 			      page_size, msix_entries[q_id]);
 		if (err) {
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
index d73256da4b80..74b9ff90640c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
@@ -172,7 +172,7 @@ struct hinic_eq_work {
 
 struct hinic_eq {
 	struct hinic_hwif       *hwif;
-
+	struct hinic_hwdev      *hwdev;
 	enum hinic_eq_type      type;
 	int                     q_id;
 	u32                     q_len;
@@ -220,7 +220,7 @@ struct hinic_ceq_cb {
 
 struct hinic_ceqs {
 	struct hinic_hwif       *hwif;
-
+	struct hinic_hwdev		*hwdev;
 	struct hinic_eq         ceq[HINIC_MAX_CEQS];
 	int                     num_ceqs;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index d66f86fa3f46..a4581c988a63 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/err.h>
 
+#include "hinic_hw_dev.h"
 #include "hinic_hw_if.h"
 #include "hinic_hw_eqs.h"
 #include "hinic_hw_wqe.h"
@@ -34,6 +35,8 @@
 #define DB_IDX(db, db_base)             \
 	(((unsigned long)(db) - (unsigned long)(db_base)) / HINIC_DB_PAGE_SIZE)
 
+#define HINIC_PAGE_SIZE_HW(pg_size)	((u8)ilog2((u32)((pg_size) >> 12)))
+
 enum io_cmd {
 	IO_CMD_MODIFY_QUEUE_CTXT = 0,
 	IO_CMD_CLEAN_QUEUE_CTXT,
@@ -484,6 +487,33 @@ void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, int num_qps)
 	devm_kfree(&pdev->dev, func_to_io->qps);
 }
 
+int hinic_set_wq_page_size(struct hinic_hwdev *hwdev, u16 func_idx,
+			   u32 page_size)
+{
+	struct hinic_wq_page_size page_size_info = {0};
+	u16 out_size = sizeof(page_size_info);
+	struct hinic_pfhwdev *pfhwdev;
+	int err;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	page_size_info.func_idx = func_idx;
+	page_size_info.ppf_idx = HINIC_HWIF_PPF_IDX(hwdev->hwif);
+	page_size_info.page_size = HINIC_PAGE_SIZE_HW(page_size);
+
+	err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
+				HINIC_COMM_CMD_PAGESIZE_SET, &page_size_info,
+				sizeof(page_size_info), &page_size_info,
+				&out_size, HINIC_MGMT_MSG_SYNC);
+	if (err || !out_size || page_size_info.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set wq page size, err: %d, status: 0x%x, out_size: 0x%0x\n",
+			err, page_size_info.status, out_size);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 /**
  * hinic_io_init - Initialize the IO components
  * @func_to_io: func to io channel that holds the IO components
@@ -506,6 +536,7 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io,
 	func_to_io->hwif = hwif;
 	func_to_io->qps = NULL;
 	func_to_io->max_qps = max_qps;
+	func_to_io->ceqs.hwdev = func_to_io->hwdev;
 
 	err = hinic_ceqs_init(&func_to_io->ceqs, hwif, num_ceqs,
 			      HINIC_DEFAULT_CEQ_LEN, HINIC_EQ_PAGE_SIZE,
@@ -541,6 +572,14 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io,
 		func_to_io->cmdq_db_area[cmdq] = db_area;
 	}
 
+	err = hinic_set_wq_page_size(func_to_io->hwdev,
+				     HINIC_HWIF_FUNC_IDX(hwif),
+				     HINIC_DEFAULT_WQ_PAGE_SIZE);
+	if (err) {
+		dev_err(&func_to_io->hwif->pdev->dev, "Failed to set wq page size\n");
+		goto init_wq_pg_size_err;
+	}
+
 	err = hinic_init_cmdqs(&func_to_io->cmdqs, hwif,
 			       func_to_io->cmdq_db_area);
 	if (err) {
@@ -551,6 +590,11 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io,
 	return 0;
 
 err_init_cmdqs:
+	if (!HINIC_IS_VF(func_to_io->hwif))
+		hinic_set_wq_page_size(func_to_io->hwdev,
+				       HINIC_HWIF_FUNC_IDX(hwif),
+				       HINIC_HW_WQ_PAGE_SIZE);
+init_wq_pg_size_err:
 err_db_area:
 	for (type = HINIC_CMDQ_SYNC; type < cmdq; type++)
 		return_db_area(func_to_io, func_to_io->cmdq_db_area[type]);
@@ -575,6 +619,11 @@ void hinic_io_free(struct hinic_func_to_io *func_to_io)
 
 	hinic_free_cmdqs(&func_to_io->cmdqs);
 
+	if (!HINIC_IS_VF(func_to_io->hwif))
+		hinic_set_wq_page_size(func_to_io->hwdev,
+				       HINIC_HWIF_FUNC_IDX(func_to_io->hwif),
+				       HINIC_HW_WQ_PAGE_SIZE);
+
 	for (cmdq = HINIC_CMDQ_SYNC; cmdq < HINIC_MAX_CMDQ_TYPES; cmdq++)
 		return_db_area(func_to_io, func_to_io->cmdq_db_area[cmdq]);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
index cac2b722e7dc..28c0594f636d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
@@ -20,6 +20,8 @@
 
 #define HINIC_DB_PAGE_SIZE      SZ_4K
 #define HINIC_DB_SIZE           SZ_4M
+#define HINIC_HW_WQ_PAGE_SIZE	SZ_4K
+#define HINIC_DEFAULT_WQ_PAGE_SIZE SZ_256K
 
 #define HINIC_DB_MAX_AREAS      (HINIC_DB_SIZE / HINIC_DB_PAGE_SIZE)
 
@@ -47,7 +49,7 @@ struct hinic_free_db_area {
 
 struct hinic_func_to_io {
 	struct hinic_hwif       *hwif;
-
+	struct hinic_hwdev      *hwdev;
 	struct hinic_ceqs       ceqs;
 
 	struct hinic_wqs        wqs;
@@ -69,8 +71,27 @@ struct hinic_func_to_io {
 	void __iomem                    *cmdq_db_area[HINIC_MAX_CMDQ_TYPES];
 
 	struct hinic_cmdqs              cmdqs;
+
+	u16			max_vfs;
+	struct vf_data_storage	*vf_infos;
+	u8			link_status;
 };
 
+struct hinic_wq_page_size {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_idx;
+	u8	ppf_idx;
+	u8	page_size;
+
+	u32	rsvd1;
+};
+
+int hinic_set_wq_page_size(struct hinic_hwdev *hwdev, u16 func_idx,
+			   u32 page_size);
+
 int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
 			u16 base_qpn, int num_qps,
 			struct msix_entry *sq_msix_entries,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 8995e32dd1c0..eef855f11a01 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -353,7 +353,11 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
-	return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
+	if (HINIC_IS_VF(hwif))
+		return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in,
+					in_size, buf_out, out_size, 0);
+	else
+		return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
 				MSG_NOT_RESP);
 }
@@ -390,8 +394,8 @@ static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt,
 			    recv_msg->msg, recv_msg->msg_len,
 			    buf_out, &out_size);
 	else
-		dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n",
-			recv_msg->mod);
+		dev_err(&pdev->dev, "No MGMT msg handler, mod: %d, cmd: %d\n",
+			recv_msg->mod, recv_msg->cmd);
 
 	mgmt_cb->state &= ~HINIC_MGMT_CB_RUNNING;
 
@@ -553,6 +557,10 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt,
 	int err;
 
 	pf_to_mgmt->hwif = hwif;
+	pf_to_mgmt->hwdev = hwdev;
+
+	if (HINIC_IS_VF(hwif))
+		return 0;
 
 	sema_init(&pf_to_mgmt->sync_msg_lock, 1);
 	pf_to_mgmt->sync_msg_id = 0;
@@ -584,6 +592,9 @@ void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt)
 	struct hinic_pfhwdev *pfhwdev = mgmt_to_pfhwdev(pf_to_mgmt);
 	struct hinic_hwdev *hwdev = &pfhwdev->hwdev;
 
+	if (HINIC_IS_VF(hwdev->hwif))
+		return;
+
 	hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU);
 	hinic_api_cmd_free(pf_to_mgmt->cmd_chain);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index a5ab044f98cc..c2b142c08b0e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -62,6 +62,7 @@ enum hinic_cfg_cmd {
 enum hinic_comm_cmd {
 	HINIC_COMM_CMD_START_FLR          = 0x1,
 	HINIC_COMM_CMD_IO_STATUS_GET    = 0x3,
+	HINIC_COMM_CMD_DMA_ATTR_SET	    = 0x4,
 
 	HINIC_COMM_CMD_CMDQ_CTXT_SET    = 0x10,
 	HINIC_COMM_CMD_CMDQ_CTXT_GET    = 0x11,
@@ -75,7 +76,13 @@ enum hinic_comm_cmd {
 
 	HINIC_COMM_CMD_IO_RES_CLEAR     = 0x29,
 
-	HINIC_COMM_CMD_MAX              = 0x32,
+	HINIC_COMM_CMD_CEQ_CTRL_REG_WR_BY_UP = 0x33,
+
+	HINIC_COMM_CMD_L2NIC_RESET		= 0x4b,
+
+	HINIC_COMM_CMD_PAGESIZE_SET	= 0x50,
+
+	HINIC_COMM_CMD_MAX              = 0x51,
 };
 
 enum hinic_mgmt_cb_state {
@@ -108,7 +115,7 @@ struct hinic_mgmt_cb {
 
 struct hinic_pf_to_mgmt {
 	struct hinic_hwif               *hwif;
-
+	struct hinic_hwdev		*hwdev;
 	struct semaphore                sync_msg_lock;
 	u16                             sync_msg_id;
 	u8                              *sync_msg_buf;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index be364b7a7019..20c5c8ea452e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -108,7 +108,12 @@ void hinic_sq_prepare_ctxt(struct hinic_sq_ctxt *sq_ctxt,
 	wq_page_pfn_hi = upper_32_bits(wq_page_pfn);
 	wq_page_pfn_lo = lower_32_bits(wq_page_pfn);
 
-	wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr);
+	/* If only one page, use 0-level CLA */
+	if (wq->num_q_pages == 1)
+		wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq_page_addr);
+	else
+		wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr);
+
 	wq_block_pfn_hi = upper_32_bits(wq_block_pfn);
 	wq_block_pfn_lo = lower_32_bits(wq_block_pfn);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index 79091e131418..c30d092e48d5 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -38,8 +38,8 @@
 #define HINIC_SQ_WQEBB_SIZE                     64
 #define HINIC_RQ_WQEBB_SIZE                     32
 
-#define HINIC_SQ_PAGE_SIZE                      SZ_4K
-#define HINIC_RQ_PAGE_SIZE                      SZ_4K
+#define HINIC_SQ_PAGE_SIZE                      SZ_256K
+#define HINIC_RQ_PAGE_SIZE                      SZ_256K
 
 #define HINIC_SQ_DEPTH                          SZ_4K
 #define HINIC_RQ_DEPTH                          SZ_4K
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
index 03363216ff59..5dc3743f8091 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
@@ -503,7 +503,7 @@ err_alloc_wq_pages:
  * Return 0 - Success, negative - Failure
  **/
 int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
-		      u16 wqebb_size, u16 wq_page_size, u16 q_depth,
+		      u16 wqebb_size, u32 wq_page_size, u16 q_depth,
 		      u16 max_wqe_size)
 {
 	struct hinic_hwif *hwif = wqs->hwif;
@@ -600,7 +600,7 @@ void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq)
  **/
 int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 			 struct hinic_wq *wq, struct hinic_hwif *hwif,
-			 int cmdq_blocks, u16 wqebb_size, u16 wq_page_size,
+			 int cmdq_blocks, u16 wqebb_size, u32 wq_page_size,
 			 u16 q_depth, u16 max_wqe_size)
 {
 	struct pci_dev *pdev = hwif->pdev;
@@ -768,7 +768,10 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 
 	*prod_idx = curr_prod_idx;
 
-	if (curr_pg != end_pg) {
+	/* If we only have one page, still need to get shadown wqe when
+	 * wqe rolling-over page
+	 */
+	if (curr_pg != end_pg || MASKED_WQE_IDX(wq, end_prod_idx) < *prod_idx) {
 		void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size];
 
 		copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *prod_idx);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
index 811eef744140..b06f8c0255de 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
@@ -26,7 +26,7 @@ struct hinic_wq {
 	int             block_idx;
 
 	u16             wqebb_size;
-	u16             wq_page_size;
+	u32             wq_page_size;
 	u16             q_depth;
 	u16             max_wqe_size;
 	u16             num_wqebbs_per_page;
@@ -76,7 +76,7 @@ struct hinic_cmdq_pages {
 
 int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 			 struct hinic_wq *wq, struct hinic_hwif *hwif,
-			 int cmdq_blocks, u16 wqebb_size, u16 wq_page_size,
+			 int cmdq_blocks, u16 wqebb_size, u32 wq_page_size,
 			 u16 q_depth, u16 max_wqe_size);
 
 void hinic_wqs_cmdq_free(struct hinic_cmdq_pages *cmdq_pages,
@@ -88,7 +88,7 @@ int hinic_wqs_alloc(struct hinic_wqs *wqs, int num_wqs,
 void hinic_wqs_free(struct hinic_wqs *wqs);
 
 int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
-		      u16 wqebb_size, u16 wq_page_size, u16 q_depth,
+		      u16 wqebb_size, u32 wq_page_size, u16 q_depth,
 		      u16 max_wqe_size);
 
 void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 13560975c103..cd71249f9b1c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -29,6 +29,7 @@
 #include "hinic_tx.h"
 #include "hinic_rx.h"
 #include "hinic_dev.h"
+#include "hinic_sriov.h"
 
 MODULE_AUTHOR("Huawei Technologies CO., Ltd");
 MODULE_DESCRIPTION("Huawei Intelligent NIC driver");
@@ -46,6 +47,7 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 #define HINIC_DEV_ID_DUAL_PORT_100GE        0x0200
 #define HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ   0x0205
 #define HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ    0x0210
+#define HINIC_DEV_ID_VF    0x375e
 
 #define HINIC_WQ_NAME                   "hinic_dev"
 
@@ -65,6 +67,8 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 #define rx_mode_work_to_nic_dev(rx_mode_work) \
 		container_of(rx_mode_work, struct hinic_dev, rx_mode_work)
 
+#define HINIC_WAIT_SRIOV_CFG_TIMEOUT	15000
+
 static int change_mac_addr(struct net_device *netdev, const u8 *addr);
 
 static int set_features(struct hinic_dev *nic_dev,
@@ -423,8 +427,9 @@ static int hinic_open(struct net_device *netdev)
 		goto err_func_port_state;
 	}
 
-	/* Wait up to 3 sec between port enable to link state */
-	msleep(3000);
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		/* Wait up to 3 sec between port enable to link state */
+		msleep(3000);
 
 	down(&nic_dev->mgmt_lock);
 
@@ -434,6 +439,9 @@ static int hinic_open(struct net_device *netdev)
 		goto err_port_link;
 	}
 
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		hinic_notify_all_vfs_link_changed(nic_dev->hwdev, link_state);
+
 	if (link_state == HINIC_LINK_STATE_UP)
 		nic_dev->flags |= HINIC_LINK_UP;
 
@@ -497,6 +505,9 @@ static int hinic_close(struct net_device *netdev)
 
 	up(&nic_dev->mgmt_lock);
 
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		hinic_notify_all_vfs_link_changed(nic_dev->hwdev, 0);
+
 	err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
 	if (err) {
 		netif_err(nic_dev, drv, netdev,
@@ -685,7 +696,7 @@ static int hinic_vlan_rx_add_vid(struct net_device *netdev,
 	}
 
 	err = hinic_port_add_mac(nic_dev, netdev->dev_addr, vid);
-	if (err) {
+	if (err && err != HINIC_PF_SET_VF_ALREADY) {
 		netif_err(nic_dev, drv, netdev, "Failed to set mac\n");
 		goto err_add_mac;
 	}
@@ -737,8 +748,6 @@ static void set_rx_mode(struct work_struct *work)
 	struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work);
 	struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work);
 
-	netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n");
-
 	hinic_port_set_rx_mode(nic_dev, rx_mode_work->rx_mode);
 
 	__dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
@@ -896,6 +905,10 @@ static void link_status_event_handler(void *handle, void *buf_in, u16 in_size,
 		netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is DOWN\n");
 	}
 
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		hinic_notify_all_vfs_link_changed(nic_dev->hwdev,
+						  link_status->link);
+
 	ret_link_status = buf_out;
 	ret_link_status->status = 0;
 
@@ -969,7 +982,9 @@ static int nic_dev_init(struct pci_dev *pdev)
 	}
 
 	hinic_set_ethtool_ops(netdev);
+
 	netdev->netdev_ops = &hinic_netdev_ops;
+
 	netdev->max_mtu = ETH_MAX_MTU;
 
 	nic_dev = netdev_priv(netdev);
@@ -981,6 +996,8 @@ static int nic_dev_init(struct pci_dev *pdev)
 	nic_dev->rxqs = NULL;
 	nic_dev->tx_weight = tx_weight;
 	nic_dev->rx_weight = rx_weight;
+	nic_dev->sriov_info.hwdev = hwdev;
+	nic_dev->sriov_info.pdev = pdev;
 
 	sema_init(&nic_dev->mgmt_lock, 1);
 
@@ -1007,11 +1024,25 @@ static int nic_dev_init(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, netdev);
 
 	err = hinic_port_get_mac(nic_dev, netdev->dev_addr);
-	if (err)
-		dev_warn(&pdev->dev, "Failed to get mac address\n");
+	if (err) {
+		dev_err(&pdev->dev, "Failed to get mac address\n");
+		goto err_get_mac;
+	}
+
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
+		if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) {
+			dev_err(&pdev->dev, "Invalid MAC address\n");
+			err = -EIO;
+			goto err_add_mac;
+		}
+
+		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
+			 netdev->dev_addr);
+		eth_hw_addr_random(netdev);
+	}
 
 	err = hinic_port_add_mac(nic_dev, netdev->dev_addr, 0);
-	if (err) {
+	if (err && err != HINIC_PF_SET_VF_ALREADY) {
 		dev_err(&pdev->dev, "Failed to add mac\n");
 		goto err_add_mac;
 	}
@@ -1053,6 +1084,7 @@ err_set_features:
 	cancel_work_sync(&rx_mode_work->work);
 
 err_set_mtu:
+err_get_mac:
 err_add_mac:
 	pci_set_drvdata(pdev, NULL);
 	destroy_workqueue(nic_dev->workq);
@@ -1126,12 +1158,37 @@ err_pci_regions:
 	return err;
 }
 
+#define HINIC_WAIT_SRIOV_CFG_TIMEOUT	15000
+
+static void wait_sriov_cfg_complete(struct hinic_dev *nic_dev)
+{
+	struct hinic_sriov_info *sriov_info = &nic_dev->sriov_info;
+	u32 loop_cnt = 0;
+
+	set_bit(HINIC_FUNC_REMOVE, &sriov_info->state);
+	usleep_range(9900, 10000);
+
+	while (loop_cnt < HINIC_WAIT_SRIOV_CFG_TIMEOUT) {
+		if (!test_bit(HINIC_SRIOV_ENABLE, &sriov_info->state) &&
+		    !test_bit(HINIC_SRIOV_DISABLE, &sriov_info->state))
+			return;
+
+		usleep_range(9900, 10000);
+		loop_cnt++;
+	}
+}
+
 static void hinic_remove(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	struct hinic_rx_mode_work *rx_mode_work;
 
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) {
+		wait_sriov_cfg_complete(nic_dev);
+		hinic_pci_sriov_disable(pdev);
+	}
+
 	unregister_netdev(netdev);
 
 	hinic_hwdev_cb_unregister(nic_dev->hwdev,
@@ -1144,6 +1201,8 @@ static void hinic_remove(struct pci_dev *pdev)
 
 	destroy_workqueue(nic_dev->workq);
 
+	hinic_vf_func_free(nic_dev->hwdev);
+
 	hinic_free_hwdev(nic_dev->hwdev);
 
 	free_netdev(netdev);
@@ -1164,6 +1223,7 @@ static const struct pci_device_id hinic_pci_table[] = {
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0},
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ), 0},
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ), 0},
+	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_VF), 0},
 	{ 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, hinic_pci_table);
@@ -1174,6 +1234,7 @@ static struct pci_driver hinic_driver = {
 	.probe          = hinic_probe,
 	.remove         = hinic_remove,
 	.shutdown       = hinic_shutdown,
+	.sriov_configure = hinic_pci_sriov_configure,
 };
 
 module_pci_driver(hinic_driver);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 1e389a004e50..b7fe0adcc29a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -37,20 +37,14 @@ enum mac_op {
 static int change_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		      u16 vlan_id, enum mac_op op)
 {
-	struct net_device *netdev = nic_dev->netdev;
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_port_mac_cmd port_mac_cmd;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(port_mac_cmd);
 	struct pci_dev *pdev = hwif->pdev;
 	enum hinic_port_cmd cmd;
-	u16 out_size;
 	int err;
 
-	if (vlan_id >= VLAN_N_VID) {
-		netif_err(nic_dev, drv, netdev, "Invalid VLAN number\n");
-		return -EINVAL;
-	}
-
 	if (op == MAC_SET)
 		cmd = HINIC_PORT_CMD_SET_MAC;
 	else
@@ -63,12 +57,25 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr,
 	err = hinic_port_msg_cmd(hwdev, cmd, &port_mac_cmd,
 				 sizeof(port_mac_cmd),
 				 &port_mac_cmd, &out_size);
-	if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) {
+	if (err || out_size != sizeof(port_mac_cmd) ||
+	    (port_mac_cmd.status  &&
+	    port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY &&
+	    port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) {
 		dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n",
 			port_mac_cmd.status);
 		return -EFAULT;
 	}
 
+	if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status ==
+	    HINIC_PF_SET_VF_ALREADY) {
+		dev_warn(&pdev->dev, "PF has already set VF mac, Ignore set operation\n");
+		return HINIC_PF_SET_VF_ALREADY;
+	}
+
+	if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status ==
+	    HINIC_MGMT_STATUS_EXIST)
+		dev_warn(&pdev->dev, "MAC is repeated. Ignore set operation\n");
+
 	return 0;
 }
 
@@ -112,8 +119,8 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr)
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_port_mac_cmd port_mac_cmd;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(port_mac_cmd);
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
 	int err;
 
 	port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
@@ -144,9 +151,9 @@ int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu)
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_port_mtu_cmd port_mtu_cmd;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(port_mtu_cmd);
 	struct pci_dev *pdev = hwif->pdev;
 	int err, max_frame;
-	u16 out_size;
 
 	if (new_mtu < HINIC_MIN_MTU_SIZE) {
 		netif_err(nic_dev, drv, netdev, "mtu < MIN MTU size");
@@ -248,14 +255,9 @@ int hinic_port_link_state(struct hinic_dev *nic_dev,
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_port_link_cmd link_cmd;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(link_cmd);
 	int err;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
 	link_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE,
@@ -284,13 +286,11 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state)
 	struct hinic_port_state_cmd port_state;
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(port_state);
 	int err;
 
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "unsupported PCI Function type\n");
-		return -EINVAL;
-	}
+	if (HINIC_IS_VF(hwdev->hwif))
+		return 0;
 
 	port_state.state = state;
 
@@ -320,7 +320,7 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev,
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(func_state);
 	int err;
 
 	func_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
@@ -351,7 +351,7 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(*port_cap);
 	int err;
 
 	port_cap->func_idx = HINIC_HWIF_FUNC_IDX(hwif);
@@ -382,7 +382,7 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state)
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_tso_config tso_cfg = {0};
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(tso_cfg);
 	int err;
 
 	tso_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -405,9 +405,9 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
 {
 	struct hinic_checksum_offload rx_csum_cfg = {0};
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	u16 out_size = sizeof(rx_csum_cfg);
 	struct hinic_hwif *hwif;
 	struct pci_dev *pdev;
-	u16 out_size;
 	int err;
 
 	if (!hwdev)
@@ -443,6 +443,7 @@ int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en)
 	if (!hwdev)
 		return -EINVAL;
 
+	out_size = sizeof(vlan_cfg);
 	hwif = hwdev->hwif;
 	pdev = hwif->pdev;
 	vlan_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -465,8 +466,8 @@ int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs)
 {
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_rq_num rq_num = { 0 };
+	struct pci_dev *pdev = hwif->pdev;
 	u16 out_size = sizeof(rq_num);
 	int err;
 
@@ -491,8 +492,8 @@ static int hinic_set_rx_lro(struct hinic_dev *nic_dev, u8 ipv4_en, u8 ipv6_en,
 			    u8 max_wqe_num)
 {
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
-	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_lro_config lro_cfg = { 0 };
+	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	u16 out_size = sizeof(lro_cfg);
 	int err;
@@ -568,6 +569,9 @@ int hinic_set_rx_lro_state(struct hinic_dev *nic_dev, u8 lro_en,
 	if (err)
 		return err;
 
+	if (HINIC_IS_VF(nic_dev->hwdev->hwif))
+		return 0;
+
 	err = hinic_set_rx_lro_timer(nic_dev, lro_timer);
 	if (err)
 		return err;
@@ -741,9 +745,9 @@ int hinic_get_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx,
 {
 	struct hinic_rss_context_table ctx_tbl = { 0 };
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	u16 out_size = sizeof(ctx_tbl);
 	struct hinic_hwif *hwif;
 	struct pci_dev *pdev;
-	u16 out_size = sizeof(ctx_tbl);
 	int err;
 
 	if (!hwdev || !rss_type)
@@ -784,7 +788,7 @@ int hinic_rss_set_template_tbl(struct hinic_dev *nic_dev, u32 template_id,
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_rss_key rss_key = { 0 };
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(rss_key);
 	int err;
 
 	rss_key.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -809,9 +813,9 @@ int hinic_rss_get_template_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
 {
 	struct hinic_rss_template_key temp_key = { 0 };
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	u16 out_size = sizeof(temp_key);
 	struct hinic_hwif *hwif;
 	struct pci_dev *pdev;
-	u16 out_size = sizeof(temp_key);
 	int err;
 
 	if (!hwdev || !temp)
@@ -844,7 +848,7 @@ int hinic_rss_set_hash_engine(struct hinic_dev *nic_dev, u8 template_id,
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(rss_engine);
 	int err;
 
 	rss_engine.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -868,9 +872,9 @@ int hinic_rss_get_hash_engine(struct hinic_dev *nic_dev, u8 tmpl_idx, u8 *type)
 {
 	struct hinic_rss_engine_type hash_type = { 0 };
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	u16 out_size = sizeof(hash_type);
 	struct hinic_hwif *hwif;
 	struct pci_dev *pdev;
-	u16 out_size = sizeof(hash_type);
 	int err;
 
 	if (!hwdev || !type)
@@ -901,7 +905,7 @@ int hinic_rss_cfg(struct hinic_dev *nic_dev, u8 rss_en, u8 template_id)
 	struct hinic_rss_config rss_cfg = { 0 };
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
+	u16 out_size = sizeof(rss_cfg);
 	int err;
 
 	rss_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -927,8 +931,8 @@ int hinic_rss_template_alloc(struct hinic_dev *nic_dev, u8 *tmpl_idx)
 	struct hinic_rss_template_mgmt template_mgmt = { 0 };
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(template_mgmt);
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
 	int err;
 
 	template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -953,8 +957,8 @@ int hinic_rss_template_free(struct hinic_dev *nic_dev, u8 tmpl_idx)
 	struct hinic_rss_template_mgmt template_mgmt = { 0 };
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(template_mgmt);
 	struct pci_dev *pdev = hwif->pdev;
-	u16 out_size;
 	int err;
 
 	template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif);
@@ -1043,9 +1047,9 @@ int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver)
 {
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_version_info up_ver = {0};
+	u16 out_size = sizeof(up_ver);
 	struct hinic_hwif *hwif;
 	struct pci_dev *pdev;
-	u16 out_size;
 	int err;
 
 	if (!hwdev)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 44772fd47fc1..5ad04fb6722a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -148,9 +148,9 @@ struct hinic_port_link_status {
 	u8      version;
 	u8      rsvd0[6];
 
-	u16     rsvd1;
+	u16     func_id;
 	u8      link;
-	u8      rsvd2;
+	u8      port_id;
 };
 
 struct hinic_port_func_state_cmd {
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 815649e37cb1..af20d0dd6de7 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -432,9 +432,11 @@ static int rx_poll(struct napi_struct *napi, int budget)
 		return budget;
 
 	napi_complete(napi);
-	hinic_hwdev_set_msix_state(nic_dev->hwdev,
-				   rq->msix_entry,
-				   HINIC_MSIX_ENABLE);
+
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		hinic_hwdev_set_msix_state(nic_dev->hwdev,
+					   rq->msix_entry,
+					   HINIC_MSIX_ENABLE);
 
 	return pkts;
 }
@@ -461,9 +463,10 @@ static irqreturn_t rx_irq(int irq, void *data)
 
 	/* Disable the interrupt until napi will be completed */
 	nic_dev = netdev_priv(rxq->netdev);
-	hinic_hwdev_set_msix_state(nic_dev->hwdev,
-				   rq->msix_entry,
-				   HINIC_MSIX_DISABLE);
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		hinic_hwdev_set_msix_state(nic_dev->hwdev,
+					   rq->msix_entry,
+					   HINIC_MSIX_DISABLE);
 
 	nic_dev = netdev_priv(rxq->netdev);
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, rq->msix_entry);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
new file mode 100644
index 000000000000..d1c4e1428b38
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -0,0 +1,698 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ */
+
+#include <linux/pci.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic_hw_dev.h"
+#include "hinic_dev.h"
+#include "hinic_hw_mbox.h"
+#include "hinic_hw_cmdq.h"
+#include "hinic_port.h"
+#include "hinic_sriov.h"
+
+static unsigned char set_vf_link_state;
+module_param(set_vf_link_state, byte, 0444);
+MODULE_PARM_DESC(set_vf_link_state, "Set vf link state, 0 represents link auto, 1 represents link always up, 2 represents link always down. - default is 0.");
+
+#define HINIC_VLAN_PRIORITY_SHIFT 13
+#define HINIC_ADD_VLAN_IN_MAC 0x8000
+
+int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
+		  u16 func_id)
+{
+	struct hinic_port_mac_cmd mac_info = {0};
+	u16 out_size = sizeof(mac_info);
+	int err;
+
+	mac_info.func_idx = func_id;
+	mac_info.vlan_id = vlan_id;
+	memcpy(mac_info.mac, mac_addr, ETH_ALEN);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info,
+				 sizeof(mac_info), &mac_info, &out_size);
+	if (err || out_size != sizeof(mac_info) ||
+	    (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY &&
+	    mac_info.status != HINIC_MGMT_STATUS_EXIST)) {
+		dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to change MAC, ret = %d\n",
+			mac_info.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void hinic_notify_vf_link_status(struct hinic_hwdev *hwdev, u16 vf_id,
+					u8 link_status)
+{
+	struct vf_data_storage *vf_infos = hwdev->func_to_io.vf_infos;
+	struct hinic_port_link_status link = {0};
+	u16 out_size = sizeof(link);
+	int err;
+
+	if (vf_infos[HW_VF_ID_TO_OS(vf_id)].registered) {
+		link.link = link_status;
+		link.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+		err = hinic_mbox_to_vf(hwdev, HINIC_MOD_L2NIC,
+				       vf_id, HINIC_PORT_CMD_LINK_STATUS_REPORT,
+				       &link, sizeof(link),
+				       &link, &out_size, 0);
+		if (err || !out_size || link.status)
+			dev_err(&hwdev->hwif->pdev->dev,
+				"Send link change event to VF %d failed, err: %d, status: 0x%x, out_size: 0x%x\n",
+				HW_VF_ID_TO_OS(vf_id), err,
+				link.status, out_size);
+	}
+}
+
+/* send link change event mbox msg to active vfs under the pf */
+void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev,
+				       u8 link_status)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	u16 i;
+
+	nic_io->link_status = link_status;
+	for (i = 1; i <= nic_io->max_vfs; i++) {
+		if (!nic_io->vf_infos[HW_VF_ID_TO_OS(i)].link_forced)
+			hinic_notify_vf_link_status(hwdev, i,  link_status);
+	}
+}
+
+u16 hinic_vf_info_vlanprio(struct hinic_hwdev *hwdev, int vf_id)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	u16 pf_vlan, vlanprio;
+	u8 pf_qos;
+
+	pf_vlan = nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan;
+	pf_qos = nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos;
+	vlanprio = pf_vlan | pf_qos << HINIC_VLAN_PRIORITY_SHIFT;
+
+	return vlanprio;
+}
+
+int hinic_set_vf_vlan(struct hinic_hwdev *hwdev, bool add, u16 vid,
+		      u8 qos, int vf_id)
+{
+	struct hinic_vf_vlan_config vf_vlan = {0};
+	u16 out_size = sizeof(vf_vlan);
+	int err;
+	u8 cmd;
+
+	/* VLAN 0 is a special case, don't allow it to be removed */
+	if (!vid && !add)
+		return 0;
+
+	vf_vlan.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+	vf_vlan.vlan_id = vid;
+	vf_vlan.qos = qos;
+
+	if (add)
+		cmd = HINIC_PORT_CMD_SET_VF_VLAN;
+	else
+		cmd = HINIC_PORT_CMD_CLR_VF_VLAN;
+
+	err = hinic_port_msg_cmd(hwdev, cmd, &vf_vlan,
+				 sizeof(vf_vlan), &vf_vlan, &out_size);
+	if (err || !out_size || vf_vlan.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF %d vlan, err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), err, vf_vlan.status, out_size);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id)
+{
+	struct vf_data_storage *vf_info;
+	u16 func_id, vlan_id;
+	int err = 0;
+
+	vf_info = hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id);
+	if (vf_info->pf_set_mac) {
+		func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+
+		vlan_id = 0;
+
+		err = hinic_set_mac(hwdev, vf_info->vf_mac_addr, vlan_id,
+				    func_id);
+		if (err) {
+			dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set VF %d MAC\n",
+				HW_VF_ID_TO_OS(vf_id));
+			return err;
+		}
+	}
+
+	if (hinic_vf_info_vlanprio(hwdev, vf_id)) {
+		err = hinic_set_vf_vlan(hwdev, true, vf_info->pf_vlan,
+					vf_info->pf_qos, vf_id);
+		if (err) {
+			dev_err(&hwdev->hwif->pdev->dev, "Failed to add VF %d VLAN_QOS\n",
+				HW_VF_ID_TO_OS(vf_id));
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int hinic_register_vf_msg_handler(void *hwdev, u16 vf_id,
+				  void *buf_in, u16 in_size,
+				  void *buf_out, u16 *out_size)
+{
+	struct hinic_register_vf *register_info = buf_out;
+	struct hinic_hwdev *hw_dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+	int err;
+
+	nic_io = &hw_dev->func_to_io;
+	if (vf_id > nic_io->max_vfs) {
+		dev_err(&hw_dev->hwif->pdev->dev, "Register VF id %d exceed limit[0-%d]\n",
+			HW_VF_ID_TO_OS(vf_id), HW_VF_ID_TO_OS(nic_io->max_vfs));
+		register_info->status = EFAULT;
+		return -EFAULT;
+	}
+
+	*out_size = sizeof(*register_info);
+	err = hinic_init_vf_config(hw_dev, vf_id);
+	if (err) {
+		register_info->status = EFAULT;
+		return err;
+	}
+
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].registered = true;
+
+	return 0;
+}
+
+int hinic_unregister_vf_msg_handler(void *hwdev, u16 vf_id,
+				    void *buf_in, u16 in_size,
+				    void *buf_out, u16 *out_size)
+{
+	struct hinic_hwdev *hw_dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+
+	nic_io = &hw_dev->func_to_io;
+	*out_size = 0;
+	if (vf_id > nic_io->max_vfs)
+		return 0;
+
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].registered = false;
+
+	return 0;
+}
+
+int hinic_change_vf_mtu_msg_handler(void *hwdev, u16 vf_id,
+				    void *buf_in, u16 in_size,
+				    void *buf_out, u16 *out_size)
+{
+	struct hinic_hwdev *hw_dev = hwdev;
+	int err;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU, buf_in,
+				 in_size, buf_out, out_size);
+	if (err) {
+		dev_err(&hw_dev->hwif->pdev->dev, "Failed to set VF %u mtu\n",
+			vf_id);
+		return err;
+	}
+
+	return 0;
+}
+
+int hinic_get_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+				 void *buf_in, u16 in_size,
+				 void *buf_out, u16 *out_size)
+{
+	struct hinic_port_mac_cmd *mac_info = buf_out;
+	struct hinic_hwdev *dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+	struct vf_data_storage *vf_info;
+
+	nic_io = &dev->func_to_io;
+	vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id);
+
+	memcpy(mac_info->mac, vf_info->vf_mac_addr, ETH_ALEN);
+	mac_info->status = 0;
+	*out_size = sizeof(*mac_info);
+
+	return 0;
+}
+
+int hinic_set_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+				 void *buf_in, u16 in_size,
+				 void *buf_out, u16 *out_size)
+{
+	struct hinic_port_mac_cmd *mac_out = buf_out;
+	struct hinic_port_mac_cmd *mac_in = buf_in;
+	struct hinic_hwdev *hw_dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+	struct vf_data_storage *vf_info;
+	int err;
+
+	nic_io =  &hw_dev->func_to_io;
+	vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id);
+	if (vf_info->pf_set_mac && !(vf_info->trust) &&
+	    is_valid_ether_addr(mac_in->mac)) {
+		dev_warn(&hw_dev->hwif->pdev->dev, "PF has already set VF %d MAC address\n",
+			 HW_VF_ID_TO_OS(vf_id));
+		mac_out->status = HINIC_PF_SET_VF_ALREADY;
+		*out_size = sizeof(*mac_out);
+		return 0;
+	}
+
+	err = hinic_port_msg_cmd(hw_dev, HINIC_PORT_CMD_SET_MAC, buf_in,
+				 in_size, buf_out, out_size);
+	if ((err &&  err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) || !(*out_size)) {
+		dev_err(&hw_dev->hwif->pdev->dev,
+			"Failed to set VF %d MAC address, err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), err, mac_out->status, *out_size);
+		return -EFAULT;
+	}
+
+	return err;
+}
+
+int hinic_del_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+				 void *buf_in, u16 in_size,
+				 void *buf_out, u16 *out_size)
+{
+	struct hinic_port_mac_cmd *mac_out = buf_out;
+	struct hinic_port_mac_cmd *mac_in = buf_in;
+	struct hinic_hwdev *hw_dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+	struct vf_data_storage *vf_info;
+	int err;
+
+	nic_io = &hw_dev->func_to_io;
+	vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id);
+	if (vf_info->pf_set_mac  && is_valid_ether_addr(mac_in->mac) &&
+	    !memcmp(vf_info->vf_mac_addr, mac_in->mac, ETH_ALEN)) {
+		dev_warn(&hw_dev->hwif->pdev->dev, "PF has already set VF mac.\n");
+		mac_out->status = HINIC_PF_SET_VF_ALREADY;
+		*out_size = sizeof(*mac_out);
+		return 0;
+	}
+
+	err = hinic_port_msg_cmd(hw_dev, HINIC_PORT_CMD_DEL_MAC, buf_in,
+				 in_size, buf_out, out_size);
+	if ((err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) || !(*out_size)) {
+		dev_err(&hw_dev->hwif->pdev->dev, "Failed to delete VF %d MAC, err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), err, mac_out->status, *out_size);
+		return -EFAULT;
+	}
+
+	return err;
+}
+
+int hinic_get_vf_link_status_msg_handler(void *hwdev, u16 vf_id,
+					 void *buf_in, u16 in_size,
+					 void *buf_out, u16 *out_size)
+{
+	struct hinic_port_link_cmd *get_link = buf_out;
+	struct hinic_hwdev *hw_dev = hwdev;
+	struct vf_data_storage *vf_infos;
+	struct hinic_func_to_io *nic_io;
+	bool link_forced, link_up;
+
+	nic_io = &hw_dev->func_to_io;
+	vf_infos = nic_io->vf_infos;
+	link_forced = vf_infos[HW_VF_ID_TO_OS(vf_id)].link_forced;
+	link_up = vf_infos[HW_VF_ID_TO_OS(vf_id)].link_up;
+
+	if (link_forced)
+		get_link->state = link_up ?
+			HINIC_LINK_STATE_UP : HINIC_LINK_STATE_DOWN;
+	else
+		get_link->state = nic_io->link_status;
+
+	get_link->status = 0;
+	*out_size = sizeof(*get_link);
+
+	return 0;
+}
+
+struct vf_cmd_msg_handle nic_vf_cmd_msg_handler[] = {
+	{HINIC_PORT_CMD_VF_REGISTER, hinic_register_vf_msg_handler},
+	{HINIC_PORT_CMD_VF_UNREGISTER, hinic_unregister_vf_msg_handler},
+	{HINIC_PORT_CMD_CHANGE_MTU, hinic_change_vf_mtu_msg_handler},
+	{HINIC_PORT_CMD_GET_MAC, hinic_get_vf_mac_msg_handler},
+	{HINIC_PORT_CMD_SET_MAC, hinic_set_vf_mac_msg_handler},
+	{HINIC_PORT_CMD_DEL_MAC, hinic_del_vf_mac_msg_handler},
+	{HINIC_PORT_CMD_GET_LINK_STATE, hinic_get_vf_link_status_msg_handler},
+};
+
+#define CHECK_IPSU_15BIT	0X8000
+
+struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+
+	return &nic_dev->sriov_info;
+}
+
+int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	int err;
+
+	err = hinic_set_vf_vlan(hwdev, false,
+				nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan,
+				nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos,
+				vf_id);
+	if (err)
+		return err;
+
+	dev_info(&hwdev->hwif->pdev->dev, "Remove VLAN %d on VF %d\n",
+		 nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan,
+		 HW_VF_ID_TO_OS(vf_id));
+
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan = 0;
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos = 0;
+
+	return 0;
+}
+
+/* pf receive message from vf */
+int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
+			u16 in_size, void *buf_out, u16 *out_size)
+{
+	struct vf_cmd_msg_handle *vf_msg_handle;
+	struct hinic_hwdev *dev = hwdev;
+	struct hinic_func_to_io *nic_io;
+	struct hinic_pfhwdev *pfhwdev;
+	u32 i, cmd_number;
+	int err = 0;
+
+	if (!hwdev)
+		return -EFAULT;
+
+	cmd_number = sizeof(nic_vf_cmd_msg_handler) /
+			    sizeof(struct vf_cmd_msg_handle);
+	pfhwdev = container_of(dev, struct hinic_pfhwdev, hwdev);
+	nic_io = &dev->func_to_io;
+	for (i = 0; i < cmd_number; i++) {
+		vf_msg_handle = &nic_vf_cmd_msg_handler[i];
+		if (cmd == vf_msg_handle->cmd &&
+		    vf_msg_handle->cmd_msg_handler) {
+			err = vf_msg_handle->cmd_msg_handler(hwdev, vf_id,
+							     buf_in, in_size,
+							     buf_out,
+							     out_size);
+			break;
+		}
+	}
+	if (i == cmd_number)
+		err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC,
+					cmd, buf_in, in_size, buf_out,
+					out_size, HINIC_MGMT_MSG_SYNC);
+
+	if (err &&  err != HINIC_MBOX_PF_BUSY_ACTIVE_FW)
+		dev_err(&nic_io->hwif->pdev->dev, "PF receive VF L2NIC cmd: %d process error, err:%d\n",
+			cmd, err);
+	return err;
+}
+
+static int cfg_mbx_pf_proc_vf_msg(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
+				  u16 in_size, void *buf_out, u16 *out_size)
+{
+	struct hinic_dev_cap *dev_cap = buf_out;
+	struct hinic_hwdev *dev = hwdev;
+	struct hinic_cap *cap;
+
+	cap = &dev->nic_cap;
+	memset(dev_cap, 0, sizeof(*dev_cap));
+
+	dev_cap->max_vf = cap->max_vf;
+	dev_cap->max_sqs = cap->max_vf_qps;
+	dev_cap->max_rqs = cap->max_vf_qps;
+
+	*out_size = sizeof(*dev_cap);
+
+	return 0;
+}
+
+static int hinic_init_vf_infos(struct hinic_func_to_io *nic_io, u16 vf_id)
+{
+	struct vf_data_storage *vf_infos = nic_io->vf_infos;
+
+	if (set_vf_link_state > HINIC_IFLA_VF_LINK_STATE_DISABLE) {
+		dev_warn(&nic_io->hwif->pdev->dev, "Module Parameter set_vf_link_state value %d is out of range, resetting to %d\n",
+			 set_vf_link_state, HINIC_IFLA_VF_LINK_STATE_AUTO);
+		set_vf_link_state = HINIC_IFLA_VF_LINK_STATE_AUTO;
+	}
+
+	switch (set_vf_link_state) {
+	case HINIC_IFLA_VF_LINK_STATE_AUTO:
+		vf_infos[vf_id].link_forced = false;
+		break;
+	case HINIC_IFLA_VF_LINK_STATE_ENABLE:
+		vf_infos[vf_id].link_forced = true;
+		vf_infos[vf_id].link_up = true;
+		break;
+	case HINIC_IFLA_VF_LINK_STATE_DISABLE:
+		vf_infos[vf_id].link_forced = true;
+		vf_infos[vf_id].link_up = false;
+		break;
+	default:
+		dev_err(&nic_io->hwif->pdev->dev, "Invalid input parameter set_vf_link_state: %d\n",
+			set_vf_link_state);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
+{
+	struct vf_data_storage *vf_infos;
+	u16 func_id;
+
+	func_id = hinic_glb_pf_vf_offset(nic_dev->hwdev->hwif) + vf_id;
+	vf_infos = nic_dev->hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id);
+	if (vf_infos->pf_set_mac)
+		hinic_port_del_mac(nic_dev, vf_infos->vf_mac_addr, 0);
+
+	if (hinic_vf_info_vlanprio(nic_dev->hwdev, vf_id))
+		hinic_kill_vf_vlan(nic_dev->hwdev, vf_id);
+
+	memset(vf_infos, 0, sizeof(*vf_infos));
+	/* set vf_infos to default */
+	hinic_init_vf_infos(&nic_dev->hwdev->func_to_io, HW_VF_ID_TO_OS(vf_id));
+}
+
+int hinic_deinit_vf_hw(struct hinic_sriov_info *sriov_info, u16 start_vf_id,
+		       u16 end_vf_id)
+{
+	struct hinic_dev *nic_dev;
+	u16 func_idx, idx;
+
+	nic_dev = container_of(sriov_info, struct hinic_dev, sriov_info);
+
+	for (idx = start_vf_id; idx <= end_vf_id; idx++) {
+		func_idx = hinic_glb_pf_vf_offset(nic_dev->hwdev->hwif) + idx;
+		hinic_set_wq_page_size(nic_dev->hwdev, func_idx,
+				       HINIC_HW_WQ_PAGE_SIZE);
+		hinic_clear_vf_infos(nic_dev, idx);
+	}
+
+	return 0;
+}
+
+int hinic_vf_func_init(struct hinic_hwdev *hwdev)
+{
+	struct hinic_register_vf register_info = {0};
+	u16 out_size = sizeof(register_info);
+	struct hinic_func_to_io *nic_io;
+	int err = 0;
+	u32 size, i;
+
+	nic_io = &hwdev->func_to_io;
+
+	if (HINIC_IS_VF(hwdev->hwif)) {
+		err = hinic_mbox_to_pf(hwdev, HINIC_MOD_L2NIC,
+				       HINIC_PORT_CMD_VF_REGISTER,
+				       &register_info, sizeof(register_info),
+				       &register_info, &out_size, 0);
+		if (err || register_info.status || !out_size) {
+			dev_err(&hwdev->hwif->pdev->dev,
+				"Failed to register VF, err: %d, status: 0x%x, out size: 0x%x\n",
+				err, register_info.status, out_size);
+			hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC);
+			return -EIO;
+		}
+	} else {
+		err = hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_CFGM,
+						cfg_mbx_pf_proc_vf_msg);
+		if (err) {
+			dev_err(&hwdev->hwif->pdev->dev,
+				"Register PF mailbox callback failed\n");
+			return err;
+		}
+		nic_io->max_vfs = hwdev->nic_cap.max_vf;
+		size = sizeof(*nic_io->vf_infos) * nic_io->max_vfs;
+		if (size != 0) {
+			nic_io->vf_infos = kzalloc(size, GFP_KERNEL);
+			if (!nic_io->vf_infos) {
+				err = -ENOMEM;
+				goto out_free_nic_io;
+			}
+
+			for (i = 0; i < nic_io->max_vfs; i++) {
+				err = hinic_init_vf_infos(nic_io, i);
+				if (err)
+					goto err_init_vf_infos;
+			}
+
+			err = hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_L2NIC,
+							nic_pf_mbox_handler);
+			if (err)
+				goto err_register_pf_mbox_cb;
+		}
+	}
+
+	return 0;
+
+err_register_pf_mbox_cb:
+err_init_vf_infos:
+	kfree(nic_io->vf_infos);
+out_free_nic_io:
+	return err;
+}
+
+void hinic_vf_func_free(struct hinic_hwdev *hwdev)
+{
+	struct hinic_register_vf unregister = {0};
+	u16 out_size = sizeof(unregister);
+	int err;
+
+	if (HINIC_IS_VF(hwdev->hwif)) {
+		err = hinic_mbox_to_pf(hwdev, HINIC_MOD_L2NIC,
+				       HINIC_PORT_CMD_VF_UNREGISTER,
+				       &unregister, sizeof(unregister),
+				       &unregister, &out_size, 0);
+		if (err || !out_size || unregister.status)
+			dev_err(&hwdev->hwif->pdev->dev, "Failed to unregister VF, err: %d, status: 0x%x, out_size: 0x%x\n",
+				err, unregister.status, out_size);
+	} else {
+		if (hwdev->func_to_io.vf_infos) {
+			hinic_unregister_pf_mbox_cb(hwdev, HINIC_MOD_L2NIC);
+			kfree(hwdev->func_to_io.vf_infos);
+		}
+	}
+}
+
+int hinic_init_vf_hw(struct hinic_hwdev *hwdev, u16 start_vf_id, u16 end_vf_id)
+{
+	u16 i, func_idx;
+	int err;
+
+	/* vf use 256K as default wq page size, and can't change it */
+	for (i = start_vf_id; i <= end_vf_id; i++) {
+		func_idx = hinic_glb_pf_vf_offset(hwdev->hwif) + i;
+		err = hinic_set_wq_page_size(hwdev, func_idx,
+					     HINIC_DEFAULT_WQ_PAGE_SIZE);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int hinic_pci_sriov_disable(struct pci_dev *pdev)
+{
+	struct hinic_sriov_info *sriov_info;
+	u16 tmp_vfs;
+
+	sriov_info = hinic_get_sriov_info_by_pcidev(pdev);
+	/* if SR-IOV is already disabled then nothing will be done */
+	if (!sriov_info->sriov_enabled)
+		return 0;
+
+	set_bit(HINIC_SRIOV_DISABLE, &sriov_info->state);
+
+	/* If our VFs are assigned we cannot shut down SR-IOV
+	 * without causing issues, so just leave the hardware
+	 * available but disabled
+	 */
+	if (pci_vfs_assigned(sriov_info->pdev)) {
+		clear_bit(HINIC_SRIOV_DISABLE, &sriov_info->state);
+		dev_warn(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n");
+		return -EPERM;
+	}
+	sriov_info->sriov_enabled = false;
+
+	/* disable iov and allow time for transactions to clear */
+	pci_disable_sriov(sriov_info->pdev);
+
+	tmp_vfs = (u16)sriov_info->num_vfs;
+	sriov_info->num_vfs = 0;
+	hinic_deinit_vf_hw(sriov_info, OS_VF_ID_TO_HW(0),
+			   OS_VF_ID_TO_HW(tmp_vfs - 1));
+
+	clear_bit(HINIC_SRIOV_DISABLE, &sriov_info->state);
+
+	return 0;
+}
+
+int hinic_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
+{
+	struct hinic_sriov_info *sriov_info;
+	int err;
+
+	sriov_info = hinic_get_sriov_info_by_pcidev(pdev);
+
+	if (test_and_set_bit(HINIC_SRIOV_ENABLE, &sriov_info->state)) {
+		dev_err(&pdev->dev,
+			"SR-IOV enable in process, please wait, num_vfs %d\n",
+			num_vfs);
+		return -EPERM;
+	}
+
+	err = hinic_init_vf_hw(sriov_info->hwdev, OS_VF_ID_TO_HW(0),
+			       OS_VF_ID_TO_HW((u16)num_vfs - 1));
+	if (err) {
+		dev_err(&sriov_info->pdev->dev,
+			"Failed to init vf in hardware before enable sriov, error %d\n",
+			err);
+		clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state);
+		return err;
+	}
+
+	err = pci_enable_sriov(sriov_info->pdev, num_vfs);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Failed to enable SR-IOV, error %d\n", err);
+		clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state);
+		return err;
+	}
+
+	sriov_info->sriov_enabled = true;
+	sriov_info->num_vfs = num_vfs;
+	clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state);
+
+	return num_vfs;
+}
+
+int hinic_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
+{
+	struct hinic_sriov_info *sriov_info;
+
+	sriov_info = hinic_get_sriov_info_by_pcidev(dev);
+
+	if (test_bit(HINIC_FUNC_REMOVE, &sriov_info->state))
+		return -EBUSY;
+
+	if (!num_vfs)
+		return hinic_pci_sriov_disable(dev);
+	else
+		return hinic_pci_sriov_enable(dev, num_vfs);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
new file mode 100644
index 000000000000..4889eabe7b7c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ */
+
+#ifndef HINIC_SRIOV_H
+#define HINIC_SRIOV_H
+
+#include "hinic_hw_dev.h"
+
+#define OS_VF_ID_TO_HW(os_vf_id) ((os_vf_id) + 1)
+#define HW_VF_ID_TO_OS(hw_vf_id) ((hw_vf_id) - 1)
+
+enum hinic_sriov_state {
+	HINIC_SRIOV_DISABLE,
+	HINIC_SRIOV_ENABLE,
+	HINIC_FUNC_REMOVE,
+};
+
+enum {
+	HINIC_IFLA_VF_LINK_STATE_AUTO,	/* link state of the uplink */
+	HINIC_IFLA_VF_LINK_STATE_ENABLE,	/* link always up */
+	HINIC_IFLA_VF_LINK_STATE_DISABLE,	/* link always down */
+};
+
+struct hinic_sriov_info {
+	struct pci_dev *pdev;
+	struct hinic_hwdev *hwdev;
+	bool sriov_enabled;
+	unsigned int num_vfs;
+	unsigned long state;
+};
+
+struct vf_data_storage {
+	u8 vf_mac_addr[ETH_ALEN];
+	bool registered;
+	bool pf_set_mac;
+	u16 pf_vlan;
+	u8 pf_qos;
+	u32 max_rate;
+	u32 min_rate;
+
+	bool link_forced;
+	bool link_up;		/* only valid if VF link is forced */
+	bool spoofchk;
+	bool trust;
+};
+
+struct hinic_register_vf {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+};
+
+struct hinic_vf_vlan_config {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+
+	u16 func_id;
+	u16 vlan_id;
+	u8  qos;
+	u8  rsvd1[7];
+};
+
+void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev,
+				       u8 link_status);
+
+int hinic_pci_sriov_disable(struct pci_dev *dev);
+
+int hinic_pci_sriov_enable(struct pci_dev *dev, int num_vfs);
+
+int hinic_vf_func_init(struct hinic_hwdev *hwdev);
+
+void hinic_vf_func_free(struct hinic_hwdev *hwdev);
+
+int hinic_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 365016450bdb..4c66a0bc1b28 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -673,9 +673,11 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 
 	if (pkts < budget) {
 		napi_complete(napi);
-		hinic_hwdev_set_msix_state(nic_dev->hwdev,
-					   sq->msix_entry,
-					   HINIC_MSIX_ENABLE);
+		if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+			hinic_hwdev_set_msix_state(nic_dev->hwdev,
+						   sq->msix_entry,
+						   HINIC_MSIX_ENABLE);
+
 		return pkts;
 	}
 
@@ -701,10 +703,11 @@ static irqreturn_t tx_irq(int irq, void *data)
 
 	nic_dev = netdev_priv(txq->netdev);
 
-	/* Disable the interrupt until napi will be completed */
-	hinic_hwdev_set_msix_state(nic_dev->hwdev,
-				   txq->sq->msix_entry,
-				   HINIC_MSIX_DISABLE);
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+		/* Disable the interrupt until napi will be completed */
+		hinic_hwdev_set_msix_state(nic_dev->hwdev,
+					   txq->sq->msix_entry,
+					   HINIC_MSIX_DISABLE);
 
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, txq->sq->msix_entry);
 
-- 
cgit v1.2.3


From 1f62cfa19a619f82c098468660b7950477101d45 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Sat, 25 Apr 2020 01:21:11 +0000
Subject: hinic: add net_device_ops associated with vf

adds ndo_set_vf_mac/ndo_set_vf_vlan/ndo_get_vf_config and
ndo_set_vf_trust to configure netdev of virtual function

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_main.c  |  43 +++-
 drivers/net/ethernet/huawei/hinic/hinic_sriov.c | 318 ++++++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_sriov.h |  23 ++
 3 files changed, 383 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index cd71249f9b1c..b66bb86cff96 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -779,8 +779,26 @@ static void hinic_set_rx_mode(struct net_device *netdev)
 static void hinic_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	u16 sw_pi, hw_ci, sw_ci;
+	struct hinic_sq *sq;
+	u16 num_sqs, q_id;
+
+	num_sqs = hinic_hwdev_num_qps(nic_dev->hwdev);
 
 	netif_err(nic_dev, drv, netdev, "Tx timeout\n");
+
+	for (q_id = 0; q_id < num_sqs; q_id++) {
+		if (!netif_xmit_stopped(netdev_get_tx_queue(netdev, q_id)))
+			continue;
+
+		sq = hinic_hwdev_get_sq(nic_dev->hwdev, q_id);
+		sw_pi = atomic_read(&sq->wq->prod_idx) & sq->wq->mask;
+		hw_ci = be16_to_cpu(*(u16 *)(sq->hw_ci_addr)) & sq->wq->mask;
+		sw_ci = atomic_read(&sq->wq->cons_idx) & sq->wq->mask;
+		netif_err(nic_dev, drv, netdev, "Txq%d: sw_pi: %d, hw_ci: %d, sw_ci: %d, napi->state: 0x%lx\n",
+			  q_id, sw_pi, hw_ci, sw_ci,
+			  nic_dev->txqs[q_id].napi.state);
+	}
 }
 
 static void hinic_get_stats64(struct net_device *netdev,
@@ -846,6 +864,26 @@ static const struct net_device_ops hinic_netdev_ops = {
 	.ndo_get_stats64 = hinic_get_stats64,
 	.ndo_fix_features = hinic_fix_features,
 	.ndo_set_features = hinic_set_features,
+	.ndo_set_vf_mac	= hinic_ndo_set_vf_mac,
+	.ndo_set_vf_vlan = hinic_ndo_set_vf_vlan,
+	.ndo_get_vf_config = hinic_ndo_get_vf_config,
+	.ndo_set_vf_trust = hinic_ndo_set_vf_trust,
+};
+
+static const struct net_device_ops hinicvf_netdev_ops = {
+	.ndo_open = hinic_open,
+	.ndo_stop = hinic_close,
+	.ndo_change_mtu = hinic_change_mtu,
+	.ndo_set_mac_address = hinic_set_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_vlan_rx_add_vid = hinic_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid = hinic_vlan_rx_kill_vid,
+	.ndo_set_rx_mode = hinic_set_rx_mode,
+	.ndo_start_xmit = hinic_xmit_frame,
+	.ndo_tx_timeout = hinic_tx_timeout,
+	.ndo_get_stats64 = hinic_get_stats64,
+	.ndo_fix_features = hinic_fix_features,
+	.ndo_set_features = hinic_set_features,
 };
 
 static void netdev_features_init(struct net_device *netdev)
@@ -983,7 +1021,10 @@ static int nic_dev_init(struct pci_dev *pdev)
 
 	hinic_set_ethtool_ops(netdev);
 
-	netdev->netdev_ops = &hinic_netdev_ops;
+	if (!HINIC_IS_VF(hwdev->hwif))
+		netdev->netdev_ops = &hinic_netdev_ops;
+	else
+		netdev->netdev_ops = &hinicvf_netdev_ops;
 
 	netdev->max_mtu = ETH_MAX_MTU;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index d1c4e1428b38..b24788e9733c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -359,6 +359,168 @@ struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev)
 	return &nic_dev->sriov_info;
 }
 
+static int hinic_check_mac_info(u8 status, u16 vlan_id)
+{
+	if ((status && status != HINIC_MGMT_STATUS_EXIST &&
+	     status != HINIC_PF_SET_VF_ALREADY) ||
+	    (vlan_id & CHECK_IPSU_15BIT &&
+	     status == HINIC_MGMT_STATUS_EXIST))
+		return -EINVAL;
+
+	return 0;
+}
+
+#define HINIC_VLAN_ID_MASK	0x7FFF
+
+int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, u8 *new_mac,
+		     u16 vlan_id, u16 func_id)
+{
+	struct hinic_port_mac_update mac_info = {0};
+	u16 out_size = sizeof(mac_info);
+	int err;
+
+	if (!hwdev || !old_mac || !new_mac)
+		return -EINVAL;
+
+	if ((vlan_id & HINIC_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(&hwdev->hwif->pdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	memcpy(mac_info.old_mac, old_mac, ETH_ALEN);
+	memcpy(mac_info.new_mac, new_mac, ETH_ALEN);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_UPDATE_MAC, &mac_info,
+				 sizeof(mac_info), &mac_info, &out_size);
+
+	if (err || !out_size ||
+	    hinic_check_mac_info(mac_info.status, mac_info.vlan_id)) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, mac_info.status, out_size);
+		return -EINVAL;
+	}
+
+	if (mac_info.status == HINIC_PF_SET_VF_ALREADY) {
+		dev_warn(&hwdev->hwif->pdev->dev,
+			 "PF has already set VF MAC. Ignore update operation\n");
+		return HINIC_PF_SET_VF_ALREADY;
+	}
+
+	if (mac_info.status == HINIC_MGMT_STATUS_EXIST)
+		dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n");
+
+	return 0;
+}
+
+void hinic_get_vf_config(struct hinic_hwdev *hwdev, u16 vf_id,
+			 struct ifla_vf_info *ivi)
+{
+	struct vf_data_storage *vfinfo;
+
+	vfinfo = hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id);
+
+	ivi->vf = HW_VF_ID_TO_OS(vf_id);
+	memcpy(ivi->mac, vfinfo->vf_mac_addr, ETH_ALEN);
+	ivi->vlan = vfinfo->pf_vlan;
+	ivi->qos = vfinfo->pf_qos;
+	ivi->spoofchk = vfinfo->spoofchk;
+	ivi->trusted = vfinfo->trust;
+	ivi->max_tx_rate = vfinfo->max_rate;
+	ivi->min_tx_rate = vfinfo->min_rate;
+
+	if (!vfinfo->link_forced)
+		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
+	else if (vfinfo->link_up)
+		ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE;
+	else
+		ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE;
+}
+
+int hinic_ndo_get_vf_config(struct net_device *netdev,
+			    int vf, struct ifla_vf_info *ivi)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+
+	sriov_info = &nic_dev->sriov_info;
+	if (vf >= sriov_info->num_vfs)
+		return -EINVAL;
+
+	hinic_get_vf_config(sriov_info->hwdev, OS_VF_ID_TO_HW(vf), ivi);
+
+	return 0;
+}
+
+int hinic_set_vf_mac(struct hinic_hwdev *hwdev, int vf, unsigned char *mac_addr)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	struct vf_data_storage *vf_info;
+	u16 func_id;
+	int err;
+
+	vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf);
+
+	/* duplicate request, so just return success */
+	if (vf_info->pf_set_mac &&
+	    !memcmp(vf_info->vf_mac_addr, mac_addr, ETH_ALEN))
+		return 0;
+
+	vf_info->pf_set_mac = true;
+
+	func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf;
+	err = hinic_update_mac(hwdev, vf_info->vf_mac_addr,
+			       mac_addr, 0, func_id);
+	if (err) {
+		vf_info->pf_set_mac = false;
+		return err;
+	}
+
+	memcpy(vf_info->vf_mac_addr, mac_addr, ETH_ALEN);
+
+	return 0;
+}
+
+int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+	int err;
+
+	sriov_info = &nic_dev->sriov_info;
+	if (!is_valid_ether_addr(mac) || vf >= sriov_info->num_vfs)
+		return -EINVAL;
+
+	err = hinic_set_vf_mac(sriov_info->hwdev, OS_VF_ID_TO_HW(vf), mac);
+	if (err)
+		return err;
+
+	netif_info(nic_dev, drv, netdev, "Setting MAC %pM on VF %d\n", mac, vf);
+	netif_info(nic_dev, drv, netdev, "Reload the VF driver to make this change effective.");
+
+	return 0;
+}
+
+int hinic_add_vf_vlan(struct hinic_hwdev *hwdev, int vf_id, u16 vlan, u8 qos)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	int err;
+
+	err = hinic_set_vf_vlan(hwdev, true, vlan, qos, vf_id);
+	if (err)
+		return err;
+
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan = vlan;
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos = qos;
+
+	dev_info(&hwdev->hwif->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n",
+		 vlan, qos, HW_VF_ID_TO_OS(vf_id));
+	return 0;
+}
+
 int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
 {
 	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
@@ -381,6 +543,159 @@ int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
 	return 0;
 }
 
+int hinic_update_mac_vlan(struct hinic_dev *nic_dev, u16 old_vlan, u16 new_vlan,
+			  int vf_id)
+{
+	struct vf_data_storage *vf_info;
+	u16 vlan_id;
+	int err;
+
+	if (!nic_dev || old_vlan >= VLAN_N_VID || new_vlan >= VLAN_N_VID)
+		return -EINVAL;
+
+	vf_info = nic_dev->hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id);
+	if (!vf_info->pf_set_mac)
+		return 0;
+
+	vlan_id = old_vlan;
+	if (vlan_id)
+		vlan_id |= HINIC_ADD_VLAN_IN_MAC;
+
+	err = hinic_port_del_mac(nic_dev, vf_info->vf_mac_addr, vlan_id);
+	if (err) {
+		dev_err(&nic_dev->hwdev->hwif->pdev->dev, "Failed to delete VF %d MAC %pM vlan %d\n",
+			HW_VF_ID_TO_OS(vf_id), vf_info->vf_mac_addr, old_vlan);
+		return err;
+	}
+
+	vlan_id = new_vlan;
+	if (vlan_id)
+		vlan_id |= HINIC_ADD_VLAN_IN_MAC;
+
+	err = hinic_port_add_mac(nic_dev, vf_info->vf_mac_addr, vlan_id);
+	if (err) {
+		dev_err(&nic_dev->hwdev->hwif->pdev->dev, "Failed to add VF %d MAC %pM vlan %d\n",
+			HW_VF_ID_TO_OS(vf_id), vf_info->vf_mac_addr, new_vlan);
+		goto out;
+	}
+
+	return 0;
+
+out:
+	vlan_id = old_vlan;
+	if (vlan_id)
+		vlan_id |= HINIC_ADD_VLAN_IN_MAC;
+	hinic_port_add_mac(nic_dev, vf_info->vf_mac_addr, vlan_id);
+
+	return err;
+}
+
+static int set_hw_vf_vlan(struct hinic_dev *nic_dev,
+			  u16 cur_vlanprio, int vf, u16 vlan, u8 qos)
+{
+	u16 old_vlan = cur_vlanprio & VLAN_VID_MASK;
+	int err = 0;
+
+	if (vlan || qos) {
+		if (cur_vlanprio) {
+			err = hinic_kill_vf_vlan(nic_dev->hwdev,
+						 OS_VF_ID_TO_HW(vf));
+			if (err) {
+				dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to delete vf %d old vlan %d\n",
+					vf, old_vlan);
+				goto out;
+			}
+		}
+		err = hinic_add_vf_vlan(nic_dev->hwdev,
+					OS_VF_ID_TO_HW(vf), vlan, qos);
+		if (err) {
+			dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to add vf %d new vlan %d\n",
+				vf, vlan);
+			goto out;
+		}
+	} else {
+		err = hinic_kill_vf_vlan(nic_dev->hwdev, OS_VF_ID_TO_HW(vf));
+		if (err) {
+			dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to delete vf %d vlan %d\n",
+				vf, old_vlan);
+			goto out;
+		}
+	}
+
+	err = hinic_update_mac_vlan(nic_dev, old_vlan, vlan,
+				    OS_VF_ID_TO_HW(vf));
+
+out:
+	return err;
+}
+
+int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
+			  __be16 vlan_proto)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+	u16 vlanprio, cur_vlanprio;
+
+	sriov_info = &nic_dev->sriov_info;
+	if (vf >= sriov_info->num_vfs || vlan > 4095 || qos > 7)
+		return -EINVAL;
+	if (vlan_proto != htons(ETH_P_8021Q))
+		return -EPROTONOSUPPORT;
+	vlanprio = vlan | qos << HINIC_VLAN_PRIORITY_SHIFT;
+	cur_vlanprio = hinic_vf_info_vlanprio(nic_dev->hwdev,
+					      OS_VF_ID_TO_HW(vf));
+	/* duplicate request, so just return success */
+	if (vlanprio == cur_vlanprio)
+		return 0;
+
+	return set_hw_vf_vlan(nic_dev, cur_vlanprio, vf, vlan, qos);
+}
+
+int hinic_set_vf_trust(struct hinic_hwdev *hwdev, u16 vf_id, bool trust)
+{
+	struct vf_data_storage *vf_infos;
+	struct hinic_func_to_io *nic_io;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	nic_io = &hwdev->func_to_io;
+	vf_infos = nic_io->vf_infos;
+	vf_infos[vf_id].trust = trust;
+
+	return 0;
+}
+
+int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
+{
+	struct hinic_dev *adapter = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+	struct hinic_func_to_io *nic_io;
+	bool cur_trust;
+	int err;
+
+	sriov_info = &adapter->sriov_info;
+	nic_io = &adapter->hwdev->func_to_io;
+
+	if (vf >= sriov_info->num_vfs)
+		return -EINVAL;
+
+	cur_trust = nic_io->vf_infos[vf].trust;
+	/* same request, so just return success */
+	if ((setting && cur_trust) || (!setting && !cur_trust))
+		return 0;
+
+	err = hinic_set_vf_trust(adapter->hwdev, vf, setting);
+	if (!err)
+		dev_info(&sriov_info->pdev->dev, "Set VF %d trusted %s succeed\n",
+			 vf, setting ? "on" : "off");
+	else
+		dev_err(&sriov_info->pdev->dev, "Failed set VF %d trusted %s\n",
+			vf, setting ? "on" : "off");
+
+	return err;
+}
+
 /* pf receive message from vf */
 int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
 			u16 in_size, void *buf_out, u16 *out_size)
@@ -484,6 +799,9 @@ void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
 	if (hinic_vf_info_vlanprio(nic_dev->hwdev, vf_id))
 		hinic_kill_vf_vlan(nic_dev->hwdev, vf_id);
 
+	if (vf_infos->trust)
+		hinic_set_vf_trust(nic_dev->hwdev, vf_id, false);
+
 	memset(vf_infos, 0, sizeof(*vf_infos));
 	/* set vf_infos to default */
 	hinic_init_vf_infos(&nic_dev->hwdev->func_to_io, HW_VF_ID_TO_OS(vf_id));
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
index 4889eabe7b7c..64affc7474b5 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
@@ -52,6 +52,19 @@ struct hinic_register_vf {
 	u8	rsvd0[6];
 };
 
+struct hinic_port_mac_update {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	vlan_id;
+	u16	rsvd1;
+	u8	old_mac[ETH_ALEN];
+	u16	rsvd2;
+	u8	new_mac[ETH_ALEN];
+};
+
 struct hinic_vf_vlan_config {
 	u8 status;
 	u8 version;
@@ -63,6 +76,16 @@ struct hinic_vf_vlan_config {
 	u8  rsvd1[7];
 };
 
+int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac);
+
+int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
+			  __be16 vlan_proto);
+
+int hinic_ndo_get_vf_config(struct net_device *netdev,
+			    int vf, struct ifla_vf_info *ivi);
+
+int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting);
+
 void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev,
 				       u8 link_status);
 
-- 
cgit v1.2.3


From 3fd8dc269ff0647819589c21b2ce60af6fc0a455 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sun, 26 Apr 2020 10:13:48 +0800
Subject: net: hns3: remove an unnecessary check in hclge_set_umv_space()

Since hclge_set_umv_space() is only called by hclge_init_umv_space(),
parameter 'allocated_size' will not be NULL.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c74990a59e10..e2fec832fdf0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7227,8 +7227,7 @@ static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 		return ret;
 	}
 
-	if (allocated_size)
-		*allocated_size = le32_to_cpu(desc.data[1]);
+	*allocated_size = le32_to_cpu(desc.data[1]);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 0767ec04289757c0edc2322957ba51d97446eaa4 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 24 Apr 2020 06:59:14 +0200
Subject: net: ag71xx: extend link validation to support other SoCs

Most (all?) QCA SoCs have two MAC with different supported link
capabilities. Extend ag71xx_mac_validate() to properly validate this
variants.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/ag71xx.c | 43 +++++++++++++++++++++++++++++++----
 1 file changed, 38 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 02b7705393ca..112edbd30823 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -871,13 +871,40 @@ static void ag71xx_mac_validate(struct phylink_config *config,
 			    unsigned long *supported,
 			    struct phylink_link_state *state)
 {
+	struct ag71xx *ag = netdev_priv(to_net_dev(config->dev));
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 
-	if (state->interface != PHY_INTERFACE_MODE_NA &&
-	    state->interface != PHY_INTERFACE_MODE_GMII &&
-	    state->interface != PHY_INTERFACE_MODE_MII) {
-		bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
-		return;
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_NA:
+		break;
+	case PHY_INTERFACE_MODE_MII:
+		if ((ag71xx_is(ag, AR9330) && ag->mac_idx == 0) ||
+		    ag71xx_is(ag, AR9340) ||
+		    ag71xx_is(ag, QCA9530) ||
+		    (ag71xx_is(ag, QCA9550) && ag->mac_idx == 1))
+			break;
+		goto unsupported;
+	case PHY_INTERFACE_MODE_GMII:
+		if ((ag71xx_is(ag, AR9330) && ag->mac_idx == 1) ||
+		    (ag71xx_is(ag, AR9340) && ag->mac_idx == 1) ||
+		    (ag71xx_is(ag, QCA9530) && ag->mac_idx == 1))
+			break;
+		goto unsupported;
+	case PHY_INTERFACE_MODE_SGMII:
+		if (ag71xx_is(ag, QCA9550) && ag->mac_idx == 0)
+			break;
+		goto unsupported;
+	case PHY_INTERFACE_MODE_RMII:
+		if (ag71xx_is(ag, AR9340) && ag->mac_idx == 0)
+			break;
+		goto unsupported;
+	case PHY_INTERFACE_MODE_RGMII:
+		if ((ag71xx_is(ag, AR9340) && ag->mac_idx == 0) ||
+		    (ag71xx_is(ag, QCA9550) && ag->mac_idx == 1))
+			break;
+		goto unsupported;
+	default:
+		goto unsupported;
 	}
 
 	phylink_set(mask, MII);
@@ -889,6 +916,8 @@ static void ag71xx_mac_validate(struct phylink_config *config,
 	phylink_set(mask, 100baseT_Full);
 
 	if (state->interface == PHY_INTERFACE_MODE_NA ||
+	    state->interface == PHY_INTERFACE_MODE_SGMII ||
+	    state->interface == PHY_INTERFACE_MODE_RGMII ||
 	    state->interface == PHY_INTERFACE_MODE_GMII) {
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseX_Full);
@@ -898,6 +927,10 @@ static void ag71xx_mac_validate(struct phylink_config *config,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
 	bitmap_and(state->advertising, state->advertising, mask,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	return;
+unsupported:
+	bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
 static void ag71xx_mac_pcs_get_state(struct phylink_config *config,
-- 
cgit v1.2.3


From 975e8505e6701c77b43bcdd5acc48d3735063b68 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 26 Apr 2020 23:35:59 +0200
Subject: r8169: improve handling CPCMD_MASK

It's sufficient to do the masking once in probe() for clearing
unwanted bits that may have been set by the BIOS.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 4c616701856a..06a877fe74ba 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3845,7 +3845,6 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 {
 	rtl_unlock_config_regs(tp);
 
-	tp->cp_cmd &= CPCMD_MASK;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
@@ -5424,7 +5423,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->mac_version = chipset;
 
-	tp->cp_cmd = RTL_R16(tp, CPlusCmd);
+	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;
 
 	if (sizeof(dma_addr_t) > 4 && tp->mac_version >= RTL_GIGA_MAC_VER_18 &&
 	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
-- 
cgit v1.2.3


From 10478283f210e64ac682083083437dd5f89b7c4a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 26 Apr 2020 23:36:56 +0200
Subject: r8169: improve configuring RxConfig register

Two bits in RxConfig are controlled by the following dev->feature's:
- NETIF_F_RXALL
- NETIF_F_HW_VLAN_CTAG_RX (since RTL8125)

We have to take care that RxConfig gets fully configured in
rtl_hw_start() after e.g. resume from hibernation. Therefore:

- Factor out setting the feature-controlled RxConfig bits to a new
  function rtl_set_rx_config_features() that is called from
  rtl8169_set_features() and rtl_hw_start().
- Don't deal with RX_VLAN_8125 in rtl_init_rxcfg(), it will be set
  by rtl_set_rx_config_features().
- Don't handle NETIF_F_RXALL in rtl_set_rx_mode().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 38 ++++++++++++++++---------------
 1 file changed, 20 insertions(+), 18 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 06a877fe74ba..f70e36c20431 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -388,10 +388,12 @@ enum rtl_register_content {
 	/* rx_mode_bits */
 	AcceptErr	= 0x20,
 	AcceptRunt	= 0x10,
+#define RX_CONFIG_ACCEPT_ERR_MASK	0x30
 	AcceptBroadcast	= 0x08,
 	AcceptMulticast	= 0x04,
 	AcceptMyPhys	= 0x02,
 	AcceptAllPhys	= 0x01,
+#define RX_CONFIG_ACCEPT_OK_MASK	0x0f
 #define RX_CONFIG_ACCEPT_MASK		0x3f
 
 	/* TxConfigBits */
@@ -1497,19 +1499,15 @@ static netdev_features_t rtl8169_fix_features(struct net_device *dev,
 	return features;
 }
 
-static int rtl8169_set_features(struct net_device *dev,
-				netdev_features_t features)
+static void rtl_set_rx_config_features(struct rtl8169_private *tp,
+				       netdev_features_t features)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-	u32 rx_config;
-
-	rtl_lock_work(tp);
+	u32 rx_config = RTL_R32(tp, RxConfig);
 
-	rx_config = RTL_R32(tp, RxConfig);
 	if (features & NETIF_F_RXALL)
-		rx_config |= (AcceptErr | AcceptRunt);
+		rx_config |= RX_CONFIG_ACCEPT_ERR_MASK;
 	else
-		rx_config &= ~(AcceptErr | AcceptRunt);
+		rx_config &= ~RX_CONFIG_ACCEPT_ERR_MASK;
 
 	if (rtl_is_8125(tp)) {
 		if (features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -1519,6 +1517,16 @@ static int rtl8169_set_features(struct net_device *dev,
 	}
 
 	RTL_W32(tp, RxConfig, rx_config);
+}
+
+static int rtl8169_set_features(struct net_device *dev,
+				netdev_features_t features)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	rtl_lock_work(tp);
+
+	rtl_set_rx_config_features(tp, features);
 
 	if (features & NETIF_F_RXCSUM)
 		tp->cp_cmd |= RxChkSum;
@@ -2395,8 +2403,6 @@ static void rtl_pll_power_up(struct rtl8169_private *tp)
 
 static void rtl_init_rxcfg(struct rtl8169_private *tp)
 {
-	u32 vlan;
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
@@ -2411,9 +2417,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_61:
-		/* VLAN flags are controlled by NETIF_F_HW_VLAN_CTAG_RX */
-		vlan = RTL_R32(tp, RxConfig) & RX_VLAN_8125;
-		RTL_W32(tp, RxConfig, vlan | RX_FETCH_DFLT_8125 | RX_DMA_BURST);
+		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
 	default:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST);
@@ -2680,14 +2684,11 @@ static void rtl_set_rx_mode(struct net_device *dev)
 		}
 	}
 
-	if (dev->features & NETIF_F_RXALL)
-		rx_mode |= (AcceptErr | AcceptRunt);
-
 	RTL_W32(tp, MAR0 + 4, mc_filter[1]);
 	RTL_W32(tp, MAR0 + 0, mc_filter[0]);
 
 	tmp = RTL_R32(tp, RxConfig);
-	RTL_W32(tp, RxConfig, (tmp & ~RX_CONFIG_ACCEPT_MASK) | rx_mode);
+	RTL_W32(tp, RxConfig, (tmp & ~RX_CONFIG_ACCEPT_OK_MASK) | rx_mode);
 }
 
 DECLARE_RTL_COND(rtl_csiar_cond)
@@ -3866,6 +3867,7 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 	RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
 	rtl_init_rxcfg(tp);
 	rtl_set_tx_config_registers(tp);
+	rtl_set_rx_config_features(tp, tp->dev->features);
 	rtl_set_rx_mode(tp->dev);
 	rtl_irq_enable(tp);
 }
-- 
cgit v1.2.3


From 49c958ccd2433114ca8a96c996b5016aa89c7ba5 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:12:58 +0300
Subject: mlxsw: spectrum_acl: Move block helpers into inline header functions

The struct is defined in the header, no need to have the helpers
in the c file. Move the helpers to the header.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 60 ++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 43 ----------------
 2 files changed, 51 insertions(+), 52 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index ca56e72cb4b7..f158cd98f8d8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -677,12 +677,57 @@ struct mlxsw_sp_acl_block {
 };
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
-struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block);
-unsigned int
-mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block);
-void mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block);
-void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block);
-bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block);
+
+static inline struct mlxsw_sp *
+mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block)
+{
+	return block->mlxsw_sp;
+}
+
+static inline unsigned int
+mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block)
+{
+	return block ? block->rule_count : 0;
+}
+
+static inline void
+mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block)
+{
+	if (block)
+		block->disable_count++;
+}
+
+static inline void
+mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block)
+{
+	if (block)
+		block->disable_count--;
+}
+
+static inline bool
+mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block)
+{
+	return block->disable_count;
+}
+
+static inline bool
+mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block)
+{
+	return block->egress_binding_count;
+}
+
+static inline bool
+mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block)
+{
+	return block->ingress_binding_count;
+}
+
+static inline bool
+mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block)
+{
+	return block->ingress_binding_count && block->egress_binding_count;
+}
+
 struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp,
 						     struct net *net);
 void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block);
@@ -695,9 +740,6 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_block *block,
 			      struct mlxsw_sp_port *mlxsw_sp_port,
 			      bool ingress);
-bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block);
-bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block);
-bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block, u32 chain_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 01cff711bbd2..bb06c007b3f2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -94,49 +94,6 @@ struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp)
 	return mlxsw_sp->acl->dummy_fid;
 }
 
-struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block)
-{
-	return block->mlxsw_sp;
-}
-
-unsigned int
-mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block)
-{
-	return block ? block->rule_count : 0;
-}
-
-void mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block)
-{
-	if (block)
-		block->disable_count++;
-}
-
-void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block)
-{
-	if (block)
-		block->disable_count--;
-}
-
-bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block)
-{
-	return block->disable_count;
-}
-
-bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block)
-{
-	return block->egress_binding_count;
-}
-
-bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block)
-{
-	return block->ingress_binding_count;
-}
-
-bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block)
-{
-	return block->ingress_binding_count && block->egress_binding_count;
-}
-
 static bool
 mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset)
 {
-- 
cgit v1.2.3


From 3bc3ffb6e911f9de099d81187ae99b45966cbd05 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:12:59 +0300
Subject: mlxsw: spectrum: Rename acl_block to flow_block

The acl_block structure is going to be used for non-acl case - matchall
offload. So rename it accordingly.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 71 ++++++++++---------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 64 ++++++++---------
 .../ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c    | 14 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 82 +++++++++++-----------
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 24 +++----
 5 files changed, 128 insertions(+), 127 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 24ca8d5bc564..f64e8da21d4a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1544,23 +1544,23 @@ static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 }
 
 static int
-mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
+mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_flow_block *flow_block,
 			     struct flow_cls_offload *f)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_acl_block_mlxsw_sp(acl_block);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_flow_block_mlxsw_sp(flow_block);
 
 	switch (f->command) {
 	case FLOW_CLS_REPLACE:
-		return mlxsw_sp_flower_replace(mlxsw_sp, acl_block, f);
+		return mlxsw_sp_flower_replace(mlxsw_sp, flow_block, f);
 	case FLOW_CLS_DESTROY:
-		mlxsw_sp_flower_destroy(mlxsw_sp, acl_block, f);
+		mlxsw_sp_flower_destroy(mlxsw_sp, flow_block, f);
 		return 0;
 	case FLOW_CLS_STATS:
-		return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
+		return mlxsw_sp_flower_stats(mlxsw_sp, flow_block, f);
 	case FLOW_CLS_TMPLT_CREATE:
-		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
+		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, flow_block, f);
 	case FLOW_CLS_TMPLT_DESTROY:
-		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
+		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, flow_block, f);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1607,16 +1607,16 @@ static int mlxsw_sp_setup_tc_block_cb_matchall_eg(enum tc_setup_type type,
 static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 					     void *type_data, void *cb_priv)
 {
-	struct mlxsw_sp_acl_block *acl_block = cb_priv;
+	struct mlxsw_sp_flow_block *flow_block = cb_priv;
 
 	switch (type) {
 	case TC_SETUP_CLSMATCHALL:
 		return 0;
 	case TC_SETUP_CLSFLOWER:
-		if (mlxsw_sp_acl_block_disabled(acl_block))
+		if (mlxsw_sp_flow_block_disabled(flow_block))
 			return -EOPNOTSUPP;
 
-		return mlxsw_sp_setup_tc_cls_flower(acl_block, type_data);
+		return mlxsw_sp_setup_tc_cls_flower(flow_block, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1624,9 +1624,9 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 
 static void mlxsw_sp_tc_block_flower_release(void *cb_priv)
 {
-	struct mlxsw_sp_acl_block *acl_block = cb_priv;
+	struct mlxsw_sp_flow_block *flow_block = cb_priv;
 
-	mlxsw_sp_acl_block_destroy(acl_block);
+	mlxsw_sp_flow_block_destroy(flow_block);
 }
 
 static LIST_HEAD(mlxsw_sp_block_cb_list);
@@ -1636,7 +1636,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 			            struct flow_block_offload *f, bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_acl_block *acl_block;
+	struct mlxsw_sp_flow_block *flow_block;
 	struct flow_block_cb *block_cb;
 	bool register_block = false;
 	int err;
@@ -1645,31 +1645,31 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 					mlxsw_sp_setup_tc_block_cb_flower,
 					mlxsw_sp);
 	if (!block_cb) {
-		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net);
-		if (!acl_block)
+		flow_block = mlxsw_sp_flow_block_create(mlxsw_sp, f->net);
+		if (!flow_block)
 			return -ENOMEM;
 		block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower,
-					       mlxsw_sp, acl_block,
+					       mlxsw_sp, flow_block,
 					       mlxsw_sp_tc_block_flower_release);
 		if (IS_ERR(block_cb)) {
-			mlxsw_sp_acl_block_destroy(acl_block);
+			mlxsw_sp_flow_block_destroy(flow_block);
 			err = PTR_ERR(block_cb);
 			goto err_cb_register;
 		}
 		register_block = true;
 	} else {
-		acl_block = flow_block_cb_priv(block_cb);
+		flow_block = flow_block_cb_priv(block_cb);
 	}
 	flow_block_cb_incref(block_cb);
-	err = mlxsw_sp_acl_block_bind(mlxsw_sp, acl_block,
-				      mlxsw_sp_port, ingress, f->extack);
+	err = mlxsw_sp_flow_block_bind(mlxsw_sp, flow_block,
+				       mlxsw_sp_port, ingress, f->extack);
 	if (err)
 		goto err_block_bind;
 
 	if (ingress)
-		mlxsw_sp_port->ing_acl_block = acl_block;
+		mlxsw_sp_port->ing_flow_block = flow_block;
 	else
-		mlxsw_sp_port->eg_acl_block = acl_block;
+		mlxsw_sp_port->eg_flow_block = flow_block;
 
 	if (register_block) {
 		flow_block_cb_add(block_cb, f);
@@ -1687,10 +1687,11 @@ err_cb_register:
 
 static void
 mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct flow_block_offload *f, bool ingress)
+				      struct flow_block_offload *f,
+				      bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_acl_block *acl_block;
+	struct mlxsw_sp_flow_block *flow_block;
 	struct flow_block_cb *block_cb;
 	int err;
 
@@ -1701,13 +1702,13 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 		return;
 
 	if (ingress)
-		mlxsw_sp_port->ing_acl_block = NULL;
+		mlxsw_sp_port->ing_flow_block = NULL;
 	else
-		mlxsw_sp_port->eg_acl_block = NULL;
+		mlxsw_sp_port->eg_flow_block = NULL;
 
-	acl_block = flow_block_cb_priv(block_cb);
-	err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
-					mlxsw_sp_port, ingress);
+	flow_block = flow_block_cb_priv(block_cb);
+	err = mlxsw_sp_flow_block_unbind(mlxsw_sp, flow_block,
+					 mlxsw_sp_port, ingress);
 	if (!err && !flow_block_cb_decref(block_cb)) {
 		flow_block_cb_remove(block_cb, f);
 		list_del(&block_cb->driver_list);
@@ -1797,17 +1798,17 @@ static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable)
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 
 	if (!enable) {
-		if (mlxsw_sp_acl_block_rule_count(mlxsw_sp_port->ing_acl_block) ||
-		    mlxsw_sp_acl_block_rule_count(mlxsw_sp_port->eg_acl_block) ||
+		if (mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->ing_flow_block) ||
+		    mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->eg_flow_block) ||
 		    !list_empty(&mlxsw_sp_port->mall_tc_list)) {
 			netdev_err(dev, "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 			return -EINVAL;
 		}
-		mlxsw_sp_acl_block_disable_inc(mlxsw_sp_port->ing_acl_block);
-		mlxsw_sp_acl_block_disable_inc(mlxsw_sp_port->eg_acl_block);
+		mlxsw_sp_flow_block_disable_inc(mlxsw_sp_port->ing_flow_block);
+		mlxsw_sp_flow_block_disable_inc(mlxsw_sp_port->eg_flow_block);
 	} else {
-		mlxsw_sp_acl_block_disable_dec(mlxsw_sp_port->ing_acl_block);
-		mlxsw_sp_acl_block_disable_dec(mlxsw_sp_port->eg_acl_block);
+		mlxsw_sp_flow_block_disable_dec(mlxsw_sp_port->ing_flow_block);
+		mlxsw_sp_flow_block_disable_dec(mlxsw_sp_port->eg_flow_block);
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f158cd98f8d8..65b1a2d87c2d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -287,8 +287,8 @@ struct mlxsw_sp_port {
 	struct mlxsw_sp_port_vlan *default_vlan;
 	struct mlxsw_sp_qdisc_state *qdisc;
 	unsigned acl_rule_count;
-	struct mlxsw_sp_acl_block *ing_acl_block;
-	struct mlxsw_sp_acl_block *eg_acl_block;
+	struct mlxsw_sp_flow_block *ing_flow_block;
+	struct mlxsw_sp_flow_block *eg_flow_block;
 	struct {
 		struct delayed_work shaper_dw;
 		struct hwtstamp_config hwtstamp_config;
@@ -654,7 +654,7 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int counter_index;
 };
 
-struct mlxsw_sp_acl_block;
+struct mlxsw_sp_flow_block;
 struct mlxsw_sp_acl_ruleset;
 
 /* spectrum_acl.c */
@@ -663,7 +663,7 @@ enum mlxsw_sp_acl_profile {
 	MLXSW_SP_ACL_PROFILE_MR,
 };
 
-struct mlxsw_sp_acl_block {
+struct mlxsw_sp_flow_block {
 	struct list_head binding_list;
 	struct mlxsw_sp_acl_ruleset *ruleset_zero;
 	struct mlxsw_sp *mlxsw_sp;
@@ -679,74 +679,74 @@ struct mlxsw_sp_acl_block {
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
 
 static inline struct mlxsw_sp *
-mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_mlxsw_sp(struct mlxsw_sp_flow_block *block)
 {
 	return block->mlxsw_sp;
 }
 
 static inline unsigned int
-mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_rule_count(const struct mlxsw_sp_flow_block *block)
 {
 	return block ? block->rule_count : 0;
 }
 
 static inline void
-mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_disable_inc(struct mlxsw_sp_flow_block *block)
 {
 	if (block)
 		block->disable_count++;
 }
 
 static inline void
-mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_disable_dec(struct mlxsw_sp_flow_block *block)
 {
 	if (block)
 		block->disable_count--;
 }
 
 static inline bool
-mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_disabled(const struct mlxsw_sp_flow_block *block)
 {
 	return block->disable_count;
 }
 
 static inline bool
-mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_is_egress_bound(const struct mlxsw_sp_flow_block *block)
 {
 	return block->egress_binding_count;
 }
 
 static inline bool
-mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_is_ingress_bound(const struct mlxsw_sp_flow_block *block)
 {
 	return block->ingress_binding_count;
 }
 
 static inline bool
-mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_flow_block_is_mixed_bound(const struct mlxsw_sp_flow_block *block)
 {
 	return block->ingress_binding_count && block->egress_binding_count;
 }
 
-struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp,
-						     struct net *net);
-void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block);
-int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block,
-			    struct mlxsw_sp_port *mlxsw_sp_port,
-			    bool ingress,
-			    struct netlink_ext_ack *extack);
-int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_block *block,
-			      struct mlxsw_sp_port *mlxsw_sp_port,
-			      bool ingress);
+struct mlxsw_sp_flow_block *mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp,
+						       struct net *net);
+void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block);
+int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_flow_block *block,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     bool ingress,
+			     struct netlink_ext_ack *extack);
+int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_flow_block *block,
+			       struct mlxsw_sp_port *mlxsw_sp_port,
+			       bool ingress);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block, u32 chain_index,
+			    struct mlxsw_sp_flow_block *block, u32 chain_index,
 			    enum mlxsw_sp_acl_profile profile);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
-			 struct mlxsw_sp_acl_block *block, u32 chain_index,
+			 struct mlxsw_sp_flow_block *block, u32 chain_index,
 			 enum mlxsw_sp_acl_profile profile,
 			 struct mlxsw_afk_element_usage *tmplt_elusage);
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
@@ -778,7 +778,7 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei,
 int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
-				  struct mlxsw_sp_acl_block *block,
+				  struct mlxsw_sp_flow_block *block,
 				  struct net_device *out_dev,
 				  struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
@@ -901,19 +901,19 @@ extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block,
+			    struct mlxsw_sp_flow_block *block,
 			    struct flow_cls_offload *f);
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_acl_block *block,
+			     struct mlxsw_sp_flow_block *block,
 			     struct flow_cls_offload *f);
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
-			  struct mlxsw_sp_acl_block *block,
+			  struct mlxsw_sp_flow_block *block,
 			  struct flow_cls_offload *f);
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_block *block,
+				 struct mlxsw_sp_flow_block *block,
 				 struct flow_cls_offload *f);
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_block *block,
+				   struct mlxsw_sp_flow_block *block,
 				   struct flow_cls_offload *f);
 
 /* spectrum_qdisc.c */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
index e31ec75ac035..a11d911302f1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -9,7 +9,7 @@
 
 struct mlxsw_sp2_mr_tcam {
 	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_acl_block *acl_block;
+	struct mlxsw_sp_flow_block *flow_block;
 	struct mlxsw_sp_acl_ruleset *ruleset4;
 	struct mlxsw_sp_acl_ruleset *ruleset6;
 };
@@ -61,7 +61,7 @@ static int mlxsw_sp2_mr_tcam_ipv4_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
 				     mlxsw_sp2_mr_tcam_usage_ipv4,
 				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv4));
 	mr_tcam->ruleset4 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
-						     mr_tcam->acl_block,
+						     mr_tcam->flow_block,
 						     MLXSW_SP_L3_PROTO_IPV4,
 						     MLXSW_SP_ACL_PROFILE_MR,
 						     &elusage);
@@ -111,7 +111,7 @@ static int mlxsw_sp2_mr_tcam_ipv6_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
 				     mlxsw_sp2_mr_tcam_usage_ipv6,
 				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv6));
 	mr_tcam->ruleset6 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
-						     mr_tcam->acl_block,
+						     mr_tcam->flow_block,
 						     MLXSW_SP_L3_PROTO_IPV6,
 						     MLXSW_SP_ACL_PROFILE_MR,
 						     &elusage);
@@ -289,8 +289,8 @@ static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 	int err;
 
 	mr_tcam->mlxsw_sp = mlxsw_sp;
-	mr_tcam->acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, NULL);
-	if (!mr_tcam->acl_block)
+	mr_tcam->flow_block = mlxsw_sp_flow_block_create(mlxsw_sp, NULL);
+	if (!mr_tcam->flow_block)
 		return -ENOMEM;
 
 	err = mlxsw_sp2_mr_tcam_ipv4_init(mr_tcam);
@@ -306,7 +306,7 @@ static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 err_ipv6_init:
 	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
 err_ipv4_init:
-	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
+	mlxsw_sp_flow_block_destroy(mr_tcam->flow_block);
 	return err;
 }
 
@@ -316,7 +316,7 @@ static void mlxsw_sp2_mr_tcam_fini(void *priv)
 
 	mlxsw_sp2_mr_tcam_ipv6_fini(mr_tcam);
 	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
-	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
+	mlxsw_sp_flow_block_destroy(mr_tcam->flow_block);
 }
 
 const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index bb06c007b3f2..f9524cb95e9f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -40,7 +40,7 @@ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl)
 	return acl->afk;
 }
 
-struct mlxsw_sp_acl_block_binding {
+struct mlxsw_sp_flow_block_binding {
 	struct list_head list;
 	struct net_device *dev;
 	struct mlxsw_sp_port *mlxsw_sp_port;
@@ -48,7 +48,7 @@ struct mlxsw_sp_acl_block_binding {
 };
 
 struct mlxsw_sp_acl_ruleset_ht_key {
-	struct mlxsw_sp_acl_block *block;
+	struct mlxsw_sp_flow_block *block;
 	u32 chain_index;
 	const struct mlxsw_sp_acl_profile_ops *ops;
 };
@@ -103,8 +103,8 @@ mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset)
 
 static int
 mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
-			  struct mlxsw_sp_acl_block *block,
-			  struct mlxsw_sp_acl_block_binding *binding)
+			  struct mlxsw_sp_flow_block *block,
+			  struct mlxsw_sp_flow_block_binding *binding)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = block->ruleset_zero;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -115,8 +115,8 @@ mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
 
 static void
 mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block,
-			    struct mlxsw_sp_acl_block_binding *binding)
+			    struct mlxsw_sp_flow_block *block,
+			    struct mlxsw_sp_flow_block_binding *binding)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = block->ruleset_zero;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -126,7 +126,7 @@ mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
 }
 
 static bool
-mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_acl_block *block)
+mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_flow_block *block)
 {
 	return block->ruleset_zero;
 }
@@ -134,9 +134,9 @@ mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_acl_block *block)
 static int
 mlxsw_sp_acl_ruleset_block_bind(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_ruleset *ruleset,
-				struct mlxsw_sp_acl_block *block)
+				struct mlxsw_sp_flow_block *block)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 	int err;
 
 	block->ruleset_zero = ruleset;
@@ -159,19 +159,19 @@ rollback:
 static void
 mlxsw_sp_acl_ruleset_block_unbind(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ruleset *ruleset,
-				  struct mlxsw_sp_acl_block *block)
+				  struct mlxsw_sp_flow_block *block)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 
 	list_for_each_entry(binding, &block->binding_list, list)
 		mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding);
 	block->ruleset_zero = NULL;
 }
 
-struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp,
-						     struct net *net)
+struct mlxsw_sp_flow_block *
+mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net)
 {
-	struct mlxsw_sp_acl_block *block;
+	struct mlxsw_sp_flow_block *block;
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
@@ -182,17 +182,17 @@ struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp,
 	return block;
 }
 
-void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block)
+void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block)
 {
 	WARN_ON(!list_empty(&block->binding_list));
 	kfree(block);
 }
 
-static struct mlxsw_sp_acl_block_binding *
-mlxsw_sp_acl_block_lookup(struct mlxsw_sp_acl_block *block,
-			  struct mlxsw_sp_port *mlxsw_sp_port, bool ingress)
+static struct mlxsw_sp_flow_block_binding *
+mlxsw_sp_flow_block_lookup(struct mlxsw_sp_flow_block *block,
+			   struct mlxsw_sp_port *mlxsw_sp_port, bool ingress)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 
 	list_for_each_entry(binding, &block->binding_list, list)
 		if (binding->mlxsw_sp_port == mlxsw_sp_port &&
@@ -201,16 +201,16 @@ mlxsw_sp_acl_block_lookup(struct mlxsw_sp_acl_block *block,
 	return NULL;
 }
 
-int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block,
-			    struct mlxsw_sp_port *mlxsw_sp_port,
-			    bool ingress,
-			    struct netlink_ext_ack *extack)
+int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_flow_block *block,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     bool ingress,
+			     struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 	int err;
 
-	if (WARN_ON(mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress)))
+	if (WARN_ON(mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress)))
 		return -EEXIST;
 
 	if (ingress && block->ingress_blocker_rule_count) {
@@ -247,14 +247,14 @@ err_ruleset_bind:
 	return err;
 }
 
-int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_block *block,
-			      struct mlxsw_sp_port *mlxsw_sp_port,
-			      bool ingress)
+int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_flow_block *block,
+			       struct mlxsw_sp_port *mlxsw_sp_port,
+			       bool ingress)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 
-	binding = mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress);
+	binding = mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress);
 	if (!binding)
 		return -ENOENT;
 
@@ -274,7 +274,7 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 
 static struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block, u32 chain_index,
+			    struct mlxsw_sp_flow_block *block, u32 chain_index,
 			    const struct mlxsw_sp_acl_profile_ops *ops,
 			    struct mlxsw_afk_element_usage *tmplt_elusage)
 {
@@ -345,7 +345,7 @@ static void mlxsw_sp_acl_ruleset_ref_dec(struct mlxsw_sp *mlxsw_sp,
 
 static struct mlxsw_sp_acl_ruleset *
 __mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp_acl *acl,
-			      struct mlxsw_sp_acl_block *block, u32 chain_index,
+			      struct mlxsw_sp_flow_block *block, u32 chain_index,
 			      const struct mlxsw_sp_acl_profile_ops *ops)
 {
 	struct mlxsw_sp_acl_ruleset_ht_key ht_key;
@@ -360,7 +360,7 @@ __mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp_acl *acl,
 
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block, u32 chain_index,
+			    struct mlxsw_sp_flow_block *block, u32 chain_index,
 			    enum mlxsw_sp_acl_profile profile)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops;
@@ -378,7 +378,7 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
-			 struct mlxsw_sp_acl_block *block, u32 chain_index,
+			 struct mlxsw_sp_flow_block *block, u32 chain_index,
 			 enum mlxsw_sp_acl_profile profile,
 			 struct mlxsw_afk_element_usage *tmplt_elusage)
 {
@@ -541,11 +541,11 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
-				  struct mlxsw_sp_acl_block *block,
+				  struct mlxsw_sp_flow_block *block,
 				  struct net_device *out_dev,
 				  struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp_acl_block_binding *binding;
+	struct mlxsw_sp_flow_block_binding *binding;
 	struct mlxsw_sp_port *in_port;
 
 	if (!list_is_singular(&block->binding_list)) {
@@ -553,7 +553,7 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 		return -EOPNOTSUPP;
 	}
 	binding = list_first_entry(&block->binding_list,
-				   struct mlxsw_sp_acl_block_binding, list);
+				   struct mlxsw_sp_flow_block_binding, list);
 	in_port = binding->mlxsw_sp_port;
 
 	return mlxsw_afa_block_append_mirror(rulei->act_block,
@@ -775,7 +775,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
-	struct mlxsw_sp_acl_block *block = ruleset->ht_key.block;
+	struct mlxsw_sp_flow_block *block = ruleset->ht_key.block;
 	int err;
 
 	err = ops->rule_add(mlxsw_sp, ruleset->priv, rule->priv, rule->rulei);
@@ -819,7 +819,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
-	struct mlxsw_sp_acl_block *block = ruleset->ht_key.block;
+	struct mlxsw_sp_flow_block *block = ruleset->ht_key.block;
 
 	block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker;
 	block->ingress_blocker_rule_count -= rule->rulei->ingress_bind_blocker;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 51117a5a6bbf..89c2e9820e95 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -15,7 +15,7 @@
 #include "core_acl_flex_keys.h"
 
 static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
-					 struct mlxsw_sp_acl_block *block,
+					 struct mlxsw_sp_flow_block *block,
 					 struct mlxsw_sp_acl_rule_info *rulei,
 					 struct flow_action *flow_action,
 					 struct netlink_ext_ack *extack)
@@ -53,11 +53,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		case FLOW_ACTION_DROP: {
 			bool ingress;
 
-			if (mlxsw_sp_acl_block_is_mixed_bound(block)) {
+			if (mlxsw_sp_flow_block_is_mixed_bound(block)) {
 				NL_SET_ERR_MSG_MOD(extack, "Drop action is not supported when block is bound to ingress and egress");
 				return -EOPNOTSUPP;
 			}
-			ingress = mlxsw_sp_acl_block_is_ingress_bound(block);
+			ingress = mlxsw_sp_flow_block_is_ingress_bound(block);
 			err = mlxsw_sp_acl_rulei_act_drop(rulei, ingress,
 							  act->cookie, extack);
 			if (err) {
@@ -106,7 +106,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			struct mlxsw_sp_fid *fid;
 			u16 fid_index;
 
-			if (mlxsw_sp_acl_block_is_egress_bound(block)) {
+			if (mlxsw_sp_flow_block_is_egress_bound(block)) {
 				NL_SET_ERR_MSG_MOD(extack, "Redirect action is not supported on egress");
 				return -EOPNOTSUPP;
 			}
@@ -190,7 +190,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei,
 				      struct flow_cls_offload *f,
-				      struct mlxsw_sp_acl_block *block)
+				      struct mlxsw_sp_flow_block *block)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct mlxsw_sp_port *mlxsw_sp_port;
@@ -371,7 +371,7 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_block *block,
+				 struct mlxsw_sp_flow_block *block,
 				 struct mlxsw_sp_acl_rule_info *rulei,
 				 struct flow_cls_offload *f)
 {
@@ -460,7 +460,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 		struct flow_match_vlan match;
 
 		flow_rule_match_vlan(rule, &match);
-		if (mlxsw_sp_acl_block_is_egress_bound(block)) {
+		if (mlxsw_sp_flow_block_is_egress_bound(block)) {
 			NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress");
 			return -EOPNOTSUPP;
 		}
@@ -505,7 +505,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_block *block,
+			    struct mlxsw_sp_flow_block *block,
 			    struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
@@ -552,7 +552,7 @@ err_rule_create:
 }
 
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_acl_block *block,
+			     struct mlxsw_sp_flow_block *block,
 			     struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -574,7 +574,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
-			  struct mlxsw_sp_acl_block *block,
+			  struct mlxsw_sp_flow_block *block,
 			  struct flow_cls_offload *f)
 {
 	enum flow_action_hw_stats used_hw_stats = FLOW_ACTION_HW_STATS_DISABLED;
@@ -611,7 +611,7 @@ err_rule_get_stats:
 }
 
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_block *block,
+				 struct mlxsw_sp_flow_block *block,
 				 struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -632,7 +632,7 @@ int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 }
 
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_block *block,
+				   struct mlxsw_sp_flow_block *block,
 				   struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
-- 
cgit v1.2.3


From d52238eb7bcf53225841217af12fe1383205fcaa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:00 +0300
Subject: mlxsw: spectrum: Push flow_block related functions into a separate
 file

The code around flow_block is currently mixed in spectrum_acl.c.
However, as it really does not directly relate to ACL part only,
push the bits into a separate file.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  34 ++++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 131 +--------------------
 .../net/ethernet/mellanox/mlxsw/spectrum_flow.c    | 120 +++++++++++++++++++
 4 files changed, 151 insertions(+), 135 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 0e86a581d45b..59cbf02d6731 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -21,6 +21,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_acl_atcam.o spectrum_acl_erp.o \
 				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
 				   spectrum_acl_bloom_filter.o spectrum_acl.o \
+				   spectrum_flow.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 65b1a2d87c2d..d4ef079aab4b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -654,15 +654,7 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int counter_index;
 };
 
-struct mlxsw_sp_flow_block;
-struct mlxsw_sp_acl_ruleset;
-
-/* spectrum_acl.c */
-enum mlxsw_sp_acl_profile {
-	MLXSW_SP_ACL_PROFILE_FLOWER,
-	MLXSW_SP_ACL_PROFILE_MR,
-};
-
+/* spectrum_flow.c */
 struct mlxsw_sp_flow_block {
 	struct list_head binding_list;
 	struct mlxsw_sp_acl_ruleset *ruleset_zero;
@@ -676,7 +668,12 @@ struct mlxsw_sp_flow_block {
 	struct net *net;
 };
 
-struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
+struct mlxsw_sp_flow_block_binding {
+	struct list_head list;
+	struct net_device *dev;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	bool ingress;
+};
 
 static inline struct mlxsw_sp *
 mlxsw_sp_flow_block_mlxsw_sp(struct mlxsw_sp_flow_block *block)
@@ -740,6 +737,23 @@ int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_flow_block *block,
 			       struct mlxsw_sp_port *mlxsw_sp_port,
 			       bool ingress);
+
+/* spectrum_acl.c */
+struct mlxsw_sp_acl_ruleset;
+
+enum mlxsw_sp_acl_profile {
+	MLXSW_SP_ACL_PROFILE_FLOWER,
+	MLXSW_SP_ACL_PROFILE_MR,
+};
+
+struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
+
+int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_flow_block *block,
+			      struct mlxsw_sp_flow_block_binding *binding);
+void mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_flow_block *block,
+				 struct mlxsw_sp_flow_block_binding *binding);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_flow_block *block, u32 chain_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index f9524cb95e9f..800eaa6be3c0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -40,13 +40,6 @@ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl)
 	return acl->afk;
 }
 
-struct mlxsw_sp_flow_block_binding {
-	struct list_head list;
-	struct net_device *dev;
-	struct mlxsw_sp_port *mlxsw_sp_port;
-	bool ingress;
-};
-
 struct mlxsw_sp_acl_ruleset_ht_key {
 	struct mlxsw_sp_flow_block *block;
 	u32 chain_index;
@@ -101,10 +94,9 @@ mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset)
 	return ruleset->ref_count == 2;
 }
 
-static int
-mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
-			  struct mlxsw_sp_flow_block *block,
-			  struct mlxsw_sp_flow_block_binding *binding)
+int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_flow_block *block,
+			      struct mlxsw_sp_flow_block_binding *binding)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = block->ruleset_zero;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -113,10 +105,9 @@ mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
 				 binding->mlxsw_sp_port, binding->ingress);
 }
 
-static void
-mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_flow_block *block,
-			    struct mlxsw_sp_flow_block_binding *binding)
+void mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_flow_block *block,
+				 struct mlxsw_sp_flow_block_binding *binding)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset = block->ruleset_zero;
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -125,12 +116,6 @@ mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
 			    binding->mlxsw_sp_port, binding->ingress);
 }
 
-static bool
-mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_flow_block *block)
-{
-	return block->ruleset_zero;
-}
-
 static int
 mlxsw_sp_acl_ruleset_block_bind(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_ruleset *ruleset,
@@ -168,110 +153,6 @@ mlxsw_sp_acl_ruleset_block_unbind(struct mlxsw_sp *mlxsw_sp,
 	block->ruleset_zero = NULL;
 }
 
-struct mlxsw_sp_flow_block *
-mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net)
-{
-	struct mlxsw_sp_flow_block *block;
-
-	block = kzalloc(sizeof(*block), GFP_KERNEL);
-	if (!block)
-		return NULL;
-	INIT_LIST_HEAD(&block->binding_list);
-	block->mlxsw_sp = mlxsw_sp;
-	block->net = net;
-	return block;
-}
-
-void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block)
-{
-	WARN_ON(!list_empty(&block->binding_list));
-	kfree(block);
-}
-
-static struct mlxsw_sp_flow_block_binding *
-mlxsw_sp_flow_block_lookup(struct mlxsw_sp_flow_block *block,
-			   struct mlxsw_sp_port *mlxsw_sp_port, bool ingress)
-{
-	struct mlxsw_sp_flow_block_binding *binding;
-
-	list_for_each_entry(binding, &block->binding_list, list)
-		if (binding->mlxsw_sp_port == mlxsw_sp_port &&
-		    binding->ingress == ingress)
-			return binding;
-	return NULL;
-}
-
-int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_flow_block *block,
-			     struct mlxsw_sp_port *mlxsw_sp_port,
-			     bool ingress,
-			     struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sp_flow_block_binding *binding;
-	int err;
-
-	if (WARN_ON(mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress)))
-		return -EEXIST;
-
-	if (ingress && block->ingress_blocker_rule_count) {
-		NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to ingress because it contains unsupported rules");
-		return -EOPNOTSUPP;
-	}
-
-	if (!ingress && block->egress_blocker_rule_count) {
-		NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules");
-		return -EOPNOTSUPP;
-	}
-
-	binding = kzalloc(sizeof(*binding), GFP_KERNEL);
-	if (!binding)
-		return -ENOMEM;
-	binding->mlxsw_sp_port = mlxsw_sp_port;
-	binding->ingress = ingress;
-
-	if (mlxsw_sp_acl_ruleset_block_bound(block)) {
-		err = mlxsw_sp_acl_ruleset_bind(mlxsw_sp, block, binding);
-		if (err)
-			goto err_ruleset_bind;
-	}
-
-	if (ingress)
-		block->ingress_binding_count++;
-	else
-		block->egress_binding_count++;
-	list_add(&binding->list, &block->binding_list);
-	return 0;
-
-err_ruleset_bind:
-	kfree(binding);
-	return err;
-}
-
-int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
-			       struct mlxsw_sp_flow_block *block,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       bool ingress)
-{
-	struct mlxsw_sp_flow_block_binding *binding;
-
-	binding = mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress);
-	if (!binding)
-		return -ENOENT;
-
-	list_del(&binding->list);
-
-	if (ingress)
-		block->ingress_binding_count--;
-	else
-		block->egress_binding_count--;
-
-	if (mlxsw_sp_acl_ruleset_block_bound(block))
-		mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding);
-
-	kfree(binding);
-	return 0;
-}
-
 static struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_flow_block *block, u32 chain_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
new file mode 100644
index 000000000000..655e1df5c95a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2020 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <net/net_namespace.h>
+
+#include "spectrum.h"
+
+struct mlxsw_sp_flow_block *
+mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net)
+{
+	struct mlxsw_sp_flow_block *block;
+
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return NULL;
+	INIT_LIST_HEAD(&block->binding_list);
+	block->mlxsw_sp = mlxsw_sp;
+	block->net = net;
+	return block;
+}
+
+void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block)
+{
+	WARN_ON(!list_empty(&block->binding_list));
+	kfree(block);
+}
+
+static struct mlxsw_sp_flow_block_binding *
+mlxsw_sp_flow_block_lookup(struct mlxsw_sp_flow_block *block,
+			   struct mlxsw_sp_port *mlxsw_sp_port, bool ingress)
+{
+	struct mlxsw_sp_flow_block_binding *binding;
+
+	list_for_each_entry(binding, &block->binding_list, list)
+		if (binding->mlxsw_sp_port == mlxsw_sp_port &&
+		    binding->ingress == ingress)
+			return binding;
+	return NULL;
+}
+
+static bool
+mlxsw_sp_flow_block_ruleset_bound(const struct mlxsw_sp_flow_block *block)
+{
+	return block->ruleset_zero;
+}
+
+int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_flow_block *block,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     bool ingress,
+			     struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_flow_block_binding *binding;
+	int err;
+
+	if (WARN_ON(mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress)))
+		return -EEXIST;
+
+	if (ingress && block->ingress_blocker_rule_count) {
+		NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to ingress because it contains unsupported rules");
+		return -EOPNOTSUPP;
+	}
+
+	if (!ingress && block->egress_blocker_rule_count) {
+		NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules");
+		return -EOPNOTSUPP;
+	}
+
+	binding = kzalloc(sizeof(*binding), GFP_KERNEL);
+	if (!binding)
+		return -ENOMEM;
+	binding->mlxsw_sp_port = mlxsw_sp_port;
+	binding->ingress = ingress;
+
+	if (mlxsw_sp_flow_block_ruleset_bound(block)) {
+		err = mlxsw_sp_acl_ruleset_bind(mlxsw_sp, block, binding);
+		if (err)
+			goto err_ruleset_bind;
+	}
+
+	if (ingress)
+		block->ingress_binding_count++;
+	else
+		block->egress_binding_count++;
+	list_add(&binding->list, &block->binding_list);
+	return 0;
+
+err_ruleset_bind:
+	kfree(binding);
+	return err;
+}
+
+int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_flow_block *block,
+			       struct mlxsw_sp_port *mlxsw_sp_port,
+			       bool ingress)
+{
+	struct mlxsw_sp_flow_block_binding *binding;
+
+	binding = mlxsw_sp_flow_block_lookup(block, mlxsw_sp_port, ingress);
+	if (!binding)
+		return -ENOENT;
+
+	list_del(&binding->list);
+
+	if (ingress)
+		block->ingress_binding_count--;
+	else
+		block->egress_binding_count--;
+
+	if (mlxsw_sp_flow_block_ruleset_bound(block))
+		mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding);
+
+	kfree(binding);
+	return 0;
+}
-- 
cgit v1.2.3


From d7fcc986224d77c4ab66f436e7eaa11170c509af Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:01 +0300
Subject: mlxsw: spectrum: Push matchall bits into a separate file

Similar to flower, have matchall related code in a separate file.
Do some small renaming on the way (consistent "mall" prefixes,
dropped "_tc_", dropped "_port_" where suitable).

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 186 +------------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  28 +--
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 202 +++++++++++++++++++++
 4 files changed, 214 insertions(+), 204 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 59cbf02d6731..4aeabb35c943 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -21,7 +21,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_acl_atcam.o spectrum_acl_erp.o \
 				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
 				   spectrum_acl_bloom_filter.o spectrum_acl.o \
-				   spectrum_flow.o \
+				   spectrum_flow.o spectrum_matchall.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f64e8da21d4a..ff25f8fc55e9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -25,9 +25,7 @@
 #include <linux/log2.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
-#include <net/tc_act/tc_mirred.h>
 #include <net/netevent.h>
-#include <net/tc_act/tc_sample.h>
 #include <net/addrconf.h>
 
 #include "spectrum.h"
@@ -582,16 +580,6 @@ static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
-static int mlxsw_sp_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				    bool enable, u32 rate)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char mpsc_pl[MLXSW_REG_MPSC_LEN];
-
-	mlxsw_reg_mpsc_pack(mpsc_pl, mlxsw_sp_port->local_port, enable, rate);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpsc), mpsc_pl);
-}
-
 static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port,
 					  bool is_up)
 {
@@ -1362,181 +1350,15 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static struct mlxsw_sp_port_mall_tc_entry *
-mlxsw_sp_port_mall_tc_entry_find(struct mlxsw_sp_port *port,
-				 unsigned long cookie) {
-	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
-
-	list_for_each_entry(mall_tc_entry, &port->mall_tc_list, list)
-		if (mall_tc_entry->cookie == cookie)
-			return mall_tc_entry;
-
-	return NULL;
-}
-
-static int
-mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror,
-				      const struct flow_action_entry *act,
-				      bool ingress)
-{
-	enum mlxsw_sp_span_type span_type;
-
-	if (!act->dev) {
-		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
-		return -EINVAL;
-	}
-
-	mirror->ingress = ingress;
-	span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, act->dev, span_type,
-					true, &mirror->span_id);
-}
-
-static void
-mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror)
-{
-	enum mlxsw_sp_span_type span_type;
-
-	span_type = mirror->ingress ?
-			MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->span_id,
-				 span_type, true);
-}
-
-static int
-mlxsw_sp_port_add_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct tc_cls_matchall_offload *cls,
-				      const struct flow_action_entry *act,
-				      bool ingress)
-{
-	int err;
-
-	if (!mlxsw_sp_port->sample)
-		return -EOPNOTSUPP;
-	if (rtnl_dereference(mlxsw_sp_port->sample->psample_group)) {
-		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
-		return -EEXIST;
-	}
-	if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
-		netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
-			   act->sample.psample_group);
-	mlxsw_sp_port->sample->truncate = act->sample.truncate;
-	mlxsw_sp_port->sample->trunc_size = act->sample.trunc_size;
-	mlxsw_sp_port->sample->rate = act->sample.rate;
-
-	err = mlxsw_sp_port_sample_set(mlxsw_sp_port, true, act->sample.rate);
-	if (err)
-		goto err_port_sample_set;
-	return 0;
-
-err_port_sample_set:
-	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
-	return err;
-}
-
-static void
-mlxsw_sp_port_del_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	if (!mlxsw_sp_port->sample)
-		return;
-
-	mlxsw_sp_port_sample_set(mlxsw_sp_port, false, 1);
-	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
-}
-
-static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct tc_cls_matchall_offload *f,
-					  bool ingress)
-{
-	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
-	__be16 protocol = f->common.protocol;
-	struct flow_action_entry *act;
-	int err;
-
-	if (!flow_offload_has_one_action(&f->rule->action)) {
-		netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
-	if (!mall_tc_entry)
-		return -ENOMEM;
-	mall_tc_entry->cookie = f->cookie;
-
-	act = &f->rule->action.entries[0];
-
-	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
-		struct mlxsw_sp_port_mall_mirror_tc_entry *mirror;
-
-		mall_tc_entry->type = MLXSW_SP_PORT_MALL_MIRROR;
-		mirror = &mall_tc_entry->mirror;
-		err = mlxsw_sp_port_add_cls_matchall_mirror(mlxsw_sp_port,
-							    mirror, act,
-							    ingress);
-	} else if (act->id == FLOW_ACTION_SAMPLE &&
-		   protocol == htons(ETH_P_ALL)) {
-		mall_tc_entry->type = MLXSW_SP_PORT_MALL_SAMPLE;
-		err = mlxsw_sp_port_add_cls_matchall_sample(mlxsw_sp_port, f,
-							    act, ingress);
-	} else {
-		err = -EOPNOTSUPP;
-	}
-
-	if (err)
-		goto err_add_action;
-
-	list_add_tail(&mall_tc_entry->list, &mlxsw_sp_port->mall_tc_list);
-	return 0;
-
-err_add_action:
-	kfree(mall_tc_entry);
-	return err;
-}
-
-static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
-					   struct tc_cls_matchall_offload *f)
-{
-	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
-
-	mall_tc_entry = mlxsw_sp_port_mall_tc_entry_find(mlxsw_sp_port,
-							 f->cookie);
-	if (!mall_tc_entry) {
-		netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n");
-		return;
-	}
-	list_del(&mall_tc_entry->list);
-
-	switch (mall_tc_entry->type) {
-	case MLXSW_SP_PORT_MALL_MIRROR:
-		mlxsw_sp_port_del_cls_matchall_mirror(mlxsw_sp_port,
-						      &mall_tc_entry->mirror);
-		break;
-	case MLXSW_SP_PORT_MALL_SAMPLE:
-		mlxsw_sp_port_del_cls_matchall_sample(mlxsw_sp_port);
-		break;
-	default:
-		WARN_ON(1);
-	}
-
-	kfree(mall_tc_entry);
-}
-
 static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 					  struct tc_cls_matchall_offload *f,
 					  bool ingress)
 {
 	switch (f->command) {
 	case TC_CLSMATCHALL_REPLACE:
-		return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, f,
-						      ingress);
+		return mlxsw_sp_mall_replace(mlxsw_sp_port, f, ingress);
 	case TC_CLSMATCHALL_DESTROY:
-		mlxsw_sp_port_del_cls_matchall(mlxsw_sp_port, f);
+		mlxsw_sp_mall_destroy(mlxsw_sp_port, f);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1800,7 +1622,7 @@ static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable)
 	if (!enable) {
 		if (mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->ing_flow_block) ||
 		    mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->eg_flow_block) ||
-		    !list_empty(&mlxsw_sp_port->mall_tc_list)) {
+		    !list_empty(&mlxsw_sp_port->mall_list)) {
 			netdev_err(dev, "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 			return -EINVAL;
 		}
@@ -3696,7 +3518,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->mapping = *port_mapping;
 	mlxsw_sp_port->link.autoneg = 1;
 	INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list);
-	INIT_LIST_HEAD(&mlxsw_sp_port->mall_tc_list);
+	INIT_LIST_HEAD(&mlxsw_sp_port->mall_list);
 
 	mlxsw_sp_port->pcpu_stats =
 		netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index d4ef079aab4b..5c2f1af53e53 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -109,25 +109,6 @@ struct mlxsw_sp_mid {
 	unsigned long *ports_in_mid; /* bits array */
 };
 
-enum mlxsw_sp_port_mall_action_type {
-	MLXSW_SP_PORT_MALL_MIRROR,
-	MLXSW_SP_PORT_MALL_SAMPLE,
-};
-
-struct mlxsw_sp_port_mall_mirror_tc_entry {
-	int span_id;
-	bool ingress;
-};
-
-struct mlxsw_sp_port_mall_tc_entry {
-	struct list_head list;
-	unsigned long cookie;
-	enum mlxsw_sp_port_mall_action_type type;
-	union {
-		struct mlxsw_sp_port_mall_mirror_tc_entry mirror;
-	};
-};
-
 struct mlxsw_sp_sb;
 struct mlxsw_sp_bridge;
 struct mlxsw_sp_router;
@@ -274,8 +255,7 @@ struct mlxsw_sp_port {
 					       * the same localport can have
 					       * different mapping.
 					       */
-	/* TC handles */
-	struct list_head mall_tc_list;
+	struct list_head mall_list;
 	struct {
 		#define MLXSW_HW_STATS_UPDATE_TIME HZ
 		struct rtnl_link_stats64 stats;
@@ -913,6 +893,12 @@ extern const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops;
 extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
 extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
+/* spectrum_matchall.c */
+int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct tc_cls_matchall_offload *f, bool ingress);
+void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct tc_cls_matchall_offload *f);
+
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_flow_block *block,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
new file mode 100644
index 000000000000..56f21cfdb48e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2020 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <net/flow_offload.h>
+
+#include "spectrum.h"
+#include "spectrum_span.h"
+#include "reg.h"
+
+enum mlxsw_sp_mall_action_type {
+	MLXSW_SP_MALL_ACTION_TYPE_MIRROR,
+	MLXSW_SP_MALL_ACTION_TYPE_SAMPLE,
+};
+
+struct mlxsw_sp_mall_mirror_entry {
+	int span_id;
+	bool ingress;
+};
+
+struct mlxsw_sp_mall_entry {
+	struct list_head list;
+	unsigned long cookie;
+	enum mlxsw_sp_mall_action_type type;
+	union {
+		struct mlxsw_sp_mall_mirror_entry mirror;
+	};
+};
+
+static struct mlxsw_sp_mall_entry *
+mlxsw_sp_mall_entry_find(struct mlxsw_sp_port *port, unsigned long cookie)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+
+	list_for_each_entry(mall_entry, &port->mall_list, list)
+		if (mall_entry->cookie == cookie)
+			return mall_entry;
+
+	return NULL;
+}
+
+static int
+mlxsw_sp_mall_port_mirror_add(struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct mlxsw_sp_mall_mirror_entry *mirror,
+			      const struct flow_action_entry *act,
+			      bool ingress)
+{
+	enum mlxsw_sp_span_type span_type;
+
+	if (!act->dev) {
+		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
+		return -EINVAL;
+	}
+
+	mirror->ingress = ingress;
+	span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
+	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, act->dev, span_type,
+					true, &mirror->span_id);
+}
+
+static void
+mlxsw_sp_mall_port_mirror_del(struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct mlxsw_sp_mall_mirror_entry *mirror)
+{
+	enum mlxsw_sp_span_type span_type;
+
+	span_type = mirror->ingress ? MLXSW_SP_SPAN_INGRESS :
+				      MLXSW_SP_SPAN_EGRESS;
+	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->span_id,
+				 span_type, true);
+}
+
+static int mlxsw_sp_mall_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					 bool enable, u32 rate)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char mpsc_pl[MLXSW_REG_MPSC_LEN];
+
+	mlxsw_reg_mpsc_pack(mpsc_pl, mlxsw_sp_port->local_port, enable, rate);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpsc), mpsc_pl);
+}
+
+static int
+mlxsw_sp_mall_port_sample_add(struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct tc_cls_matchall_offload *cls,
+			      const struct flow_action_entry *act, bool ingress)
+{
+	int err;
+
+	if (!mlxsw_sp_port->sample)
+		return -EOPNOTSUPP;
+	if (rtnl_dereference(mlxsw_sp_port->sample->psample_group)) {
+		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
+		return -EEXIST;
+	}
+	if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
+		netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
+			   act->sample.psample_group);
+	mlxsw_sp_port->sample->truncate = act->sample.truncate;
+	mlxsw_sp_port->sample->trunc_size = act->sample.trunc_size;
+	mlxsw_sp_port->sample->rate = act->sample.rate;
+
+	err = mlxsw_sp_mall_port_sample_set(mlxsw_sp_port, true,
+					    act->sample.rate);
+	if (err)
+		goto err_port_sample_set;
+	return 0;
+
+err_port_sample_set:
+	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
+	return err;
+}
+
+static void
+mlxsw_sp_mall_port_sample_del(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	if (!mlxsw_sp_port->sample)
+		return;
+
+	mlxsw_sp_mall_port_sample_set(mlxsw_sp_port, false, 1);
+	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
+}
+
+int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct tc_cls_matchall_offload *f, bool ingress)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+	__be16 protocol = f->common.protocol;
+	struct flow_action_entry *act;
+	int err;
+
+	if (!flow_offload_has_one_action(&f->rule->action)) {
+		netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	mall_entry = kzalloc(sizeof(*mall_entry), GFP_KERNEL);
+	if (!mall_entry)
+		return -ENOMEM;
+	mall_entry->cookie = f->cookie;
+
+	act = &f->rule->action.entries[0];
+
+	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
+		struct mlxsw_sp_mall_mirror_entry *mirror;
+
+		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR;
+		mirror = &mall_entry->mirror;
+		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mirror, act,
+						    ingress);
+	} else if (act->id == FLOW_ACTION_SAMPLE &&
+		   protocol == htons(ETH_P_ALL)) {
+		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_SAMPLE;
+		err = mlxsw_sp_mall_port_sample_add(mlxsw_sp_port, f, act,
+						    ingress);
+	} else {
+		err = -EOPNOTSUPP;
+	}
+
+	if (err)
+		goto err_add_action;
+
+	list_add_tail(&mall_entry->list, &mlxsw_sp_port->mall_list);
+	return 0;
+
+err_add_action:
+	kfree(mall_entry);
+	return err;
+}
+
+void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct tc_cls_matchall_offload *f)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+
+	mall_entry = mlxsw_sp_mall_entry_find(mlxsw_sp_port, f->cookie);
+	if (!mall_entry) {
+		netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n");
+		return;
+	}
+	list_del(&mall_entry->list);
+
+	switch (mall_entry->type) {
+	case MLXSW_SP_MALL_ACTION_TYPE_MIRROR:
+		mlxsw_sp_mall_port_mirror_del(mlxsw_sp_port,
+					      &mall_entry->mirror);
+		break;
+	case MLXSW_SP_MALL_ACTION_TYPE_SAMPLE:
+		mlxsw_sp_mall_port_sample_del(mlxsw_sp_port);
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	kfree(mall_entry);
+}
-- 
cgit v1.2.3


From 6c8cd435b58780ded6e3e06d722249ec181efb36 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:02 +0300
Subject: mlxsw: spectrum_acl: Use block variable in mlxsw_sp_acl_rule_del()

On couple of places in mlxsw_sp_acl_rule_del(), block variable is not
used directly as it could be. So do it.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 800eaa6be3c0..c61f78e30397 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -704,14 +704,13 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 
 	block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker;
 	block->ingress_blocker_rule_count -= rule->rulei->ingress_bind_blocker;
-	ruleset->ht_key.block->rule_count--;
+	block->rule_count--;
 	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_del(&rule->list);
 	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	if (!ruleset->ht_key.chain_index &&
 	    mlxsw_sp_acl_ruleset_is_singular(ruleset))
-		mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset,
-						  ruleset->ht_key.block);
+		mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset, block);
 	rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node,
 			       mlxsw_sp_acl_rule_ht_params);
 	ops->rule_del(mlxsw_sp, rule->priv);
-- 
cgit v1.2.3


From 780ba878a1b024e176dc27c980e1600a23d7b5c5 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:03 +0300
Subject: mlxsw: spectrum_matchall: Pass mall_entry as arg to
 mlxsw_sp_mall_port_mirror_add()

In the preparation for future changes, have the
mlxsw_sp_mall_port_mirror_add() function to accept mall_entry including
the "to_dev" originally obtained from act pointer.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 34 +++++++++++-----------
 1 file changed, 17 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index 56f21cfdb48e..b57267f0c9a1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -16,6 +16,7 @@ enum mlxsw_sp_mall_action_type {
 };
 
 struct mlxsw_sp_mall_mirror_entry {
+	const struct net_device *to_dev;
 	int span_id;
 	bool ingress;
 };
@@ -43,32 +44,34 @@ mlxsw_sp_mall_entry_find(struct mlxsw_sp_port *port, unsigned long cookie)
 
 static int
 mlxsw_sp_mall_port_mirror_add(struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct mlxsw_sp_mall_mirror_entry *mirror,
-			      const struct flow_action_entry *act,
+			      struct mlxsw_sp_mall_entry *mall_entry,
 			      bool ingress)
 {
 	enum mlxsw_sp_span_type span_type;
 
-	if (!act->dev) {
+	if (!mall_entry->mirror.to_dev) {
 		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
 		return -EINVAL;
 	}
 
-	mirror->ingress = ingress;
-	span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, act->dev, span_type,
-					true, &mirror->span_id);
+	mall_entry->mirror.ingress = ingress;
+	span_type = mall_entry->mirror.ingress ? MLXSW_SP_SPAN_INGRESS :
+						 MLXSW_SP_SPAN_EGRESS;
+	return mlxsw_sp_span_mirror_add(mlxsw_sp_port,
+					mall_entry->mirror.to_dev,
+					span_type, true,
+					&mall_entry->mirror.span_id);
 }
 
 static void
 mlxsw_sp_mall_port_mirror_del(struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct mlxsw_sp_mall_mirror_entry *mirror)
+			      struct mlxsw_sp_mall_entry *mall_entry)
 {
 	enum mlxsw_sp_span_type span_type;
 
-	span_type = mirror->ingress ? MLXSW_SP_SPAN_INGRESS :
-				      MLXSW_SP_SPAN_EGRESS;
-	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->span_id,
+	span_type = mall_entry->mirror.ingress ? MLXSW_SP_SPAN_INGRESS :
+						 MLXSW_SP_SPAN_EGRESS;
+	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mall_entry->mirror.span_id,
 				 span_type, true);
 }
 
@@ -148,11 +151,9 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 	act = &f->rule->action.entries[0];
 
 	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
-		struct mlxsw_sp_mall_mirror_entry *mirror;
-
 		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR;
-		mirror = &mall_entry->mirror;
-		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mirror, act,
+		mall_entry->mirror.to_dev = act->dev;
+		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mall_entry,
 						    ingress);
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
@@ -188,8 +189,7 @@ void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	switch (mall_entry->type) {
 	case MLXSW_SP_MALL_ACTION_TYPE_MIRROR:
-		mlxsw_sp_mall_port_mirror_del(mlxsw_sp_port,
-					      &mall_entry->mirror);
+		mlxsw_sp_mall_port_mirror_del(mlxsw_sp_port, mall_entry);
 		break;
 	case MLXSW_SP_MALL_ACTION_TYPE_SAMPLE:
 		mlxsw_sp_mall_port_sample_del(mlxsw_sp_port);
-- 
cgit v1.2.3


From c7ea0e162fc84602fde67d41edf72ae3f4f4a14f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:04 +0300
Subject: mlxsw: spectrum_matchall: Pass mall_entry as arg to
 mlxsw_sp_mall_port_sample_add()

In the preparation for future changes, have the
mlxsw_sp_mall_port_sample_add() function to accept mall_entry including
all needed info originally obtained from cls and act pointers.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 35 ++++++++++++----------
 1 file changed, 19 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index b57267f0c9a1..adaaee208655 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -27,6 +27,7 @@ struct mlxsw_sp_mall_entry {
 	enum mlxsw_sp_mall_action_type type;
 	union {
 		struct mlxsw_sp_mall_mirror_entry mirror;
+		struct mlxsw_sp_port_sample sample;
 	};
 };
 
@@ -87,8 +88,7 @@ static int mlxsw_sp_mall_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_mall_port_sample_add(struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct tc_cls_matchall_offload *cls,
-			      const struct flow_action_entry *act, bool ingress)
+			      struct mlxsw_sp_mall_entry *mall_entry)
 {
 	int err;
 
@@ -98,19 +98,14 @@ mlxsw_sp_mall_port_sample_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
 		return -EEXIST;
 	}
-	if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
-		netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
-		return -EOPNOTSUPP;
-	}
-
 	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
-			   act->sample.psample_group);
-	mlxsw_sp_port->sample->truncate = act->sample.truncate;
-	mlxsw_sp_port->sample->trunc_size = act->sample.trunc_size;
-	mlxsw_sp_port->sample->rate = act->sample.rate;
+			   mall_entry->sample.psample_group);
+	mlxsw_sp_port->sample->truncate = mall_entry->sample.truncate;
+	mlxsw_sp_port->sample->trunc_size = mall_entry->sample.trunc_size;
+	mlxsw_sp_port->sample->rate = mall_entry->sample.rate;
 
 	err = mlxsw_sp_mall_port_sample_set(mlxsw_sp_port, true,
-					    act->sample.rate);
+					    mall_entry->sample.rate);
 	if (err)
 		goto err_port_sample_set;
 	return 0;
@@ -157,20 +152,28 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 						    ingress);
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
+		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
+			netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
+			err = -EOPNOTSUPP;
+			goto errout;
+		}
 		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_SAMPLE;
-		err = mlxsw_sp_mall_port_sample_add(mlxsw_sp_port, f, act,
-						    ingress);
+		mall_entry->sample.psample_group = act->sample.psample_group;
+		mall_entry->sample.truncate = act->sample.truncate;
+		mall_entry->sample.trunc_size = act->sample.trunc_size;
+		mall_entry->sample.rate = act->sample.rate;
+		err = mlxsw_sp_mall_port_sample_add(mlxsw_sp_port, mall_entry);
 	} else {
 		err = -EOPNOTSUPP;
 	}
 
 	if (err)
-		goto err_add_action;
+		goto errout;
 
 	list_add_tail(&mall_entry->list, &mlxsw_sp_port->mall_list);
 	return 0;
 
-err_add_action:
+errout:
 	kfree(mall_entry);
 	return err;
 }
-- 
cgit v1.2.3


From 47fa15eae487f3f454d004894671ebea53e77bde Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:05 +0300
Subject: mlxsw: spectrum_matchall: Move ingress indication into mall_entry

Instead of having it in mirror_entry structure, move it to mall_entry
and set it during rule insertion.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_matchall.c    | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index adaaee208655..c05e28971d06 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -18,13 +18,13 @@ enum mlxsw_sp_mall_action_type {
 struct mlxsw_sp_mall_mirror_entry {
 	const struct net_device *to_dev;
 	int span_id;
-	bool ingress;
 };
 
 struct mlxsw_sp_mall_entry {
 	struct list_head list;
 	unsigned long cookie;
 	enum mlxsw_sp_mall_action_type type;
+	bool ingress;
 	union {
 		struct mlxsw_sp_mall_mirror_entry mirror;
 		struct mlxsw_sp_port_sample sample;
@@ -45,8 +45,7 @@ mlxsw_sp_mall_entry_find(struct mlxsw_sp_port *port, unsigned long cookie)
 
 static int
 mlxsw_sp_mall_port_mirror_add(struct mlxsw_sp_port *mlxsw_sp_port,
-			      struct mlxsw_sp_mall_entry *mall_entry,
-			      bool ingress)
+			      struct mlxsw_sp_mall_entry *mall_entry)
 {
 	enum mlxsw_sp_span_type span_type;
 
@@ -55,9 +54,8 @@ mlxsw_sp_mall_port_mirror_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return -EINVAL;
 	}
 
-	mall_entry->mirror.ingress = ingress;
-	span_type = mall_entry->mirror.ingress ? MLXSW_SP_SPAN_INGRESS :
-						 MLXSW_SP_SPAN_EGRESS;
+	span_type = mall_entry->ingress ? MLXSW_SP_SPAN_INGRESS :
+					  MLXSW_SP_SPAN_EGRESS;
 	return mlxsw_sp_span_mirror_add(mlxsw_sp_port,
 					mall_entry->mirror.to_dev,
 					span_type, true,
@@ -70,8 +68,8 @@ mlxsw_sp_mall_port_mirror_del(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	enum mlxsw_sp_span_type span_type;
 
-	span_type = mall_entry->mirror.ingress ? MLXSW_SP_SPAN_INGRESS :
-						 MLXSW_SP_SPAN_EGRESS;
+	span_type = mall_entry->ingress ? MLXSW_SP_SPAN_INGRESS :
+					  MLXSW_SP_SPAN_EGRESS;
 	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mall_entry->mirror.span_id,
 				 span_type, true);
 }
@@ -142,14 +140,14 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (!mall_entry)
 		return -ENOMEM;
 	mall_entry->cookie = f->cookie;
+	mall_entry->ingress = ingress;
 
 	act = &f->rule->action.entries[0];
 
 	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
 		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR;
 		mall_entry->mirror.to_dev = act->dev;
-		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mall_entry,
-						    ingress);
+		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mall_entry);
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
 		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
-- 
cgit v1.2.3


From dd0fbc89d274e392a077c5dc9a21d581de3252d1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:06 +0300
Subject: mlxsw: spectrum_matchall: Push per-port rule add/del into separate
 functions

As the replace/destroy is going to be used later on per-block, push
the per-port rule addition/deletion into separate functions.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 48 ++++++++++++++++------
 1 file changed, 35 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index c05e28971d06..41301027a47c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -123,6 +123,37 @@ mlxsw_sp_mall_port_sample_del(struct mlxsw_sp_port *mlxsw_sp_port)
 	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
 }
 
+static int
+mlxsw_sp_mall_port_rule_add(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct mlxsw_sp_mall_entry *mall_entry)
+{
+	switch (mall_entry->type) {
+	case MLXSW_SP_MALL_ACTION_TYPE_MIRROR:
+		return mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mall_entry);
+	case MLXSW_SP_MALL_ACTION_TYPE_SAMPLE:
+		return mlxsw_sp_mall_port_sample_add(mlxsw_sp_port, mall_entry);
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
+static void
+mlxsw_sp_mall_port_rule_del(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct mlxsw_sp_mall_entry *mall_entry)
+{
+	switch (mall_entry->type) {
+	case MLXSW_SP_MALL_ACTION_TYPE_MIRROR:
+		mlxsw_sp_mall_port_mirror_del(mlxsw_sp_port, mall_entry);
+		break;
+	case MLXSW_SP_MALL_ACTION_TYPE_SAMPLE:
+		mlxsw_sp_mall_port_sample_del(mlxsw_sp_port);
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
 int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 			  struct tc_cls_matchall_offload *f, bool ingress)
 {
@@ -147,7 +178,6 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
 		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR;
 		mall_entry->mirror.to_dev = act->dev;
-		err = mlxsw_sp_mall_port_mirror_add(mlxsw_sp_port, mall_entry);
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
 		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
@@ -160,11 +190,12 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 		mall_entry->sample.truncate = act->sample.truncate;
 		mall_entry->sample.trunc_size = act->sample.trunc_size;
 		mall_entry->sample.rate = act->sample.rate;
-		err = mlxsw_sp_mall_port_sample_add(mlxsw_sp_port, mall_entry);
 	} else {
 		err = -EOPNOTSUPP;
+		goto errout;
 	}
 
+	err = mlxsw_sp_mall_port_rule_add(mlxsw_sp_port, mall_entry);
 	if (err)
 		goto errout;
 
@@ -186,18 +217,9 @@ void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 		netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n");
 		return;
 	}
-	list_del(&mall_entry->list);
 
-	switch (mall_entry->type) {
-	case MLXSW_SP_MALL_ACTION_TYPE_MIRROR:
-		mlxsw_sp_mall_port_mirror_del(mlxsw_sp_port, mall_entry);
-		break;
-	case MLXSW_SP_MALL_ACTION_TYPE_SAMPLE:
-		mlxsw_sp_mall_port_sample_del(mlxsw_sp_port);
-		break;
-	default:
-		WARN_ON(1);
-	}
+	mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
 
+	list_del(&mall_entry->list);
 	kfree(mall_entry);
 }
-- 
cgit v1.2.3


From 481ff57aadf5ea36bb3c5a9e659a2e1c5ecc6725 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:07 +0300
Subject: mlxsw: spectrum: Avoid copying sample values and use RCU pointer
 direcly instead

Currently, only the psample_group is accessed using RCU on RX path.
However, it is possible (unlikely) that other sample values get change
during RX processing. Fix this by having the port->sample struct
accessed as RCU pointer, containing all sample values including
psample_group pointer. That avoids extra alloc per-port, copying the
values and the race condition described above.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 30 +++++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  4 +--
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 17 +++++-------
 3 files changed, 14 insertions(+), 37 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ff25f8fc55e9..5952ec26c169 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3527,13 +3527,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_alloc_stats;
 	}
 
-	mlxsw_sp_port->sample = kzalloc(sizeof(*mlxsw_sp_port->sample),
-					GFP_KERNEL);
-	if (!mlxsw_sp_port->sample) {
-		err = -ENOMEM;
-		goto err_alloc_sample;
-	}
-
 	INIT_DELAYED_WORK(&mlxsw_sp_port->periodic_hw_stats.update_dw,
 			  &update_stats_cache);
 
@@ -3720,8 +3713,6 @@ err_dev_addr_init:
 err_port_swid_set:
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
 err_port_module_map:
-	kfree(mlxsw_sp_port->sample);
-err_alloc_sample:
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 err_alloc_stats:
 	free_netdev(dev);
@@ -3749,7 +3740,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
-	kfree(mlxsw_sp_port->sample);
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 	WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vlans_list));
 	free_netdev(mlxsw_sp_port->dev);
@@ -4236,7 +4226,7 @@ static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port,
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
-	struct psample_group *psample_group;
+	struct mlxsw_sp_port_sample *sample;
 	u32 size;
 
 	if (unlikely(!mlxsw_sp_port)) {
@@ -4244,22 +4234,14 @@ static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port,
 				     local_port);
 		goto out;
 	}
-	if (unlikely(!mlxsw_sp_port->sample)) {
-		dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: sample skb received on unsupported port\n",
-				     local_port);
-		goto out;
-	}
-
-	size = mlxsw_sp_port->sample->truncate ?
-		  mlxsw_sp_port->sample->trunc_size : skb->len;
 
 	rcu_read_lock();
-	psample_group = rcu_dereference(mlxsw_sp_port->sample->psample_group);
-	if (!psample_group)
+	sample = rcu_dereference(mlxsw_sp_port->sample);
+	if (!sample)
 		goto out_unlock;
-	psample_sample_packet(psample_group, skb, size,
-			      mlxsw_sp_port->dev->ifindex, 0,
-			      mlxsw_sp_port->sample->rate);
+	size = sample->truncate ? sample->trunc_size : skb->len;
+	psample_sample_packet(sample->psample_group, skb, size,
+			      mlxsw_sp_port->dev->ifindex, 0, sample->rate);
 out_unlock:
 	rcu_read_unlock();
 out:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 5c2f1af53e53..4cdb7f1d7436 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -192,7 +192,7 @@ struct mlxsw_sp_port_pcpu_stats {
 };
 
 struct mlxsw_sp_port_sample {
-	struct psample_group __rcu *psample_group;
+	struct psample_group *psample_group;
 	u32 trunc_size;
 	u32 rate;
 	bool truncate;
@@ -262,7 +262,7 @@ struct mlxsw_sp_port {
 		struct mlxsw_sp_port_xstats xstats;
 		struct delayed_work update_dw;
 	} periodic_hw_stats;
-	struct mlxsw_sp_port_sample *sample;
+	struct mlxsw_sp_port_sample __rcu *sample;
 	struct list_head vlans_list;
 	struct mlxsw_sp_port_vlan *default_vlan;
 	struct mlxsw_sp_qdisc_state *qdisc;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index 41301027a47c..bda5fb34162a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -29,6 +29,7 @@ struct mlxsw_sp_mall_entry {
 		struct mlxsw_sp_mall_mirror_entry mirror;
 		struct mlxsw_sp_port_sample sample;
 	};
+	struct rcu_head rcu;
 };
 
 static struct mlxsw_sp_mall_entry *
@@ -90,17 +91,11 @@ mlxsw_sp_mall_port_sample_add(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	int err;
 
-	if (!mlxsw_sp_port->sample)
-		return -EOPNOTSUPP;
-	if (rtnl_dereference(mlxsw_sp_port->sample->psample_group)) {
+	if (rtnl_dereference(mlxsw_sp_port->sample)) {
 		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
 		return -EEXIST;
 	}
-	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
-			   mall_entry->sample.psample_group);
-	mlxsw_sp_port->sample->truncate = mall_entry->sample.truncate;
-	mlxsw_sp_port->sample->trunc_size = mall_entry->sample.trunc_size;
-	mlxsw_sp_port->sample->rate = mall_entry->sample.rate;
+	rcu_assign_pointer(mlxsw_sp_port->sample, &mall_entry->sample);
 
 	err = mlxsw_sp_mall_port_sample_set(mlxsw_sp_port, true,
 					    mall_entry->sample.rate);
@@ -109,7 +104,7 @@ mlxsw_sp_mall_port_sample_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	return 0;
 
 err_port_sample_set:
-	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
+	RCU_INIT_POINTER(mlxsw_sp_port->sample, NULL);
 	return err;
 }
 
@@ -120,7 +115,7 @@ mlxsw_sp_mall_port_sample_del(struct mlxsw_sp_port *mlxsw_sp_port)
 		return;
 
 	mlxsw_sp_mall_port_sample_set(mlxsw_sp_port, false, 1);
-	RCU_INIT_POINTER(mlxsw_sp_port->sample->psample_group, NULL);
+	RCU_INIT_POINTER(mlxsw_sp_port->sample, NULL);
 }
 
 static int
@@ -221,5 +216,5 @@ void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
 
 	list_del(&mall_entry->list);
-	kfree(mall_entry);
+	kfree_rcu(mall_entry, rcu); /* sample RX packets may be in-flight */
 }
-- 
cgit v1.2.3


From 3c650136afba8233e738849149b578d0ad6d2023 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:08 +0300
Subject: mlxsw: spectrum_matchall: Process matchall events from the same cb as
 flower

Currently there are two callbacks registered: one for matchall,
one for flower. This causes the user to see "in_hw_count 2" in TC filter
dump. Because of this and also as a preparation for future matchall
offload for rules equivalent to flower-all-match, move the processing of
shared block into matchall.c. Leave only one cb for mlxsw driver
per-block.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 125 +++++----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  12 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_flow.c    |  17 ++-
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    |  90 ++++++++++++---
 4 files changed, 124 insertions(+), 120 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5952ec26c169..ceaf73ac2008 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1350,15 +1350,15 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
-					  struct tc_cls_matchall_offload *f,
-					  bool ingress)
+static int
+mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_flow_block *flow_block,
+			       struct tc_cls_matchall_offload *f)
 {
 	switch (f->command) {
 	case TC_CLSMATCHALL_REPLACE:
-		return mlxsw_sp_mall_replace(mlxsw_sp_port, f, ingress);
+		return mlxsw_sp_mall_replace(flow_block, f);
 	case TC_CLSMATCHALL_DESTROY:
-		mlxsw_sp_mall_destroy(mlxsw_sp_port, f);
+		mlxsw_sp_mall_destroy(flow_block, f);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1389,62 +1389,25 @@ mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_flow_block *flow_block,
 	}
 }
 
-static int mlxsw_sp_setup_tc_block_cb_matchall(enum tc_setup_type type,
-					       void *type_data,
-					       void *cb_priv, bool ingress)
+static int mlxsw_sp_setup_tc_block_cb(enum tc_setup_type type,
+				      void *type_data, void *cb_priv)
 {
-	struct mlxsw_sp_port *mlxsw_sp_port = cb_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSMATCHALL:
-		if (!tc_cls_can_offload_and_chain0(mlxsw_sp_port->dev,
-						   type_data))
-			return -EOPNOTSUPP;
+	struct mlxsw_sp_flow_block *flow_block = cb_priv;
 
-		return mlxsw_sp_setup_tc_cls_matchall(mlxsw_sp_port, type_data,
-						      ingress);
-	case TC_SETUP_CLSFLOWER:
-		return 0;
-	default:
+	if (mlxsw_sp_flow_block_disabled(flow_block))
 		return -EOPNOTSUPP;
-	}
-}
-
-static int mlxsw_sp_setup_tc_block_cb_matchall_ig(enum tc_setup_type type,
-						  void *type_data,
-						  void *cb_priv)
-{
-	return mlxsw_sp_setup_tc_block_cb_matchall(type, type_data,
-						   cb_priv, true);
-}
-
-static int mlxsw_sp_setup_tc_block_cb_matchall_eg(enum tc_setup_type type,
-						  void *type_data,
-						  void *cb_priv)
-{
-	return mlxsw_sp_setup_tc_block_cb_matchall(type, type_data,
-						   cb_priv, false);
-}
-
-static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
-					     void *type_data, void *cb_priv)
-{
-	struct mlxsw_sp_flow_block *flow_block = cb_priv;
 
 	switch (type) {
 	case TC_SETUP_CLSMATCHALL:
-		return 0;
+		return mlxsw_sp_setup_tc_cls_matchall(flow_block, type_data);
 	case TC_SETUP_CLSFLOWER:
-		if (mlxsw_sp_flow_block_disabled(flow_block))
-			return -EOPNOTSUPP;
-
 		return mlxsw_sp_setup_tc_cls_flower(flow_block, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-static void mlxsw_sp_tc_block_flower_release(void *cb_priv)
+static void mlxsw_sp_tc_block_release(void *cb_priv)
 {
 	struct mlxsw_sp_flow_block *flow_block = cb_priv;
 
@@ -1453,9 +1416,9 @@ static void mlxsw_sp_tc_block_flower_release(void *cb_priv)
 
 static LIST_HEAD(mlxsw_sp_block_cb_list);
 
-static int
-mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-			            struct flow_block_offload *f, bool ingress)
+static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port,
+					struct flow_block_offload *f,
+					bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_flow_block *flow_block;
@@ -1463,16 +1426,15 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 	bool register_block = false;
 	int err;
 
-	block_cb = flow_block_cb_lookup(f->block,
-					mlxsw_sp_setup_tc_block_cb_flower,
+	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_setup_tc_block_cb,
 					mlxsw_sp);
 	if (!block_cb) {
 		flow_block = mlxsw_sp_flow_block_create(mlxsw_sp, f->net);
 		if (!flow_block)
 			return -ENOMEM;
-		block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower,
+		block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb,
 					       mlxsw_sp, flow_block,
-					       mlxsw_sp_tc_block_flower_release);
+					       mlxsw_sp_tc_block_release);
 		if (IS_ERR(block_cb)) {
 			mlxsw_sp_flow_block_destroy(flow_block);
 			err = PTR_ERR(block_cb);
@@ -1507,18 +1469,16 @@ err_cb_register:
 	return err;
 }
 
-static void
-mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct flow_block_offload *f,
-				      bool ingress)
+static void mlxsw_sp_setup_tc_block_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
+					   struct flow_block_offload *f,
+					   bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_flow_block *flow_block;
 	struct flow_block_cb *block_cb;
 	int err;
 
-	block_cb = flow_block_cb_lookup(f->block,
-					mlxsw_sp_setup_tc_block_cb_flower,
+	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_setup_tc_block_cb,
 					mlxsw_sp);
 	if (!block_cb)
 		return;
@@ -1540,51 +1500,22 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 				   struct flow_block_offload *f)
 {
-	struct flow_block_cb *block_cb;
-	flow_setup_cb_t *cb;
 	bool ingress;
-	int err;
 
-	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
-		cb = mlxsw_sp_setup_tc_block_cb_matchall_ig;
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		ingress = true;
-	} else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
-		cb = mlxsw_sp_setup_tc_block_cb_matchall_eg;
+	else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
 		ingress = false;
-	} else {
+	else
 		return -EOPNOTSUPP;
-	}
 
 	f->driver_block_list = &mlxsw_sp_block_cb_list;
 
 	switch (f->command) {
 	case FLOW_BLOCK_BIND:
-		if (flow_block_cb_is_busy(cb, mlxsw_sp_port,
-					  &mlxsw_sp_block_cb_list))
-			return -EBUSY;
-
-		block_cb = flow_block_cb_alloc(cb, mlxsw_sp_port,
-					       mlxsw_sp_port, NULL);
-		if (IS_ERR(block_cb))
-			return PTR_ERR(block_cb);
-		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port, f,
-							  ingress);
-		if (err) {
-			flow_block_cb_free(block_cb);
-			return err;
-		}
-		flow_block_cb_add(block_cb, f);
-		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
-		return 0;
+		return mlxsw_sp_setup_tc_block_bind(mlxsw_sp_port, f, ingress);
 	case FLOW_BLOCK_UNBIND:
-		mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port,
-						      f, ingress);
-		block_cb = flow_block_cb_lookup(f->block, cb, mlxsw_sp_port);
-		if (!block_cb)
-			return -ENOENT;
-
-		flow_block_cb_remove(block_cb, f);
-		list_del(&block_cb->driver_list);
+		mlxsw_sp_setup_tc_block_unbind(mlxsw_sp_port, f, ingress);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1621,8 +1552,7 @@ static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable)
 
 	if (!enable) {
 		if (mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->ing_flow_block) ||
-		    mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->eg_flow_block) ||
-		    !list_empty(&mlxsw_sp_port->mall_list)) {
+		    mlxsw_sp_flow_block_rule_count(mlxsw_sp_port->eg_flow_block)) {
 			netdev_err(dev, "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 			return -EINVAL;
 		}
@@ -3518,7 +3448,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->mapping = *port_mapping;
 	mlxsw_sp_port->link.autoneg = 1;
 	INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list);
-	INIT_LIST_HEAD(&mlxsw_sp_port->mall_list);
 
 	mlxsw_sp_port->pcpu_stats =
 		netdev_alloc_pcpu_stats(struct mlxsw_sp_port_pcpu_stats);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4cdb7f1d7436..57d320728914 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -255,7 +255,6 @@ struct mlxsw_sp_port {
 					       * the same localport can have
 					       * different mapping.
 					       */
-	struct list_head mall_list;
 	struct {
 		#define MLXSW_HW_STATS_UPDATE_TIME HZ
 		struct rtnl_link_stats64 stats;
@@ -637,6 +636,7 @@ struct mlxsw_sp_acl_rule_info {
 /* spectrum_flow.c */
 struct mlxsw_sp_flow_block {
 	struct list_head binding_list;
+	struct list_head mall_list;
 	struct mlxsw_sp_acl_ruleset *ruleset_zero;
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned int rule_count;
@@ -894,10 +894,14 @@ extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
 extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_matchall.c */
-int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
-			  struct tc_cls_matchall_offload *f, bool ingress);
-void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
+			  struct tc_cls_matchall_offload *f);
+void mlxsw_sp_mall_destroy(struct mlxsw_sp_flow_block *block,
 			   struct tc_cls_matchall_offload *f);
+int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
+			    struct mlxsw_sp_port *mlxsw_sp_port);
+void mlxsw_sp_mall_port_unbind(struct mlxsw_sp_flow_block *block,
+			       struct mlxsw_sp_port *mlxsw_sp_port);
 
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
index 655e1df5c95a..51de6aca1930 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
@@ -18,6 +18,7 @@ mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net)
 	if (!block)
 		return NULL;
 	INIT_LIST_HEAD(&block->binding_list);
+	INIT_LIST_HEAD(&block->mall_list);
 	block->mlxsw_sp = mlxsw_sp;
 	block->net = net;
 	return block;
@@ -70,9 +71,15 @@ int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
 		return -EOPNOTSUPP;
 	}
 
+	err = mlxsw_sp_mall_port_bind(block, mlxsw_sp_port);
+	if (err)
+		return err;
+
 	binding = kzalloc(sizeof(*binding), GFP_KERNEL);
-	if (!binding)
-		return -ENOMEM;
+	if (!binding) {
+		err = -ENOMEM;
+		goto err_binding_alloc;
+	}
 	binding->mlxsw_sp_port = mlxsw_sp_port;
 	binding->ingress = ingress;
 
@@ -91,6 +98,9 @@ int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
 
 err_ruleset_bind:
 	kfree(binding);
+err_binding_alloc:
+	mlxsw_sp_mall_port_unbind(block, mlxsw_sp_port);
+
 	return err;
 }
 
@@ -116,5 +126,8 @@ int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding);
 
 	kfree(binding);
+
+	mlxsw_sp_mall_port_unbind(block, mlxsw_sp_port);
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index bda5fb34162a..889da63072be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -33,11 +33,11 @@ struct mlxsw_sp_mall_entry {
 };
 
 static struct mlxsw_sp_mall_entry *
-mlxsw_sp_mall_entry_find(struct mlxsw_sp_port *port, unsigned long cookie)
+mlxsw_sp_mall_entry_find(struct mlxsw_sp_flow_block *block, unsigned long cookie)
 {
 	struct mlxsw_sp_mall_entry *mall_entry;
 
-	list_for_each_entry(mall_entry, &port->mall_list, list)
+	list_for_each_entry(mall_entry, &block->mall_list, list)
 		if (mall_entry->cookie == cookie)
 			return mall_entry;
 
@@ -149,16 +149,27 @@ mlxsw_sp_mall_port_rule_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
-int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
-			  struct tc_cls_matchall_offload *f, bool ingress)
+int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
+			  struct tc_cls_matchall_offload *f)
 {
+	struct mlxsw_sp_flow_block_binding *binding;
 	struct mlxsw_sp_mall_entry *mall_entry;
 	__be16 protocol = f->common.protocol;
 	struct flow_action_entry *act;
 	int err;
 
 	if (!flow_offload_has_one_action(&f->rule->action)) {
-		netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n");
+		NL_SET_ERR_MSG(f->common.extack, "Only singular actions are supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (f->common.chain_index) {
+		NL_SET_ERR_MSG(f->common.extack, "Only chain 0 is supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (mlxsw_sp_flow_block_is_mixed_bound(block)) {
+		NL_SET_ERR_MSG(f->common.extack, "Only not mixed bound blocks are supported");
 		return -EOPNOTSUPP;
 	}
 
@@ -166,7 +177,7 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (!mall_entry)
 		return -ENOMEM;
 	mall_entry->cookie = f->cookie;
-	mall_entry->ingress = ingress;
+	mall_entry->ingress = mlxsw_sp_flow_block_is_ingress_bound(block);
 
 	act = &f->rule->action.entries[0];
 
@@ -176,7 +187,7 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
 		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
-			netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
+			NL_SET_ERR_MSG(f->common.extack, "Sample rate not supported");
 			err = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -190,31 +201,78 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_port *mlxsw_sp_port,
 		goto errout;
 	}
 
-	err = mlxsw_sp_mall_port_rule_add(mlxsw_sp_port, mall_entry);
-	if (err)
-		goto errout;
+	list_for_each_entry(binding, &block->binding_list, list) {
+		err = mlxsw_sp_mall_port_rule_add(binding->mlxsw_sp_port,
+						  mall_entry);
+		if (err)
+			goto rollback;
+	}
 
-	list_add_tail(&mall_entry->list, &mlxsw_sp_port->mall_list);
+	block->rule_count++;
+	if (mall_entry->ingress)
+		block->egress_blocker_rule_count++;
+	else
+		block->ingress_blocker_rule_count++;
+	list_add_tail(&mall_entry->list, &block->mall_list);
 	return 0;
 
+rollback:
+	list_for_each_entry_continue_reverse(binding, &block->binding_list,
+					     list)
+		mlxsw_sp_mall_port_rule_del(binding->mlxsw_sp_port, mall_entry);
 errout:
 	kfree(mall_entry);
 	return err;
 }
 
-void mlxsw_sp_mall_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+void mlxsw_sp_mall_destroy(struct mlxsw_sp_flow_block *block,
 			   struct tc_cls_matchall_offload *f)
 {
+	struct mlxsw_sp_flow_block_binding *binding;
 	struct mlxsw_sp_mall_entry *mall_entry;
 
-	mall_entry = mlxsw_sp_mall_entry_find(mlxsw_sp_port, f->cookie);
+	mall_entry = mlxsw_sp_mall_entry_find(block, f->cookie);
 	if (!mall_entry) {
-		netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n");
+		NL_SET_ERR_MSG(f->common.extack, "Entry not found");
 		return;
 	}
 
-	mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
-
 	list_del(&mall_entry->list);
+	if (mall_entry->ingress)
+		block->egress_blocker_rule_count--;
+	else
+		block->ingress_blocker_rule_count--;
+	block->rule_count--;
+	list_for_each_entry(binding, &block->binding_list, list)
+		mlxsw_sp_mall_port_rule_del(binding->mlxsw_sp_port, mall_entry);
 	kfree_rcu(mall_entry, rcu); /* sample RX packets may be in-flight */
 }
+
+int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
+			    struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+	int err;
+
+	list_for_each_entry(mall_entry, &block->mall_list, list) {
+		err = mlxsw_sp_mall_port_rule_add(mlxsw_sp_port, mall_entry);
+		if (err)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	list_for_each_entry_continue_reverse(mall_entry, &block->mall_list,
+					     list)
+		mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
+	return err;
+}
+
+void mlxsw_sp_mall_port_unbind(struct mlxsw_sp_flow_block *block,
+			       struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+
+	list_for_each_entry(mall_entry, &block->mall_list, list)
+		mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
+}
-- 
cgit v1.2.3


From 19f06771ca3dd8346972bc7627f9bcb7b6a8ce0b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:13:09 +0300
Subject: mlxsw: spectrum: Move flow offload binding into spectrum_flow.c

Move the code taking case of setup of flow offload into spectrum_flow.c
Do small renaming of callbacks on the way.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 173 -------------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  11 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_flow.c    | 188 ++++++++++++++++++++-
 3 files changed, 181 insertions(+), 191 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ceaf73ac2008..f78bde8bc16e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1350,178 +1350,6 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static int
-mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_flow_block *flow_block,
-			       struct tc_cls_matchall_offload *f)
-{
-	switch (f->command) {
-	case TC_CLSMATCHALL_REPLACE:
-		return mlxsw_sp_mall_replace(flow_block, f);
-	case TC_CLSMATCHALL_DESTROY:
-		mlxsw_sp_mall_destroy(flow_block, f);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int
-mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_flow_block *flow_block,
-			     struct flow_cls_offload *f)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_flow_block_mlxsw_sp(flow_block);
-
-	switch (f->command) {
-	case FLOW_CLS_REPLACE:
-		return mlxsw_sp_flower_replace(mlxsw_sp, flow_block, f);
-	case FLOW_CLS_DESTROY:
-		mlxsw_sp_flower_destroy(mlxsw_sp, flow_block, f);
-		return 0;
-	case FLOW_CLS_STATS:
-		return mlxsw_sp_flower_stats(mlxsw_sp, flow_block, f);
-	case FLOW_CLS_TMPLT_CREATE:
-		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, flow_block, f);
-	case FLOW_CLS_TMPLT_DESTROY:
-		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, flow_block, f);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlxsw_sp_setup_tc_block_cb(enum tc_setup_type type,
-				      void *type_data, void *cb_priv)
-{
-	struct mlxsw_sp_flow_block *flow_block = cb_priv;
-
-	if (mlxsw_sp_flow_block_disabled(flow_block))
-		return -EOPNOTSUPP;
-
-	switch (type) {
-	case TC_SETUP_CLSMATCHALL:
-		return mlxsw_sp_setup_tc_cls_matchall(flow_block, type_data);
-	case TC_SETUP_CLSFLOWER:
-		return mlxsw_sp_setup_tc_cls_flower(flow_block, type_data);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void mlxsw_sp_tc_block_release(void *cb_priv)
-{
-	struct mlxsw_sp_flow_block *flow_block = cb_priv;
-
-	mlxsw_sp_flow_block_destroy(flow_block);
-}
-
-static LIST_HEAD(mlxsw_sp_block_cb_list);
-
-static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-					struct flow_block_offload *f,
-					bool ingress)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_flow_block *flow_block;
-	struct flow_block_cb *block_cb;
-	bool register_block = false;
-	int err;
-
-	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_setup_tc_block_cb,
-					mlxsw_sp);
-	if (!block_cb) {
-		flow_block = mlxsw_sp_flow_block_create(mlxsw_sp, f->net);
-		if (!flow_block)
-			return -ENOMEM;
-		block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb,
-					       mlxsw_sp, flow_block,
-					       mlxsw_sp_tc_block_release);
-		if (IS_ERR(block_cb)) {
-			mlxsw_sp_flow_block_destroy(flow_block);
-			err = PTR_ERR(block_cb);
-			goto err_cb_register;
-		}
-		register_block = true;
-	} else {
-		flow_block = flow_block_cb_priv(block_cb);
-	}
-	flow_block_cb_incref(block_cb);
-	err = mlxsw_sp_flow_block_bind(mlxsw_sp, flow_block,
-				       mlxsw_sp_port, ingress, f->extack);
-	if (err)
-		goto err_block_bind;
-
-	if (ingress)
-		mlxsw_sp_port->ing_flow_block = flow_block;
-	else
-		mlxsw_sp_port->eg_flow_block = flow_block;
-
-	if (register_block) {
-		flow_block_cb_add(block_cb, f);
-		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
-	}
-
-	return 0;
-
-err_block_bind:
-	if (!flow_block_cb_decref(block_cb))
-		flow_block_cb_free(block_cb);
-err_cb_register:
-	return err;
-}
-
-static void mlxsw_sp_setup_tc_block_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
-					   struct flow_block_offload *f,
-					   bool ingress)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_flow_block *flow_block;
-	struct flow_block_cb *block_cb;
-	int err;
-
-	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_setup_tc_block_cb,
-					mlxsw_sp);
-	if (!block_cb)
-		return;
-
-	if (ingress)
-		mlxsw_sp_port->ing_flow_block = NULL;
-	else
-		mlxsw_sp_port->eg_flow_block = NULL;
-
-	flow_block = flow_block_cb_priv(block_cb);
-	err = mlxsw_sp_flow_block_unbind(mlxsw_sp, flow_block,
-					 mlxsw_sp_port, ingress);
-	if (!err && !flow_block_cb_decref(block_cb)) {
-		flow_block_cb_remove(block_cb, f);
-		list_del(&block_cb->driver_list);
-	}
-}
-
-static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
-				   struct flow_block_offload *f)
-{
-	bool ingress;
-
-	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		ingress = true;
-	else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
-	f->driver_block_list = &mlxsw_sp_block_cb_list;
-
-	switch (f->command) {
-	case FLOW_BLOCK_BIND:
-		return mlxsw_sp_setup_tc_block_bind(mlxsw_sp_port, f, ingress);
-	case FLOW_BLOCK_UNBIND:
-		mlxsw_sp_setup_tc_block_unbind(mlxsw_sp_port, f, ingress);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			     void *type_data)
 {
@@ -1545,7 +1373,6 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-
 static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 57d320728914..a12ca673c224 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -708,15 +708,8 @@ mlxsw_sp_flow_block_is_mixed_bound(const struct mlxsw_sp_flow_block *block)
 struct mlxsw_sp_flow_block *mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp,
 						       struct net *net);
 void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block);
-int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_flow_block *block,
-			     struct mlxsw_sp_port *mlxsw_sp_port,
-			     bool ingress,
-			     struct netlink_ext_ack *extack);
-int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
-			       struct mlxsw_sp_flow_block *block,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       bool ingress);
+int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct flow_block_offload *f);
 
 /* spectrum_acl.c */
 struct mlxsw_sp_acl_ruleset;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
index 51de6aca1930..ecab581ff956 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
@@ -49,11 +49,11 @@ mlxsw_sp_flow_block_ruleset_bound(const struct mlxsw_sp_flow_block *block)
 	return block->ruleset_zero;
 }
 
-int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_flow_block *block,
-			     struct mlxsw_sp_port *mlxsw_sp_port,
-			     bool ingress,
-			     struct netlink_ext_ack *extack)
+static int mlxsw_sp_flow_block_bind(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_flow_block *block,
+				    struct mlxsw_sp_port *mlxsw_sp_port,
+				    bool ingress,
+				    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_flow_block_binding *binding;
 	int err;
@@ -104,10 +104,10 @@ err_binding_alloc:
 	return err;
 }
 
-int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
-			       struct mlxsw_sp_flow_block *block,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       bool ingress)
+static int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_flow_block *block,
+				      struct mlxsw_sp_port *mlxsw_sp_port,
+				      bool ingress)
 {
 	struct mlxsw_sp_flow_block_binding *binding;
 
@@ -131,3 +131,173 @@ int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
 
 	return 0;
 }
+
+static int mlxsw_sp_flow_block_mall_cb(struct mlxsw_sp_flow_block *flow_block,
+				       struct tc_cls_matchall_offload *f)
+{
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return mlxsw_sp_mall_replace(flow_block, f);
+	case TC_CLSMATCHALL_DESTROY:
+		mlxsw_sp_mall_destroy(flow_block, f);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlxsw_sp_flow_block_flower_cb(struct mlxsw_sp_flow_block *flow_block,
+					 struct flow_cls_offload *f)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_flow_block_mlxsw_sp(flow_block);
+
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return mlxsw_sp_flower_replace(mlxsw_sp, flow_block, f);
+	case FLOW_CLS_DESTROY:
+		mlxsw_sp_flower_destroy(mlxsw_sp, flow_block, f);
+		return 0;
+	case FLOW_CLS_STATS:
+		return mlxsw_sp_flower_stats(mlxsw_sp, flow_block, f);
+	case FLOW_CLS_TMPLT_CREATE:
+		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, flow_block, f);
+	case FLOW_CLS_TMPLT_DESTROY:
+		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, flow_block, f);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlxsw_sp_flow_block_cb(enum tc_setup_type type,
+				  void *type_data, void *cb_priv)
+{
+	struct mlxsw_sp_flow_block *flow_block = cb_priv;
+
+	if (mlxsw_sp_flow_block_disabled(flow_block))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSMATCHALL:
+		return mlxsw_sp_flow_block_mall_cb(flow_block, type_data);
+	case TC_SETUP_CLSFLOWER:
+		return mlxsw_sp_flow_block_flower_cb(flow_block, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void mlxsw_sp_tc_block_release(void *cb_priv)
+{
+	struct mlxsw_sp_flow_block *flow_block = cb_priv;
+
+	mlxsw_sp_flow_block_destroy(flow_block);
+}
+
+static LIST_HEAD(mlxsw_sp_block_cb_list);
+
+static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port,
+					struct flow_block_offload *f,
+					bool ingress)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_flow_block *flow_block;
+	struct flow_block_cb *block_cb;
+	bool register_block = false;
+	int err;
+
+	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_flow_block_cb,
+					mlxsw_sp);
+	if (!block_cb) {
+		flow_block = mlxsw_sp_flow_block_create(mlxsw_sp, f->net);
+		if (!flow_block)
+			return -ENOMEM;
+		block_cb = flow_block_cb_alloc(mlxsw_sp_flow_block_cb,
+					       mlxsw_sp, flow_block,
+					       mlxsw_sp_tc_block_release);
+		if (IS_ERR(block_cb)) {
+			mlxsw_sp_flow_block_destroy(flow_block);
+			err = PTR_ERR(block_cb);
+			goto err_cb_register;
+		}
+		register_block = true;
+	} else {
+		flow_block = flow_block_cb_priv(block_cb);
+	}
+	flow_block_cb_incref(block_cb);
+	err = mlxsw_sp_flow_block_bind(mlxsw_sp, flow_block,
+				       mlxsw_sp_port, ingress, f->extack);
+	if (err)
+		goto err_block_bind;
+
+	if (ingress)
+		mlxsw_sp_port->ing_flow_block = flow_block;
+	else
+		mlxsw_sp_port->eg_flow_block = flow_block;
+
+	if (register_block) {
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
+	}
+
+	return 0;
+
+err_block_bind:
+	if (!flow_block_cb_decref(block_cb))
+		flow_block_cb_free(block_cb);
+err_cb_register:
+	return err;
+}
+
+static void mlxsw_sp_setup_tc_block_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
+					   struct flow_block_offload *f,
+					   bool ingress)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_flow_block *flow_block;
+	struct flow_block_cb *block_cb;
+	int err;
+
+	block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_flow_block_cb,
+					mlxsw_sp);
+	if (!block_cb)
+		return;
+
+	if (ingress)
+		mlxsw_sp_port->ing_flow_block = NULL;
+	else
+		mlxsw_sp_port->eg_flow_block = NULL;
+
+	flow_block = flow_block_cb_priv(block_cb);
+	err = mlxsw_sp_flow_block_unbind(mlxsw_sp, flow_block,
+					 mlxsw_sp_port, ingress);
+	if (!err && !flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+	}
+}
+
+int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct flow_block_offload *f)
+{
+	bool ingress;
+
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		ingress = true;
+	else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		ingress = false;
+	else
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = &mlxsw_sp_block_cb_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		return mlxsw_sp_setup_tc_block_bind(mlxsw_sp_port, f, ingress);
+	case FLOW_BLOCK_UNBIND:
+		mlxsw_sp_setup_tc_block_unbind(mlxsw_sp_port, f, ingress);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
-- 
cgit v1.2.3


From 0c2006b29e5f62784c70209e71da7876267e0e2d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 27 Apr 2020 21:07:00 +0200
Subject: r8169: improve error message if no dedicated PHY driver is found

There's a number of consumer mainboards where the BIOS leaves the PHY
in a state that it's reporting an invalid PHY ID. To detect such cases
add the PHY ID to the error message if no dedicated PHY driver is found.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index f70e36c20431..68d5255568a5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5197,7 +5197,8 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 		/* Most chip versions fail with the genphy driver.
 		 * Therefore ensure that the dedicated PHY driver is loaded.
 		 */
-		dev_err(&pdev->dev, "realtek.ko not loaded, maybe it needs to be added to initramfs?\n");
+		dev_err(&pdev->dev, "no dedicated PHY driver found for PHY ID 0x%08x, maybe realtek.ko needs to be added to initramfs?\n",
+			tp->phydev->phy_id);
 		return -EUNATCH;
 	}
 
-- 
cgit v1.2.3


From 2ac757e4152e3322a04a6dfb3d1fa010d3521abf Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 09:33:43 +0000
Subject: net: ethernet: ti: fix return value check in
 k3_cppi_desc_pool_create_name()

In case of error, the function gen_pool_create() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check should be
replaced with NULL test.

Fixes: 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/k3-cppi-desc-pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
index ad7cfc1316ce..38cc12f9f133 100644
--- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
+++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
@@ -64,8 +64,8 @@ k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
 		return ERR_PTR(-ENOMEM);
 
 	pool->gen_pool = gen_pool_create(ilog2(pool->desc_size), -1);
-	if (IS_ERR(pool->gen_pool)) {
-		ret = PTR_ERR(pool->gen_pool);
+	if (!pool->gen_pool) {
+		ret = -ENOMEM;
 		dev_err(pool->dev, "pool create failed %d\n", ret);
 		kfree_const(pool_name);
 		goto gen_pool_create_fail;
-- 
cgit v1.2.3


From d65dbedfd298344747033f17c1efd2afc8082bc7 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 24 Apr 2020 12:45:02 -0700
Subject: net/mlx5: Add support for COPY steering action

Add COPY type to modify_header action. IPsec feature is the first
feature that needs COPY steering action.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c                          | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c         | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c            | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c       | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c           | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c   | 2 +-
 include/linux/mlx5/mlx5_ifc.h                              | 8 ++++----
 8 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 862b7bf3e646..69cb7e6e8955 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -427,7 +427,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER)(
 
 	num_actions = uverbs_attr_ptr_get_array_size(
 		attrs, MLX5_IB_ATTR_CREATE_MODIFY_HEADER_ACTIONS_PRM,
-		MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto));
+		MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto));
 	if (num_actions < 0)
 		return num_actions;
 
@@ -648,7 +648,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 			UA_MANDATORY),
 	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_CREATE_MODIFY_HEADER_ACTIONS_PRM,
 			   UVERBS_ATTR_MIN_SIZE(MLX5_UN_SZ_BYTES(
-				   set_action_in_add_action_in_auto)),
+				   set_add_copy_action_in_auto)),
 			   UA_MANDATORY,
 			   UA_ALLOC_AND_COPY),
 	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_CREATE_MODIFY_HEADER_FT_TYPE,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index ad3e3a65d403..91464f70a3fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -385,7 +385,7 @@ mlx5_tc_ct_entry_create_nat(struct mlx5_tc_ct_priv *ct_priv,
 	char *modact;
 	int err, i;
 
-	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+	action_size = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto);
 
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 88c0e460e995..12c5ca5b93ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -61,7 +61,7 @@
 #include "lib/geneve.h"
 #include "diag/en_tc_tracepoint.h"
 
-#define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)
+#define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)
 
 struct mlx5_nic_flow_attr {
 	u32 action;
@@ -2660,7 +2660,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	set_vals = &hdrs[0].vals;
 	add_vals = &hdrs[1].vals;
 
-	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+	action_size = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto);
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		bool skip;
@@ -2793,7 +2793,7 @@ int alloc_mod_hdr_actions(struct mlx5_core_dev *mdev,
 	if (mod_hdr_acts->num_actions < mod_hdr_acts->max_actions)
 		return 0;
 
-	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+	action_size = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto);
 
 	max_hw_actions = mlx5e_flow_namespace_max_modify_action(mdev,
 								namespace);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c
index 029001040737..d5bf908dfecd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c
@@ -274,7 +274,7 @@ mlx5_esw_chains_destroy_fdb_table(struct mlx5_eswitch *esw,
 static int
 create_fdb_chain_restore(struct fdb_chain *fdb_chain)
 {
-	char modact[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)];
+	char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)];
 	struct mlx5_eswitch *esw = fdb_chain->esw;
 	struct mlx5_modify_hdr *mod_hdr;
 	u32 index;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index dc098bb58973..703f307c5967 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1490,7 +1490,7 @@ static void esw_destroy_restore_table(struct mlx5_eswitch *esw)
 
 static int esw_create_restore_table(struct mlx5_eswitch *esw)
 {
-	u8 modact[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+	u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1900,7 +1900,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
 static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 						     struct mlx5_vport *vport)
 {
-	u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_flow_act flow_act = {};
 	int err = 0;
 	u32 key;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 304d1e4f0541..1a8e826ac86b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -791,7 +791,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		return -EOPNOTSUPP;
 	}
 
-	actions_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * num_actions;
+	actions_size = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) * num_actions;
 	inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + actions_size;
 
 	in = kzalloc(inlen, GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 3b3f5b9d4f95..8887b2440c7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -576,7 +576,7 @@ static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 	struct mlx5dr_action *action;
 	size_t actions_sz;
 
-	actions_sz = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) *
+	actions_sz = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) *
 		num_actions;
 	action = mlx5dr_action_create_modify_header(dr_domain, 0,
 						    actions_sz,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6fa24918eade..3ad2c51ccde9 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5670,9 +5670,9 @@ struct mlx5_ifc_copy_action_in_bits {
 	u8         reserved_at_38[0x8];
 };
 
-union mlx5_ifc_set_action_in_add_action_in_auto_bits {
-	struct mlx5_ifc_set_action_in_bits set_action_in;
-	struct mlx5_ifc_add_action_in_bits add_action_in;
+union mlx5_ifc_set_add_copy_action_in_auto_bits {
+	struct mlx5_ifc_set_action_in_bits  set_action_in;
+	struct mlx5_ifc_add_action_in_bits  add_action_in;
 	struct mlx5_ifc_copy_action_in_bits copy_action_in;
 	u8         reserved_at_0[0x40];
 };
@@ -5746,7 +5746,7 @@ struct mlx5_ifc_alloc_modify_header_context_in_bits {
 	u8         reserved_at_68[0x10];
 	u8         num_of_actions[0x8];
 
-	union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0];
+	union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0];
 };
 
 struct mlx5_ifc_dealloc_modify_header_context_out_bits {
-- 
cgit v1.2.3


From dff8e2d15283dd92582ddeec25ca86e4cf2618c7 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Fri, 24 Apr 2020 12:45:04 -0700
Subject: net/mlx5: Use aligned variable while allocating ICM memory

The alignment value is part of the input structure, so use it and spare
extra memory allocation when is not needed.
Now, using the new ability when allocating icm for Direct-Rule
insertion.
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c   | 15 ++++--
 .../mellanox/mlx5/core/steering/dr_icm_pool.c      | 53 ++++++++++------------
 include/linux/mlx5/driver.h                        |  3 +-
 4 files changed, 38 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f10675213115..65e0e24d463b 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2444,7 +2444,7 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
 	act_size = roundup_pow_of_two(act_size);
 
 	dm->size = act_size;
-	err = mlx5_dm_sw_icm_alloc(dev, type, act_size,
+	err = mlx5_dm_sw_icm_alloc(dev, type, act_size, attr->alignment,
 				   to_mucontext(ctx)->devx_uid, &dm->dev_addr,
 				   &dm->icm_dm.obj_id);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
index 6cbccba56f70..3d5e57ff558c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c
@@ -90,7 +90,8 @@ void mlx5_dm_cleanup(struct mlx5_core_dev *dev)
 }
 
 int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
-			 u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id)
+			 u64 length, u32 log_alignment, u16 uid,
+			 phys_addr_t *addr, u32 *obj_id)
 {
 	u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
@@ -99,6 +100,7 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 	unsigned long *block_map;
 	u64 icm_start_addr;
 	u32 log_icm_size;
+	u64 align_mask;
 	u32 max_blocks;
 	u64 block_idx;
 	void *sw_icm;
@@ -136,11 +138,14 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 		return -EOPNOTSUPP;
 
 	max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
+
+	if (log_alignment < MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
+		log_alignment = MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+	align_mask = BIT(log_alignment - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) - 1;
+
 	spin_lock(&dm->lock);
-	block_idx = bitmap_find_next_zero_area(block_map,
-					       max_blocks,
-					       0,
-					       num_blocks, 0);
+	block_idx = bitmap_find_next_zero_area(block_map, max_blocks, 0,
+					       num_blocks, align_mask);
 
 	if (block_idx < max_blocks)
 		bitmap_set(block_map,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
index 30d2d7376f56..cc33515b9aba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
@@ -95,13 +95,12 @@ static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev,
 }
 
 static struct mlx5dr_icm_mr *
-dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
-		      enum mlx5_sw_icm_type type,
-		      size_t align_base)
+dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool)
 {
 	struct mlx5_core_dev *mdev = pool->dmn->mdev;
+	enum mlx5_sw_icm_type dm_type;
 	struct mlx5dr_icm_mr *icm_mr;
-	size_t align_diff;
+	size_t log_align_base;
 	int err;
 
 	icm_mr = kvzalloc(sizeof(*icm_mr), GFP_KERNEL);
@@ -111,14 +110,22 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
 	icm_mr->pool = pool;
 	INIT_LIST_HEAD(&icm_mr->mr_list);
 
-	icm_mr->dm.type = type;
-
-	/* 2^log_biggest_table * entry-size * double-for-alignment */
 	icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
-							       pool->icm_type) * 2;
+							       pool->icm_type);
+
+	if (pool->icm_type == DR_ICM_TYPE_STE) {
+		dm_type = MLX5_SW_ICM_TYPE_STEERING;
+		log_align_base = ilog2(icm_mr->dm.length);
+	} else {
+		dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY;
+		/* Align base is 64B */
+		log_align_base = ilog2(DR_ICM_MODIFY_HDR_ALIGN_BASE);
+	}
+	icm_mr->dm.type = dm_type;
 
-	err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
-				   &icm_mr->dm.addr, &icm_mr->dm.obj_id);
+	err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length,
+				   log_align_base, 0, &icm_mr->dm.addr,
+				   &icm_mr->dm.obj_id);
 	if (err) {
 		mlx5dr_err(pool->dmn, "Failed to allocate SW ICM memory, err (%d)\n", err);
 		goto free_icm_mr;
@@ -137,15 +144,18 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
 
 	icm_mr->icm_start_addr = icm_mr->dm.addr;
 
-	/* align_base is always a power of 2 */
-	align_diff = icm_mr->icm_start_addr & (align_base - 1);
-	if (align_diff)
-		icm_mr->used_length = align_base - align_diff;
+	if (icm_mr->icm_start_addr & (BIT(log_align_base) - 1)) {
+		mlx5dr_err(pool->dmn, "Failed to get Aligned ICM mem (asked: %zu)\n",
+			   log_align_base);
+		goto free_mkey;
+	}
 
 	list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list);
 
 	return icm_mr;
 
+free_mkey:
+	mlx5_core_destroy_mkey(mdev, &icm_mr->mkey);
 free_dm:
 	mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
 			       icm_mr->dm.addr, icm_mr->dm.obj_id);
@@ -200,24 +210,11 @@ static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket)
 	struct mlx5dr_icm_pool *pool = bucket->pool;
 	struct mlx5dr_icm_mr *icm_mr = NULL;
 	struct mlx5dr_icm_chunk *chunk;
-	enum mlx5_sw_icm_type dm_type;
-	size_t align_base;
 	int i, err = 0;
 
 	mr_req_size = bucket->num_of_entries * bucket->entry_size;
 	mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
 							 pool->icm_type);
-
-	if (pool->icm_type == DR_ICM_TYPE_STE) {
-		dm_type = MLX5_SW_ICM_TYPE_STEERING;
-		/* Align base is the biggest chunk size / row size */
-		align_base = mr_row_size;
-	} else {
-		dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY;
-		/* Align base is 64B */
-		align_base = DR_ICM_MODIFY_HDR_ALIGN_BASE;
-	}
-
 	mutex_lock(&pool->mr_mutex);
 	if (!list_empty(&pool->icm_mr_list)) {
 		icm_mr = list_last_entry(&pool->icm_mr_list,
@@ -228,7 +225,7 @@ static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket)
 	}
 
 	if (!icm_mr || mr_free_size < mr_row_size) {
-		icm_mr = dr_icm_pool_mr_create(pool, dm_type, align_base);
+		icm_mr = dr_icm_pool_mr_create(pool);
 		if (!icm_mr) {
 			err = -ENOMEM;
 			goto out_err;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b60e5ab7906b..b46537a81703 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1080,7 +1080,8 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
-			 u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id);
+			 u64 length, u32 log_alignment, u16 uid,
+			 phys_addr_t *addr, u32 *obj_id);
 int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
-- 
cgit v1.2.3


From 244faedfd4d8e8c8e9f3c628d29bb74196b49743 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Fri, 24 Apr 2020 12:45:05 -0700
Subject: net/mlx5: Refactor imm_inval_pkey field in cqe struct

The imm_inval_pkey field can hold four different types of data,
depends on the usage, the data could be one of the below:
- Immediate field of the received message
- Invalidate rkey
- Pkey of the packet
- Flow table metadata

Current implementation doesn't reflect the intended usage of the
field at usage time.

Reflect the different types by replace this field with a union,
modify code where this field is used to reflect its intended
usage.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cq.c                 | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 include/linux/mlx5/device.h                     | 7 ++++++-
 3 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 32c05730dfe9..0c18cb6a2f14 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -202,7 +202,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	case MLX5_CQE_RESP_WR_IMM:
 		wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
 		wc->wc_flags	= IB_WC_WITH_IMM;
-		wc->ex.imm_data = cqe->imm_inval_pkey;
+		wc->ex.imm_data = cqe->immediate;
 		break;
 	case MLX5_CQE_RESP_SEND:
 		wc->opcode   = IB_WC_RECV;
@@ -214,12 +214,12 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	case MLX5_CQE_RESP_SEND_IMM:
 		wc->opcode	= IB_WC_RECV;
 		wc->wc_flags	= IB_WC_WITH_IMM;
-		wc->ex.imm_data = cqe->imm_inval_pkey;
+		wc->ex.imm_data = cqe->immediate;
 		break;
 	case MLX5_CQE_RESP_SEND_INV:
 		wc->opcode	= IB_WC_RECV;
 		wc->wc_flags	= IB_WC_WITH_INVALIDATE;
-		wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey);
+		wc->ex.invalidate_rkey = be32_to_cpu(cqe->inval_rkey);
 		break;
 	}
 	wc->src_qp	   = be32_to_cpu(cqe->flags_rqpn) & 0xffffff;
@@ -227,7 +227,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
 	wc->wc_flags |= g ? IB_WC_GRH : 0;
 	if (unlikely(is_qp1(qp->ibqp.qp_type))) {
-		u16 pkey = be32_to_cpu(cqe->imm_inval_pkey) & 0xffff;
+		u16 pkey = be32_to_cpu(cqe->pkey) & 0xffff;
 
 		ib_find_cached_pkey(&dev->ib_dev, qp->port, pkey,
 				    &wc->pkey_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 12c5ca5b93ca..5b632434866f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4891,7 +4891,7 @@ bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe,
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
 	if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
 		reg_c0 = 0;
-	reg_c1 = be32_to_cpu(cqe->imm_inval_pkey);
+	reg_c1 = be32_to_cpu(cqe->ft_metadata);
 
 	if (!reg_c0)
 		return true;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 7b57877e501e..746e17473d72 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -767,7 +767,12 @@ struct mlx5_cqe64 {
 	u8		l4_l3_hdr_type;
 	__be16		vlan_info;
 	__be32		srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */
-	__be32		imm_inval_pkey;
+	union {
+		__be32 immediate;
+		__be32 inval_rkey;
+		__be32 pkey;
+		__be32 ft_metadata;
+	};
 	u8		rsvd40[4];
 	__be32		byte_cnt;
 	__be32		timestamp_h;
-- 
cgit v1.2.3


From 88fb831f773e6c51ec528eacb524f00f518f7e54 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Tue, 28 Apr 2020 10:42:22 -0700
Subject: dpaa2-eth: Use proper division helper in dpaa2_dbg_ch_show

When building arm32 allmodconfig:

ERROR: modpost: "__aeabi_uldivmod"
[drivers/net/ethernet/freescale/dpaa2/fsl-dpaa2-eth.ko] undefined!

frames and cdan are both of type __u64 (unsigned long long) so we need
to use div64_u64 to avoid this issues.

Fixes: 460fd830dd9d ("dpaa2-eth: add channel stat to debugfs")
Link: https://github.com/ClangBuiltLinux/linux/issues/1012
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Reported-by: kernelci.org bot <bot@kernelci.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
index 80291afff3ea..0a31e4268dfb 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -139,7 +139,7 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
 			   ch->stats.dequeue_portal_busy,
 			   ch->stats.frames,
 			   ch->stats.cdan,
-			   ch->stats.frames / ch->stats.cdan,
+			   div64_u64(ch->stats.frames, ch->stats.cdan),
 			   ch->buf_count);
 	}
 
-- 
cgit v1.2.3


From 790ab249b55d75fdb427b92f81964cd7cb525eec Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 28 Apr 2020 19:58:33 +0200
Subject: net: ethernet: fec: Prevent MII event after MII_SPEED write

The change to polled IO for MDIO completion assumes that MII events
are only generated for MDIO transactions. However on some SoCs writing
to the MII_SPEED register can also trigger an MII event. As a result,
the next MDIO read has a pending MII event, and immediately reads the
data registers before it contains useful data. When the read does
complete, another MII event is posted, which results in the next read
also going wrong, and the cycle continues.

By writing 0 to the MII_DATA register before writing to the speed
register, this MII event for the MII_SPEED is suppressed, and polled
IO works as expected.

Fixes: 29ae6bd1b0d8 ("net: ethernet: fec: Replace interrupt driven MDIO with polled IO")
Reported-by: Andy Duan <fugang.duan@nxp.com>
Suggested-by: Andy Duan <fugang.duan@nxp.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1ae075a246a3..aa5e744ec098 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -996,6 +996,9 @@ fec_restart(struct net_device *ndev)
 		writel(0x0, fep->hwp + FEC_X_CNTRL);
 	}
 
+	/* Prevent an MII event being report when changing speed */
+	writel(0, fep->hwp + FEC_MII_DATA);
+
 	/* Set MII speed */
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
@@ -1182,6 +1185,10 @@ fec_stop(struct net_device *ndev)
 		writel(val, fep->hwp + FEC_ECNTRL);
 		fec_enet_stop_mode(fep, true);
 	}
+
+	/* Prevent an MII event being report when changing speed */
+	writel(0, fep->hwp + FEC_MII_DATA);
+
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 	/* We have to keep ENET enabled to have MII interrupt stay working */
@@ -2142,6 +2149,16 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	if (suppress_preamble)
 		fep->phy_speed |= BIT(7);
 
+	/* Clear MMFR to avoid to generate MII event by writing MSCR.
+	 * MII event generation condition:
+	 * - writing MSCR:
+	 *	- mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
+	 *	  mscr_reg_data_in[7:0] != 0
+	 * - writing MMFR:
+	 *	- mscr[7:0]_not_zero
+	 */
+	writel(0, fep->hwp + FEC_MII_DATA);
+
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 	/* Clear any pending transaction complete indication */
-- 
cgit v1.2.3


From cb10228d234c49e2035bfce7bdb42c29e1049c5c Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Wed, 29 Apr 2020 11:46:24 +0800
Subject: net: hns3: adds support for reading module eeprom info

This patch adds support for reading the optical module eeprom
info via "ethtool -m".

Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |   4 +
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c |  75 +++++++++++++++
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h |  15 +++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 102 +++++++++++++++++++++
 4 files changed, 196 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 6291aa9f06b0..5602bf226687 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -374,6 +374,8 @@ struct hnae3_ae_dev {
  *   Set the max tx rate of specified vf.
  * set_vf_mac
  *   Configure the default MAC for specified VF
+ * get_module_eeprom
+ *   Get the optical module eeprom info.
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -548,6 +550,8 @@ struct hnae3_ae_ops {
 	int (*set_vf_rate)(struct hnae3_handle *handle, int vf,
 			   int min_tx_rate, int max_tx_rate, bool force);
 	int (*set_vf_mac)(struct hnae3_handle *handle, int vf, u8 *p);
+	int (*get_module_eeprom)(struct hnae3_handle *handle, u32 offset,
+				 u32 len, u8 *data);
 };
 
 struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 4d9c85f049dc..1a105f2f87a4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -4,6 +4,7 @@
 #include <linux/etherdevice.h>
 #include <linux/string.h>
 #include <linux/phy.h>
+#include <linux/sfp.h>
 
 #include "hns3_enet.h"
 
@@ -12,6 +13,11 @@ struct hns3_stats {
 	int stats_offset;
 };
 
+struct hns3_sfp_type {
+	u8 type;
+	u8 ext_type;
+};
+
 /* tqp related stats */
 #define HNS3_TQP_STAT(_string, _member)	{			\
 	.stats_string = _string,				\
@@ -1386,6 +1392,73 @@ static int hns3_set_fecparam(struct net_device *netdev,
 	return ops->set_fec(handle, fec_mode);
 }
 
+static int hns3_get_module_info(struct net_device *netdev,
+				struct ethtool_modinfo *modinfo)
+{
+#define HNS3_SFF_8636_V1_3 0x03
+
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	struct hns3_sfp_type sfp_type;
+	int ret;
+
+	if (handle->pdev->revision == 0x20 || !ops->get_module_eeprom)
+		return -EOPNOTSUPP;
+
+	memset(&sfp_type, 0, sizeof(sfp_type));
+	ret = ops->get_module_eeprom(handle, 0, sizeof(sfp_type) / sizeof(u8),
+				     (u8 *)&sfp_type);
+	if (ret)
+		return ret;
+
+	switch (sfp_type.type) {
+	case SFF8024_ID_SFP:
+		modinfo->type = ETH_MODULE_SFF_8472;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		break;
+	case SFF8024_ID_QSFP_8438:
+		modinfo->type = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
+		break;
+	case SFF8024_ID_QSFP_8436_8636:
+		if (sfp_type.ext_type < HNS3_SFF_8636_V1_3) {
+			modinfo->type = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
+		}
+		break;
+	case SFF8024_ID_QSFP28_8636:
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
+		break;
+	default:
+		netdev_err(netdev, "Optical module unknown: %#x\n",
+			   sfp_type.type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hns3_get_module_eeprom(struct net_device *netdev,
+				  struct ethtool_eeprom *ee, u8 *data)
+{
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+
+	if (handle->pdev->revision == 0x20 || !ops->get_module_eeprom)
+		return -EOPNOTSUPP;
+
+	if (!ee->len)
+		return -EINVAL;
+
+	memset(data, 0, ee->len);
+
+	return ops->get_module_eeprom(handle, ee->offset, ee->len, data);
+}
+
 #define HNS3_ETHTOOL_COALESCE	(ETHTOOL_COALESCE_USECS |		\
 				 ETHTOOL_COALESCE_USE_ADAPTIVE |	\
 				 ETHTOOL_COALESCE_RX_USECS_HIGH |	\
@@ -1449,6 +1522,8 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.set_msglevel = hns3_set_msglevel,
 	.get_fecparam = hns3_get_fecparam,
 	.set_fecparam = hns3_set_fecparam,
+	.get_module_info = hns3_get_module_info,
+	.get_module_eeprom = hns3_get_module_eeprom,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 90e422efe590..9a9d752aedc5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -270,6 +270,8 @@ enum hclge_opcode_type {
 	HCLGE_OPC_M7_COMPAT_CFG		= 0x701A,
 
 	/* SFP command */
+	HCLGE_OPC_GET_SFP_EEPROM	= 0x7100,
+	HCLGE_OPC_GET_SFP_EXIST		= 0x7101,
 	HCLGE_OPC_GET_SFP_INFO		= 0x7104,
 
 	/* Error INT commands */
@@ -1054,6 +1056,19 @@ struct hclge_firmware_compat_cmd {
 	u8 rsv[20];
 };
 
+#define HCLGE_SFP_INFO_CMD_NUM	6
+#define HCLGE_SFP_INFO_BD0_LEN	20
+#define HCLGE_SFP_INFO_BDX_LEN	24
+#define HCLGE_SFP_INFO_MAX_LEN \
+	(HCLGE_SFP_INFO_BD0_LEN + \
+	(HCLGE_SFP_INFO_CMD_NUM - 1) * HCLGE_SFP_INFO_BDX_LEN)
+
+struct hclge_sfp_info_bd0_cmd {
+	__le16 offset;
+	__le16 read_len;
+	u8 data[HCLGE_SFP_INFO_BD0_LEN];
+};
+
 int hclge_cmd_init(struct hclge_dev *hdev);
 static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e2fec832fdf0..71a54ddb51f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11119,6 +11119,107 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
 	}
 }
 
+static bool hclge_module_existed(struct hclge_dev *hdev)
+{
+	struct hclge_desc desc;
+	u32 existed;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GET_SFP_EXIST, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get SFP exist state, ret = %d\n", ret);
+		return false;
+	}
+
+	existed = le32_to_cpu(desc.data[0]);
+
+	return existed != 0;
+}
+
+/* need 6 bds(total 140 bytes) in one reading
+ * return the number of bytes actually read, 0 means read failed.
+ */
+static u16 hclge_get_sfp_eeprom_info(struct hclge_dev *hdev, u32 offset,
+				     u32 len, u8 *data)
+{
+	struct hclge_desc desc[HCLGE_SFP_INFO_CMD_NUM];
+	struct hclge_sfp_info_bd0_cmd *sfp_info_bd0;
+	u16 read_len;
+	u16 copy_len;
+	int ret;
+	int i;
+
+	/* setup all 6 bds to read module eeprom info. */
+	for (i = 0; i < HCLGE_SFP_INFO_CMD_NUM; i++) {
+		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_SFP_EEPROM,
+					   true);
+
+		/* bd0~bd4 need next flag */
+		if (i < HCLGE_SFP_INFO_CMD_NUM - 1)
+			desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	}
+
+	/* setup bd0, this bd contains offset and read length. */
+	sfp_info_bd0 = (struct hclge_sfp_info_bd0_cmd *)desc[0].data;
+	sfp_info_bd0->offset = cpu_to_le16((u16)offset);
+	read_len = min_t(u16, len, HCLGE_SFP_INFO_MAX_LEN);
+	sfp_info_bd0->read_len = cpu_to_le16(read_len);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, i);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get SFP eeprom info, ret = %d\n", ret);
+		return 0;
+	}
+
+	/* copy sfp info from bd0 to out buffer. */
+	copy_len = min_t(u16, len, HCLGE_SFP_INFO_BD0_LEN);
+	memcpy(data, sfp_info_bd0->data, copy_len);
+	read_len = copy_len;
+
+	/* copy sfp info from bd1~bd5 to out buffer if needed. */
+	for (i = 1; i < HCLGE_SFP_INFO_CMD_NUM; i++) {
+		if (read_len >= len)
+			return read_len;
+
+		copy_len = min_t(u16, len - read_len, HCLGE_SFP_INFO_BDX_LEN);
+		memcpy(data + read_len, desc[i].data, copy_len);
+		read_len += copy_len;
+	}
+
+	return read_len;
+}
+
+static int hclge_get_module_eeprom(struct hnae3_handle *handle, u32 offset,
+				   u32 len, u8 *data)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	u32 read_len = 0;
+	u16 data_len;
+
+	if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_FIBER)
+		return -EOPNOTSUPP;
+
+	if (!hclge_module_existed(hdev))
+		return -ENXIO;
+
+	while (read_len < len) {
+		data_len = hclge_get_sfp_eeprom_info(hdev,
+						     offset + read_len,
+						     len - read_len,
+						     data + read_len);
+		if (!data_len)
+			return -EIO;
+
+		read_len += data_len;
+	}
+
+	return 0;
+}
+
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
@@ -11211,6 +11312,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_vf_trust = hclge_set_vf_trust,
 	.set_vf_rate = hclge_set_vf_rate,
 	.set_vf_mac = hclge_set_vf_mac,
+	.get_module_eeprom = hclge_get_module_eeprom,
 };
 
 static struct hnae3_ae_algo ae_algo = {
-- 
cgit v1.2.3


From 21615efa6a69891fa287bade979d56dd68b09878 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 29 Apr 2020 12:15:42 -0700
Subject: Revert "net: ethernet: fec: Prevent MII event after MII_SPEED write"

This reverts commit 790ab249b55d75fdb427b92f81964cd7cb525eec.

This change needs more work.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index aa5e744ec098..1ae075a246a3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -996,9 +996,6 @@ fec_restart(struct net_device *ndev)
 		writel(0x0, fep->hwp + FEC_X_CNTRL);
 	}
 
-	/* Prevent an MII event being report when changing speed */
-	writel(0, fep->hwp + FEC_MII_DATA);
-
 	/* Set MII speed */
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
@@ -1185,10 +1182,6 @@ fec_stop(struct net_device *ndev)
 		writel(val, fep->hwp + FEC_ECNTRL);
 		fec_enet_stop_mode(fep, true);
 	}
-
-	/* Prevent an MII event being report when changing speed */
-	writel(0, fep->hwp + FEC_MII_DATA);
-
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 	/* We have to keep ENET enabled to have MII interrupt stay working */
@@ -2149,16 +2142,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	if (suppress_preamble)
 		fep->phy_speed |= BIT(7);
 
-	/* Clear MMFR to avoid to generate MII event by writing MSCR.
-	 * MII event generation condition:
-	 * - writing MSCR:
-	 *	- mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
-	 *	  mscr_reg_data_in[7:0] != 0
-	 * - writing MMFR:
-	 *	- mscr[7:0]_not_zero
-	 */
-	writel(0, fep->hwp + FEC_MII_DATA);
-
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 	/* Clear any pending transaction complete indication */
-- 
cgit v1.2.3


From 72f96347628e73dbb61b307f18dd19293cc6792a Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:00 -0700
Subject: net: bcmgenet: set Rx mode before starting netif

This commit explicitly calls the bcmgenet_set_rx_mode() function when
the network interface is started. This function is normally called by
ndo_set_rx_mode when the flags are changed, but apparently not when
the driver is suspended and resumed.

This change ensures that address filtering or promiscuous mode are
properly restored by the driver after the MAC may have been reset.

Fixes: b6e978e50444 ("net: bcmgenet: add suspend/resume callbacks")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 351d0282f199..eb0dd4d4800c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -65,6 +65,9 @@
 #define GENET_RDMA_REG_OFF	(priv->hw_params->rdma_offset + \
 				TOTAL_DESC * DMA_DESC_SIZE)
 
+/* Forward declarations */
+static void bcmgenet_set_rx_mode(struct net_device *dev);
+
 static inline void bcmgenet_writel(u32 value, void __iomem *offset)
 {
 	/* MIPS chips strapped for BE will automagically configure the
@@ -2793,6 +2796,7 @@ static void bcmgenet_netif_start(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	/* Start the network engine */
+	bcmgenet_set_rx_mode(dev);
 	bcmgenet_enable_rx_napi(priv);
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
-- 
cgit v1.2.3


From 6f7689057a0f10a6c967b9f2759d7a3dc948b930 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:01 -0700
Subject: net: bcmgenet: Fix WoL with password after deep sleep

Broadcom STB chips support a deep sleep mode where all register contents
are lost. Because we were stashing the MagicPacket password into some of
these registers a suspend into that deep sleep then a resumption would
not lead to being able to wake-up from MagicPacket with password again.

Fix this by keeping a software copy of the password and program it
during suspend.

Fixes: c51de7f3976b ("net: bcmgenet: add Wake-on-LAN support code")
Suggested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h     |  2 ++
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 39 ++++++++++------------
 2 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index daf8fb2c39b6..c3bfe97f2e5c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -14,6 +14,7 @@
 #include <linux/if_vlan.h>
 #include <linux/phy.h>
 #include <linux/dim.h>
+#include <linux/ethtool.h>
 
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
@@ -676,6 +677,7 @@ struct bcmgenet_priv {
 	/* WOL */
 	struct clk *clk_wol;
 	u32 wolopts;
+	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index c9a43695b182..597c0498689a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -41,18 +41,13 @@
 void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE;
 	wol->wolopts = priv->wolopts;
 	memset(wol->sopass, 0, sizeof(wol->sopass));
 
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		reg = bcmgenet_umac_readl(priv, UMAC_MPD_PW_MS);
-		put_unaligned_be16(reg, &wol->sopass[0]);
-		reg = bcmgenet_umac_readl(priv, UMAC_MPD_PW_LS);
-		put_unaligned_be32(reg, &wol->sopass[2]);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 /* ethtool function - set WOL (Wake on LAN) settings.
@@ -62,7 +57,6 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
-	u32 reg;
 
 	if (!device_can_wakeup(kdev))
 		return -ENOTSUPP;
@@ -70,17 +64,8 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts & ~(WAKE_MAGIC | WAKE_MAGICSECURE))
 		return -EINVAL;
 
-	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		bcmgenet_umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-				     UMAC_MPD_PW_MS);
-		bcmgenet_umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-				     UMAC_MPD_PW_LS);
-		reg |= MPD_PW_EN;
-	} else {
-		reg &= ~MPD_PW_EN;
-	}
-	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -120,6 +105,14 @@ static int bcmgenet_poll_wol_status(struct bcmgenet_priv *priv)
 	return retries;
 }
 
+static void bcmgenet_set_mpd_password(struct bcmgenet_priv *priv)
+{
+	bcmgenet_umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			     UMAC_MPD_PW_MS);
+	bcmgenet_umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			     UMAC_MPD_PW_LS);
+}
+
 int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
@@ -144,13 +137,17 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 	reg |= MPD_EN;
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		bcmgenet_set_mpd_password(priv);
+		reg |= MPD_PW_EN;
+	}
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
 	if (retries < 0) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-		reg &= ~MPD_EN;
+		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 		return retries;
 	}
@@ -189,7 +186,7 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 	if (!(reg & MPD_EN))
 		return;	/* already powered up so skip the rest */
-	reg &= ~MPD_EN;
+	reg &= ~(MPD_EN | MPD_PW_EN);
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	/* Disable CRC Forward */
-- 
cgit v1.2.3


From 1a1d5106c1e37321f3fe394b786d1aece56d0df5 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:02 -0700
Subject: net: bcmgenet: move clk_wol management to bcmgenet_wol

The GENET_POWER_WOL_MAGIC power up and power down code configures
the device for WoL when suspending and disables the WoL logic when
resuming. It makes sense that this code should also manage the WoL
clocking.

This commit consolidates the logic and moves it earlier in the
resume sequence.

Since the clock is now only enabled if WoL is successfully entered
the wol_active flag is introduced to track that state to keep the
clock enables and disables balanced in case a suspend is aborted.
The MPD_EN hardware bit can't be used because it can be cleared
when the MAC is reset by a deep sleep.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 19 +++++++------------
 drivers/net/ethernet/broadcom/genet/bcmgenet.h     |  3 ++-
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 14 +++++++++++---
 3 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index eb0dd4d4800c..57b8608feae1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014-2019 Broadcom
+ * Copyright (c) 2014-2020 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet: " fmt
@@ -3619,6 +3619,10 @@ static int bcmgenet_resume(struct device *d)
 	if (ret)
 		return ret;
 
+	/* From WOL-enabled suspend, switch to regular clock */
+	if (device_may_wakeup(d) && priv->wolopts)
+		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
+
 	/* If this is an internal GPHY, power it back on now, before UniMAC is
 	 * brought out of reset as absolutely no UniMAC activity is allowed
 	 */
@@ -3629,10 +3633,6 @@ static int bcmgenet_resume(struct device *d)
 
 	init_umac(priv);
 
-	/* From WOL-enabled suspend, switch to regular clock */
-	if (priv->wolopts)
-		clk_disable_unprepare(priv->clk_wol);
-
 	phy_init_hw(dev->phydev);
 
 	/* Speed settings must be restored */
@@ -3650,9 +3650,6 @@ static int bcmgenet_resume(struct device *d)
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 	}
 
-	if (priv->wolopts)
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-
 	/* Disable RX/TX DMA and flush TX queues */
 	dma_ctrl = bcmgenet_dma_disable(priv);
 
@@ -3702,12 +3699,10 @@ static int bcmgenet_suspend(struct device *d)
 		phy_suspend(dev->phydev);
 
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
-	if (device_may_wakeup(d) && priv->wolopts) {
+	if (device_may_wakeup(d) && priv->wolopts)
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
-		clk_prepare_enable(priv->clk_wol);
-	} else if (priv->internal_phy) {
+	else if (priv->internal_phy)
 		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
-	}
 
 	/* Turn off the clocks */
 	clk_disable_unprepare(priv->clk);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index c3bfe97f2e5c..a858b7305832 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2014-2017 Broadcom
+ * Copyright (c) 2014-2020 Broadcom
  */
 
 #ifndef __BCMGENET_H__
@@ -678,6 +678,7 @@ struct bcmgenet_priv {
 	struct clk *clk_wol;
 	u32 wolopts;
 	u8 sopass[SOPASS_MAX];
+	bool wol_active;
 
 	struct bcmgenet_mib_counters mib;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 597c0498689a..da45a4645b94 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014-2017 Broadcom
+ * Copyright (c) 2014-2020 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet_wol: " fmt
@@ -155,6 +155,9 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	netif_dbg(priv, wol, dev, "MPD WOL-ready status set after %d msec\n",
 		  retries);
 
+	clk_prepare_enable(priv->clk_wol);
+	priv->wol_active = 1;
+
 	/* Enable CRC forward */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	priv->crc_fwd_en = 1;
@@ -183,9 +186,14 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 		return;
 	}
 
+	if (!priv->wol_active)
+		return;	/* failed to suspend so skip the rest */
+
+	priv->wol_active = 0;
+	clk_disable_unprepare(priv->clk_wol);
+
+	/* Disable Magic Packet Detection */
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-	if (!(reg & MPD_EN))
-		return;	/* already powered up so skip the rest */
 	reg &= ~(MPD_EN | MPD_PW_EN);
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
-- 
cgit v1.2.3


From 14da1510fedc2d72ca81344a0f62939e0a1bc648 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:03 -0700
Subject: Revert "net: bcmgenet: remove unused function in bcmgenet.c"

This reverts commit e2072600a24161b7ddcfb26814f69f5fbc8ef85a.

This commit restores the previous implementation of Hardware Filter
Block functions to the file for use in subsequent commits.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 122 +++++++++++++++++++++++++
 1 file changed, 122 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 57b8608feae1..b37ef05c5083 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2759,6 +2759,128 @@ static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
 	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
 }
 
+static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv,
+					   u32 f_index)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	return !!(reg & (1 << (f_index % 32)));
+}
+
+static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	reg |= (1 << (f_index % 32));
+	bcmgenet_hfb_reg_writel(priv, reg, offset);
+}
+
+static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
+						     u32 f_index, u32 rx_queue)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = f_index / 8;
+	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
+	reg &= ~(0xF << (4 * (f_index % 8)));
+	reg |= ((rx_queue & 0xF) << (4 * (f_index % 8)));
+	bcmgenet_rdma_writel(priv, reg, DMA_INDEX2RING_0 + offset);
+}
+
+static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
+					   u32 f_index, u32 f_length)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_LEN_V3PLUS +
+		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
+		 sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	reg &= ~(0xFF << (8 * (f_index % 4)));
+	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
+	bcmgenet_hfb_reg_writel(priv, reg, offset);
+}
+
+static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv)
+{
+	u32 f_index;
+
+	for (f_index = 0; f_index < priv->hw_params->hfb_filter_cnt; f_index++)
+		if (!bcmgenet_hfb_is_filter_enabled(priv, f_index))
+			return f_index;
+
+	return -ENOMEM;
+}
+
+/* bcmgenet_hfb_add_filter
+ *
+ * Add new filter to Hardware Filter Block to match and direct Rx traffic to
+ * desired Rx queue.
+ *
+ * f_data is an array of unsigned 32-bit integers where each 32-bit integer
+ * provides filter data for 2 bytes (4 nibbles) of Rx frame:
+ *
+ * bits 31:20 - unused
+ * bit  19    - nibble 0 match enable
+ * bit  18    - nibble 1 match enable
+ * bit  17    - nibble 2 match enable
+ * bit  16    - nibble 3 match enable
+ * bits 15:12 - nibble 0 data
+ * bits 11:8  - nibble 1 data
+ * bits 7:4   - nibble 2 data
+ * bits 3:0   - nibble 3 data
+ *
+ * Example:
+ * In order to match:
+ * - Ethernet frame type = 0x0800 (IP)
+ * - IP version field = 4
+ * - IP protocol field = 0x11 (UDP)
+ *
+ * The following filter is needed:
+ * u32 hfb_filter_ipv4_udp[] = {
+ *   Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ *   Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000,
+ *   Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011,
+ * };
+ *
+ * To add the filter to HFB and direct the traffic to Rx queue 0, call:
+ * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp,
+ *                         ARRAY_SIZE(hfb_filter_ipv4_udp), 0);
+ */
+int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
+			    u32 f_length, u32 rx_queue)
+{
+	int f_index;
+	u32 i;
+
+	f_index = bcmgenet_hfb_find_unused_filter(priv);
+	if (f_index < 0)
+		return -ENOMEM;
+
+	if (f_length > priv->hw_params->hfb_filter_size)
+		return -EINVAL;
+
+	for (i = 0; i < f_length; i++)
+		bcmgenet_hfb_writel(priv, f_data[i],
+			(f_index * priv->hw_params->hfb_filter_size + i) *
+			sizeof(u32));
+
+	bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length);
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue);
+	bcmgenet_hfb_enable_filter(priv, f_index);
+	bcmgenet_hfb_reg_writel(priv, 0x1, HFB_CTRL);
+
+	return 0;
+}
+
 /* bcmgenet_hfb_clear
  *
  * Clear Hardware Filter Block and disable all filtering.
-- 
cgit v1.2.3


From 854295d03ca04461f275d723289a5886e6827498 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:04 -0700
Subject: net: bcmgenet: code movement

The Hardware Filter Block code will be used by ethtool functions
when defining flow types so this commit moves the functions in the
file to prevent the need for prototype declarations.

This is broken out to facilitate review.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 308 ++++++++++++-------------
 1 file changed, 154 insertions(+), 154 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b37ef05c5083..ad41944d2cc0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -459,6 +459,160 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
 			genet_dma_ring_regs[r]);
 }
 
+static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv,
+					   u32 f_index)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	return !!(reg & (1 << (f_index % 32)));
+}
+
+static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	reg |= (1 << (f_index % 32));
+	bcmgenet_hfb_reg_writel(priv, reg, offset);
+}
+
+static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
+						     u32 f_index, u32 rx_queue)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = f_index / 8;
+	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
+	reg &= ~(0xF << (4 * (f_index % 8)));
+	reg |= ((rx_queue & 0xF) << (4 * (f_index % 8)));
+	bcmgenet_rdma_writel(priv, reg, DMA_INDEX2RING_0 + offset);
+}
+
+static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
+					   u32 f_index, u32 f_length)
+{
+	u32 offset;
+	u32 reg;
+
+	offset = HFB_FLT_LEN_V3PLUS +
+		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
+		 sizeof(u32);
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	reg &= ~(0xFF << (8 * (f_index % 4)));
+	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
+	bcmgenet_hfb_reg_writel(priv, reg, offset);
+}
+
+static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv)
+{
+	u32 f_index;
+
+	for (f_index = 0; f_index < priv->hw_params->hfb_filter_cnt; f_index++)
+		if (!bcmgenet_hfb_is_filter_enabled(priv, f_index))
+			return f_index;
+
+	return -ENOMEM;
+}
+
+/* bcmgenet_hfb_add_filter
+ *
+ * Add new filter to Hardware Filter Block to match and direct Rx traffic to
+ * desired Rx queue.
+ *
+ * f_data is an array of unsigned 32-bit integers where each 32-bit integer
+ * provides filter data for 2 bytes (4 nibbles) of Rx frame:
+ *
+ * bits 31:20 - unused
+ * bit  19    - nibble 0 match enable
+ * bit  18    - nibble 1 match enable
+ * bit  17    - nibble 2 match enable
+ * bit  16    - nibble 3 match enable
+ * bits 15:12 - nibble 0 data
+ * bits 11:8  - nibble 1 data
+ * bits 7:4   - nibble 2 data
+ * bits 3:0   - nibble 3 data
+ *
+ * Example:
+ * In order to match:
+ * - Ethernet frame type = 0x0800 (IP)
+ * - IP version field = 4
+ * - IP protocol field = 0x11 (UDP)
+ *
+ * The following filter is needed:
+ * u32 hfb_filter_ipv4_udp[] = {
+ *   Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+ *   Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000,
+ *   Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011,
+ * };
+ *
+ * To add the filter to HFB and direct the traffic to Rx queue 0, call:
+ * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp,
+ *                         ARRAY_SIZE(hfb_filter_ipv4_udp), 0);
+ */
+int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
+			    u32 f_length, u32 rx_queue)
+{
+	int f_index;
+	u32 i;
+
+	f_index = bcmgenet_hfb_find_unused_filter(priv);
+	if (f_index < 0)
+		return -ENOMEM;
+
+	if (f_length > priv->hw_params->hfb_filter_size)
+		return -EINVAL;
+
+	for (i = 0; i < f_length; i++)
+		bcmgenet_hfb_writel(priv, f_data[i],
+			(f_index * priv->hw_params->hfb_filter_size + i) *
+			sizeof(u32));
+
+	bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length);
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue);
+	bcmgenet_hfb_enable_filter(priv, f_index);
+	bcmgenet_hfb_reg_writel(priv, 0x1, HFB_CTRL);
+
+	return 0;
+}
+
+/* bcmgenet_hfb_clear
+ *
+ * Clear Hardware Filter Block and disable all filtering.
+ */
+static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
+{
+	u32 i;
+
+	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
+	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
+	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);
+
+	for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
+		bcmgenet_rdma_writel(priv, 0x0, i);
+
+	for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
+		bcmgenet_hfb_reg_writel(priv, 0x0,
+					HFB_FLT_LEN_V3PLUS + i * sizeof(u32));
+
+	for (i = 0; i < priv->hw_params->hfb_filter_cnt *
+			priv->hw_params->hfb_filter_size; i++)
+		bcmgenet_hfb_writel(priv, 0x0, i * sizeof(u32));
+}
+
+static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
+{
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		return;
+
+	bcmgenet_hfb_clear(priv);
+}
+
 static int bcmgenet_begin(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -2759,160 +2913,6 @@ static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
 	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
 }
 
-static bool bcmgenet_hfb_is_filter_enabled(struct bcmgenet_priv *priv,
-					   u32 f_index)
-{
-	u32 offset;
-	u32 reg;
-
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	return !!(reg & (1 << (f_index % 32)));
-}
-
-static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
-{
-	u32 offset;
-	u32 reg;
-
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg |= (1 << (f_index % 32));
-	bcmgenet_hfb_reg_writel(priv, reg, offset);
-}
-
-static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
-						     u32 f_index, u32 rx_queue)
-{
-	u32 offset;
-	u32 reg;
-
-	offset = f_index / 8;
-	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
-	reg &= ~(0xF << (4 * (f_index % 8)));
-	reg |= ((rx_queue & 0xF) << (4 * (f_index % 8)));
-	bcmgenet_rdma_writel(priv, reg, DMA_INDEX2RING_0 + offset);
-}
-
-static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
-					   u32 f_index, u32 f_length)
-{
-	u32 offset;
-	u32 reg;
-
-	offset = HFB_FLT_LEN_V3PLUS +
-		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
-		 sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg &= ~(0xFF << (8 * (f_index % 4)));
-	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
-	bcmgenet_hfb_reg_writel(priv, reg, offset);
-}
-
-static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv)
-{
-	u32 f_index;
-
-	for (f_index = 0; f_index < priv->hw_params->hfb_filter_cnt; f_index++)
-		if (!bcmgenet_hfb_is_filter_enabled(priv, f_index))
-			return f_index;
-
-	return -ENOMEM;
-}
-
-/* bcmgenet_hfb_add_filter
- *
- * Add new filter to Hardware Filter Block to match and direct Rx traffic to
- * desired Rx queue.
- *
- * f_data is an array of unsigned 32-bit integers where each 32-bit integer
- * provides filter data for 2 bytes (4 nibbles) of Rx frame:
- *
- * bits 31:20 - unused
- * bit  19    - nibble 0 match enable
- * bit  18    - nibble 1 match enable
- * bit  17    - nibble 2 match enable
- * bit  16    - nibble 3 match enable
- * bits 15:12 - nibble 0 data
- * bits 11:8  - nibble 1 data
- * bits 7:4   - nibble 2 data
- * bits 3:0   - nibble 3 data
- *
- * Example:
- * In order to match:
- * - Ethernet frame type = 0x0800 (IP)
- * - IP version field = 4
- * - IP protocol field = 0x11 (UDP)
- *
- * The following filter is needed:
- * u32 hfb_filter_ipv4_udp[] = {
- *   Rx frame offset 0x00: 0x00000000, 0x00000000, 0x00000000, 0x00000000,
- *   Rx frame offset 0x08: 0x00000000, 0x00000000, 0x000F0800, 0x00084000,
- *   Rx frame offset 0x10: 0x00000000, 0x00000000, 0x00000000, 0x00030011,
- * };
- *
- * To add the filter to HFB and direct the traffic to Rx queue 0, call:
- * bcmgenet_hfb_add_filter(priv, hfb_filter_ipv4_udp,
- *                         ARRAY_SIZE(hfb_filter_ipv4_udp), 0);
- */
-int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
-			    u32 f_length, u32 rx_queue)
-{
-	int f_index;
-	u32 i;
-
-	f_index = bcmgenet_hfb_find_unused_filter(priv);
-	if (f_index < 0)
-		return -ENOMEM;
-
-	if (f_length > priv->hw_params->hfb_filter_size)
-		return -EINVAL;
-
-	for (i = 0; i < f_length; i++)
-		bcmgenet_hfb_writel(priv, f_data[i],
-			(f_index * priv->hw_params->hfb_filter_size + i) *
-			sizeof(u32));
-
-	bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length);
-	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue);
-	bcmgenet_hfb_enable_filter(priv, f_index);
-	bcmgenet_hfb_reg_writel(priv, 0x1, HFB_CTRL);
-
-	return 0;
-}
-
-/* bcmgenet_hfb_clear
- *
- * Clear Hardware Filter Block and disable all filtering.
- */
-static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
-{
-	u32 i;
-
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);
-
-	for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
-		bcmgenet_rdma_writel(priv, 0x0, i);
-
-	for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
-		bcmgenet_hfb_reg_writel(priv, 0x0,
-					HFB_FLT_LEN_V3PLUS + i * sizeof(u32));
-
-	for (i = 0; i < priv->hw_params->hfb_filter_cnt *
-			priv->hw_params->hfb_filter_size; i++)
-		bcmgenet_hfb_writel(priv, 0x0, i * sizeof(u32));
-}
-
-static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
-{
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
-	bcmgenet_hfb_clear(priv);
-}
-
 static void bcmgenet_netif_start(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-- 
cgit v1.2.3


From 3e370952287c55e5fd240cb8bb41ef8acff8829d Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:05 -0700
Subject: net: bcmgenet: add support for ethtool rxnfc flows

This commit enables driver support for ethtool commands of this form:
ethtool -N|-U|--config-nfc|--config-ntuple devname
    flow-type ether|ip4
    [src xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]]
    [dst xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]] [proto N [m N]]
    [src-ip x.x.x.x [m x.x.x.x]] [dst-ip x.x.x.x [m x.x.x.x]] [tos N [m N]]
    [l4proto N [m N]] [src-port N [m N]] [dst-port N [m N]] [spi N [m N]]
    [l4data N [m N]] [vlan-etype N [m N]] [vlan N [m N]]
    [dst-mac xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]] [action 0] [loc N] |
    delete N

Since there is only one Rx Ring in this implementation action 0 behaves no
differently from not specifying a rule.

The rules can be seen with ethtool commands of this form:
ethtool -n|-u|--show-nfc|--show-ntuple devname [rule N]

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 483 ++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  16 +
 2 files changed, 488 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ad41944d2cc0..5ef1ea7e5312 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -479,6 +479,30 @@ static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
 	reg = bcmgenet_hfb_reg_readl(priv, offset);
 	reg |= (1 << (f_index % 32));
 	bcmgenet_hfb_reg_writel(priv, reg, offset);
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	reg |= RBUF_HFB_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+}
+
+static void bcmgenet_hfb_disable_filter(struct bcmgenet_priv *priv, u32 f_index)
+{
+	u32 offset, reg, reg1;
+
+	offset = HFB_FLT_ENABLE_V3PLUS;
+	reg = bcmgenet_hfb_reg_readl(priv, offset);
+	reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
+	if  (f_index < 32) {
+		reg1 &= ~(1 << (f_index % 32));
+		bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
+	} else {
+		reg &= ~(1 << (f_index % 32));
+		bcmgenet_hfb_reg_writel(priv, reg, offset);
+	}
+	if (!reg && !reg1) {
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg &= ~RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	}
 }
 
 static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
@@ -513,13 +537,213 @@ static int bcmgenet_hfb_find_unused_filter(struct bcmgenet_priv *priv)
 {
 	u32 f_index;
 
-	for (f_index = 0; f_index < priv->hw_params->hfb_filter_cnt; f_index++)
+	/* First MAX_NUM_OF_FS_RULES are reserved for Rx NFC filters */
+	for (f_index = MAX_NUM_OF_FS_RULES;
+	     f_index < priv->hw_params->hfb_filter_cnt; f_index++)
 		if (!bcmgenet_hfb_is_filter_enabled(priv, f_index))
 			return f_index;
 
 	return -ENOMEM;
 }
 
+static int bcmgenet_hfb_validate_mask(void *mask, size_t size)
+{
+	while (size) {
+		switch (*(unsigned char *)mask++) {
+		case 0x00:
+		case 0x0f:
+		case 0xf0:
+		case 0xff:
+			size--;
+			continue;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+#define VALIDATE_MASK(x) \
+	bcmgenet_hfb_validate_mask(&(x), sizeof(x))
+
+static int bcmgenet_hfb_insert_data(u32 *f, int offset,
+				    void *val, void *mask, size_t size)
+{
+	int index;
+	u32 tmp;
+
+	index = offset / 2;
+	tmp = f[index];
+
+	while (size--) {
+		if (offset++ & 1) {
+			tmp &= ~0x300FF;
+			tmp |= (*(unsigned char *)val++);
+			switch ((*(unsigned char *)mask++)) {
+			case 0xFF:
+				tmp |= 0x30000;
+				break;
+			case 0xF0:
+				tmp |= 0x20000;
+				break;
+			case 0x0F:
+				tmp |= 0x10000;
+				break;
+			}
+			f[index++] = tmp;
+			if (size)
+				tmp = f[index];
+		} else {
+			tmp &= ~0xCFF00;
+			tmp |= (*(unsigned char *)val++) << 8;
+			switch ((*(unsigned char *)mask++)) {
+			case 0xFF:
+				tmp |= 0xC0000;
+				break;
+			case 0xF0:
+				tmp |= 0x80000;
+				break;
+			case 0x0F:
+				tmp |= 0x40000;
+				break;
+			}
+			if (!size)
+				f[index] = tmp;
+		}
+	}
+
+	return 0;
+}
+
+static void bcmgenet_hfb_set_filter(struct bcmgenet_priv *priv, u32 *f_data,
+				    u32 f_length, u32 rx_queue, int f_index)
+{
+	u32 base = f_index * priv->hw_params->hfb_filter_size;
+	int i;
+
+	for (i = 0; i < f_length; i++)
+		bcmgenet_hfb_writel(priv, f_data[i], (base + i) * sizeof(u32));
+
+	bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length);
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue);
+}
+
+static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
+					    struct bcmgenet_rxnfc_rule *rule)
+{
+	struct ethtool_rx_flow_spec *fs = &rule->fs;
+	int err = 0, offset = 0, f_length = 0;
+	u16 val_16, mask_16;
+	u8 val_8, mask_8;
+	size_t size;
+	u32 *f_data;
+
+	f_data = kcalloc(priv->hw_params->hfb_filter_size, sizeof(u32),
+			 GFP_KERNEL);
+	if (!f_data)
+		return -ENOMEM;
+
+	if (fs->flow_type & FLOW_MAC_EXT) {
+		bcmgenet_hfb_insert_data(f_data, 0,
+					 &fs->h_ext.h_dest, &fs->m_ext.h_dest,
+					 sizeof(fs->h_ext.h_dest));
+	}
+
+	if (fs->flow_type & FLOW_EXT) {
+		if (fs->m_ext.vlan_etype ||
+		    fs->m_ext.vlan_tci) {
+			bcmgenet_hfb_insert_data(f_data, 12,
+						 &fs->h_ext.vlan_etype,
+						 &fs->m_ext.vlan_etype,
+						 sizeof(fs->h_ext.vlan_etype));
+			bcmgenet_hfb_insert_data(f_data, 14,
+						 &fs->h_ext.vlan_tci,
+						 &fs->m_ext.vlan_tci,
+						 sizeof(fs->h_ext.vlan_tci));
+			offset += VLAN_HLEN;
+			f_length += DIV_ROUND_UP(VLAN_HLEN, 2);
+		}
+	}
+
+	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case ETHER_FLOW:
+		f_length += DIV_ROUND_UP(ETH_HLEN, 2);
+		bcmgenet_hfb_insert_data(f_data, 0,
+					 &fs->h_u.ether_spec.h_dest,
+					 &fs->m_u.ether_spec.h_dest,
+					 sizeof(fs->h_u.ether_spec.h_dest));
+		bcmgenet_hfb_insert_data(f_data, ETH_ALEN,
+					 &fs->h_u.ether_spec.h_source,
+					 &fs->m_u.ether_spec.h_source,
+					 sizeof(fs->h_u.ether_spec.h_source));
+		bcmgenet_hfb_insert_data(f_data, (2 * ETH_ALEN) + offset,
+					 &fs->h_u.ether_spec.h_proto,
+					 &fs->m_u.ether_spec.h_proto,
+					 sizeof(fs->h_u.ether_spec.h_proto));
+		break;
+	case IP_USER_FLOW:
+		f_length += DIV_ROUND_UP(ETH_HLEN + 20, 2);
+		/* Specify IP Ether Type */
+		val_16 = htons(ETH_P_IP);
+		mask_16 = 0xFFFF;
+		bcmgenet_hfb_insert_data(f_data, (2 * ETH_ALEN) + offset,
+					 &val_16, &mask_16, sizeof(val_16));
+		bcmgenet_hfb_insert_data(f_data, 15 + offset,
+					 &fs->h_u.usr_ip4_spec.tos,
+					 &fs->m_u.usr_ip4_spec.tos,
+					 sizeof(fs->h_u.usr_ip4_spec.tos));
+		bcmgenet_hfb_insert_data(f_data, 23 + offset,
+					 &fs->h_u.usr_ip4_spec.proto,
+					 &fs->m_u.usr_ip4_spec.proto,
+					 sizeof(fs->h_u.usr_ip4_spec.proto));
+		bcmgenet_hfb_insert_data(f_data, 26 + offset,
+					 &fs->h_u.usr_ip4_spec.ip4src,
+					 &fs->m_u.usr_ip4_spec.ip4src,
+					 sizeof(fs->h_u.usr_ip4_spec.ip4src));
+		bcmgenet_hfb_insert_data(f_data, 30 + offset,
+					 &fs->h_u.usr_ip4_spec.ip4dst,
+					 &fs->m_u.usr_ip4_spec.ip4dst,
+					 sizeof(fs->h_u.usr_ip4_spec.ip4dst));
+		if (!fs->m_u.usr_ip4_spec.l4_4_bytes)
+			break;
+
+		/* Only supports 20 byte IPv4 header */
+		val_8 = 0x45;
+		mask_8 = 0xFF;
+		bcmgenet_hfb_insert_data(f_data, ETH_HLEN + offset,
+					 &val_8, &mask_8,
+					 sizeof(val_8));
+		size = sizeof(fs->h_u.usr_ip4_spec.l4_4_bytes);
+		bcmgenet_hfb_insert_data(f_data,
+					 ETH_HLEN + 20 + offset,
+					 &fs->h_u.usr_ip4_spec.l4_4_bytes,
+					 &fs->m_u.usr_ip4_spec.l4_4_bytes,
+					 size);
+		f_length += DIV_ROUND_UP(size, 2);
+		break;
+	}
+
+	if (!fs->ring_cookie) {
+		/* Ring 0 flows can be handled by the default Descriptor Ring
+		 * We'll map them to ring 0, but don't enable the filter
+		 */
+		bcmgenet_hfb_set_filter(priv, f_data, f_length,	0,
+					fs->location);
+		rule->state = BCMGENET_RXNFC_STATE_DISABLED;
+	} else {
+		/* Other Rx rings are direct mapped here */
+		bcmgenet_hfb_set_filter(priv, f_data, f_length,
+					fs->ring_cookie, fs->location);
+		bcmgenet_hfb_enable_filter(priv, fs->location);
+		rule->state = BCMGENET_RXNFC_STATE_ENABLED;
+	}
+
+	kfree(f_data);
+
+	return err;
+}
+
 /* bcmgenet_hfb_add_filter
  *
  * Add new filter to Hardware Filter Block to match and direct Rx traffic to
@@ -559,7 +783,6 @@ int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
 			    u32 f_length, u32 rx_queue)
 {
 	int f_index;
-	u32 i;
 
 	f_index = bcmgenet_hfb_find_unused_filter(priv);
 	if (f_index < 0)
@@ -568,15 +791,8 @@ int bcmgenet_hfb_add_filter(struct bcmgenet_priv *priv, u32 *f_data,
 	if (f_length > priv->hw_params->hfb_filter_size)
 		return -EINVAL;
 
-	for (i = 0; i < f_length; i++)
-		bcmgenet_hfb_writel(priv, f_data[i],
-			(f_index * priv->hw_params->hfb_filter_size + i) *
-			sizeof(u32));
-
-	bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length);
-	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue);
+	bcmgenet_hfb_set_filter(priv, f_data, f_length, rx_queue, f_index);
 	bcmgenet_hfb_enable_filter(priv, f_index);
-	bcmgenet_hfb_reg_writel(priv, 0x1, HFB_CTRL);
 
 	return 0;
 }
@@ -607,9 +823,17 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
 
 static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
 {
+	int i;
+
 	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
 		return;
 
+	INIT_LIST_HEAD(&priv->rxnfc_list);
+	for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) {
+		INIT_LIST_HEAD(&priv->rxnfc_rules[i].list);
+		priv->rxnfc_rules[i].state = BCMGENET_RXNFC_STATE_UNUSED;
+	}
+
 	bcmgenet_hfb_clear(priv);
 }
 
@@ -1197,6 +1421,228 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
 
+static int bcmgenet_validate_flow(struct net_device *dev,
+				  struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_usrip4_spec *l4_mask;
+	struct ethhdr *eth_mask;
+
+	if (cmd->fs.location >= MAX_NUM_OF_FS_RULES) {
+		netdev_err(dev, "rxnfc: Invalid location (%d)\n",
+			   cmd->fs.location);
+		return -EINVAL;
+	}
+
+	switch (cmd->fs.flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+	case IP_USER_FLOW:
+		l4_mask = &cmd->fs.m_u.usr_ip4_spec;
+		/* don't allow mask which isn't valid */
+		if (VALIDATE_MASK(l4_mask->ip4src) ||
+		    VALIDATE_MASK(l4_mask->ip4dst) ||
+		    VALIDATE_MASK(l4_mask->l4_4_bytes) ||
+		    VALIDATE_MASK(l4_mask->proto) ||
+		    VALIDATE_MASK(l4_mask->ip_ver) ||
+		    VALIDATE_MASK(l4_mask->tos)) {
+			netdev_err(dev, "rxnfc: Unsupported mask\n");
+			return -EINVAL;
+		}
+		break;
+	case ETHER_FLOW:
+		eth_mask = &cmd->fs.m_u.ether_spec;
+		/* don't allow mask which isn't valid */
+		if (VALIDATE_MASK(eth_mask->h_source) ||
+		    VALIDATE_MASK(eth_mask->h_source) ||
+		    VALIDATE_MASK(eth_mask->h_proto)) {
+			netdev_err(dev, "rxnfc: Unsupported mask\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		netdev_err(dev, "rxnfc: Unsupported flow type (0x%x)\n",
+			   cmd->fs.flow_type);
+		return -EINVAL;
+	}
+
+	if ((cmd->fs.flow_type & FLOW_EXT)) {
+		/* don't allow mask which isn't valid */
+		if (VALIDATE_MASK(cmd->fs.m_ext.vlan_etype) ||
+		    VALIDATE_MASK(cmd->fs.m_ext.vlan_tci)) {
+			netdev_err(dev, "rxnfc: Unsupported mask\n");
+			return -EINVAL;
+		}
+		if (cmd->fs.m_ext.data[0] || cmd->fs.m_ext.data[1]) {
+			netdev_err(dev, "rxnfc: user-def not supported\n");
+			return -EINVAL;
+		}
+	}
+
+	if ((cmd->fs.flow_type & FLOW_MAC_EXT)) {
+		/* don't allow mask which isn't valid */
+		if (VALIDATE_MASK(cmd->fs.m_ext.h_dest)) {
+			netdev_err(dev, "rxnfc: Unsupported mask\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int bcmgenet_insert_flow(struct net_device *dev,
+				struct ethtool_rxnfc *cmd)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *loc_rule;
+	int err;
+
+	if (priv->hw_params->hfb_filter_size < 128) {
+		netdev_err(dev, "rxnfc: Not supported by this device\n");
+		return -EINVAL;
+	}
+
+	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues) {
+		netdev_err(dev, "rxnfc: Unsupported action (%llu)\n",
+			   cmd->fs.ring_cookie);
+		return -EINVAL;
+	}
+
+	err = bcmgenet_validate_flow(dev, cmd);
+	if (err)
+		return err;
+
+	loc_rule = &priv->rxnfc_rules[cmd->fs.location];
+	if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+	if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED)
+		list_del(&loc_rule->list);
+	loc_rule->state = BCMGENET_RXNFC_STATE_UNUSED;
+	memcpy(&loc_rule->fs, &cmd->fs,
+	       sizeof(struct ethtool_rx_flow_spec));
+
+	err = bcmgenet_hfb_create_rxnfc_filter(priv, loc_rule);
+	if (err) {
+		netdev_err(dev, "rxnfc: Could not install rule (%d)\n",
+			   err);
+		return err;
+	}
+
+	list_add_tail(&loc_rule->list, &priv->rxnfc_list);
+
+	return 0;
+}
+
+static int bcmgenet_delete_flow(struct net_device *dev,
+				struct ethtool_rxnfc *cmd)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	int err = 0;
+
+	if (cmd->fs.location >= MAX_NUM_OF_FS_RULES)
+		return -EINVAL;
+
+	rule = &priv->rxnfc_rules[cmd->fs.location];
+	if (rule->state == BCMGENET_RXNFC_STATE_UNUSED) {
+		err =  -ENOENT;
+		goto out;
+	}
+
+	if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+	if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
+		list_del(&rule->list);
+	rule->state = BCMGENET_RXNFC_STATE_UNUSED;
+	memset(&rule->fs, 0, sizeof(struct ethtool_rx_flow_spec));
+
+out:
+	return err;
+}
+
+static int bcmgenet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	int err = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = bcmgenet_insert_flow(dev, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = bcmgenet_delete_flow(dev, cmd);
+		break;
+	default:
+		netdev_warn(priv->dev, "Unsupported ethtool command. (%d)\n",
+			    cmd->cmd);
+		return -EINVAL;
+	}
+
+	return err;
+}
+
+static int bcmgenet_get_flow(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			     int loc)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	int err = 0;
+
+	if (loc < 0 || loc >= MAX_NUM_OF_FS_RULES)
+		return -EINVAL;
+
+	rule = &priv->rxnfc_rules[loc];
+	if (rule->state == BCMGENET_RXNFC_STATE_UNUSED)
+		err = -ENOENT;
+	else
+		memcpy(&cmd->fs, &rule->fs,
+		       sizeof(struct ethtool_rx_flow_spec));
+
+	return err;
+}
+
+static int bcmgenet_get_num_flows(struct bcmgenet_priv *priv)
+{
+	struct list_head *pos;
+	int res = 0;
+
+	list_for_each(pos, &priv->rxnfc_list)
+		res++;
+
+	return res;
+}
+
+static int bcmgenet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			      u32 *rule_locs)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	int err = 0;
+	int i = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = priv->hw_params->rx_queues ?: 1;
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = bcmgenet_get_num_flows(priv);
+		cmd->data = MAX_NUM_OF_FS_RULES;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = bcmgenet_get_flow(dev, cmd, cmd->fs.location);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		list_for_each_entry(rule, &priv->rxnfc_list, list)
+			if (i < cmd->rule_cnt)
+				rule_locs[i++] = rule->fs.location;
+		cmd->rule_cnt = i;
+		cmd->data = MAX_NUM_OF_FS_RULES;
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
 /* standard ethtool support functions. */
 static const struct ethtool_ops bcmgenet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
@@ -1221,6 +1667,8 @@ static const struct ethtool_ops bcmgenet_ethtool_ops = {
 	.get_link_ksettings	= bcmgenet_get_link_ksettings,
 	.set_link_ksettings	= bcmgenet_set_link_ksettings,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_rxnfc		= bcmgenet_get_rxnfc,
+	.set_rxnfc		= bcmgenet_set_rxnfc,
 };
 
 /* Power down the unimac, based on mode. */
@@ -3730,8 +4178,8 @@ static int bcmgenet_resume(struct device *d)
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned long dma_ctrl;
+	u32 offset, reg;
 	int ret;
-	u32 reg;
 
 	if (!netif_running(dev))
 		return 0;
@@ -3766,6 +4214,11 @@ static int bcmgenet_resume(struct device *d)
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
+	offset = HFB_FLT_ENABLE_V3PLUS;
+	bcmgenet_hfb_reg_writel(priv, priv->hfb_en[1], offset);
+	bcmgenet_hfb_reg_writel(priv, priv->hfb_en[2], offset + sizeof(u32));
+	bcmgenet_hfb_reg_writel(priv, priv->hfb_en[0], HFB_CTRL);
+
 	if (priv->internal_phy) {
 		reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 		reg |= EXT_ENERGY_DET_MASK;
@@ -3809,6 +4262,7 @@ static int bcmgenet_suspend(struct device *d)
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	int ret = 0;
+	u32 offset;
 
 	if (!netif_running(dev))
 		return 0;
@@ -3820,6 +4274,13 @@ static int bcmgenet_suspend(struct device *d)
 	if (!device_may_wakeup(d))
 		phy_suspend(dev->phydev);
 
+	/* Preserve filter state and disable filtering */
+	priv->hfb_en[0] = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	offset = HFB_FLT_ENABLE_V3PLUS;
+	priv->hfb_en[1] = bcmgenet_hfb_reg_readl(priv, offset);
+	priv->hfb_en[2] = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
+
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts)
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index a858b7305832..031d91f45067 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -32,6 +32,7 @@
 #define DMA_MAX_BURST_LENGTH    0x10
 
 /* misc. configuration */
+#define MAX_NUM_OF_FS_RULES		16
 #define CLEAR_ALL_HFB			0xFF
 #define DMA_FC_THRESH_HI		(TOTAL_DESC >> 4)
 #define DMA_FC_THRESH_LO		5
@@ -609,6 +610,18 @@ struct bcmgenet_rx_ring {
 	struct bcmgenet_priv *priv;
 };
 
+enum bcmgenet_rxnfc_state {
+	BCMGENET_RXNFC_STATE_UNUSED = 0,
+	BCMGENET_RXNFC_STATE_DISABLED,
+	BCMGENET_RXNFC_STATE_ENABLED
+};
+
+struct bcmgenet_rxnfc_rule {
+	struct	list_head list;
+	struct ethtool_rx_flow_spec	fs;
+	enum bcmgenet_rxnfc_state state;
+};
+
 /* device context */
 struct bcmgenet_priv {
 	void __iomem *base;
@@ -627,6 +640,8 @@ struct bcmgenet_priv {
 	struct enet_cb *rx_cbs;
 	unsigned int num_rx_bds;
 	unsigned int rx_buf_len;
+	struct bcmgenet_rxnfc_rule rxnfc_rules[MAX_NUM_OF_FS_RULES];
+	struct list_head rxnfc_list;
 
 	struct bcmgenet_rx_ring rx_rings[DESC_INDEX + 1];
 
@@ -679,6 +694,7 @@ struct bcmgenet_priv {
 	u32 wolopts;
 	u8 sopass[SOPASS_MAX];
 	bool wol_active;
+	u32 hfb_en[3];
 
 	struct bcmgenet_mib_counters mib;
 
-- 
cgit v1.2.3


From f50932cca632fb87ab4de678ecc7c3b41116140b Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 29 Apr 2020 13:02:06 -0700
Subject: net: bcmgenet: add WAKE_FILTER support

This commit enables support for the WAKE_FILTER method of Wake on
LAN for the GENET driver. The method can be enabled by adding 'f'
to the interface 'wol' setting specified by ethtool.

Rx network flow rules can be specified using ethtool. Rules that
define a flow-type with the RX_CLS_FLOW_WAKE action (i.e. -2) can
wake the system from the 'standby' power state when the WAKE_FILTER
WoL method is enabled.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     |  5 ++-
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 43 +++++++++++++++++-----
 2 files changed, 37 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 5ef1ea7e5312..ad614d7201bd 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -724,7 +724,7 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 		break;
 	}
 
-	if (!fs->ring_cookie) {
+	if (!fs->ring_cookie || fs->ring_cookie == RX_CLS_FLOW_WAKE) {
 		/* Ring 0 flows can be handled by the default Descriptor Ring
 		 * We'll map them to ring 0, but don't enable the filter
 		 */
@@ -1499,7 +1499,8 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues) {
+	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues &&
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE) {
 		netdev_err(dev, "rxnfc: Unsupported action (%llu)\n",
 			   cmd->fs.ring_cookie);
 		return -EINVAL;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index da45a4645b94..4b9d65f392c2 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -42,7 +42,7 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
-	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE;
+	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
 	memset(wol->sopass, 0, sizeof(wol->sopass));
 
@@ -61,7 +61,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (!device_can_wakeup(kdev))
 		return -ENOTSUPP;
 
-	if (wol->wolopts & ~(WAKE_MAGIC | WAKE_MAGICSECURE))
+	if (wol->wolopts & ~(WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER))
 		return -EINVAL;
 
 	if (wol->wolopts & WAKE_MAGICSECURE)
@@ -117,8 +117,9 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
+	struct bcmgenet_rxnfc_rule *rule;
+	u32 reg, hfb_ctrl_reg, hfb_enable = 0;
 	int retries = 0;
-	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
 		netif_err(priv, wol, dev, "unsupported mode: %d\n", mode);
@@ -135,13 +136,24 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	mdelay(10);
 
-	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-	reg |= MPD_EN;
-	if (priv->wolopts & WAKE_MAGICSECURE) {
-		bcmgenet_set_mpd_password(priv);
-		reg |= MPD_PW_EN;
+	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
+		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
+		reg |= MPD_EN;
+		if (priv->wolopts & WAKE_MAGICSECURE) {
+			bcmgenet_set_mpd_password(priv);
+			reg |= MPD_PW_EN;
+		}
+		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
+	}
+
+	hfb_ctrl_reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	if (priv->wolopts & WAKE_FILTER) {
+		list_for_each_entry(rule, &priv->rxnfc_list, list)
+			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE)
+				hfb_enable |= (1 << rule->fs.location);
+		reg = (hfb_ctrl_reg & ~RBUF_HFB_EN) | RBUF_ACPI_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 	}
-	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
@@ -149,6 +161,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
+		bcmgenet_hfb_reg_writel(priv, hfb_ctrl_reg, HFB_CTRL);
 		return retries;
 	}
 
@@ -158,6 +171,13 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	clk_prepare_enable(priv->clk_wol);
 	priv->wol_active = 1;
 
+	if (hfb_enable) {
+		bcmgenet_hfb_reg_writel(priv, hfb_enable,
+					HFB_FLT_ENABLE_V3PLUS + 4);
+		hfb_ctrl_reg = RBUF_HFB_EN | RBUF_ACPI_EN;
+		bcmgenet_hfb_reg_writel(priv, hfb_ctrl_reg, HFB_CTRL);
+	}
+
 	/* Enable CRC forward */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	priv->crc_fwd_en = 1;
@@ -197,6 +217,11 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~(MPD_EN | MPD_PW_EN);
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
+	/* Disable WAKE_FILTER Detection */
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+
 	/* Disable CRC Forward */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	reg &= ~CMD_CRC_FWD;
-- 
cgit v1.2.3


From 72d3fef16158b9c1852855a3846757ec165c16e1 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 22 Apr 2020 09:19:08 +0300
Subject: net/mlx5: IPsec, Fix coverity issue

The cited commit introduced the following coverity issue at functions
mlx5_fpga_is_ipsec_device() and mlx5_fpga_ipsec_release_sa_ctx():
- bit_and_with_zero:
  accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT is always 0.

As MLX5_ACCEL_ESP_ACTION_DECRYPT is not a bitwise flag and was wrongly
used with bitwise operation, the above expression is always zero value
as MLX5_ACCEL_ESP_ACTION_DECRYPT is zero.

Fix by using "==" comparison operator instead.

Fixes: 7dfee4b1d79e ("net/mlx5: IPsec, Refactor SA handle creation and destruction")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 0604216eb94f..b463787d6ca1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -708,7 +708,7 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
 		goto exists;
 	}
 
-	if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT) {
+	if (accel_xfrm->attrs.action == MLX5_ACCEL_ESP_ACTION_DECRYPT) {
 		err = ida_simple_get(&fipsec->halloc, 1, 0, GFP_KERNEL);
 		if (err < 0) {
 			context = ERR_PTR(err);
@@ -759,7 +759,7 @@ delete_hash:
 				       rhash_sa));
 unlock_hash:
 	mutex_unlock(&fipsec->sa_hash_lock);
-	if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT)
+	if (accel_xfrm->attrs.action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
 		ida_simple_remove(&fipsec->halloc, sa_ctx->sa_handle);
 exists:
 	mutex_unlock(&fpga_xfrm->lock);
-- 
cgit v1.2.3


From 9c8e7434e0349b26df82ed25522e812e4feeb873 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 3 Apr 2020 05:49:02 -0500
Subject: net/mlx5e: Use helper API to get devlink port index for all port
 flavours

Use existing helper API to get unique devlink port index for all
devlink port flavours.

Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 55457f268495..2de54d865dc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -2056,26 +2056,22 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 		return 0;
 
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	pfnum = PCI_FUNC(dev->pdev->devfn);
 
-	if (rep->vport == MLX5_VPORT_UPLINK) {
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		devlink_port_attrs_set(&rpriv->dl_port,
 				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
 				       pfnum, false, 0,
 				       &ppid.id[0], ppid.id_len);
-		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
-	} else if (rep->vport == MLX5_VPORT_PF) {
+	else if (rep->vport == MLX5_VPORT_PF)
 		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
 					      pfnum);
-		dl_port_index = rep->vport;
-	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch,
-					    rpriv->rep->vport)) {
+	else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport))
 		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
 					      pfnum, rep->vport - 1);
-		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
-	}
 
 	return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index);
 }
-- 
cgit v1.2.3


From e59b254cbecc10088b691a2abdaeb6ded872b7a1 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Fri, 24 Apr 2020 16:43:57 +0800
Subject: net/mlx5e: Remove unneeded semicolon

Fixes coccicheck warning:

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c:690:2-3: Unneeded semicolon

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 1079558d292a..77b3f372e831 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -687,7 +687,7 @@ mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 		return mlx5_tc_ct_block_flow_offload_stats(ft, f);
 	default:
 		break;
-	};
+	}
 
 	return -EOPNOTSUPP;
 }
-- 
cgit v1.2.3


From 70a5698a5683cd504b03c6030ee622b1bec3f702 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 26 Apr 2020 09:52:02 +0300
Subject: net/mlx5e: CT: Avoid false warning about rule may be used
 uninitialized

Avoid gcc warning by preset rule to invalid ptr.

Fixes: 4c3844d9e97e ("net/mlx5e: CT: Introduce connection tracking")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 77b3f372e831..44f806e79e8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1131,7 +1131,7 @@ mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 {
 	bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
 	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
-	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_handle *rule = ERR_PTR(-EINVAL);
 	int err;
 
 	if (!ct_priv)
-- 
cgit v1.2.3


From d2658b4a1d06e8458f2c88ee600afa1b1acd2627 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 14 Apr 2020 11:30:39 +0300
Subject: net/mlx5: CT: Remove unused variables

Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 44f806e79e8d..5568ded97e0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -73,9 +73,7 @@ struct mlx5_ct_ft {
 struct mlx5_ct_entry {
 	u16 zone;
 	struct rhash_head node;
-	struct flow_rule *flow_rule;
 	struct mlx5_fc *counter;
-	unsigned long lastuse;
 	unsigned long cookie;
 	unsigned long restore_cookie;
 	struct mlx5_ct_zone_rule zone_rules[2];
@@ -603,7 +601,6 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 		return -ENOMEM;
 
 	entry->zone = ft->zone;
-	entry->flow_rule = flow_rule;
 	entry->cookie = flow->cookie;
 	entry->restore_cookie = meta_action->ct_metadata.cookie;
 
-- 
cgit v1.2.3


From 51dde00b8fb3cf07e577be6aa4d98ee1f34b84be Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 15 Apr 2020 19:34:03 +0300
Subject: net/mlx5: Remove unused field in EQ

The size field in EQ is not in use.
Remove it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 4be4d2d36218..4aaca7400fb2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -27,7 +27,6 @@ struct mlx5_eq {
 	__be32 __iomem	        *doorbell;
 	u32                     cons_index;
 	struct mlx5_frag_buf    buf;
-	int                     size;
 	unsigned int            vecidx;
 	unsigned int            irqn;
 	u8                      eqn;
-- 
cgit v1.2.3


From c655c1f46957eb4f30221c52580e38f85058e167 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 30 Mar 2020 14:27:08 +0300
Subject: net/mlx5: Add helper function to release fw page

Factor out the fwp address release page to an helper function, will be
used in the downstream patch.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 30 ++++++++++++----------
 1 file changed, 17 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 3d6f617abb7d..c39907c641a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -181,25 +181,17 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 
 #define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
 
-static void free_4k(struct mlx5_core_dev *dev, u64 addr)
+static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp)
 {
-	struct fw_page *fwp;
-	int n;
+	int n = (fwp->addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 
-	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
-	if (!fwp) {
-		mlx5_core_warn(dev, "page not found\n");
-		return;
-	}
-
-	n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 	fwp->free_count++;
 	set_bit(n, &fwp->bitmask);
 	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(dev->device, addr & MLX5_U64_4K_PAGE_MASK,
+		dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
 			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
@@ -208,6 +200,18 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 	}
 }
 
+static void free_addr(struct mlx5_core_dev *dev, u64 addr)
+{
+	struct fw_page *fwp;
+
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
+	if (!fwp) {
+		mlx5_core_warn(dev, "page not found\n");
+		return;
+	}
+	free_fwp(dev, fwp);
+}
+
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 {
 	struct device *device = dev->device;
@@ -329,7 +333,7 @@ retry:
 
 out_4k:
 	for (i--; i >= 0; i--)
-		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
+		free_addr(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
 out_free:
 	kvfree(in);
 	if (notify_fail)
@@ -408,7 +412,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	}
 
 	for (i = 0; i < num_claimed; i++)
-		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
+		free_addr(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
 
 	if (nclaimed)
 		*nclaimed = num_claimed;
-- 
cgit v1.2.3


From c7636942d278db7f502c626a47d2ce1111602716 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 19 Apr 2020 10:20:40 +0300
Subject: net/mlx5: Rate limit page not found error messages

Thousands of pages are released with free_addr() function. In case of
buggy sync between FW and driver on released address, the log will be
flooded with error messages. Use mlx5_core_warn_rl() to limit it.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index c39907c641a0..c790d6e3d204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -206,7 +206,7 @@ static void free_addr(struct mlx5_core_dev *dev, u64 addr)
 
 	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
 	if (!fwp) {
-		mlx5_core_warn(dev, "page not found\n");
+		mlx5_core_warn_rl(dev, "page not found\n");
 		return;
 	}
 	free_fwp(dev, fwp);
-- 
cgit v1.2.3


From c6168161f693e6d26cdcce891f99399f1432ac80 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 1 Apr 2020 10:30:32 +0300
Subject: net/mlx5: Add support for release all pages event

If FW sets release_all_pages bit in MLX5_EVENT_TYPE_PAGE_REQUEST,
driver shall release all pages of a given function id, with no further
pages reclaim negotiation with FW nor MANAGE_PAGES commands from driver
towards FW.

Upon receiving this bit as part of pages reclaim event, driver will
initiate release all flow, in which it will iterate and release all
function's pages.

As part of driver <-> FW capabilities handshake, FW will report
release_all_pages max HCA cap bit, and driver will set the
release_all_pages bit in HCA cap.

NIC: ConnectX-4 Lx
CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
Test case: Simulataniously FLR 4 VFs, and measure FW release pages by
driver.
Before: 3.18 Sec
After:  0.31 Sec

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  3 ++
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 41 ++++++++++++++++++++--
 2 files changed, 41 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index fbbf51026b52..742ba012c234 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -549,6 +549,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 			 num_vhca_ports,
 			 MLX5_CAP_GEN_MAX(dev, num_vhca_ports));
 
+	if (MLX5_CAP_GEN_MAX(dev, release_all_pages))
+		MLX5_SET(cmd_hca_cap, set_hca_cap, release_all_pages, 1);
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index c790d6e3d204..8ce78f42dfc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -50,6 +50,7 @@ struct mlx5_pages_req {
 	u8	ec_function;
 	s32	npages;
 	struct work_struct work;
+	u8	release_all;
 };
 
 struct fw_page {
@@ -341,6 +342,33 @@ out_free:
 	return err;
 }
 
+static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
+			      bool ec_function)
+{
+	struct rb_node *p;
+	int npages = 0;
+
+	p = rb_first(&dev->priv.page_root);
+	while (p) {
+		struct fw_page *fwp = rb_entry(p, struct fw_page, rb_node);
+
+		p = rb_next(p);
+		if (fwp->func_id != func_id)
+			continue;
+		free_fwp(dev, fwp);
+		npages++;
+	}
+
+	dev->priv.fw_pages -= npages;
+	if (func_id)
+		dev->priv.vfs_pages -= npages;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages -= npages;
+
+	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
+		      npages, ec_function, func_id);
+}
+
 static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 			     u32 *in, int in_size, u32 *out, int out_size)
 {
@@ -434,7 +462,9 @@ static void pages_work_handler(struct work_struct *work)
 	struct mlx5_core_dev *dev = req->dev;
 	int err = 0;
 
-	if (req->npages < 0)
+	if (req->release_all)
+		release_all_pages(dev, req->func_id, req->ec_function);
+	else if (req->npages < 0)
 		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL,
 				    req->ec_function);
 	else if (req->npages > 0)
@@ -449,6 +479,7 @@ static void pages_work_handler(struct work_struct *work)
 
 enum {
 	EC_FUNCTION_MASK = 0x8000,
+	RELEASE_ALL_PAGES_MASK = 0x4000,
 };
 
 static int req_pages_handler(struct notifier_block *nb,
@@ -459,6 +490,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	struct mlx5_priv *priv;
 	struct mlx5_eqe *eqe;
 	bool ec_function;
+	bool release_all;
 	u16 func_id;
 	s32 npages;
 
@@ -469,8 +501,10 @@ static int req_pages_handler(struct notifier_block *nb,
 	func_id = be16_to_cpu(eqe->data.req_pages.func_id);
 	npages  = be32_to_cpu(eqe->data.req_pages.num_pages);
 	ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK;
-	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
-		      func_id, npages);
+	release_all = be16_to_cpu(eqe->data.req_pages.ec_function) &
+		      RELEASE_ALL_PAGES_MASK;
+	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d, release_all %d\n",
+		      func_id, npages, release_all);
 	req = kzalloc(sizeof(*req), GFP_ATOMIC);
 	if (!req) {
 		mlx5_core_warn(dev, "failed to allocate pages request\n");
@@ -481,6 +515,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	req->func_id = func_id;
 	req->npages = npages;
 	req->ec_function = ec_function;
+	req->release_all = release_all;
 	INIT_WORK(&req->work, pages_work_handler);
 	queue_work(dev->priv.pg_wq, &req->work);
 	return NOTIFY_OK;
-- 
cgit v1.2.3


From e658664c77c11c5ba77dfb231138505ecac71c80 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 8 Aug 2019 12:32:17 +0300
Subject: net/mlx5e: Use proper name field for the UMR key

Even though some of the WQE control segment's field share
the same memory bits (a union of fields), prefer having the
right field name for every different usage.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 10c933e5da9a..bf3fdbea1074 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -233,7 +233,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	cseg->qpn_ds    = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
 				      ds_cnt);
 	cseg->fm_ce_se  = MLX5_WQE_CTRL_CQ_UPDATE;
-	cseg->imm       = rq->mkey_be;
+	cseg->umr_mkey  = rq->mkey_be;
 
 	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
 	ucseg->xlt_octowords =
-- 
cgit v1.2.3


From f1b95753eeedc00f1223e8033d96dae9f996ca6d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 9 Feb 2020 17:06:49 +0200
Subject: net/mlx5e: TX, Generalise code and usage of error CQE dump

Error CQE was dumped only for TXQ SQs.
Generalise the function, and add usage for error completions
on ICO SQs and XDP SQs.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 16 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 13 ++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c   | 18 +-----------------
 4 files changed, 27 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 9f6967d76053..c0249fc77eaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -189,6 +189,22 @@ static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
 	}
 }
 
+static inline void mlx5e_dump_error_cqe(struct mlx5e_cq *cq, u32 sqn,
+					struct mlx5_err_cqe *err_cqe)
+{
+	struct mlx5_cqwq *wq = &cq->wq;
+	u32 ci;
+
+	ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1);
+
+	netdev_err(cq->channel->netdev,
+		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
+		   cq->mcq.cqn, ci, sqn,
+		   get_cqe_opcode((struct mlx5_cqe64 *)err_cqe),
+		   err_cqe->syndrome, err_cqe->vendor_err_synd);
+	mlx5_dump_err_cqe(cq->mdev, err_cqe);
+}
+
 /* SW parser related functions */
 
 struct mlx5e_swp_spec {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index f049e0ac308a..f9dad2639061 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -415,11 +415,6 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ))
-			netdev_WARN_ONCE(sq->channel->netdev,
-					 "Bad OP in XDPSQ CQE: 0x%x\n",
-					 get_cqe_opcode(cqe));
-
 		do {
 			struct mlx5e_xdp_wqe_info *wi;
 			u16 ci;
@@ -432,6 +427,14 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true);
 		} while (!last_wqe);
+
+		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
+			netdev_WARN_ONCE(sq->channel->netdev,
+					 "Bad OP in XDPSQ CQE: 0x%x\n",
+					 get_cqe_opcode(cqe));
+			mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
+					     (struct mlx5_err_cqe *)cqe);
+		}
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	if (xsk_frames)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e2beb89c1832..4db1c92f0019 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -631,6 +631,8 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 				netdev_WARN_ONCE(cq->channel->netdev,
 						 "Bad OP in ICOSQ CQE: 0x%x\n",
 						 get_cqe_opcode(cqe));
+				mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
+						     (struct mlx5_err_cqe *)cqe);
 				if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 					queue_work(cq->channel->priv->wq, &sq->recover_work);
 				break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index fd6b2a1898c5..1679557f34c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -399,22 +399,6 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
 }
 
-static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
-				 struct mlx5_err_cqe *err_cqe)
-{
-	struct mlx5_cqwq *wq = &sq->cq.wq;
-	u32 ci;
-
-	ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1);
-
-	netdev_err(sq->channel->netdev,
-		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
-		   sq->cq.mcq.cqn, ci, sq->sqn,
-		   get_cqe_opcode((struct mlx5_cqe64 *)err_cqe),
-		   err_cqe->syndrome, err_cqe->vendor_err_synd);
-	mlx5_dump_err_cqe(sq->cq.mdev, err_cqe);
-}
-
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq_stats *stats;
@@ -501,7 +485,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
-				mlx5e_dump_error_cqe(sq,
+				mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
 						     (struct mlx5_err_cqe *)cqe);
 				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 				queue_work(cq->channel->priv->wq,
-- 
cgit v1.2.3


From e2e11dbf36936d9cfea99c5b7386acea67b21634 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 9 Feb 2020 17:13:23 +0200
Subject: net/mlx5e: XDP, Print the offending TX descriptor on error completion

Upon an error completion on an XDP SQ, print the offending WQE
to ease the debug process.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index f9dad2639061..6f32a697a4bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -408,7 +408,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 	i = 0;
 	do {
-		u16 wqe_counter;
+		struct mlx5e_xdp_wqe_info *wi;
+		u16 wqe_counter, ci;
 		bool last_wqe;
 
 		mlx5_cqwq_pop(&cq->wq);
@@ -416,9 +417,6 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
 		do {
-			struct mlx5e_xdp_wqe_info *wi;
-			u16 ci;
-
 			last_wqe = (sqcc == wqe_counter);
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.wqe_info[ci];
@@ -434,6 +432,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 					 get_cqe_opcode(cqe));
 			mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
 					     (struct mlx5_err_cqe *)cqe);
+			mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 		}
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
-- 
cgit v1.2.3


From fed0c6cfcd58f29ff60f47559b88a6289b6b680a Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 15 Nov 2019 13:48:38 +0200
Subject: net/mlx5e: Fetch WQE: reuse code and enforce typing

There are multiple functions mlx5{e,i}_*_fetch_wqe that contain the same
code, that is repeated, because they operate on different SQ struct
types. mlx5e_sq_fetch_wqe also returns void *, instead of the concrete
WQE type.

This commit generalizes the fetch WQE operation by putting this code
into a single function. To simplify calls of the generic function in
concrete use cases, macros are provided that substitute the right WQE
size and cast the return type.

Before this patch, fetch_wqe used to calculate pi itself, but the value
was often known to the caller. This calculation is moved outside to
eliminate this unnecessary step and prepare for the fill_frag_edge
refactoring in the next patch.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h         | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c          |  6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h          | 13 -------------
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h   |  8 ++++++++
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c    | 15 ++++++++++-----
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c   |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c           | 10 ++++++----
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h     | 11 ++---------
 8 files changed, 38 insertions(+), 40 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index c0249fc77eaa..8682d9148ab9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -33,19 +33,19 @@ mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
 }
 
-static inline void *
-mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq, size_t size, u16 *pi)
+static inline void *mlx5e_fetch_wqe(struct mlx5_wq_cyc *wq, u16 pi, size_t wqe_size)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
 	void *wqe;
 
-	*pi  = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
-	memset(wqe, 0, size);
+	wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+	memset(wqe, 0, wqe_size);
 
 	return wqe;
 }
 
+#define MLX5E_TX_FETCH_WQE(sq, pi) \
+	((struct mlx5e_tx_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, sizeof(struct mlx5e_tx_wqe)))
+
 static inline struct mlx5e_tx_wqe *
 mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 6f32a697a4bf..cf089520c031 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -188,10 +188,12 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 
-	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS))
+	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) {
 		mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
+		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	}
 
-	session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi);
+	session->wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	prefetchw(session->wqe->data);
 	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index d7587f40ecae..4fd0ff47bdc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -186,19 +186,6 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 	session->ds_count++;
 }
 
-static inline struct mlx5e_tx_wqe *
-mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-
-	*pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
-	memset(wqe, 0, sizeof(*wqe));
-
-	return wqe;
-}
-
 static inline void
 mlx5e_xdpi_fifo_push(struct mlx5e_xdp_info_fifo *fifo,
 		     struct mlx5e_xdp_info *xi)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 63116be6b1d6..9daaec244385 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -27,6 +27,14 @@ struct mlx5e_dump_wqe {
 	struct mlx5_wqe_data_seg data;
 };
 
+#define MLX5E_TLS_FETCH_UMR_WQE(sq, pi) \
+	((struct mlx5e_umr_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, MLX5E_KTLS_STATIC_UMR_WQE_SZ))
+#define MLX5E_TLS_FETCH_PROGRESS_WQE(sq, pi) \
+	((struct mlx5e_tx_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, MLX5E_KTLS_PROGRESS_WQE_SZ))
+#define MLX5E_TLS_FETCH_DUMP_WQE(sq, pi) \
+	((struct mlx5e_dump_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, \
+						  sizeof(struct mlx5e_dump_wqe)))
+
 #define MLX5E_KTLS_DUMP_WQEBBS \
 	(DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 52a56622034a..717d36b45aa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -137,7 +137,8 @@ post_static_params(struct mlx5e_txqsq *sq,
 	struct mlx5e_umr_wqe *umr_wqe;
 	u16 pi;
 
-	umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi);
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	umr_wqe = MLX5E_TLS_FETCH_UMR_WQE(sq, pi);
 	build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
 	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
@@ -151,7 +152,8 @@ post_progress_params(struct mlx5e_txqsq *sq,
 	struct mlx5e_tx_wqe *wqe;
 	u16 pi;
 
-	wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi);
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wqe = MLX5E_TLS_FETCH_PROGRESS_WQE(sq, pi);
 	build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
 	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
@@ -278,7 +280,8 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	int fsz;
 	u16 pi;
 
-	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wqe = MLX5E_TLS_FETCH_DUMP_WQE(sq, pi);
 
 	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
 
@@ -449,7 +452,8 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 
 	if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
 		mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false);
-		*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+		*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+		*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
 		stats->tls_ctx++;
 	}
 
@@ -460,7 +464,8 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 
 		switch (ret) {
 		case MLX5E_KTLS_SYNC_DONE:
-			*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+			*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+			*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
 			break;
 		case MLX5E_KTLS_SYNC_SKIP_NO_DATA:
 			if (likely(!skb->decrypted))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index ef1ed15a53b4..1d7ddeb7a46b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -248,7 +248,8 @@ mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
 				    cpu_to_be64(info.rcd_sn));
 	mlx5e_sq_xmit(sq, nskb, *wqe, *pi, true);
-	*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+	*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
 	return skb;
 
 err_out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 1679557f34c0..ec1429596cb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -324,7 +324,8 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		struct mlx5_wqe_ctrl_seg cur_ctrl = wqe->ctrl;
 #endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
+		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+		wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 #ifdef CONFIG_MLX5_EN_IPSEC
 		wqe->eth = cur_eth;
 #endif
@@ -389,7 +390,8 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	u16 pi;
 
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
-	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
@@ -622,10 +624,10 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+		pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
 	}
 
-	mlx5i_sq_fetch_wqe(sq, &wqe, pi);
+	wqe = MLX5I_SQ_FETCH_WQE(sq, pi);
 
 	/* fill wqe */
 	wi       = &sq->db.wqe_info[pi];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 3483ba642cfe..7844ab5d0ce7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -110,15 +110,8 @@ struct mlx5i_tx_wqe {
 	struct mlx5_wqe_data_seg     data[];
 };
 
-static inline void mlx5i_sq_fetch_wqe(struct mlx5e_txqsq *sq,
-				      struct mlx5i_tx_wqe **wqe,
-				      u16 pi)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-
-	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-	memset(*wqe, 0, sizeof(**wqe));
-}
+#define MLX5I_SQ_FETCH_WQE(sq, pi) \
+	((struct mlx5i_tx_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, sizeof(struct mlx5i_tx_wqe)))
 
 netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
-- 
cgit v1.2.3


From 7d42c8e9ab50091e4dda29066975fbb7aa0f1585 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 16 Apr 2020 11:32:42 +0300
Subject: net/mlx5e: Rename ICOSQ WQE info struct and field

Structs mlx5e_txqsq and mlx5e_xdpsq contain wqe_info arrays to store
supplementary information corresponding to WQEs in the queue. Struct
mlx5e_icosq also has such an array, but it's called differently -
ico_wqe. This patch renames it to unify with the other SQs.

In addition, rename the struct to emphasize its specific usage.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |  4 ++--
 4 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e8508c74eaa8..0864b76ca2c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -370,7 +370,7 @@ enum {
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 };
 
-struct mlx5e_sq_wqe_info {
+struct mlx5e_icosq_wqe_info {
 	u8  opcode;
 	u8 num_wqebbs;
 
@@ -552,7 +552,7 @@ struct mlx5e_icosq {
 
 	/* write@xmit, read@completion */
 	struct {
-		struct mlx5e_sq_wqe_info *ico_wqe;
+		struct mlx5e_icosq_wqe_info *wqe_info;
 	} db;
 
 	/* read only */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bf3fdbea1074..048a4f8601a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1027,17 +1027,17 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kvfree(sq->db.ico_wqe);
+	kvfree(sq->db.wqe_info);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	size_t size;
 
-	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
-						  sizeof(*sq->db.ico_wqe)),
-				       GFP_KERNEL, numa);
-	if (!sq->db.ico_wqe)
+	size = array_size(wq_sz, sizeof(*sq->db.wqe_info));
+	sq->db.wqe_info = kvzalloc_node(size, GFP_KERNEL, numa);
+	if (!sq->db.wqe_info)
 		return -ENOMEM;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 4db1c92f0019..9f33a0e7dd9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -472,7 +472,7 @@ static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 					      struct mlx5_wq_cyc *wq,
 					      u16 pi, u16 nnops)
 {
-	struct mlx5e_sq_wqe_info *edge_wi, *wi = &sq->db.ico_wqe[pi];
+	struct mlx5e_icosq_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
 
 	edge_wi = wi + nnops;
 
@@ -527,9 +527,9 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 			    MLX5_OPCODE_UMR);
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
-	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
-	sq->db.ico_wqe[pi].num_wqebbs = MLX5E_UMR_WQEBBS;
-	sq->db.ico_wqe[pi].umr.rq = rq;
+	sq->db.wqe_info[pi].opcode = MLX5_OPCODE_UMR;
+	sq->db.wqe_info[pi].num_wqebbs = MLX5E_UMR_WQEBBS;
+	sq->db.wqe_info[pi].umr.rq = rq;
 	sq->pc += MLX5E_UMR_WQEBBS;
 
 	sq->doorbell_cseg = &umr_wqe->ctrl;
@@ -618,13 +618,13 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
 		do {
-			struct mlx5e_sq_wqe_info *wi;
+			struct mlx5e_icosq_wqe_info *wi;
 			u16 ci;
 
 			last_wqe = (sqcc == wqe_counter);
 
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			wi = &sq->db.ico_wqe[ci];
+			wi = &sq->db.wqe_info[ci];
 			sqcc += wi->num_wqebbs;
 
 			if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index acb20215a33b..869fd58a6775 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -78,8 +78,8 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 	struct mlx5e_tx_wqe *nopwqe;
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
-	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
-	sq->db.ico_wqe[pi].num_wqebbs = 1;
+	sq->db.wqe_info[pi].opcode = MLX5_OPCODE_NOP;
+	sq->db.wqe_info[pi].num_wqebbs = 1;
 	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
-- 
cgit v1.2.3


From ec9cdca0663a543ede2072ff091beec1787e3374 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 16 Apr 2020 11:29:49 +0300
Subject: net/mlx5e: Unify reserving space for WQEs

In our fast-path design, a WQE (Work Queue Element) must not cross the
page boundary. To enforce that, for WQEs consisting of more than one BB
(Basic Block), the driver checks the available contiguous space in the
WQ in advance, and if it's not enough, it pads it with NOPs.

This patch modifies the code that calculates the position of next WQE,
considering the padding, and prepares the WQE. This code is common for
all SQ types. In this patch it's reorganized in a way that makes the
usage pattern unified for all SQ types, and makes the implementations
self-contained and look almost the same, preparing the repeating code to
further attempts to deduplicate it.

One place is left as is: mlx5e_sq_xmit and mlx5e_fill_sq_frag_edge call
inside, because it is special in a way that it may also copy WQE's cseg
and eseg when reserving space. This will be eliminated in one of the
following patches, and this place will be converted to the new approach,
too.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h  | 56 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   | 31 ++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h   | 17 -------
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 16 +------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 26 +---------
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    | 11 +----
 6 files changed, 88 insertions(+), 69 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 8682d9148ab9..89fe65593c16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -81,6 +81,62 @@ mlx5e_post_nop_fence(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 	return wqe;
 }
 
+static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi, contig_wqebbs;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs < size)) {
+		struct mlx5e_tx_wqe_info *wi, *edge_wi;
+
+		wi = &sq->db.wqe_info[pi];
+		edge_wi = wi + contig_wqebbs;
+
+		/* Fill SQ frag edge with NOPs to avoid WQE wrapping two pages. */
+		for (; wi < edge_wi; wi++) {
+			*wi = (struct mlx5e_tx_wqe_info) {
+				.num_wqebbs = 1,
+			};
+			mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		}
+		sq->stats->nop += contig_wqebbs;
+
+		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	}
+
+	return pi;
+}
+
+static inline u16 mlx5e_icosq_get_next_pi(struct mlx5e_icosq *sq, u16 size)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi, contig_wqebbs;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs < size)) {
+		struct mlx5e_icosq_wqe_info *wi, *edge_wi;
+
+		wi = &sq->db.wqe_info[pi];
+		edge_wi = wi + contig_wqebbs;
+
+		/* Fill SQ frag edge with NOPs to avoid WQE wrapping two pages. */
+		for (; wi < edge_wi; wi++) {
+			*wi = (struct mlx5e_icosq_wqe_info) {
+				.opcode = MLX5_OPCODE_NOP,
+				.num_wqebbs = 1,
+			};
+			mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		}
+
+		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	}
+
+	return pi;
+}
+
 static inline void
 mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
 			u16 pi, u16 nnops)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index cf089520c031..c4a7fb4ecd14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -178,21 +178,42 @@ xdp_abort:
 	}
 }
 
-static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+static u16 mlx5e_xdpsq_get_next_pi(struct mlx5e_xdpsq *sq, u16 size)
 {
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
-	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u16 pi, contig_wqebbs;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs < size)) {
+		struct mlx5e_xdp_wqe_info *wi, *edge_wi;
+
+		wi = &sq->db.wqe_info[pi];
+		edge_wi = wi + contig_wqebbs;
+
+		/* Fill SQ frag edge with NOPs to avoid WQE wrapping two pages. */
+		for (; wi < edge_wi; wi++) {
+			*wi = (struct mlx5e_xdp_wqe_info) {
+				.num_wqebbs = 1,
+				.num_pkts = 0,
+			};
+			mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+		}
+		sq->stats->nops += contig_wqebbs;
 
-	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) {
-		mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
 		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	}
 
+	return pi;
+}
+
+static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+	u16 pi;
+
+	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS);
 	session->wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	prefetchw(session->wqe->data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 4fd0ff47bdc3..ed6f045febeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -137,23 +137,6 @@ mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
 	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
 }
 
-static inline void
-mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq,
-			   u16 pi, u16 nnops)
-{
-	struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		wi->num_wqebbs = 1;
-		wi->num_pkts   = 0;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-
-	sq->stats->nops += nnops;
-}
-
 static inline void
 mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 			 struct mlx5e_xdp_xmit_data *xdptxd,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 717d36b45aa9..ba973937f0b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -165,14 +165,8 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 			      bool skip_static_post, bool fence_first_post)
 {
 	bool progress_fence = skip_static_post || !fence_first_post;
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 contig_wqebbs_room, pi;
 
-	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
-	if (unlikely(contig_wqebbs_room <
-		     MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS))
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
+	mlx5e_txqsq_get_next_pi(sq, MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS);
 
 	if (!skip_static_post)
 		post_static_params(sq, priv_tx, fence_first_post);
@@ -346,10 +340,8 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 			 u32 seq)
 {
 	struct mlx5e_sq_stats *stats = sq->stats;
-	struct mlx5_wq_cyc *wq = &sq->wq;
 	enum mlx5e_ktls_sync_retval ret;
 	struct tx_sync_info info = {};
-	u16 contig_wqebbs_room, pi;
 	u8 num_wqebbs;
 	int i = 0;
 
@@ -380,11 +372,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	}
 
 	num_wqebbs = mlx5e_ktls_dumps_num_wqebbs(sq, info.nr_frags, info.sync_len);
-	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
-
-	if (unlikely(contig_wqebbs_room < num_wqebbs))
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
+	mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
 
 	for (; i < info.nr_frags; i++) {
 		unsigned int orig_fsz, frag_offset = 0, n = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9f33a0e7dd9a..d9a5a669b84d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -468,22 +468,6 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n)
 	mlx5_wq_ll_update_db_record(wq);
 }
 
-static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
-					      struct mlx5_wq_cyc *wq,
-					      u16 pi, u16 nnops)
-{
-	struct mlx5e_icosq_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		wi->opcode = MLX5_OPCODE_NOP;
-		wi->num_wqebbs = 1;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-}
-
 static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
@@ -492,7 +476,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *umr_wqe;
 	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
-	u16 pi, contig_wqebbs_room;
+	u16 pi;
 	int err;
 	int i;
 
@@ -502,13 +486,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		goto err;
 	}
 
-	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
-	if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) {
-		mlx5e_fill_icosq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	}
-
+	pi = mlx5e_icosq_get_next_pi(sq, MLX5E_UMR_WQEBBS);
 	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
 	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts));
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index ec1429596cb7..583e1b201b75 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -572,7 +572,6 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
 			  bool xmit_more)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5i_tx_wqe *wqe;
 
 	struct mlx5_wqe_datagram_seg *datagram;
@@ -582,9 +581,9 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	u16 headlen, ihs, pi, contig_wqebbs_room;
 	u16 ds_cnt, ds_cnt_inl = 0;
 	u8 num_wqebbs, opcode;
+	u16 headlen, ihs, pi;
 	u32 num_bytes;
 	int num_dma;
 	__be16 mss;
@@ -620,13 +619,7 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
-	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-	}
-
+	pi = mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
 	wqe = MLX5I_SQ_FETCH_WQE(sq, pi);
 
 	/* fill wqe */
-- 
cgit v1.2.3


From ddc2118ef064ca130f06716829e11e02b3915fd0 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 30 Apr 2020 09:32:45 +0800
Subject: hinic: make a bunch of functions static

These fucntions is used only in hinic_sriov.c,
so make them static to fix sparse warnings.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_sriov.c | 91 +++++++++++++------------
 1 file changed, 48 insertions(+), 43 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index b24788e9733c..0d44af9dce2a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -23,8 +23,8 @@ MODULE_PARM_DESC(set_vf_link_state, "Set vf link state, 0 represents link auto,
 #define HINIC_VLAN_PRIORITY_SHIFT 13
 #define HINIC_ADD_VLAN_IN_MAC 0x8000
 
-int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id,
-		  u16 func_id)
+static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr,
+			 u16 vlan_id, u16 func_id)
 {
 	struct hinic_port_mac_cmd mac_info = {0};
 	u16 out_size = sizeof(mac_info);
@@ -84,7 +84,7 @@ void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev,
 	}
 }
 
-u16 hinic_vf_info_vlanprio(struct hinic_hwdev *hwdev, int vf_id)
+static u16 hinic_vf_info_vlanprio(struct hinic_hwdev *hwdev, int vf_id)
 {
 	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
 	u16 pf_vlan, vlanprio;
@@ -97,8 +97,8 @@ u16 hinic_vf_info_vlanprio(struct hinic_hwdev *hwdev, int vf_id)
 	return vlanprio;
 }
 
-int hinic_set_vf_vlan(struct hinic_hwdev *hwdev, bool add, u16 vid,
-		      u8 qos, int vf_id)
+static int hinic_set_vf_vlan(struct hinic_hwdev *hwdev, bool add, u16 vid,
+			     u8 qos, int vf_id)
 {
 	struct hinic_vf_vlan_config vf_vlan = {0};
 	u16 out_size = sizeof(vf_vlan);
@@ -163,9 +163,9 @@ static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id)
 	return 0;
 }
 
-int hinic_register_vf_msg_handler(void *hwdev, u16 vf_id,
-				  void *buf_in, u16 in_size,
-				  void *buf_out, u16 *out_size)
+static int hinic_register_vf_msg_handler(void *hwdev, u16 vf_id,
+					 void *buf_in, u16 in_size,
+					 void *buf_out, u16 *out_size)
 {
 	struct hinic_register_vf *register_info = buf_out;
 	struct hinic_hwdev *hw_dev = hwdev;
@@ -192,9 +192,9 @@ int hinic_register_vf_msg_handler(void *hwdev, u16 vf_id,
 	return 0;
 }
 
-int hinic_unregister_vf_msg_handler(void *hwdev, u16 vf_id,
-				    void *buf_in, u16 in_size,
-				    void *buf_out, u16 *out_size)
+static int hinic_unregister_vf_msg_handler(void *hwdev, u16 vf_id,
+					   void *buf_in, u16 in_size,
+					   void *buf_out, u16 *out_size)
 {
 	struct hinic_hwdev *hw_dev = hwdev;
 	struct hinic_func_to_io *nic_io;
@@ -209,9 +209,9 @@ int hinic_unregister_vf_msg_handler(void *hwdev, u16 vf_id,
 	return 0;
 }
 
-int hinic_change_vf_mtu_msg_handler(void *hwdev, u16 vf_id,
-				    void *buf_in, u16 in_size,
-				    void *buf_out, u16 *out_size)
+static int hinic_change_vf_mtu_msg_handler(void *hwdev, u16 vf_id,
+					   void *buf_in, u16 in_size,
+					   void *buf_out, u16 *out_size)
 {
 	struct hinic_hwdev *hw_dev = hwdev;
 	int err;
@@ -227,9 +227,9 @@ int hinic_change_vf_mtu_msg_handler(void *hwdev, u16 vf_id,
 	return 0;
 }
 
-int hinic_get_vf_mac_msg_handler(void *hwdev, u16 vf_id,
-				 void *buf_in, u16 in_size,
-				 void *buf_out, u16 *out_size)
+static int hinic_get_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+					void *buf_in, u16 in_size,
+					void *buf_out, u16 *out_size)
 {
 	struct hinic_port_mac_cmd *mac_info = buf_out;
 	struct hinic_hwdev *dev = hwdev;
@@ -246,9 +246,9 @@ int hinic_get_vf_mac_msg_handler(void *hwdev, u16 vf_id,
 	return 0;
 }
 
-int hinic_set_vf_mac_msg_handler(void *hwdev, u16 vf_id,
-				 void *buf_in, u16 in_size,
-				 void *buf_out, u16 *out_size)
+static int hinic_set_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+					void *buf_in, u16 in_size,
+					void *buf_out, u16 *out_size)
 {
 	struct hinic_port_mac_cmd *mac_out = buf_out;
 	struct hinic_port_mac_cmd *mac_in = buf_in;
@@ -280,9 +280,9 @@ int hinic_set_vf_mac_msg_handler(void *hwdev, u16 vf_id,
 	return err;
 }
 
-int hinic_del_vf_mac_msg_handler(void *hwdev, u16 vf_id,
-				 void *buf_in, u16 in_size,
-				 void *buf_out, u16 *out_size)
+static int hinic_del_vf_mac_msg_handler(void *hwdev, u16 vf_id,
+					void *buf_in, u16 in_size,
+					void *buf_out, u16 *out_size)
 {
 	struct hinic_port_mac_cmd *mac_out = buf_out;
 	struct hinic_port_mac_cmd *mac_in = buf_in;
@@ -312,9 +312,9 @@ int hinic_del_vf_mac_msg_handler(void *hwdev, u16 vf_id,
 	return err;
 }
 
-int hinic_get_vf_link_status_msg_handler(void *hwdev, u16 vf_id,
-					 void *buf_in, u16 in_size,
-					 void *buf_out, u16 *out_size)
+static int hinic_get_vf_link_status_msg_handler(void *hwdev, u16 vf_id,
+						void *buf_in, u16 in_size,
+						void *buf_out, u16 *out_size)
 {
 	struct hinic_port_link_cmd *get_link = buf_out;
 	struct hinic_hwdev *hw_dev = hwdev;
@@ -339,7 +339,7 @@ int hinic_get_vf_link_status_msg_handler(void *hwdev, u16 vf_id,
 	return 0;
 }
 
-struct vf_cmd_msg_handle nic_vf_cmd_msg_handler[] = {
+static struct vf_cmd_msg_handle nic_vf_cmd_msg_handler[] = {
 	{HINIC_PORT_CMD_VF_REGISTER, hinic_register_vf_msg_handler},
 	{HINIC_PORT_CMD_VF_UNREGISTER, hinic_unregister_vf_msg_handler},
 	{HINIC_PORT_CMD_CHANGE_MTU, hinic_change_vf_mtu_msg_handler},
@@ -351,6 +351,7 @@ struct vf_cmd_msg_handle nic_vf_cmd_msg_handler[] = {
 
 #define CHECK_IPSU_15BIT	0X8000
 
+static
 struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -372,8 +373,8 @@ static int hinic_check_mac_info(u8 status, u16 vlan_id)
 
 #define HINIC_VLAN_ID_MASK	0x7FFF
 
-int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, u8 *new_mac,
-		     u16 vlan_id, u16 func_id)
+static int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac,
+			    u8 *new_mac, u16 vlan_id, u16 func_id)
 {
 	struct hinic_port_mac_update mac_info = {0};
 	u16 out_size = sizeof(mac_info);
@@ -416,8 +417,8 @@ int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, u8 *new_mac,
 	return 0;
 }
 
-void hinic_get_vf_config(struct hinic_hwdev *hwdev, u16 vf_id,
-			 struct ifla_vf_info *ivi)
+static void hinic_get_vf_config(struct hinic_hwdev *hwdev, u16 vf_id,
+				struct ifla_vf_info *ivi)
 {
 	struct vf_data_storage *vfinfo;
 
@@ -455,7 +456,8 @@ int hinic_ndo_get_vf_config(struct net_device *netdev,
 	return 0;
 }
 
-int hinic_set_vf_mac(struct hinic_hwdev *hwdev, int vf, unsigned char *mac_addr)
+static int hinic_set_vf_mac(struct hinic_hwdev *hwdev, int vf,
+			    unsigned char *mac_addr)
 {
 	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
 	struct vf_data_storage *vf_info;
@@ -504,7 +506,8 @@ int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	return 0;
 }
 
-int hinic_add_vf_vlan(struct hinic_hwdev *hwdev, int vf_id, u16 vlan, u8 qos)
+static int hinic_add_vf_vlan(struct hinic_hwdev *hwdev, int vf_id,
+			     u16 vlan, u8 qos)
 {
 	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
 	int err;
@@ -521,7 +524,7 @@ int hinic_add_vf_vlan(struct hinic_hwdev *hwdev, int vf_id, u16 vlan, u8 qos)
 	return 0;
 }
 
-int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
+static int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
 {
 	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
 	int err;
@@ -543,8 +546,8 @@ int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id)
 	return 0;
 }
 
-int hinic_update_mac_vlan(struct hinic_dev *nic_dev, u16 old_vlan, u16 new_vlan,
-			  int vf_id)
+static int hinic_update_mac_vlan(struct hinic_dev *nic_dev, u16 old_vlan,
+				 u16 new_vlan, int vf_id)
 {
 	struct vf_data_storage *vf_info;
 	u16 vlan_id;
@@ -651,7 +654,8 @@ int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
 	return set_hw_vf_vlan(nic_dev, cur_vlanprio, vf, vlan, qos);
 }
 
-int hinic_set_vf_trust(struct hinic_hwdev *hwdev, u16 vf_id, bool trust)
+static int hinic_set_vf_trust(struct hinic_hwdev *hwdev, u16 vf_id,
+			      bool trust)
 {
 	struct vf_data_storage *vf_infos;
 	struct hinic_func_to_io *nic_io;
@@ -697,8 +701,8 @@ int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 }
 
 /* pf receive message from vf */
-int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
-			u16 in_size, void *buf_out, u16 *out_size)
+static int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
+			       u16 in_size, void *buf_out, u16 *out_size)
 {
 	struct vf_cmd_msg_handle *vf_msg_handle;
 	struct hinic_hwdev *dev = hwdev;
@@ -786,7 +790,7 @@ static int hinic_init_vf_infos(struct hinic_func_to_io *nic_io, u16 vf_id)
 	return 0;
 }
 
-void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
+static void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
 {
 	struct vf_data_storage *vf_infos;
 	u16 func_id;
@@ -807,8 +811,8 @@ void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
 	hinic_init_vf_infos(&nic_dev->hwdev->func_to_io, HW_VF_ID_TO_OS(vf_id));
 }
 
-int hinic_deinit_vf_hw(struct hinic_sriov_info *sriov_info, u16 start_vf_id,
-		       u16 end_vf_id)
+static int hinic_deinit_vf_hw(struct hinic_sriov_info *sriov_info,
+			      u16 start_vf_id, u16 end_vf_id)
 {
 	struct hinic_dev *nic_dev;
 	u16 func_idx, idx;
@@ -908,7 +912,8 @@ void hinic_vf_func_free(struct hinic_hwdev *hwdev)
 	}
 }
 
-int hinic_init_vf_hw(struct hinic_hwdev *hwdev, u16 start_vf_id, u16 end_vf_id)
+static int hinic_init_vf_hw(struct hinic_hwdev *hwdev, u16 start_vf_id,
+			    u16 end_vf_id)
 {
 	u16 i, func_idx;
 	int err;
-- 
cgit v1.2.3


From 40cf7fbe8a43b1d8c3c0139423abbeb9625a909a Mon Sep 17 00:00:00 2001
From: Zou Wei <zou_wei@huawei.com>
Date: Thu, 30 Apr 2020 09:51:31 +0800
Subject: hinic: Use ARRAY_SIZE for nic_vf_cmd_msg_handler

fix coccinelle warning, use ARRAY_SIZE

drivers/net/ethernet/huawei/hinic/hinic_sriov.c:713:43-44: WARNING: Use ARRAY_SIZE

v1-->v2:
   remove cmd_number

v2-->v3:
   preserve the reverse christmas tree ordering of local variables

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_sriov.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index 0d44af9dce2a..fd4aaf43874a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -708,17 +708,15 @@ static int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
 	struct hinic_hwdev *dev = hwdev;
 	struct hinic_func_to_io *nic_io;
 	struct hinic_pfhwdev *pfhwdev;
-	u32 i, cmd_number;
 	int err = 0;
+	u32 i;
 
 	if (!hwdev)
 		return -EFAULT;
 
-	cmd_number = sizeof(nic_vf_cmd_msg_handler) /
-			    sizeof(struct vf_cmd_msg_handle);
 	pfhwdev = container_of(dev, struct hinic_pfhwdev, hwdev);
 	nic_io = &dev->func_to_io;
-	for (i = 0; i < cmd_number; i++) {
+	for (i = 0; i < ARRAY_SIZE(nic_vf_cmd_msg_handler); i++) {
 		vf_msg_handle = &nic_vf_cmd_msg_handler[i];
 		if (cmd == vf_msg_handle->cmd &&
 		    vf_msg_handle->cmd_msg_handler) {
@@ -729,7 +727,7 @@ static int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
 			break;
 		}
 	}
-	if (i == cmd_number)
+	if (i == ARRAY_SIZE(nic_vf_cmd_msg_handler))
 		err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC,
 					cmd, buf_in, in_size, buf_out,
 					out_size, HINIC_MGMT_MSG_SYNC);
-- 
cgit v1.2.3


From 1569a3c44303834680e93df2ecf60f356be9b322 Mon Sep 17 00:00:00 2001
From: Tang Bin <tangbin@cmss.chinamobile.com>
Date: Thu, 30 Apr 2020 20:15:31 +0800
Subject: net/faraday: Fix unnecessary check in ftmac100_probe()

The function ftmac100_probe() is only called with an openfirmware
platform device. Therefore there is no need to check that the passed
in device is NULL.

Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/faraday/ftmac100.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 32cf54f0e35b..473b337b2e3b 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1057,9 +1057,6 @@ static int ftmac100_probe(struct platform_device *pdev)
 	struct ftmac100 *priv;
 	int err;
 
-	if (!pdev)
-		return -ENODEV;
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENXIO;
-- 
cgit v1.2.3


From 801eb0501824da196c7b1c18c453528457308c5a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:48 +0300
Subject: stmmac: intel: Fix kernel crash due to wrong error path

Unfortunately sometimes ->probe() may fail. The commit b9663b7ca6ff
("net: stmmac: Enable SERDES power up/down sequence")
messed up with error handling and thus:

[   12.811311] ------------[ cut here ]------------
[   12.811993] kernel BUG at net/core/dev.c:9937!

Fix this by properly crafted error path.

Fixes: b9663b7ca6ff ("net: stmmac: Enable SERDES power up/down sequence")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Cc: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 565da6498c84..ff22f274aa43 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4991,7 +4991,7 @@ int stmmac_dvr_probe(struct device *device,
 						 priv->plat->bsp_priv);
 
 		if (ret < 0)
-			return ret;
+			goto error_serdes_powerup;
 	}
 
 #ifdef CONFIG_DEBUG_FS
@@ -5000,6 +5000,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	return ret;
 
+error_serdes_powerup:
+	unregister_netdev(ndev);
 error_netdev_register:
 	phylink_destroy(priv->phylink);
 error_phy_setup:
-- 
cgit v1.2.3


From 09f012e64e4b8126ed6f02d0a85a57c3a0465cf9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:49 +0300
Subject: stmmac: intel: Fix clock handling on error and remove paths

clk_prepare_enable() might fail, we have to check its returned value.
Besides that we have to call clk_disable_unprepare() on the error and
remove paths. Do above in the dwmac-intel driver.

While at it, remove leftover in stmmac_pci and remove unneeded condition
for NULL-aware clk_unregister_fixed_rate() call.

Fixes: 58da0cfa6cf1 ("net: stmmac: create dwmac-intel.c to contain all Intel platform")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 20 ++++++++++++++++----
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c  |  5 -----
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 2e4aaedb93f5..d163c4b43da0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -252,6 +252,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat)
 static int intel_mgbe_common_data(struct pci_dev *pdev,
 				  struct plat_stmmacenet_data *plat)
 {
+	int ret;
 	int i;
 
 	plat->clk_csr = 5;
@@ -324,7 +325,12 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 		dev_warn(&pdev->dev, "Fail to register stmmac-clk\n");
 		plat->stmmac_clk = NULL;
 	}
-	clk_prepare_enable(plat->stmmac_clk);
+
+	ret = clk_prepare_enable(plat->stmmac_clk);
+	if (ret) {
+		clk_unregister_fixed_rate(plat->stmmac_clk);
+		return ret;
+	}
 
 	/* Set default value for multicast hash bins */
 	plat->multicast_filter_bins = HASH_TABLE_SIZE;
@@ -657,7 +663,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	res.wol_irq = pdev->irq;
 	res.irq = pdev->irq;
 
-	return stmmac_dvr_probe(&pdev->dev, plat, &res);
+	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
+	if (ret) {
+		clk_disable_unprepare(plat->stmmac_clk);
+		clk_unregister_fixed_rate(plat->stmmac_clk);
+	}
+
+	return ret;
 }
 
 /**
@@ -675,8 +687,8 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	if (priv->plat->stmmac_clk)
-		clk_unregister_fixed_rate(priv->plat->stmmac_clk);
+	clk_disable_unprepare(priv->plat->stmmac_clk);
+	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 3fb21f7ac9fb..272cb47af9f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -217,15 +217,10 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
  */
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
-	struct net_device *ndev = dev_get_drvdata(&pdev->dev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
 	int i;
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	if (priv->plat->stmmac_clk)
-		clk_unregister_fixed_rate(priv->plat->stmmac_clk);
-
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-- 
cgit v1.2.3


From e578f043ffcf8b4f0999ab9e9194f156e90c7fd3 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:50 +0300
Subject: stmmac: intel: Remove unnecessary loop for PCI BARs

Copy'n'paste without thinking is not a good idea and in this case it brought
unnecessary loop over PCI BAR resources which was needed to workaround one of
STMicro RVP boards. Remove unnecessary loops from Intel driver.

Fixes: 58da0cfa6cf1 ("net: stmmac: create dwmac-intel.c to contain all Intel platform")
Cc: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index d163c4b43da0..e9f948559499 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -606,7 +606,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	struct intel_priv_data *intel_priv;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_resources res;
-	int i;
 	int ret;
 
 	intel_priv = devm_kzalloc(&pdev->dev, sizeof(*intel_priv),
@@ -637,15 +636,9 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 		return ret;
 	}
 
-	/* Get the base address of device */
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-		ret = pcim_iomap_regions(pdev, BIT(i), pci_name(pdev));
-		if (ret)
-			return ret;
-		break;
-	}
+	ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+	if (ret)
+		return ret;
 
 	pci_set_master(pdev);
 
@@ -659,7 +652,7 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	pci_enable_msi(pdev);
 
 	memset(&res, 0, sizeof(res));
-	res.addr = pcim_iomap_table(pdev)[i];
+	res.addr = pcim_iomap_table(pdev)[0];
 	res.wol_irq = pdev->irq;
 	res.irq = pdev->irq;
 
@@ -683,19 +676,13 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 {
 	struct net_device *ndev = dev_get_drvdata(&pdev->dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
-	int i;
 
 	stmmac_dvr_remove(&pdev->dev);
 
 	clk_disable_unprepare(priv->plat->stmmac_clk);
 	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i) == 0)
-			continue;
-		pcim_iounmap_regions(pdev, BIT(i));
-		break;
-	}
+	pcim_iounmap_regions(pdev, BIT(0));
 
 	pci_disable_device(pdev);
 }
-- 
cgit v1.2.3


From 52c1f794845411c39ee6deedb443894ca141b4a7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:51 +0300
Subject: stmmac: intel: Convert to use pci_alloc_irq_vectors() API

pci_enable_msi() is deprecated API, thus, switch to modern
pci_alloc_irq_vectors().

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index e9f948559499..bb8bf31c1259 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -649,15 +649,18 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	pci_enable_msi(pdev);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (ret < 0)
+		return ret;
 
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
-	res.wol_irq = pdev->irq;
-	res.irq = pdev->irq;
+	res.wol_irq = pci_irq_vector(pdev, 0);
+	res.irq = pci_irq_vector(pdev, 0);
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (ret) {
+		pci_free_irq_vectors(pdev);
 		clk_disable_unprepare(plat->stmmac_clk);
 		clk_unregister_fixed_rate(plat->stmmac_clk);
 	}
@@ -679,6 +682,8 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
+	pci_free_irq_vectors(pdev);
+
 	clk_disable_unprepare(priv->plat->stmmac_clk);
 	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
 
-- 
cgit v1.2.3


From d5383b0376643245d82230d8a974edd193ec900c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:52 +0300
Subject: stmmac: intel: Eliminate useless conditions and variables

There are useless conditions like

	func()
	{
		...
		int ret;
		...
		ret = foo();
		if (ret)
			return ret;

		return 0;
	}

which may be replaced with direct return statement, what we have done here.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index bb8bf31c1259..b0d735e4c13c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -347,16 +347,11 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 static int ehl_common_data(struct pci_dev *pdev,
 			   struct plat_stmmacenet_data *plat)
 {
-	int ret;
-
 	plat->rx_queues_to_use = 8;
 	plat->tx_queues_to_use = 8;
 	plat->clk_ptp_rate = 200000000;
-	ret = intel_mgbe_common_data(pdev, plat);
-	if (ret)
-		return ret;
 
-	return 0;
+	return intel_mgbe_common_data(pdev, plat);
 }
 
 static int ehl_sgmii_data(struct pci_dev *pdev,
@@ -457,16 +452,11 @@ static struct stmmac_pci_info ehl_pse1_sgmii1g_pci_info = {
 static int tgl_common_data(struct pci_dev *pdev,
 			   struct plat_stmmacenet_data *plat)
 {
-	int ret;
-
 	plat->rx_queues_to_use = 6;
 	plat->tx_queues_to_use = 4;
 	plat->clk_ptp_rate = 200000000;
-	ret = intel_mgbe_common_data(pdev, plat);
-	if (ret)
-		return ret;
 
-	return 0;
+	return intel_mgbe_common_data(pdev, plat);
 }
 
 static int tgl_sgmii_data(struct pci_dev *pdev,
-- 
cgit v1.2.3


From ccacb703b0f8141757fba2931a2a7202b54194d0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:53 +0300
Subject: stmmac: intel: Fix indentation to put on one line affected code

There is no competition to get more LOCs into the kernel, and driver can look
better and have improved readability without those additional line breaks.

While at it, shorten info structures that they are all PCI, at the end it's
a PCI driver for Intel hardware.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 92 ++++++++---------------
 1 file changed, 32 insertions(+), 60 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index b0d735e4c13c..2ac9dfb3462c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -83,13 +83,9 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
 
 	/* assert clk_req */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
-
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 	data |= SERDES_PLL_CLK;
-
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* check for clk_ack assertion */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -103,13 +99,9 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 	}
 
 	/* assert lane reset */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
-
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 	data |= SERDES_RST;
-
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* check for assert lane reset reflection */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -123,14 +115,12 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 	}
 
 	/*  move power state to P0 */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 
 	data &= ~SERDES_PWR_ST_MASK;
 	data |= SERDES_PWR_ST_P0 << SERDES_PWR_ST_SHIFT;
 
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* Check for P0 state */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -159,14 +149,12 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
 
 	/*  move power state to P3 */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 
 	data &= ~SERDES_PWR_ST_MASK;
 	data |= SERDES_PWR_ST_P3 << SERDES_PWR_ST_SHIFT;
 
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* Check for P3 state */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -180,13 +168,9 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	}
 
 	/* de-assert clk_req */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
-
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 	data &= ~SERDES_PLL_CLK;
-
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* check for clk_ack de-assert */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -200,13 +184,9 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
 	}
 
 	/* de-assert lane reset */
-	data = mdiobus_read(priv->mii, serdes_phy_addr,
-			    SERDES_GCR0);
-
+	data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0);
 	data &= ~SERDES_RST;
-
-	mdiobus_write(priv->mii, serdes_phy_addr,
-		      SERDES_GCR0, data);
+	mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data);
 
 	/* check for de-assert lane reset reflection */
 	data = serdes_status_poll(priv, serdes_phy_addr,
@@ -367,7 +347,7 @@ static int ehl_sgmii_data(struct pci_dev *pdev,
 	return ehl_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_sgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_sgmii1g_info = {
 	.setup = ehl_sgmii_data,
 };
 
@@ -381,7 +361,7 @@ static int ehl_rgmii_data(struct pci_dev *pdev,
 	return ehl_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_rgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_rgmii1g_info = {
 	.setup = ehl_rgmii_data,
 };
 
@@ -400,7 +380,7 @@ static int ehl_pse0_rgmii1g_data(struct pci_dev *pdev,
 	return ehl_pse0_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_pse0_rgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_pse0_rgmii1g_info = {
 	.setup = ehl_pse0_rgmii1g_data,
 };
 
@@ -413,7 +393,7 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev,
 	return ehl_pse0_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_pse0_sgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_pse0_sgmii1g_info = {
 	.setup = ehl_pse0_sgmii1g_data,
 };
 
@@ -432,7 +412,7 @@ static int ehl_pse1_rgmii1g_data(struct pci_dev *pdev,
 	return ehl_pse1_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_pse1_rgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_pse1_rgmii1g_info = {
 	.setup = ehl_pse1_rgmii1g_data,
 };
 
@@ -445,7 +425,7 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev,
 	return ehl_pse1_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info ehl_pse1_sgmii1g_pci_info = {
+static struct stmmac_pci_info ehl_pse1_sgmii1g_info = {
 	.setup = ehl_pse1_sgmii1g_data,
 };
 
@@ -470,7 +450,7 @@ static int tgl_sgmii_data(struct pci_dev *pdev,
 	return tgl_common_data(pdev, plat);
 }
 
-static struct stmmac_pci_info tgl_sgmii1g_pci_info = {
+static struct stmmac_pci_info tgl_sgmii1g_info = {
 	.setup = tgl_sgmii_data,
 };
 
@@ -573,7 +553,7 @@ static int quark_default_data(struct pci_dev *pdev,
 	return 0;
 }
 
-static const struct stmmac_pci_info quark_pci_info = {
+static const struct stmmac_pci_info quark_info = {
 	.setup = quark_default_data,
 };
 
@@ -598,8 +578,7 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	struct stmmac_resources res;
 	int ret;
 
-	intel_priv = devm_kzalloc(&pdev->dev, sizeof(*intel_priv),
-				  GFP_KERNEL);
+	intel_priv = devm_kzalloc(&pdev->dev, sizeof(*intel_priv), GFP_KERNEL);
 	if (!intel_priv)
 		return -ENOMEM;
 
@@ -736,26 +715,19 @@ static SIMPLE_DEV_PM_OPS(intel_eth_pm_ops, intel_eth_pci_suspend,
 #define PCI_DEVICE_ID_INTEL_TGL_SGMII1G_ID		0xa0ac
 
 static const struct pci_device_id intel_eth_pci_id_table[] = {
-	{ PCI_DEVICE_DATA(INTEL, QUARK_ID, &quark_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_RGMII1G_ID, &ehl_rgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_SGMII1G_ID, &ehl_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_SGMII2G5_ID, &ehl_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_RGMII1G_ID,
-			  &ehl_pse0_rgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_SGMII1G_ID,
-			  &ehl_pse0_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_SGMII2G5_ID,
-			  &ehl_pse0_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_RGMII1G_ID,
-			  &ehl_pse1_rgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID,
-			  &ehl_pse1_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID,
-			  &ehl_pse1_sgmii1g_pci_info) },
-	{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_pci_info) },
+	{ PCI_DEVICE_DATA(INTEL, QUARK_ID, &quark_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_RGMII1G_ID, &ehl_rgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_SGMII1G_ID, &ehl_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_SGMII2G5_ID, &ehl_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_RGMII1G_ID, &ehl_pse0_rgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_SGMII1G_ID, &ehl_pse0_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE0_SGMII2G5_ID, &ehl_pse0_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_RGMII1G_ID, &ehl_pse1_rgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID, &ehl_pse1_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID, &ehl_pse1_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) },
 	{}
 };
-
 MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);
 
 static struct pci_driver intel_eth_pci_driver = {
-- 
cgit v1.2.3


From 29e0c2f39f983f3b83f6004f9fd05f8f4ce225c6 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 30 Apr 2020 18:02:54 +0300
Subject: stmmac: intel: Place object in the Makefile according to the order

Follow the order for the platform drivers, i.e. generic object are going first.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 5a6f265bc540..f9d024d6b69b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -30,6 +30,6 @@ obj-$(CONFIG_DWMAC_GENERIC)	+= dwmac-generic.o
 stmmac-platform-objs:= stmmac_platform.o
 dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o
 
-obj-$(CONFIG_DWMAC_INTEL) += dwmac-intel.o
-obj-$(CONFIG_STMMAC_PCI) += stmmac-pci.o
+obj-$(CONFIG_STMMAC_PCI)	+= stmmac-pci.o
+obj-$(CONFIG_DWMAC_INTEL)	+= dwmac-intel.o
 stmmac-pci-objs:= stmmac_pci.o
-- 
cgit v1.2.3


From d9d6ef25ecab3e10966981bc58d014576da74272 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 30 Apr 2020 18:04:02 +0200
Subject: docs: networking: convert netconsole.txt to ReST

- add SPDX header;
- add a document title;
- mark code blocks and literals as such;
- mark tables as such;
- add notes markups;
- adjust identation, whitespaces and blank lines;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/admin-guide/kernel-parameters.txt |   2 +-
 Documentation/admin-guide/serial-console.rst    |   2 +-
 Documentation/networking/index.rst              |   1 +
 Documentation/networking/netconsole.rst         | 239 ++++++++++++++++++++++++
 Documentation/networking/netconsole.txt         | 210 ---------------------
 drivers/net/Kconfig                             |   4 +-
 drivers/net/ethernet/toshiba/ps3_gelic_net.c    |   2 +-
 drivers/net/ethernet/toshiba/spider_net.c       |   2 +-
 8 files changed, 246 insertions(+), 216 deletions(-)
 create mode 100644 Documentation/networking/netconsole.rst
 delete mode 100644 Documentation/networking/netconsole.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e43f2e1f2958..398c34804bb8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -638,7 +638,7 @@
 
 			See Documentation/admin-guide/serial-console.rst for more
 			information.  See
-			Documentation/networking/netconsole.txt for an
+			Documentation/networking/netconsole.rst for an
 			alternative.
 
 		uart[8250],io,<addr>[,options]
diff --git a/Documentation/admin-guide/serial-console.rst b/Documentation/admin-guide/serial-console.rst
index a8d1e36b627a..58b32832e50a 100644
--- a/Documentation/admin-guide/serial-console.rst
+++ b/Documentation/admin-guide/serial-console.rst
@@ -54,7 +54,7 @@ You will need to create a new device to use ``/dev/console``. The official
 ``/dev/console`` is now character device 5,1.
 
 (You can also use a network device as a console.  See
-``Documentation/networking/netconsole.txt`` for information on that.)
+``Documentation/networking/netconsole.rst`` for information on that.)
 
 Here's an example that will use ``/dev/ttyS1`` (COM2) as the console.
 Replace the sample values as needed.
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 492658bf7c0d..e58f872d401d 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -80,6 +80,7 @@ Contents:
    mac80211-injection
    mpls-sysctl
    multiqueue
+   netconsole
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
new file mode 100644
index 000000000000..1f5c4a04027c
--- /dev/null
+++ b/Documentation/networking/netconsole.rst
@@ -0,0 +1,239 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========
+Netconsole
+==========
+
+
+started by Ingo Molnar <mingo@redhat.com>, 2001.09.17
+
+2.6 port and netpoll api by Matt Mackall <mpm@selenic.com>, Sep 9 2003
+
+IPv6 support by Cong Wang <xiyou.wangcong@gmail.com>, Jan 1 2013
+
+Extended console support by Tejun Heo <tj@kernel.org>, May 1 2015
+
+Please send bug reports to Matt Mackall <mpm@selenic.com>
+Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com>
+
+Introduction:
+=============
+
+This module logs kernel printk messages over UDP allowing debugging of
+problem where disk logging fails and serial consoles are impractical.
+
+It can be used either built-in or as a module. As a built-in,
+netconsole initializes immediately after NIC cards and will bring up
+the specified interface as soon as possible. While this doesn't allow
+capture of early kernel panics, it does capture most of the boot
+process.
+
+Sender and receiver configuration:
+==================================
+
+It takes a string configuration parameter "netconsole" in the
+following format::
+
+ netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
+
+   where
+	+             if present, enable extended console support
+	src-port      source for UDP packets (defaults to 6665)
+	src-ip        source IP to use (interface address)
+	dev           network interface (eth0)
+	tgt-port      port for logging agent (6666)
+	tgt-ip        IP address for logging agent
+	tgt-macaddr   ethernet MAC address for logging agent (broadcast)
+
+Examples::
+
+ linux netconsole=4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc
+
+or::
+
+ insmod netconsole netconsole=@/,@10.0.0.2/
+
+or using IPv6::
+
+ insmod netconsole netconsole=@/,@fd00:1:2:3::1/
+
+It also supports logging to multiple remote agents by specifying
+parameters for the multiple agents separated by semicolons and the
+complete string enclosed in "quotes", thusly::
+
+ modprobe netconsole netconsole="@/,@10.0.0.2/;@/eth1,6892@10.0.0.3/"
+
+Built-in netconsole starts immediately after the TCP stack is
+initialized and attempts to bring up the supplied dev at the supplied
+address.
+
+The remote host has several options to receive the kernel messages,
+for example:
+
+1) syslogd
+
+2) netcat
+
+   On distributions using a BSD-based netcat version (e.g. Fedora,
+   openSUSE and Ubuntu) the listening port must be specified without
+   the -p switch::
+
+	nc -u -l -p <port>' / 'nc -u -l <port>
+
+    or::
+
+	netcat -u -l -p <port>' / 'netcat -u -l <port>
+
+3) socat
+
+::
+
+   socat udp-recv:<port> -
+
+Dynamic reconfiguration:
+========================
+
+Dynamic reconfigurability is a useful addition to netconsole that enables
+remote logging targets to be dynamically added, removed, or have their
+parameters reconfigured at runtime from a configfs-based userspace interface.
+[ Note that the parameters of netconsole targets that were specified/created
+from the boot/module option are not exposed via this interface, and hence
+cannot be modified dynamically. ]
+
+To include this feature, select CONFIG_NETCONSOLE_DYNAMIC when building the
+netconsole module (or kernel, if netconsole is built-in).
+
+Some examples follow (where configfs is mounted at the /sys/kernel/config
+mountpoint).
+
+To add a remote logging target (target names can be arbitrary)::
+
+ cd /sys/kernel/config/netconsole/
+ mkdir target1
+
+Note that newly created targets have default parameter values (as mentioned
+above) and are disabled by default -- they must first be enabled by writing
+"1" to the "enabled" attribute (usually after setting parameters accordingly)
+as described below.
+
+To remove a target::
+
+ rmdir /sys/kernel/config/netconsole/othertarget/
+
+The interface exposes these parameters of a netconsole target to userspace:
+
+	==============  =================================       ============
+	enabled		Is this target currently enabled?	(read-write)
+	extended	Extended mode enabled			(read-write)
+	dev_name	Local network interface name		(read-write)
+	local_port	Source UDP port to use			(read-write)
+	remote_port	Remote agent's UDP port			(read-write)
+	local_ip	Source IP address to use		(read-write)
+	remote_ip	Remote agent's IP address		(read-write)
+	local_mac	Local interface's MAC address		(read-only)
+	remote_mac	Remote agent's MAC address		(read-write)
+	==============  =================================       ============
+
+The "enabled" attribute is also used to control whether the parameters of
+a target can be updated or not -- you can modify the parameters of only
+disabled targets (i.e. if "enabled" is 0).
+
+To update a target's parameters::
+
+ cat enabled				# check if enabled is 1
+ echo 0 > enabled			# disable the target (if required)
+ echo eth2 > dev_name			# set local interface
+ echo 10.0.0.4 > remote_ip		# update some parameter
+ echo cb:a9:87:65:43:21 > remote_mac	# update more parameters
+ echo 1 > enabled			# enable target again
+
+You can also update the local interface dynamically. This is especially
+useful if you want to use interfaces that have newly come up (and may not
+have existed when netconsole was loaded / initialized).
+
+Extended console:
+=================
+
+If '+' is prefixed to the configuration line or "extended" config file
+is set to 1, extended console support is enabled. An example boot
+param follows::
+
+ linux netconsole=+4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc
+
+Log messages are transmitted with extended metadata header in the
+following format which is the same as /dev/kmsg::
+
+ <level>,<sequnum>,<timestamp>,<contflag>;<message text>
+
+Non printable characters in <message text> are escaped using "\xff"
+notation. If the message contains optional dictionary, verbatim
+newline is used as the delimeter.
+
+If a message doesn't fit in certain number of bytes (currently 1000),
+the message is split into multiple fragments by netconsole. These
+fragments are transmitted with "ncfrag" header field added::
+
+ ncfrag=<byte-offset>/<total-bytes>
+
+For example, assuming a lot smaller chunk size, a message "the first
+chunk, the 2nd chunk." may be split as follows::
+
+ 6,416,1758426,-,ncfrag=0/31;the first chunk,
+ 6,416,1758426,-,ncfrag=16/31; the 2nd chunk.
+
+Miscellaneous notes:
+====================
+
+.. Warning::
+
+   the default target ethernet setting uses the broadcast
+   ethernet address to send packets, which can cause increased load on
+   other systems on the same ethernet segment.
+
+.. Tip::
+
+   some LAN switches may be configured to suppress ethernet broadcasts
+   so it is advised to explicitly specify the remote agents' MAC addresses
+   from the config parameters passed to netconsole.
+
+.. Tip::
+
+   to find out the MAC address of, say, 10.0.0.2, you may try using::
+
+	ping -c 1 10.0.0.2 ; /sbin/arp -n | grep 10.0.0.2
+
+.. Tip::
+
+   in case the remote logging agent is on a separate LAN subnet than
+   the sender, it is suggested to try specifying the MAC address of the
+   default gateway (you may use /sbin/route -n to find it out) as the
+   remote MAC address instead.
+
+.. note::
+
+   the network device (eth1 in the above case) can run any kind
+   of other network traffic, netconsole is not intrusive. Netconsole
+   might cause slight delays in other traffic if the volume of kernel
+   messages is high, but should have no other impact.
+
+.. note::
+
+   if you find that the remote logging agent is not receiving or
+   printing all messages from the sender, it is likely that you have set
+   the "console_loglevel" parameter (on the sender) to only send high
+   priority messages to the console. You can change this at runtime using::
+
+	dmesg -n 8
+
+   or by specifying "debug" on the kernel command line at boot, to send
+   all kernel messages to the console. A specific value for this parameter
+   can also be set using the "loglevel" kernel boot option. See the
+   dmesg(8) man page and Documentation/admin-guide/kernel-parameters.rst
+   for details.
+
+Netconsole was designed to be as instantaneous as possible, to
+enable the logging of even the most critical kernel bugs. It works
+from IRQ contexts as well, and does not enable interrupts while
+sending packets. Due to these unique needs, configuration cannot
+be more automatic, and some fundamental limitations will remain:
+only IP networks, UDP packets and ethernet devices are supported.
diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt
deleted file mode 100644
index 296ea00fd3eb..000000000000
--- a/Documentation/networking/netconsole.txt
+++ /dev/null
@@ -1,210 +0,0 @@
-
-started by Ingo Molnar <mingo@redhat.com>, 2001.09.17
-2.6 port and netpoll api by Matt Mackall <mpm@selenic.com>, Sep 9 2003
-IPv6 support by Cong Wang <xiyou.wangcong@gmail.com>, Jan 1 2013
-Extended console support by Tejun Heo <tj@kernel.org>, May 1 2015
-
-Please send bug reports to Matt Mackall <mpm@selenic.com>
-Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com>
-
-Introduction:
-=============
-
-This module logs kernel printk messages over UDP allowing debugging of
-problem where disk logging fails and serial consoles are impractical.
-
-It can be used either built-in or as a module. As a built-in,
-netconsole initializes immediately after NIC cards and will bring up
-the specified interface as soon as possible. While this doesn't allow
-capture of early kernel panics, it does capture most of the boot
-process.
-
-Sender and receiver configuration:
-==================================
-
-It takes a string configuration parameter "netconsole" in the
-following format:
-
- netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
-
-   where
-        +             if present, enable extended console support
-        src-port      source for UDP packets (defaults to 6665)
-        src-ip        source IP to use (interface address)
-        dev           network interface (eth0)
-        tgt-port      port for logging agent (6666)
-        tgt-ip        IP address for logging agent
-        tgt-macaddr   ethernet MAC address for logging agent (broadcast)
-
-Examples:
-
- linux netconsole=4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc
-
-  or
-
- insmod netconsole netconsole=@/,@10.0.0.2/
-
-  or using IPv6
-
- insmod netconsole netconsole=@/,@fd00:1:2:3::1/
-
-It also supports logging to multiple remote agents by specifying
-parameters for the multiple agents separated by semicolons and the
-complete string enclosed in "quotes", thusly:
-
- modprobe netconsole netconsole="@/,@10.0.0.2/;@/eth1,6892@10.0.0.3/"
-
-Built-in netconsole starts immediately after the TCP stack is
-initialized and attempts to bring up the supplied dev at the supplied
-address.
-
-The remote host has several options to receive the kernel messages,
-for example:
-
-1) syslogd
-
-2) netcat
-
-   On distributions using a BSD-based netcat version (e.g. Fedora,
-   openSUSE and Ubuntu) the listening port must be specified without
-   the -p switch:
-
-   'nc -u -l -p <port>' / 'nc -u -l <port>' or
-   'netcat -u -l -p <port>' / 'netcat -u -l <port>'
-
-3) socat
-
-   'socat udp-recv:<port> -'
-
-Dynamic reconfiguration:
-========================
-
-Dynamic reconfigurability is a useful addition to netconsole that enables
-remote logging targets to be dynamically added, removed, or have their
-parameters reconfigured at runtime from a configfs-based userspace interface.
-[ Note that the parameters of netconsole targets that were specified/created
-from the boot/module option are not exposed via this interface, and hence
-cannot be modified dynamically. ]
-
-To include this feature, select CONFIG_NETCONSOLE_DYNAMIC when building the
-netconsole module (or kernel, if netconsole is built-in).
-
-Some examples follow (where configfs is mounted at the /sys/kernel/config
-mountpoint).
-
-To add a remote logging target (target names can be arbitrary):
-
- cd /sys/kernel/config/netconsole/
- mkdir target1
-
-Note that newly created targets have default parameter values (as mentioned
-above) and are disabled by default -- they must first be enabled by writing
-"1" to the "enabled" attribute (usually after setting parameters accordingly)
-as described below.
-
-To remove a target:
-
- rmdir /sys/kernel/config/netconsole/othertarget/
-
-The interface exposes these parameters of a netconsole target to userspace:
-
-	enabled		Is this target currently enabled?	(read-write)
-	extended	Extended mode enabled			(read-write)
-	dev_name	Local network interface name		(read-write)
-	local_port	Source UDP port to use			(read-write)
-	remote_port	Remote agent's UDP port			(read-write)
-	local_ip	Source IP address to use		(read-write)
-	remote_ip	Remote agent's IP address		(read-write)
-	local_mac	Local interface's MAC address		(read-only)
-	remote_mac	Remote agent's MAC address		(read-write)
-
-The "enabled" attribute is also used to control whether the parameters of
-a target can be updated or not -- you can modify the parameters of only
-disabled targets (i.e. if "enabled" is 0).
-
-To update a target's parameters:
-
- cat enabled				# check if enabled is 1
- echo 0 > enabled			# disable the target (if required)
- echo eth2 > dev_name			# set local interface
- echo 10.0.0.4 > remote_ip		# update some parameter
- echo cb:a9:87:65:43:21 > remote_mac	# update more parameters
- echo 1 > enabled			# enable target again
-
-You can also update the local interface dynamically. This is especially
-useful if you want to use interfaces that have newly come up (and may not
-have existed when netconsole was loaded / initialized).
-
-Extended console:
-=================
-
-If '+' is prefixed to the configuration line or "extended" config file
-is set to 1, extended console support is enabled. An example boot
-param follows.
-
- linux netconsole=+4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc
-
-Log messages are transmitted with extended metadata header in the
-following format which is the same as /dev/kmsg.
-
- <level>,<sequnum>,<timestamp>,<contflag>;<message text>
-
-Non printable characters in <message text> are escaped using "\xff"
-notation. If the message contains optional dictionary, verbatim
-newline is used as the delimeter.
-
-If a message doesn't fit in certain number of bytes (currently 1000),
-the message is split into multiple fragments by netconsole. These
-fragments are transmitted with "ncfrag" header field added.
-
- ncfrag=<byte-offset>/<total-bytes>
-
-For example, assuming a lot smaller chunk size, a message "the first
-chunk, the 2nd chunk." may be split as follows.
-
- 6,416,1758426,-,ncfrag=0/31;the first chunk,
- 6,416,1758426,-,ncfrag=16/31; the 2nd chunk.
-
-Miscellaneous notes:
-====================
-
-WARNING: the default target ethernet setting uses the broadcast
-ethernet address to send packets, which can cause increased load on
-other systems on the same ethernet segment.
-
-TIP: some LAN switches may be configured to suppress ethernet broadcasts
-so it is advised to explicitly specify the remote agents' MAC addresses
-from the config parameters passed to netconsole.
-
-TIP: to find out the MAC address of, say, 10.0.0.2, you may try using:
-
- ping -c 1 10.0.0.2 ; /sbin/arp -n | grep 10.0.0.2
-
-TIP: in case the remote logging agent is on a separate LAN subnet than
-the sender, it is suggested to try specifying the MAC address of the
-default gateway (you may use /sbin/route -n to find it out) as the
-remote MAC address instead.
-
-NOTE: the network device (eth1 in the above case) can run any kind
-of other network traffic, netconsole is not intrusive. Netconsole
-might cause slight delays in other traffic if the volume of kernel
-messages is high, but should have no other impact.
-
-NOTE: if you find that the remote logging agent is not receiving or
-printing all messages from the sender, it is likely that you have set
-the "console_loglevel" parameter (on the sender) to only send high
-priority messages to the console. You can change this at runtime using:
-
- dmesg -n 8
-
-or by specifying "debug" on the kernel command line at boot, to send
-all kernel messages to the console. A specific value for this parameter
-can also be set using the "loglevel" kernel boot option. See the
-dmesg(8) man page and Documentation/admin-guide/kernel-parameters.rst for details.
-
-Netconsole was designed to be as instantaneous as possible, to
-enable the logging of even the most critical kernel bugs. It works
-from IRQ contexts as well, and does not enable interrupts while
-sending packets. Due to these unique needs, configuration cannot
-be more automatic, and some fundamental limitations will remain:
-only IP networks, UDP packets and ethernet devices are supported.
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index c822f4a6d166..ad64be98330f 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -302,7 +302,7 @@ config NETCONSOLE
 	tristate "Network console logging support"
 	---help---
 	  If you want to log kernel messages over the network, enable this.
-	  See <file:Documentation/networking/netconsole.txt> for details.
+	  See <file:Documentation/networking/netconsole.rst> for details.
 
 config NETCONSOLE_DYNAMIC
 	bool "Dynamic reconfiguration of logging targets"
@@ -312,7 +312,7 @@ config NETCONSOLE_DYNAMIC
 	  This option enables the ability to dynamically reconfigure target
 	  parameters (interface, IP addresses, port numbers, MAC addresses)
 	  at runtime through a userspace interface exported using configfs.
-	  See <file:Documentation/networking/netconsole.txt> for details.
+	  See <file:Documentation/networking/netconsole.rst> for details.
 
 config NETPOLL
 	def_bool NETCONSOLE
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 070dd6fa9401..310e6839c6e5 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1150,7 +1150,7 @@ static irqreturn_t gelic_card_interrupt(int irq, void *ptr)
  * gelic_net_poll_controller - artificial interrupt for netconsole etc.
  * @netdev: interface device structure
  *
- * see Documentation/networking/netconsole.txt
+ * see Documentation/networking/netconsole.rst
  */
 void gelic_net_poll_controller(struct net_device *netdev)
 {
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 6576271642c1..3902b3aeb0c2 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -1615,7 +1615,7 @@ spider_net_interrupt(int irq, void *ptr)
  * spider_net_poll_controller - artificial interrupt for netconsole etc.
  * @netdev: interface device structure
  *
- * see Documentation/networking/netconsole.txt
+ * see Documentation/networking/netconsole.rst
  */
 static void
 spider_net_poll_controller(struct net_device *netdev)
-- 
cgit v1.2.3


From 466010342e89240c45746f65767c7290b96a4b36 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:08 +0300
Subject: mlxsw: spectrum_span: Add APIs to get / put a SPAN agent

Given a netdev that packets should be mirrored to, create a SPAN agent
and return its identifier to the caller.

The SPAN agent is reference counted, as multiple tc-mirred actions can
point to the same destination netdev.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 43 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_span.h    |  4 ++
 2 files changed, 47 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index ae3c8a1e9a43..c4159f4a66e2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -1039,3 +1039,46 @@ void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp)
 		return;
 	mlxsw_core_schedule_work(&mlxsw_sp->span->work);
 }
+
+int mlxsw_sp_span_agent_get(struct mlxsw_sp *mlxsw_sp,
+			    const struct net_device *to_dev, int *p_span_id)
+{
+	const struct mlxsw_sp_span_entry_ops *ops;
+	struct mlxsw_sp_span_entry *span_entry;
+	struct mlxsw_sp_span_parms sparms;
+	int err;
+
+	ASSERT_RTNL();
+
+	ops = mlxsw_sp_span_entry_ops(mlxsw_sp, to_dev);
+	if (!ops) {
+		dev_err(mlxsw_sp->bus_info->dev, "Cannot mirror to requested destination\n");
+		return -EOPNOTSUPP;
+	}
+
+	memset(&sparms, 0, sizeof(sparms));
+	err = ops->parms_set(to_dev, &sparms);
+	if (err)
+		return err;
+
+	span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms);
+	if (!span_entry)
+		return -ENOBUFS;
+
+	*p_span_id = span_entry->id;
+
+	return 0;
+}
+
+void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id)
+{
+	struct mlxsw_sp_span_entry *span_entry;
+
+	ASSERT_RTNL();
+
+	span_entry = mlxsw_sp_span_entry_find_by_id(mlxsw_sp, span_id);
+	if (WARN_ON_ONCE(!span_entry))
+		return;
+
+	mlxsw_sp_span_entry_put(mlxsw_sp, span_entry);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index d23abdf957fa..b79de9a125bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -77,4 +77,8 @@ void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu);
 void mlxsw_sp_span_speed_update_work(struct work_struct *work);
 
+int mlxsw_sp_span_agent_get(struct mlxsw_sp *mlxsw_sp,
+			    const struct net_device *to_dev, int *p_span_id);
+void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id);
+
 #endif
-- 
cgit v1.2.3


From ed04458d4a900005d96b991fc0eb938875091047 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:09 +0300
Subject: mlxsw: spectrum_span: Add APIs to get / put an analyzed port

An analyzed port is a port whose incoming / outgoing traffic is mirrored
to a SPAN agent and analyzed on a remote server.

A port can be analyzed by multiple tc filters and therefore the
corresponding analyzed port entry needs to be reference counted. This is
significant because ports whose outgoing traffic is analyzed need to
have an egress mirror buffer.

Add APIs to get / put an analyzed port. Allocate an egress mirror buffer
on a port when it is first inspected at egress and free the buffer when
it is no longer inspected at egress.

Protect the list of analyzed ports with a mutex, as a later patch will
traverse it from a context in which RTNL lock is not held.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 136 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_span.h    |   4 +
 2 files changed, 140 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index c4159f4a66e2..5edf9d1bf937 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -3,6 +3,7 @@
 
 #include <linux/if_bridge.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/refcount.h>
 #include <linux/rtnetlink.h>
 #include <linux/workqueue.h>
@@ -20,11 +21,20 @@
 struct mlxsw_sp_span {
 	struct work_struct work;
 	struct mlxsw_sp *mlxsw_sp;
+	struct list_head analyzed_ports_list;
+	struct mutex analyzed_ports_lock; /* Protects analyzed_ports_list */
 	atomic_t active_entries_count;
 	int entries_count;
 	struct mlxsw_sp_span_entry entries[];
 };
 
+struct mlxsw_sp_span_analyzed_port {
+	struct list_head list; /* Member of analyzed_ports_list */
+	refcount_t ref_count;
+	u8 local_port;
+	bool ingress;
+};
+
 static void mlxsw_sp_span_respin_work(struct work_struct *work);
 
 static u64 mlxsw_sp_span_occ_get(void *priv)
@@ -49,6 +59,8 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp)
 		return -ENOMEM;
 	span->entries_count = entries_count;
 	atomic_set(&span->active_entries_count, 0);
+	mutex_init(&span->analyzed_ports_lock);
+	INIT_LIST_HEAD(&span->analyzed_ports_list);
 	span->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp->span = span;
 
@@ -79,6 +91,8 @@ void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp)
 
 		WARN_ON_ONCE(!list_empty(&curr->bound_ports_list));
 	}
+	WARN_ON_ONCE(!list_empty(&mlxsw_sp->span->analyzed_ports_list));
+	mutex_destroy(&mlxsw_sp->span->analyzed_ports_lock);
 	kfree(mlxsw_sp->span);
 }
 
@@ -1082,3 +1096,125 @@ void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id)
 
 	mlxsw_sp_span_entry_put(mlxsw_sp, span_entry);
 }
+
+static struct mlxsw_sp_span_analyzed_port *
+mlxsw_sp_span_analyzed_port_find(struct mlxsw_sp_span *span, u8 local_port,
+				 bool ingress)
+{
+	struct mlxsw_sp_span_analyzed_port *analyzed_port;
+
+	list_for_each_entry(analyzed_port, &span->analyzed_ports_list, list) {
+		if (analyzed_port->local_port == local_port &&
+		    analyzed_port->ingress == ingress)
+			return analyzed_port;
+	}
+
+	return NULL;
+}
+
+static struct mlxsw_sp_span_analyzed_port *
+mlxsw_sp_span_analyzed_port_create(struct mlxsw_sp_span *span,
+				   struct mlxsw_sp_port *mlxsw_sp_port,
+				   bool ingress)
+{
+	struct mlxsw_sp_span_analyzed_port *analyzed_port;
+	int err;
+
+	analyzed_port = kzalloc(sizeof(*analyzed_port), GFP_KERNEL);
+	if (!analyzed_port)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&analyzed_port->ref_count, 1);
+	analyzed_port->local_port = mlxsw_sp_port->local_port;
+	analyzed_port->ingress = ingress;
+	list_add_tail(&analyzed_port->list, &span->analyzed_ports_list);
+
+	/* An egress mirror buffer should be allocated on the egress port which
+	 * does the mirroring.
+	 */
+	if (!ingress) {
+		u16 mtu = mlxsw_sp_port->dev->mtu;
+
+		err = mlxsw_sp_span_port_buffsize_update(mlxsw_sp_port, mtu);
+		if (err)
+			goto err_buffsize_update;
+	}
+
+	return analyzed_port;
+
+err_buffsize_update:
+	list_del(&analyzed_port->list);
+	kfree(analyzed_port);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_span_analyzed_port_destroy(struct mlxsw_sp_span *span,
+				    struct mlxsw_sp_span_analyzed_port *
+				    analyzed_port)
+{
+	struct mlxsw_sp *mlxsw_sp = span->mlxsw_sp;
+	char sbib_pl[MLXSW_REG_SBIB_LEN];
+
+	/* Remove egress mirror buffer now that port is no longer analyzed
+	 * at egress.
+	 */
+	if (!analyzed_port->ingress) {
+		mlxsw_reg_sbib_pack(sbib_pl, analyzed_port->local_port, 0);
+		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
+	}
+
+	list_del(&analyzed_port->list);
+	kfree(analyzed_port);
+}
+
+int mlxsw_sp_span_analyzed_port_get(struct mlxsw_sp_port *mlxsw_sp_port,
+				    bool ingress)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_span_analyzed_port *analyzed_port;
+	u8 local_port = mlxsw_sp_port->local_port;
+	int err = 0;
+
+	mutex_lock(&mlxsw_sp->span->analyzed_ports_lock);
+
+	analyzed_port = mlxsw_sp_span_analyzed_port_find(mlxsw_sp->span,
+							 local_port, ingress);
+	if (analyzed_port) {
+		refcount_inc(&analyzed_port->ref_count);
+		goto out_unlock;
+	}
+
+	analyzed_port = mlxsw_sp_span_analyzed_port_create(mlxsw_sp->span,
+							   mlxsw_sp_port,
+							   ingress);
+	if (IS_ERR(analyzed_port))
+		err = PTR_ERR(analyzed_port);
+
+out_unlock:
+	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
+	return err;
+}
+
+void mlxsw_sp_span_analyzed_port_put(struct mlxsw_sp_port *mlxsw_sp_port,
+				     bool ingress)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_span_analyzed_port *analyzed_port;
+	u8 local_port = mlxsw_sp_port->local_port;
+
+	mutex_lock(&mlxsw_sp->span->analyzed_ports_lock);
+
+	analyzed_port = mlxsw_sp_span_analyzed_port_find(mlxsw_sp->span,
+							 local_port, ingress);
+	if (WARN_ON_ONCE(!analyzed_port))
+		goto out_unlock;
+
+	if (!refcount_dec_and_test(&analyzed_port->ref_count))
+		goto out_unlock;
+
+	mlxsw_sp_span_analyzed_port_destroy(mlxsw_sp->span, analyzed_port);
+
+out_unlock:
+	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index b79de9a125bb..1345eda5cc34 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -80,5 +80,9 @@ void mlxsw_sp_span_speed_update_work(struct work_struct *work);
 int mlxsw_sp_span_agent_get(struct mlxsw_sp *mlxsw_sp,
 			    const struct net_device *to_dev, int *p_span_id);
 void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id);
+int mlxsw_sp_span_analyzed_port_get(struct mlxsw_sp_port *mlxsw_sp_port,
+				    bool ingress);
+void mlxsw_sp_span_analyzed_port_put(struct mlxsw_sp_port *mlxsw_sp_port,
+				     bool ingress);
 
 #endif
-- 
cgit v1.2.3


From eb773c3a2d98e1e1cb9076419f14ebb0a2f40951 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:10 +0300
Subject: mlxsw: spectrum_span: Rename function

Next patch will introduce mlxsw_sp_span_port_buffer_disable() function
that disables the egress buffer on an analyzed port. Rename the opposite
function that updates the buffer on an analyzed port accordingly.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Suggested-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 5edf9d1bf937..c52f79a97f36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -784,7 +784,7 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
 }
 
 static int
-mlxsw_sp_span_port_buffsize_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
+mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char sbib_pl[MLXSW_REG_SBIB_LEN];
@@ -809,7 +809,7 @@ int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
 	 * updated according to the mtu value
 	 */
 	if (mlxsw_sp_span_is_egress_mirror(port))
-		return mlxsw_sp_span_port_buffsize_update(port, mtu);
+		return mlxsw_sp_span_port_buffer_update(port, mtu);
 	return 0;
 }
 
@@ -825,8 +825,8 @@ void mlxsw_sp_span_speed_update_work(struct work_struct *work)
 	 * updated according to the speed value.
 	 */
 	if (mlxsw_sp_span_is_egress_mirror(mlxsw_sp_port))
-		mlxsw_sp_span_port_buffsize_update(mlxsw_sp_port,
-						   mlxsw_sp_port->dev->mtu);
+		mlxsw_sp_span_port_buffer_update(mlxsw_sp_port,
+						 mlxsw_sp_port->dev->mtu);
 }
 
 static struct mlxsw_sp_span_inspected_port *
@@ -888,7 +888,7 @@ mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port,
 
 	/* if it is an egress SPAN, bind a shared buffer to it */
 	if (type == MLXSW_SP_SPAN_EGRESS) {
-		err = mlxsw_sp_span_port_buffsize_update(port, port->dev->mtu);
+		err = mlxsw_sp_span_port_buffer_update(port, port->dev->mtu);
 		if (err)
 			return err;
 	}
@@ -1135,14 +1135,14 @@ mlxsw_sp_span_analyzed_port_create(struct mlxsw_sp_span *span,
 	if (!ingress) {
 		u16 mtu = mlxsw_sp_port->dev->mtu;
 
-		err = mlxsw_sp_span_port_buffsize_update(mlxsw_sp_port, mtu);
+		err = mlxsw_sp_span_port_buffer_update(mlxsw_sp_port, mtu);
 		if (err)
-			goto err_buffsize_update;
+			goto err_buffer_update;
 	}
 
 	return analyzed_port;
 
-err_buffsize_update:
+err_buffer_update:
 	list_del(&analyzed_port->list);
 	kfree(analyzed_port);
 	return ERR_PTR(err);
-- 
cgit v1.2.3


From 14366da6b59203ef5fc3cf21660113b60c2f1421 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:11 +0300
Subject: mlxsw: spectrum_span: Wrap buffer change in a function

The code that adjusts the egress buffer size is not symmetric at the
moment. The update is done via a call to
mlxsw_sp_span_port_buffer_update(), but the disablement is done inline
by invoking the write to SBIB register directly.

Wrap the disablement code in mlxsw_sp_span_port_buffer_disable().

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Suggested-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index c52f79a97f36..2b9d8ce93b13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -803,6 +803,15 @@ mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 }
 
+static void mlxsw_sp_span_port_buffer_disable(struct mlxsw_sp *mlxsw_sp,
+					      u8 local_port)
+{
+	char sbib_pl[MLXSW_REG_SBIB_LEN];
+
+	mlxsw_reg_sbib_pack(sbib_pl, local_port, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
+}
+
 int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
 {
 	/* If port is egress mirrored, the shared buffer size should be
@@ -1154,15 +1163,13 @@ mlxsw_sp_span_analyzed_port_destroy(struct mlxsw_sp_span *span,
 				    analyzed_port)
 {
 	struct mlxsw_sp *mlxsw_sp = span->mlxsw_sp;
-	char sbib_pl[MLXSW_REG_SBIB_LEN];
 
 	/* Remove egress mirror buffer now that port is no longer analyzed
 	 * at egress.
 	 */
-	if (!analyzed_port->ingress) {
-		mlxsw_reg_sbib_pack(sbib_pl, analyzed_port->local_port, 0);
-		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
-	}
+	if (!analyzed_port->ingress)
+		mlxsw_sp_span_port_buffer_disable(mlxsw_sp,
+						  analyzed_port->local_port);
 
 	list_del(&analyzed_port->list);
 	kfree(analyzed_port);
-- 
cgit v1.2.3


From c056618c53a771bacf4e077e8be01de4405439ae Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:12 +0300
Subject: mlxsw: spectrum_span: Add APIs to bind / unbind a SPAN agent

Currently, a SPAN agent can only be bound to a per-port trigger where
the trigger is either an incoming packet (INGRESS) or an outgoing packet
(EGRESS) to / from the port.

A follow-up patch set will introduce the concept of global triggers and
per-{port, TC} enablement. With global triggers, the trigger entry is
only keyed by a trigger and not by a port and a trigger. The trigger can
be, for example, a packet that was early dropped.

While the binding between the SPAN agent and the trigger is performed
only once, the trigger entry needs to be reference counted, as the
trigger can be enabled on multiple ports.

Add APIs to bind / unbind a SPAN agent to a trigger and reference count
the trigger entry in preparation for global triggers.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 169 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_span.h    |  18 +++
 2 files changed, 187 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 2b9d8ce93b13..de9012ab94d5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -23,6 +23,7 @@ struct mlxsw_sp_span {
 	struct mlxsw_sp *mlxsw_sp;
 	struct list_head analyzed_ports_list;
 	struct mutex analyzed_ports_lock; /* Protects analyzed_ports_list */
+	struct list_head trigger_entries_list;
 	atomic_t active_entries_count;
 	int entries_count;
 	struct mlxsw_sp_span_entry entries[];
@@ -35,6 +36,14 @@ struct mlxsw_sp_span_analyzed_port {
 	bool ingress;
 };
 
+struct mlxsw_sp_span_trigger_entry {
+	struct list_head list; /* Member of trigger_entries_list */
+	refcount_t ref_count;
+	u8 local_port;
+	enum mlxsw_sp_span_trigger trigger;
+	struct mlxsw_sp_span_trigger_parms parms;
+};
+
 static void mlxsw_sp_span_respin_work(struct work_struct *work);
 
 static u64 mlxsw_sp_span_occ_get(void *priv)
@@ -61,6 +70,7 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp)
 	atomic_set(&span->active_entries_count, 0);
 	mutex_init(&span->analyzed_ports_lock);
 	INIT_LIST_HEAD(&span->analyzed_ports_list);
+	INIT_LIST_HEAD(&span->trigger_entries_list);
 	span->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp->span = span;
 
@@ -91,6 +101,7 @@ void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp)
 
 		WARN_ON_ONCE(!list_empty(&curr->bound_ports_list));
 	}
+	WARN_ON_ONCE(!list_empty(&mlxsw_sp->span->trigger_entries_list));
 	WARN_ON_ONCE(!list_empty(&mlxsw_sp->span->analyzed_ports_list));
 	mutex_destroy(&mlxsw_sp->span->analyzed_ports_lock);
 	kfree(mlxsw_sp->span);
@@ -1225,3 +1236,161 @@ void mlxsw_sp_span_analyzed_port_put(struct mlxsw_sp_port *mlxsw_sp_port,
 out_unlock:
 	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
 }
+
+static int
+__mlxsw_sp_span_trigger_entry_bind(struct mlxsw_sp_span *span,
+				   struct mlxsw_sp_span_trigger_entry *
+				   trigger_entry, bool enable)
+{
+	char mpar_pl[MLXSW_REG_MPAR_LEN];
+	enum mlxsw_reg_mpar_i_e i_e;
+
+	switch (trigger_entry->trigger) {
+	case MLXSW_SP_SPAN_TRIGGER_INGRESS:
+		i_e = MLXSW_REG_MPAR_TYPE_INGRESS;
+		break;
+	case MLXSW_SP_SPAN_TRIGGER_EGRESS:
+		i_e = MLXSW_REG_MPAR_TYPE_EGRESS;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	mlxsw_reg_mpar_pack(mpar_pl, trigger_entry->local_port, i_e, enable,
+			    trigger_entry->parms.span_id);
+	return mlxsw_reg_write(span->mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl);
+}
+
+static int
+mlxsw_sp_span_trigger_entry_bind(struct mlxsw_sp_span *span,
+				 struct mlxsw_sp_span_trigger_entry *
+				 trigger_entry)
+{
+	return __mlxsw_sp_span_trigger_entry_bind(span, trigger_entry, true);
+}
+
+static void
+mlxsw_sp_span_trigger_entry_unbind(struct mlxsw_sp_span *span,
+				   struct mlxsw_sp_span_trigger_entry *
+				   trigger_entry)
+{
+	__mlxsw_sp_span_trigger_entry_bind(span, trigger_entry, false);
+}
+
+static struct mlxsw_sp_span_trigger_entry *
+mlxsw_sp_span_trigger_entry_create(struct mlxsw_sp_span *span,
+				   enum mlxsw_sp_span_trigger trigger,
+				   struct mlxsw_sp_port *mlxsw_sp_port,
+				   const struct mlxsw_sp_span_trigger_parms
+				   *parms)
+{
+	struct mlxsw_sp_span_trigger_entry *trigger_entry;
+	int err;
+
+	trigger_entry = kzalloc(sizeof(*trigger_entry), GFP_KERNEL);
+	if (!trigger_entry)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&trigger_entry->ref_count, 1);
+	trigger_entry->local_port = mlxsw_sp_port->local_port;
+	trigger_entry->trigger = trigger;
+	memcpy(&trigger_entry->parms, parms, sizeof(trigger_entry->parms));
+	list_add_tail(&trigger_entry->list, &span->trigger_entries_list);
+
+	err = mlxsw_sp_span_trigger_entry_bind(span, trigger_entry);
+	if (err)
+		goto err_trigger_entry_bind;
+
+	return trigger_entry;
+
+err_trigger_entry_bind:
+	list_del(&trigger_entry->list);
+	kfree(trigger_entry);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_span_trigger_entry_destroy(struct mlxsw_sp_span *span,
+				    struct mlxsw_sp_span_trigger_entry *
+				    trigger_entry)
+{
+	mlxsw_sp_span_trigger_entry_unbind(span, trigger_entry);
+	list_del(&trigger_entry->list);
+	kfree(trigger_entry);
+}
+
+static struct mlxsw_sp_span_trigger_entry *
+mlxsw_sp_span_trigger_entry_find(struct mlxsw_sp_span *span,
+				 enum mlxsw_sp_span_trigger trigger,
+				 struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_span_trigger_entry *trigger_entry;
+
+	list_for_each_entry(trigger_entry, &span->trigger_entries_list, list) {
+		if (trigger_entry->trigger == trigger &&
+		    trigger_entry->local_port == mlxsw_sp_port->local_port)
+			return trigger_entry;
+	}
+
+	return NULL;
+}
+
+int mlxsw_sp_span_agent_bind(struct mlxsw_sp *mlxsw_sp,
+			     enum mlxsw_sp_span_trigger trigger,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct mlxsw_sp_span_trigger_parms *parms)
+{
+	struct mlxsw_sp_span_trigger_entry *trigger_entry;
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	if (!mlxsw_sp_span_entry_find_by_id(mlxsw_sp, parms->span_id))
+		return -EINVAL;
+
+	trigger_entry = mlxsw_sp_span_trigger_entry_find(mlxsw_sp->span,
+							 trigger,
+							 mlxsw_sp_port);
+	if (trigger_entry) {
+		if (trigger_entry->parms.span_id != parms->span_id)
+			return -EINVAL;
+		refcount_inc(&trigger_entry->ref_count);
+		goto out;
+	}
+
+	trigger_entry = mlxsw_sp_span_trigger_entry_create(mlxsw_sp->span,
+							   trigger,
+							   mlxsw_sp_port,
+							   parms);
+	if (IS_ERR(trigger_entry))
+		err = PTR_ERR(trigger_entry);
+
+out:
+	return err;
+}
+
+void mlxsw_sp_span_agent_unbind(struct mlxsw_sp *mlxsw_sp,
+				enum mlxsw_sp_span_trigger trigger,
+				struct mlxsw_sp_port *mlxsw_sp_port,
+				const struct mlxsw_sp_span_trigger_parms *parms)
+{
+	struct mlxsw_sp_span_trigger_entry *trigger_entry;
+
+	ASSERT_RTNL();
+
+	if (WARN_ON_ONCE(!mlxsw_sp_span_entry_find_by_id(mlxsw_sp,
+							 parms->span_id)))
+		return;
+
+	trigger_entry = mlxsw_sp_span_trigger_entry_find(mlxsw_sp->span,
+							 trigger,
+							 mlxsw_sp_port);
+	if (WARN_ON_ONCE(!trigger_entry))
+		return;
+
+	if (!refcount_dec_and_test(&trigger_entry->ref_count))
+		return;
+
+	mlxsw_sp_span_trigger_entry_destroy(mlxsw_sp->span, trigger_entry);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 1345eda5cc34..6821eeb3906b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -37,6 +37,15 @@ struct mlxsw_sp_span_parms {
 	u16 vid;
 };
 
+enum mlxsw_sp_span_trigger {
+	MLXSW_SP_SPAN_TRIGGER_INGRESS,
+	MLXSW_SP_SPAN_TRIGGER_EGRESS,
+};
+
+struct mlxsw_sp_span_trigger_parms {
+	int span_id;
+};
+
 struct mlxsw_sp_span_entry_ops;
 
 struct mlxsw_sp_span_entry {
@@ -84,5 +93,14 @@ int mlxsw_sp_span_analyzed_port_get(struct mlxsw_sp_port *mlxsw_sp_port,
 				    bool ingress);
 void mlxsw_sp_span_analyzed_port_put(struct mlxsw_sp_port *mlxsw_sp_port,
 				     bool ingress);
+int mlxsw_sp_span_agent_bind(struct mlxsw_sp *mlxsw_sp,
+			     enum mlxsw_sp_span_trigger trigger,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     const struct mlxsw_sp_span_trigger_parms *parms);
+void
+mlxsw_sp_span_agent_unbind(struct mlxsw_sp *mlxsw_sp,
+			   enum mlxsw_sp_span_trigger trigger,
+			   struct mlxsw_sp_port *mlxsw_sp_port,
+			   const struct mlxsw_sp_span_trigger_parms *parms);
 
 #endif
-- 
cgit v1.2.3


From c1d7845dfbd3dfeed2cd7bf92ec10ea97ef5d7fd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:13 +0300
Subject: mlxsw: spectrum: Convert matchall-based mirroring to new SPAN API

In matchall-based mirroring, mirroring is not done with ACLs, but a SPAN
agent is bound to the ingress / egress of a port and all incoming /
outgoing traffic is mirrored.

Convert this type of mirroring to use the new API.

First the SPAN agent is resolved, then the port is marked as analyzed
and its egress mirror buffer is potentially allocated. Lastly, the
binding is performed.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 52 ++++++++++++++++------
 1 file changed, 39 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index 889da63072be..da1c05f44cec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -48,31 +48,57 @@ static int
 mlxsw_sp_mall_port_mirror_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_mall_entry *mall_entry)
 {
-	enum mlxsw_sp_span_type span_type;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_span_trigger_parms parms;
+	enum mlxsw_sp_span_trigger trigger;
+	int err;
 
 	if (!mall_entry->mirror.to_dev) {
 		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
 		return -EINVAL;
 	}
 
-	span_type = mall_entry->ingress ? MLXSW_SP_SPAN_INGRESS :
-					  MLXSW_SP_SPAN_EGRESS;
-	return mlxsw_sp_span_mirror_add(mlxsw_sp_port,
-					mall_entry->mirror.to_dev,
-					span_type, true,
-					&mall_entry->mirror.span_id);
+	err = mlxsw_sp_span_agent_get(mlxsw_sp, mall_entry->mirror.to_dev,
+				      &mall_entry->mirror.span_id);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port,
+					      mall_entry->ingress);
+	if (err)
+		goto err_analyzed_port_get;
+
+	trigger = mall_entry->ingress ? MLXSW_SP_SPAN_TRIGGER_INGRESS :
+					MLXSW_SP_SPAN_TRIGGER_EGRESS;
+	parms.span_id = mall_entry->mirror.span_id;
+	err = mlxsw_sp_span_agent_bind(mlxsw_sp, trigger, mlxsw_sp_port,
+				       &parms);
+	if (err)
+		goto err_agent_bind;
+
+	return 0;
+
+err_agent_bind:
+	mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, mall_entry->ingress);
+err_analyzed_port_get:
+	mlxsw_sp_span_agent_put(mlxsw_sp, mall_entry->mirror.span_id);
+	return err;
 }
 
 static void
 mlxsw_sp_mall_port_mirror_del(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_mall_entry *mall_entry)
 {
-	enum mlxsw_sp_span_type span_type;
-
-	span_type = mall_entry->ingress ? MLXSW_SP_SPAN_INGRESS :
-					  MLXSW_SP_SPAN_EGRESS;
-	mlxsw_sp_span_mirror_del(mlxsw_sp_port, mall_entry->mirror.span_id,
-				 span_type, true);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_span_trigger_parms parms;
+	enum mlxsw_sp_span_trigger trigger;
+
+	trigger = mall_entry->ingress ? MLXSW_SP_SPAN_TRIGGER_INGRESS :
+					MLXSW_SP_SPAN_TRIGGER_EGRESS;
+	parms.span_id = mall_entry->mirror.span_id;
+	mlxsw_sp_span_agent_unbind(mlxsw_sp, trigger, mlxsw_sp_port, &parms);
+	mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, mall_entry->ingress);
+	mlxsw_sp_span_agent_put(mlxsw_sp, mall_entry->mirror.span_id);
 }
 
 static int mlxsw_sp_mall_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port,
-- 
cgit v1.2.3


From 7240db69c332f6625da044b048d06839ab0c2649 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:14 +0300
Subject: mlxsw: spectrum_acl: Convert flower-based mirroring to new SPAN API

In flower-based mirroring, mirroring is done with ACLs and the SPAN
agent is not bound to a port. Instead its identifier is specified in an
ACL action.

Convert this type of mirroring to use the new API.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/spectrum_acl_flex_actions.c     | 31 +++++++++++++---------
 1 file changed, 19 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index e47d1d286e93..73d56012654b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -136,28 +136,35 @@ mlxsw_sp_act_mirror_add(void *priv, u8 local_in_port,
 			const struct net_device *out_dev,
 			bool ingress, int *p_span_id)
 {
-	struct mlxsw_sp_port *in_port;
+	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = priv;
-	enum mlxsw_sp_span_type type;
+	int err;
 
-	type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	in_port = mlxsw_sp->ports[local_in_port];
+	err = mlxsw_sp_span_agent_get(mlxsw_sp, out_dev, p_span_id);
+	if (err)
+		return err;
+
+	mlxsw_sp_port = mlxsw_sp->ports[local_in_port];
+	err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, ingress);
+	if (err)
+		goto err_analyzed_port_get;
 
-	return mlxsw_sp_span_mirror_add(in_port, out_dev, type,
-					false, p_span_id);
+	return 0;
+
+err_analyzed_port_get:
+	mlxsw_sp_span_agent_put(mlxsw_sp, *p_span_id);
+	return err;
 }
 
 static void
 mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress)
 {
+	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_port *in_port;
-	enum mlxsw_sp_span_type type;
-
-	type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	in_port = mlxsw_sp->ports[local_in_port];
 
-	mlxsw_sp_span_mirror_del(in_port, span_id, type, false);
+	mlxsw_sp_port = mlxsw_sp->ports[local_in_port];
+	mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress);
+	mlxsw_sp_span_agent_put(mlxsw_sp, span_id);
 }
 
 const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
-- 
cgit v1.2.3


From 835d6b8c1a35eafba3faaf4b809f6d84517467f1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:15 +0300
Subject: mlxsw: spectrum_span: Use new analyzed ports list during speed / MTU
 change

As previously explained, each port whose outgoing traffic is analyzed
needs to have an egress mirror buffer.

The size of the egress mirror buffer is calculated based on various
parameters, two of which are the speed and the MTU of the port.

Therefore, when the MTU or the speed of a port change, the SPAN code is
called to see if the egress mirror buffer of the port needs to be
adjusted.

Currently, this is done by traversing all the SPAN agents and for each
SPAN agent the list of bound ports is traversed.

Instead of the above, traverse the recently added list of analyzed
ports.

This will later allow us to remove the old SPAN API.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 72 +++++++++++-----------
 1 file changed, 35 insertions(+), 37 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index de9012ab94d5..9cb8b509b849 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -776,24 +776,6 @@ static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
-{
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
-	struct mlxsw_sp_span_inspected_port *p;
-	int i;
-
-	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
-		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
-
-		list_for_each_entry(p, &curr->bound_ports_list, list)
-			if (p->local_port == port->local_port &&
-			    p->type == MLXSW_SP_SPAN_EGRESS)
-				return true;
-	}
-
-	return false;
-}
-
 static int
 mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 {
@@ -823,20 +805,45 @@ static void mlxsw_sp_span_port_buffer_disable(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 }
 
+static struct mlxsw_sp_span_analyzed_port *
+mlxsw_sp_span_analyzed_port_find(struct mlxsw_sp_span *span, u8 local_port,
+				 bool ingress)
+{
+	struct mlxsw_sp_span_analyzed_port *analyzed_port;
+
+	list_for_each_entry(analyzed_port, &span->analyzed_ports_list, list) {
+		if (analyzed_port->local_port == local_port &&
+		    analyzed_port->ingress == ingress)
+			return analyzed_port;
+	}
+
+	return NULL;
+}
+
 int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
 {
+	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
+	int err = 0;
+
 	/* If port is egress mirrored, the shared buffer size should be
 	 * updated according to the mtu value
 	 */
-	if (mlxsw_sp_span_is_egress_mirror(port))
-		return mlxsw_sp_span_port_buffer_update(port, mtu);
-	return 0;
+	mutex_lock(&mlxsw_sp->span->analyzed_ports_lock);
+
+	if (mlxsw_sp_span_analyzed_port_find(mlxsw_sp->span, port->local_port,
+					     false))
+		err = mlxsw_sp_span_port_buffer_update(port, mtu);
+
+	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
+
+	return err;
 }
 
 void mlxsw_sp_span_speed_update_work(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct mlxsw_sp *mlxsw_sp;
 
 	mlxsw_sp_port = container_of(dwork, struct mlxsw_sp_port,
 				     span.speed_update_dw);
@@ -844,9 +851,15 @@ void mlxsw_sp_span_speed_update_work(struct work_struct *work)
 	/* If port is egress mirrored, the shared buffer size should be
 	 * updated according to the speed value.
 	 */
-	if (mlxsw_sp_span_is_egress_mirror(mlxsw_sp_port))
+	mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	mutex_lock(&mlxsw_sp->span->analyzed_ports_lock);
+
+	if (mlxsw_sp_span_analyzed_port_find(mlxsw_sp->span,
+					     mlxsw_sp_port->local_port, false))
 		mlxsw_sp_span_port_buffer_update(mlxsw_sp_port,
 						 mlxsw_sp_port->dev->mtu);
+
+	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
 }
 
 static struct mlxsw_sp_span_inspected_port *
@@ -1117,21 +1130,6 @@ void mlxsw_sp_span_agent_put(struct mlxsw_sp *mlxsw_sp, int span_id)
 	mlxsw_sp_span_entry_put(mlxsw_sp, span_entry);
 }
 
-static struct mlxsw_sp_span_analyzed_port *
-mlxsw_sp_span_analyzed_port_find(struct mlxsw_sp_span *span, u8 local_port,
-				 bool ingress)
-{
-	struct mlxsw_sp_span_analyzed_port *analyzed_port;
-
-	list_for_each_entry(analyzed_port, &span->analyzed_ports_list, list) {
-		if (analyzed_port->local_port == local_port &&
-		    analyzed_port->ingress == ingress)
-			return analyzed_port;
-	}
-
-	return NULL;
-}
-
 static struct mlxsw_sp_span_analyzed_port *
 mlxsw_sp_span_analyzed_port_create(struct mlxsw_sp_span *span,
 				   struct mlxsw_sp_port *mlxsw_sp_port,
-- 
cgit v1.2.3


From ca0892235ae68b097f42cd39e03b17cfead7c7c7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 20:01:16 +0300
Subject: mlxsw: spectrum_span: Remove old SPAN API

Remove the old SPAN API now that matchall-based and flower-based
mirroring were converted to use the new API.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 190 +--------------------
 .../net/ethernet/mellanox/mlxsw/spectrum_span.h    |  21 ---
 2 files changed, 2 insertions(+), 209 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 9cb8b509b849..304eb8c3d8bd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -74,12 +74,8 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp)
 	span->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp->span = span;
 
-	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
-		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
-
-		INIT_LIST_HEAD(&curr->bound_ports_list);
-		curr->id = i;
-	}
+	for (i = 0; i < mlxsw_sp->span->entries_count; i++)
+		mlxsw_sp->span->entries[i].id = i;
 
 	devlink_resource_occ_get_register(devlink, MLXSW_SP_RESOURCE_SPAN,
 					  mlxsw_sp_span_occ_get, mlxsw_sp);
@@ -91,16 +87,10 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp)
 void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-	int i;
 
 	cancel_work_sync(&mlxsw_sp->span->work);
 	devlink_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_SPAN);
 
-	for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
-		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i];
-
-		WARN_ON_ONCE(!list_empty(&curr->bound_ports_list));
-	}
 	WARN_ON_ONCE(!list_empty(&mlxsw_sp->span->trigger_entries_list));
 	WARN_ON_ONCE(!list_empty(&mlxsw_sp->span->analyzed_ports_list));
 	mutex_destroy(&mlxsw_sp->span->analyzed_ports_lock);
@@ -862,131 +852,6 @@ void mlxsw_sp_span_speed_update_work(struct work_struct *work)
 	mutex_unlock(&mlxsw_sp->span->analyzed_ports_lock);
 }
 
-static struct mlxsw_sp_span_inspected_port *
-mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_span_entry *span_entry,
-				    enum mlxsw_sp_span_type type,
-				    struct mlxsw_sp_port *port,
-				    bool bind)
-{
-	struct mlxsw_sp_span_inspected_port *p;
-
-	list_for_each_entry(p, &span_entry->bound_ports_list, list)
-		if (type == p->type &&
-		    port->local_port == p->local_port &&
-		    bind == p->bound)
-			return p;
-	return NULL;
-}
-
-static int
-mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port,
-				  struct mlxsw_sp_span_entry *span_entry,
-				  enum mlxsw_sp_span_type type,
-				  bool bind)
-{
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
-	char mpar_pl[MLXSW_REG_MPAR_LEN];
-	int pa_id = span_entry->id;
-
-	/* bind the port to the SPAN entry */
-	mlxsw_reg_mpar_pack(mpar_pl, port->local_port,
-			    (enum mlxsw_reg_mpar_i_e)type, bind, pa_id);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl);
-}
-
-static int
-mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port,
-				 struct mlxsw_sp_span_entry *span_entry,
-				 enum mlxsw_sp_span_type type,
-				 bool bind)
-{
-	struct mlxsw_sp_span_inspected_port *inspected_port;
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
-	char sbib_pl[MLXSW_REG_SBIB_LEN];
-	int i;
-	int err;
-
-	/* A given (source port, direction) can only be bound to one analyzer,
-	 * so if a binding is requested, check for conflicts.
-	 */
-	if (bind)
-		for (i = 0; i < mlxsw_sp->span->entries_count; i++) {
-			struct mlxsw_sp_span_entry *curr =
-				&mlxsw_sp->span->entries[i];
-
-			if (mlxsw_sp_span_entry_bound_port_find(curr, type,
-								port, bind))
-				return -EEXIST;
-		}
-
-	/* if it is an egress SPAN, bind a shared buffer to it */
-	if (type == MLXSW_SP_SPAN_EGRESS) {
-		err = mlxsw_sp_span_port_buffer_update(port, port->dev->mtu);
-		if (err)
-			return err;
-	}
-
-	if (bind) {
-		err = mlxsw_sp_span_inspected_port_bind(port, span_entry, type,
-							true);
-		if (err)
-			goto err_port_bind;
-	}
-
-	inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL);
-	if (!inspected_port) {
-		err = -ENOMEM;
-		goto err_inspected_port_alloc;
-	}
-	inspected_port->local_port = port->local_port;
-	inspected_port->type = type;
-	inspected_port->bound = bind;
-	list_add_tail(&inspected_port->list, &span_entry->bound_ports_list);
-
-	return 0;
-
-err_inspected_port_alloc:
-	if (bind)
-		mlxsw_sp_span_inspected_port_bind(port, span_entry, type,
-						  false);
-err_port_bind:
-	if (type == MLXSW_SP_SPAN_EGRESS) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0);
-		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
-	}
-	return err;
-}
-
-static void
-mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port,
-				 struct mlxsw_sp_span_entry *span_entry,
-				 enum mlxsw_sp_span_type type,
-				 bool bind)
-{
-	struct mlxsw_sp_span_inspected_port *inspected_port;
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
-	char sbib_pl[MLXSW_REG_SBIB_LEN];
-
-	inspected_port = mlxsw_sp_span_entry_bound_port_find(span_entry, type,
-							     port, bind);
-	if (!inspected_port)
-		return;
-
-	if (bind)
-		mlxsw_sp_span_inspected_port_bind(port, span_entry, type,
-						  false);
-	/* remove the SBIB buffer if it was egress SPAN */
-	if (type == MLXSW_SP_SPAN_EGRESS) {
-		mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0);
-		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
-	}
-
-	mlxsw_sp_span_entry_put(mlxsw_sp, span_entry);
-
-	list_del(&inspected_port->list);
-	kfree(inspected_port);
-}
-
 static const struct mlxsw_sp_span_entry_ops *
 mlxsw_sp_span_entry_ops(struct mlxsw_sp *mlxsw_sp,
 			const struct net_device *to_dev)
@@ -1000,57 +865,6 @@ mlxsw_sp_span_entry_ops(struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
-			     const struct net_device *to_dev,
-			     enum mlxsw_sp_span_type type, bool bind,
-			     int *p_span_id)
-{
-	struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp;
-	const struct mlxsw_sp_span_entry_ops *ops;
-	struct mlxsw_sp_span_parms sparms = {NULL};
-	struct mlxsw_sp_span_entry *span_entry;
-	int err;
-
-	ops = mlxsw_sp_span_entry_ops(mlxsw_sp, to_dev);
-	if (!ops) {
-		netdev_err(to_dev, "Cannot mirror to %s", to_dev->name);
-		return -EOPNOTSUPP;
-	}
-
-	err = ops->parms_set(to_dev, &sparms);
-	if (err)
-		return err;
-
-	span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms);
-	if (!span_entry)
-		return -ENOBUFS;
-
-	err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind);
-	if (err)
-		goto err_port_bind;
-
-	*p_span_id = span_entry->id;
-	return 0;
-
-err_port_bind:
-	mlxsw_sp_span_entry_put(mlxsw_sp, span_entry);
-	return err;
-}
-
-void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id,
-			      enum mlxsw_sp_span_type type, bool bind)
-{
-	struct mlxsw_sp_span_entry *span_entry;
-
-	span_entry = mlxsw_sp_span_entry_find_by_id(from->mlxsw_sp, span_id);
-	if (!span_entry) {
-		netdev_err(from->dev, "no span entry found\n");
-		return;
-	}
-
-	mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind);
-}
-
 static void mlxsw_sp_span_respin_work(struct work_struct *work)
 {
 	struct mlxsw_sp_span *span;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 6821eeb3906b..9f6dd2d0f4e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -13,20 +13,6 @@
 struct mlxsw_sp;
 struct mlxsw_sp_port;
 
-enum mlxsw_sp_span_type {
-	MLXSW_SP_SPAN_EGRESS,
-	MLXSW_SP_SPAN_INGRESS
-};
-
-struct mlxsw_sp_span_inspected_port {
-	struct list_head list;
-	enum mlxsw_sp_span_type type;
-	u8 local_port;
-
-	/* Whether this is a directly bound mirror (port-to-port) or an ACL. */
-	bool bound;
-};
-
 struct mlxsw_sp_span_parms {
 	struct mlxsw_sp_port *dest_port; /* NULL for unoffloaded SPAN. */
 	unsigned int ttl;
@@ -52,7 +38,6 @@ struct mlxsw_sp_span_entry {
 	const struct net_device *to_dev;
 	const struct mlxsw_sp_span_entry_ops *ops;
 	struct mlxsw_sp_span_parms parms;
-	struct list_head bound_ports_list;
 	refcount_t ref_count;
 	int id;
 };
@@ -70,12 +55,6 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp);
 
-int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
-			     const struct net_device *to_dev,
-			     enum mlxsw_sp_span_type type,
-			     bool bind, int *p_span_id);
-void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id,
-			      enum mlxsw_sp_span_type type, bool bind);
 struct mlxsw_sp_span_entry *
 mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *to_dev);
-- 
cgit v1.2.3


From ef2c0a78aee10113d1299eb81e642470308e32ca Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:55:36 +0200
Subject: r8169: don't pass net_device to irq coalescing sub-functions

The net_device argument is just used to get a struct rtl8169_private
pointer via netdev_priv(). Therefore pass the struct rtl8169_private
pointer directly.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 68d5255568a5..1c3974ad88eb 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1805,9 +1805,9 @@ static const struct rtl_coalesce_info rtl_coalesce_info_8168_8136[] = {
 #undef rxtx_x1822
 
 /* get rx/tx scale vector corresponding to current speed */
-static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev)
+static const struct rtl_coalesce_info *
+rtl_coalesce_info(struct rtl8169_private *tp)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
 	const struct rtl_coalesce_info *ci;
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
@@ -1844,7 +1844,7 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	memset(ec, 0, sizeof(*ec));
 
 	/* get rx/tx scale corresponding to current speed and CPlusCmd[0:1] */
-	ci = rtl_coalesce_info(dev);
+	ci = rtl_coalesce_info(tp);
 	if (IS_ERR(ci))
 		return PTR_ERR(ci);
 
@@ -1874,12 +1874,12 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 
 /* choose appropriate scale factor and CPlusCmd[0:1] for (speed, nsec) */
 static const struct rtl_coalesce_scale *rtl_coalesce_choose_scale(
-			struct net_device *dev, u32 nsec, u16 *cp01)
+			struct rtl8169_private *tp, u32 nsec, u16 *cp01)
 {
 	const struct rtl_coalesce_info *ci;
 	u16 i;
 
-	ci = rtl_coalesce_info(dev);
+	ci = rtl_coalesce_info(tp);
 	if (IS_ERR(ci))
 		return ERR_CAST(ci);
 
@@ -1912,7 +1912,7 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	if (rtl_is_8125(tp))
 		return -EOPNOTSUPP;
 
-	scale = rtl_coalesce_choose_scale(dev,
+	scale = rtl_coalesce_choose_scale(tp,
 			max(p[0].usecs, p[1].usecs) * 1000, &cp01);
 	if (IS_ERR(scale))
 		return PTR_ERR(scale);
-- 
cgit v1.2.3


From 2815b30535a0613ee07d477d0c628100f40b6059 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:56:20 +0200
Subject: r8169: merge scale for tx and rx irq coalescing

Rx and tx scale are the same always. Simplify the code by using one
scale for rx and tx only.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 65 ++++++++++++-------------------
 1 file changed, 25 insertions(+), 40 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1c3974ad88eb..9932b6ffae02 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1768,41 +1768,29 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
  * 1 1                     160us           81.92us         1.31ms
  */
 
-/* rx/tx scale factors for one particular CPlusCmd[0:1] value */
-struct rtl_coalesce_scale {
-	/* Rx / Tx */
-	u32 nsecs[2];
-};
-
 /* rx/tx scale factors for all CPlusCmd[0:1] cases */
 struct rtl_coalesce_info {
 	u32 speed;
-	struct rtl_coalesce_scale scalev[4];	/* each CPlusCmd[0:1] case */
+	u32 scale_nsecs[4];
 };
 
-/* produce (r,t) pairs with each being in series of *1, *8, *8*2, *8*2*2 */
-#define rxtx_x1822(r, t) {		\
-	{{(r),		(t)}},		\
-	{{(r)*8,	(t)*8}},	\
-	{{(r)*8*2,	(t)*8*2}},	\
-	{{(r)*8*2*2,	(t)*8*2*2}},	\
-}
+/* produce array with base delay *1, *8, *8*2, *8*2*2 */
+#define COALESCE_DELAY(d) { (d), 8 * (d), 16 * (d), 32 * (d) }
+
 static const struct rtl_coalesce_info rtl_coalesce_info_8169[] = {
-	/* speed	delays:     rx00   tx00	*/
-	{ SPEED_10,	rxtx_x1822(40960, 40960)	},
-	{ SPEED_100,	rxtx_x1822( 2560,  2560)	},
-	{ SPEED_1000,	rxtx_x1822(  320,   320)	},
+	{ SPEED_10,	COALESCE_DELAY(40960) },
+	{ SPEED_100,	COALESCE_DELAY(2560) },
+	{ SPEED_1000,	COALESCE_DELAY(320) },
 	{ 0 },
 };
 
 static const struct rtl_coalesce_info rtl_coalesce_info_8168_8136[] = {
-	/* speed	delays:     rx00   tx00	*/
-	{ SPEED_10,	rxtx_x1822(40960, 40960)	},
-	{ SPEED_100,	rxtx_x1822( 2560,  2560)	},
-	{ SPEED_1000,	rxtx_x1822( 5000,  5000)	},
+	{ SPEED_10,	COALESCE_DELAY(40960) },
+	{ SPEED_100,	COALESCE_DELAY(2560) },
+	{ SPEED_1000,	COALESCE_DELAY(5000) },
 	{ 0 },
 };
-#undef rxtx_x1822
+#undef COALESCE_DELAY
 
 /* get rx/tx scale vector corresponding to current speed */
 static const struct rtl_coalesce_info *
@@ -1827,7 +1815,6 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	const struct rtl_coalesce_info *ci;
-	const struct rtl_coalesce_scale *scale;
 	struct {
 		u32 *max_frames;
 		u32 *usecs;
@@ -1835,6 +1822,7 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 		{ &ec->rx_max_coalesced_frames, &ec->rx_coalesce_usecs },
 		{ &ec->tx_max_coalesced_frames, &ec->tx_coalesce_usecs }
 	}, *p = coal_settings;
+	u32 scale;
 	int i;
 	u16 w;
 
@@ -1848,7 +1836,7 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	if (IS_ERR(ci))
 		return PTR_ERR(ci);
 
-	scale = &ci->scalev[tp->cp_cmd & INTT_MASK];
+	scale = ci->scale_nsecs[tp->cp_cmd & INTT_MASK];
 
 	/* read IntrMitigate and adjust according to scale */
 	for (w = RTL_R16(tp, IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) {
@@ -1859,7 +1847,7 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 
 	for (i = 0; i < 2; i++) {
 		p = coal_settings + i;
-		*p->usecs = (*p->usecs * scale->nsecs[i]) / 1000;
+		*p->usecs = (*p->usecs * scale) / 1000;
 
 		/*
 		 * ethtool_coalesce says it is illegal to set both usecs and
@@ -1873,32 +1861,29 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 }
 
 /* choose appropriate scale factor and CPlusCmd[0:1] for (speed, nsec) */
-static const struct rtl_coalesce_scale *rtl_coalesce_choose_scale(
-			struct rtl8169_private *tp, u32 nsec, u16 *cp01)
+static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 nsec,
+				     u16 *cp01)
 {
 	const struct rtl_coalesce_info *ci;
 	u16 i;
 
 	ci = rtl_coalesce_info(tp);
 	if (IS_ERR(ci))
-		return ERR_CAST(ci);
+		return PTR_ERR(ci);
 
 	for (i = 0; i < 4; i++) {
-		u32 rxtx_maxscale = max(ci->scalev[i].nsecs[0],
-					ci->scalev[i].nsecs[1]);
-		if (nsec <= rxtx_maxscale * RTL_COALESCE_T_MAX) {
+		if (nsec <= ci->scale_nsecs[i] * RTL_COALESCE_T_MAX) {
 			*cp01 = i;
-			return &ci->scalev[i];
+			return ci->scale_nsecs[i];
 		}
 	}
 
-	return ERR_PTR(-EINVAL);
+	return -EINVAL;
 }
 
 static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	const struct rtl_coalesce_scale *scale;
 	struct {
 		u32 frames;
 		u32 usecs;
@@ -1906,16 +1891,16 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 		{ ec->rx_max_coalesced_frames, ec->rx_coalesce_usecs },
 		{ ec->tx_max_coalesced_frames, ec->tx_coalesce_usecs }
 	}, *p = coal_settings;
-	u16 w = 0, cp01;
-	int i;
+	u16 w = 0, cp01 = 0;
+	int scale, i;
 
 	if (rtl_is_8125(tp))
 		return -EOPNOTSUPP;
 
 	scale = rtl_coalesce_choose_scale(tp,
 			max(p[0].usecs, p[1].usecs) * 1000, &cp01);
-	if (IS_ERR(scale))
-		return PTR_ERR(scale);
+	if (scale < 0)
+		return scale;
 
 	for (i = 0; i < 2; i++, p++) {
 		u32 units;
@@ -1936,7 +1921,7 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 			p->frames = 0;
 		}
 
-		units = p->usecs * 1000 / scale->nsecs[i];
+		units = p->usecs * 1000 / scale;
 		if (p->frames > RTL_COALESCE_FRAME_MAX || p->frames % 4)
 			return -EINVAL;
 
-- 
cgit v1.2.3


From 6cf96dd4272537baf4ceab452f6276da1b8d82af Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:56:58 +0200
Subject: r8169: improve rtl_get_coalesce

Use FIELD_GET() macro to make the code better readable. In addition
change the logic to round the time limit up, not down. Reason is that
a time limit <1us would be rounded to 0 currently, what would be
interpreted as "no time limit set".

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 46 ++++++++++++++-----------------
 1 file changed, 20 insertions(+), 26 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 9932b6ffae02..a36a48f713fa 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
+#include <linux/bitfield.h>
 #include <linux/prefetch.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
@@ -229,6 +230,11 @@ enum rtl_registers {
 	CPlusCmd	= 0xe0,
 	IntrMitigate	= 0xe2,
 
+#define RTL_COALESCE_TX_USECS	GENMASK(15, 12)
+#define RTL_COALESCE_TX_FRAMES	GENMASK(11, 8)
+#define RTL_COALESCE_RX_USECS	GENMASK(7, 4)
+#define RTL_COALESCE_RX_FRAMES	GENMASK(3, 0)
+
 #define RTL_COALESCE_MASK	0x0f
 #define RTL_COALESCE_SHIFT	4
 #define RTL_COALESCE_T_MAX	(RTL_COALESCE_MASK)
@@ -1815,16 +1821,8 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	const struct rtl_coalesce_info *ci;
-	struct {
-		u32 *max_frames;
-		u32 *usecs;
-	} coal_settings [] = {
-		{ &ec->rx_max_coalesced_frames, &ec->rx_coalesce_usecs },
-		{ &ec->tx_max_coalesced_frames, &ec->tx_coalesce_usecs }
-	}, *p = coal_settings;
-	u32 scale;
-	int i;
-	u16 w;
+	u32 scale, c_us, c_fr;
+	u16 intrmit;
 
 	if (rtl_is_8125(tp))
 		return -EOPNOTSUPP;
@@ -1838,24 +1836,20 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 
 	scale = ci->scale_nsecs[tp->cp_cmd & INTT_MASK];
 
-	/* read IntrMitigate and adjust according to scale */
-	for (w = RTL_R16(tp, IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) {
-		*p->max_frames = (w & RTL_COALESCE_MASK) << 2;
-		w >>= RTL_COALESCE_SHIFT;
-		*p->usecs = w & RTL_COALESCE_MASK;
-	}
+	intrmit = RTL_R16(tp, IntrMitigate);
 
-	for (i = 0; i < 2; i++) {
-		p = coal_settings + i;
-		*p->usecs = (*p->usecs * scale) / 1000;
+	c_us = FIELD_GET(RTL_COALESCE_TX_USECS, intrmit);
+	ec->tx_coalesce_usecs = DIV_ROUND_UP(c_us * scale, 1000);
 
-		/*
-		 * ethtool_coalesce says it is illegal to set both usecs and
-		 * max_frames to 0.
-		 */
-		if (!*p->usecs && !*p->max_frames)
-			*p->max_frames = 1;
-	}
+	c_fr = FIELD_GET(RTL_COALESCE_TX_FRAMES, intrmit);
+	/* ethtool_coalesce states usecs and max_frames must not both be 0 */
+	ec->tx_max_coalesced_frames = (c_us || c_fr) ? c_fr * 4 : 1;
+
+	c_us = FIELD_GET(RTL_COALESCE_RX_USECS, intrmit);
+	ec->rx_coalesce_usecs = DIV_ROUND_UP(c_us * scale, 1000);
+
+	c_fr = FIELD_GET(RTL_COALESCE_RX_FRAMES, intrmit);
+	ec->rx_max_coalesced_frames = (c_us || c_fr) ? c_fr * 4 : 1;
 
 	return 0;
 }
-- 
cgit v1.2.3


From cb9d97de05646de69b997da0137b94e00cba7f99 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:57:32 +0200
Subject: r8169: improve rtl_coalesce_choose_scale

The time limit provided by userspace is multiplied with 1000,
what could result in an overflow. Therefore change the time limit
parameter unit from ns to us, and avoid the problematic operation.
If there's no matching scale because provided time limit is too big,
return ERANGE instead of EINVAL to provide a hint to the user what's
wrong.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a36a48f713fa..6c17c234bc06 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1854,8 +1854,8 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
-/* choose appropriate scale factor and CPlusCmd[0:1] for (speed, nsec) */
-static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 nsec,
+/* choose appropriate scale factor and CPlusCmd[0:1] for (speed, usec) */
+static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 usec,
 				     u16 *cp01)
 {
 	const struct rtl_coalesce_info *ci;
@@ -1866,13 +1866,13 @@ static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 nsec,
 		return PTR_ERR(ci);
 
 	for (i = 0; i < 4; i++) {
-		if (nsec <= ci->scale_nsecs[i] * RTL_COALESCE_T_MAX) {
+		if (usec <= ci->scale_nsecs[i] * RTL_COALESCE_T_MAX / 1000U) {
 			*cp01 = i;
 			return ci->scale_nsecs[i];
 		}
 	}
 
-	return -EINVAL;
+	return -ERANGE;
 }
 
 static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
@@ -1886,13 +1886,14 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 		{ ec->tx_max_coalesced_frames, ec->tx_coalesce_usecs }
 	}, *p = coal_settings;
 	u16 w = 0, cp01 = 0;
+	u32 coal_usec_max;
 	int scale, i;
 
 	if (rtl_is_8125(tp))
 		return -EOPNOTSUPP;
 
-	scale = rtl_coalesce_choose_scale(tp,
-			max(p[0].usecs, p[1].usecs) * 1000, &cp01);
+	coal_usec_max = max(ec->rx_coalesce_usecs, ec->tx_coalesce_usecs);
+	scale = rtl_coalesce_choose_scale(tp, coal_usec_max, &cp01);
 	if (scale < 0)
 		return scale;
 
-- 
cgit v1.2.3


From bdd2be3adb7d139a598f2277af7fa625fc399af1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:58:06 +0200
Subject: r8169: improve interrupt coalescing parameter handling

The chip supports only frame limits 0, 4, 8, .. 60 internally.
Returning EINVAL for all val % 4 != 0 seems to be a little bit too
unfriendly to the user. Therefore round up the frame limit to the next
supported value. In addition round up the time limit, else a very low
limit could be rounded down to 0, and interpreted as "ignore value"
by the chip.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 6c17c234bc06..a81d46abe3c2 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1909,21 +1909,21 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 		 * - then user does `ethtool -C eth0 rx-usecs 100`
 		 *
 		 * since ethtool sends to kernel whole ethtool_coalesce
-		 * settings, if we do not handle rx_usecs=!0, rx_frames=1
-		 * we'll reject it below in `frames % 4 != 0`.
+		 * settings, if we want to ignore rx_frames then it has
+		 * to be set to 0.
 		 */
 		if (p->frames == 1) {
 			p->frames = 0;
 		}
 
-		units = p->usecs * 1000 / scale;
-		if (p->frames > RTL_COALESCE_FRAME_MAX || p->frames % 4)
-			return -EINVAL;
+		units = DIV_ROUND_UP(p->usecs * 1000, scale);
+		if (p->frames > RTL_COALESCE_FRAME_MAX)
+			return -ERANGE;
 
 		w <<= RTL_COALESCE_SHIFT;
 		w |= units;
 		w <<= RTL_COALESCE_SHIFT;
-		w |= p->frames >> 2;
+		w |= DIV_ROUND_UP(p->frames, 4);
 	}
 
 	rtl_lock_work(tp);
-- 
cgit v1.2.3


From 2b3e48b66516602d7d63142cda84b554f908eb54 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:58:47 +0200
Subject: r8169: improve rtl_set_coalesce

Use FIELD_PREP() to make the code better readable, and avoid the loop.
No functional change intended.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 70 +++++++++++++------------------
 1 file changed, 30 insertions(+), 40 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a81d46abe3c2..4fe8b1d35b69 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -235,10 +235,8 @@ enum rtl_registers {
 #define RTL_COALESCE_RX_USECS	GENMASK(7, 4)
 #define RTL_COALESCE_RX_FRAMES	GENMASK(3, 0)
 
-#define RTL_COALESCE_MASK	0x0f
-#define RTL_COALESCE_SHIFT	4
-#define RTL_COALESCE_T_MAX	(RTL_COALESCE_MASK)
-#define RTL_COALESCE_FRAME_MAX	(RTL_COALESCE_MASK << 2)
+#define RTL_COALESCE_T_MAX	0x0fU
+#define RTL_COALESCE_FRAME_MAX	(RTL_COALESCE_T_MAX * 4)
 
 	RxDescAddrLow	= 0xe4,
 	RxDescAddrHigh	= 0xe8,
@@ -1878,57 +1876,49 @@ static int rtl_coalesce_choose_scale(struct rtl8169_private *tp, u32 usec,
 static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	struct {
-		u32 frames;
-		u32 usecs;
-	} coal_settings [] = {
-		{ ec->rx_max_coalesced_frames, ec->rx_coalesce_usecs },
-		{ ec->tx_max_coalesced_frames, ec->tx_coalesce_usecs }
-	}, *p = coal_settings;
+	u32 tx_fr = ec->tx_max_coalesced_frames;
+	u32 rx_fr = ec->rx_max_coalesced_frames;
+	u32 coal_usec_max, units;
 	u16 w = 0, cp01 = 0;
-	u32 coal_usec_max;
-	int scale, i;
+	int scale;
 
 	if (rtl_is_8125(tp))
 		return -EOPNOTSUPP;
 
+	if (rx_fr > RTL_COALESCE_FRAME_MAX || tx_fr > RTL_COALESCE_FRAME_MAX)
+		return -ERANGE;
+
 	coal_usec_max = max(ec->rx_coalesce_usecs, ec->tx_coalesce_usecs);
 	scale = rtl_coalesce_choose_scale(tp, coal_usec_max, &cp01);
 	if (scale < 0)
 		return scale;
 
-	for (i = 0; i < 2; i++, p++) {
-		u32 units;
-
-		/*
-		 * accept max_frames=1 we returned in rtl_get_coalesce.
-		 * accept it not only when usecs=0 because of e.g. the following scenario:
-		 *
-		 * - both rx_usecs=0 & rx_frames=0 in hardware (no delay on RX)
-		 * - rtl_get_coalesce returns rx_usecs=0, rx_frames=1
-		 * - then user does `ethtool -C eth0 rx-usecs 100`
-		 *
-		 * since ethtool sends to kernel whole ethtool_coalesce
-		 * settings, if we want to ignore rx_frames then it has
-		 * to be set to 0.
-		 */
-		if (p->frames == 1) {
-			p->frames = 0;
-		}
+	/* Accept max_frames=1 we returned in rtl_get_coalesce. Accept it
+	 * not only when usecs=0 because of e.g. the following scenario:
+	 *
+	 * - both rx_usecs=0 & rx_frames=0 in hardware (no delay on RX)
+	 * - rtl_get_coalesce returns rx_usecs=0, rx_frames=1
+	 * - then user does `ethtool -C eth0 rx-usecs 100`
+	 *
+	 * Since ethtool sends to kernel whole ethtool_coalesce settings,
+	 * if we want to ignore rx_frames then it has to be set to 0.
+	 */
+	if (rx_fr == 1)
+		rx_fr = 0;
+	if (tx_fr == 1)
+		tx_fr = 0;
 
-		units = DIV_ROUND_UP(p->usecs * 1000, scale);
-		if (p->frames > RTL_COALESCE_FRAME_MAX)
-			return -ERANGE;
+	w |= FIELD_PREP(RTL_COALESCE_TX_FRAMES, DIV_ROUND_UP(tx_fr, 4));
+	w |= FIELD_PREP(RTL_COALESCE_RX_FRAMES, DIV_ROUND_UP(rx_fr, 4));
 
-		w <<= RTL_COALESCE_SHIFT;
-		w |= units;
-		w <<= RTL_COALESCE_SHIFT;
-		w |= DIV_ROUND_UP(p->frames, 4);
-	}
+	units = DIV_ROUND_UP(ec->tx_coalesce_usecs * 1000U, scale);
+	w |= FIELD_PREP(RTL_COALESCE_TX_USECS, units);
+	units = DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000U, scale);
+	w |= FIELD_PREP(RTL_COALESCE_RX_USECS, units);
 
 	rtl_lock_work(tp);
 
-	RTL_W16(tp, IntrMitigate, swab16(w));
+	RTL_W16(tp, IntrMitigate, w);
 
 	tp->cp_cmd = (tp->cp_cmd & ~INTT_MASK) | cp01;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-- 
cgit v1.2.3


From 81496b72e9ba1999d4ed7bb7fa407a1edef020a4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 30 Apr 2020 21:59:48 +0200
Subject: r8169: add check for invalid parameter combination in
 rtl_set_coalesce

Realtek provided information about a HW constraint that time limit must
not be set to 0 if the frame limit is >0. Add a check for this and
reject invalid parameter combinations.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 4fe8b1d35b69..aa3e63e031da 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1908,6 +1908,11 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	if (tx_fr == 1)
 		tx_fr = 0;
 
+	/* HW requires time limit to be set if frame limit is set */
+	if ((tx_fr && !ec->tx_coalesce_usecs) ||
+	    (rx_fr && !ec->rx_coalesce_usecs))
+		return -EINVAL;
+
 	w |= FIELD_PREP(RTL_COALESCE_TX_FRAMES, DIV_ROUND_UP(tx_fr, 4));
 	w |= FIELD_PREP(RTL_COALESCE_RX_FRAMES, DIV_ROUND_UP(rx_fr, 4));
 
-- 
cgit v1.2.3


From 7ae9a4f483eccfd46f40ede8d2bd28fd2f7a9c5f Mon Sep 17 00:00:00 2001
From: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Date: Mon, 27 Apr 2020 16:02:30 +0530
Subject: dpaa_eth: Fix comparing pointer to 0

Fixes coccicheck warning:
./drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:2110:30-31:
WARNING comparing pointer to 0

Avoid pointer type value compared to 0.

Signed-off-by: Aishwarya Ramakrishnan <aishwaryarj100@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 2cd1f8efdfa3..c4416a5f8816 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2107,7 +2107,7 @@ workaround:
 
 	/* Workaround for DPAA_A050385 requires data start to be aligned */
 	start = PTR_ALIGN(new_skb->data, DPAA_A050385_ALIGN);
-	if (start - new_skb->data != 0)
+	if (start - new_skb->data)
 		skb_reserve(new_skb, start - new_skb->data);
 
 	skb_put(new_skb, skb->len);
-- 
cgit v1.2.3


From 654cad8b6a17dcb00077070b27bc65873951a568 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 12:11:10 +0000
Subject: octeontx2-pf: Fix error return code in otx2_probe()

Fix to return negative error code -ENOMEM from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: 5a6d7c9daef3 ("octeontx2-pf: Mailbox communication with AF")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 411e5ea1031e..64786568af0d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1856,13 +1856,17 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	num_vec = pci_msix_vec_count(pdev);
 	hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
 					  GFP_KERNEL);
-	if (!hw->irq_name)
+	if (!hw->irq_name) {
+		err = -ENOMEM;
 		goto err_free_netdev;
+	}
 
 	hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec,
 					 sizeof(cpumask_var_t), GFP_KERNEL);
-	if (!hw->affinity_mask)
+	if (!hw->affinity_mask) {
+		err = -ENOMEM;
 		goto err_free_netdev;
+	}
 
 	/* Map CSRs */
 	pf->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
-- 
cgit v1.2.3


From f8d530ac29fe9248f5e58ca5bcf4c368f8393ccf Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 12:12:28 +0000
Subject: ice: Fix error return code in ice_add_prof()

Fix to return a error code from the error handling case
instead of 0, as done elsewhere in this function.

Fixes: 31ad4e4ee1e4 ("ice: Allocate flow profile")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 42bac3ec5526..e7a2671222d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -2962,8 +2962,10 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 
 	/* add profile info */
 	prof = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*prof), GFP_KERNEL);
-	if (!prof)
+	if (!prof) {
+		status = ICE_ERR_NO_MEMORY;
 		goto err_ice_add_prof;
+	}
 
 	prof->profile_cookie = id;
 	prof->prof_id = prof_id;
-- 
cgit v1.2.3


From 88ec7cb22ddde725ed4ce15991f0bd9dd817fd85 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 12:15:07 +0000
Subject: net: lpc-enet: fix error return code in lpc_mii_init()

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Fixes: b7370112f519 ("lpc32xx: Added ethernet driver")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Vladimir Zapolskiy <vz@mleia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/nxp/lpc_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index d20cf03a3ea0..311454d9b0bc 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -823,7 +823,8 @@ static int lpc_mii_init(struct netdata_local *pldat)
 	if (err)
 		goto err_out_unregister_bus;
 
-	if (lpc_mii_probe(pldat->ndev) != 0)
+	err = lpc_mii_probe(pldat->ndev);
+	if (err)
 		goto err_out_unregister_bus;
 
 	return 0;
-- 
cgit v1.2.3


From 0a699302be5986307b3dcf84ac7a0dd30f9e9305 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Mon, 27 Apr 2020 22:08:04 +0800
Subject: net: ethernet: fec: Revert "net: ethernet: fec: Replace interrupt
 driven MDIO with polled IO"

This reverts commit 29ae6bd1b0d8a57d7c00ab12cbb949fc41986eef.

The commit breaks ethernet function on i.MX6SX, i.MX7D, i.MX8MM,
i.MX8MQ, and i.MX8QXP platforms. Boot yocto system by NFS mounting
rootfs will be failed with the commit.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |  4 +-
 drivers/net/ethernet/freescale/fec_main.c | 67 +++++++++++++++----------------
 2 files changed, 36 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index a6cdd5b61921..e74dd1f86bba 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -376,7 +376,8 @@ struct bufdesc_ex {
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
 #define FEC_ENET_TS_TIMER       ((uint)0x00008000)
 
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF)
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
+#define FEC_NAPI_IMASK	FEC_ENET_MII
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
 /* ENET interrupt coalescing macro define */
@@ -542,6 +543,7 @@ struct fec_enet_private {
 	int	link;
 	int	full_duplex;
 	int	speed;
+	struct	completion mdio_done;
 	int	irq[FEC_IRQ_NUM];
 	bool	bufdesc_ex;
 	int	pause_flag;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1ae075a246a3..c7b84bb22f75 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -976,8 +976,8 @@ fec_restart(struct net_device *ndev)
 	writel((__force u32)cpu_to_be32(temp_mac[1]),
 	       fep->hwp + FEC_ADDR_HIGH);
 
-	/* Clear any outstanding interrupt, except MDIO. */
-	writel((0xffffffff & ~FEC_ENET_MII), fep->hwp + FEC_IEVENT);
+	/* Clear any outstanding interrupt. */
+	writel(0xffffffff, fep->hwp + FEC_IEVENT);
 
 	fec_enet_bd_init(ndev);
 
@@ -1123,7 +1123,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->link)
 		writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 	else
-		writel(0, fep->hwp + FEC_IMASK);
+		writel(FEC_ENET_MII, fep->hwp + FEC_IMASK);
 
 	/* Init the interrupt coalescing */
 	fec_enet_itr_coal_init(ndev);
@@ -1652,10 +1652,6 @@ fec_enet_interrupt(int irq, void *dev_id)
 	irqreturn_t ret = IRQ_NONE;
 
 	int_events = readl(fep->hwp + FEC_IEVENT);
-
-	/* Don't clear MDIO events, we poll for those */
-	int_events &= ~FEC_ENET_MII;
-
 	writel(int_events, fep->hwp + FEC_IEVENT);
 	fec_enet_collect_events(fep, int_events);
 
@@ -1663,12 +1659,16 @@ fec_enet_interrupt(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 
 		if (napi_schedule_prep(&fep->napi)) {
-			/* Disable interrupts */
-			writel(0, fep->hwp + FEC_IMASK);
+			/* Disable the NAPI interrupts */
+			writel(FEC_NAPI_IMASK, fep->hwp + FEC_IMASK);
 			__napi_schedule(&fep->napi);
 		}
 	}
 
+	if (int_events & FEC_ENET_MII) {
+		ret = IRQ_HANDLED;
+		complete(&fep->mdio_done);
+	}
 	return ret;
 }
 
@@ -1818,24 +1818,11 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 		phy_print_status(phy_dev);
 }
 
-static int fec_enet_mdio_wait(struct fec_enet_private *fep)
-{
-	uint ievent;
-	int ret;
-
-	ret = readl_poll_timeout_atomic(fep->hwp + FEC_IEVENT, ievent,
-					ievent & FEC_ENET_MII, 2, 30000);
-
-	if (!ret)
-		writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
-
-	return ret;
-}
-
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
+	unsigned long time_left;
 	int ret = 0, frame_start, frame_addr, frame_op;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1843,6 +1830,8 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ret < 0)
 		return ret;
 
+	reinit_completion(&fep->mdio_done);
+
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1854,9 +1843,11 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		ret = fec_enet_mdio_wait(fep);
-		if (ret) {
+		time_left = wait_for_completion_timeout(&fep->mdio_done,
+				usecs_to_jiffies(FEC_MII_TIMEOUT));
+		if (time_left == 0) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
+			ret = -ETIMEDOUT;
 			goto out;
 		}
 
@@ -1875,9 +1866,11 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		FEC_MMFR_TA, fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	ret = fec_enet_mdio_wait(fep);
-	if (ret) {
+	time_left = wait_for_completion_timeout(&fep->mdio_done,
+			usecs_to_jiffies(FEC_MII_TIMEOUT));
+	if (time_left == 0) {
 		netdev_err(fep->netdev, "MDIO read timeout\n");
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 
@@ -1895,6 +1888,7 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
+	unsigned long time_left;
 	int ret, frame_start, frame_addr;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1904,6 +1898,8 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	else
 		ret = 0;
 
+	reinit_completion(&fep->mdio_done);
+
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1915,9 +1911,11 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		ret = fec_enet_mdio_wait(fep);
-		if (ret) {
+		time_left = wait_for_completion_timeout(&fep->mdio_done,
+			usecs_to_jiffies(FEC_MII_TIMEOUT));
+		if (time_left == 0) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
+			ret = -ETIMEDOUT;
 			goto out;
 		}
 	} else {
@@ -1933,9 +1931,12 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	ret = fec_enet_mdio_wait(fep);
-	if (ret)
+	time_left = wait_for_completion_timeout(&fep->mdio_done,
+			usecs_to_jiffies(FEC_MII_TIMEOUT));
+	if (time_left == 0) {
 		netdev_err(fep->netdev, "MDIO write timeout\n");
+		ret  = -ETIMEDOUT;
+	}
 
 out:
 	pm_runtime_mark_last_busy(dev);
@@ -2144,9 +2145,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
-	/* Clear any pending transaction complete indication */
-	writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
-
 	fep->mii_bus = mdiobus_alloc();
 	if (fep->mii_bus == NULL) {
 		err = -ENOMEM;
@@ -3688,6 +3686,7 @@ fec_probe(struct platform_device *pdev)
 		fep->irq[i] = irq;
 	}
 
+	init_completion(&fep->mdio_done);
 	ret = fec_enet_mii_init(pdev);
 	if (ret)
 		goto failed_mii_init;
-- 
cgit v1.2.3


From c4db9934a33e5f276965a14b3eea7a6d64c85065 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 09:40:52 +0000
Subject: net: ll_temac: Fix return value check in temac_probe()

In case of error, the function devm_ioremap() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check should
be replaced with NULL test.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Esben Haabendal <esben@geanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/ll_temac_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 3e313e71ae36..929244064abd 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1410,9 +1410,9 @@ static int temac_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	lp->regs = devm_ioremap(&pdev->dev, res->start,
 					resource_size(res));
-	if (IS_ERR(lp->regs)) {
+	if (!lp->regs) {
 		dev_err(&pdev->dev, "could not map TEMAC registers\n");
-		return PTR_ERR(lp->regs);
+		return -ENOMEM;
 	}
 
 	/* Select register access functions with the specified
@@ -1505,10 +1505,10 @@ static int temac_probe(struct platform_device *pdev)
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 		lp->sdma_regs = devm_ioremap(&pdev->dev, res->start,
 						     resource_size(res));
-		if (IS_ERR(lp->sdma_regs)) {
+		if (!lp->sdma_regs) {
 			dev_err(&pdev->dev,
 				"could not map DMA registers\n");
-			return PTR_ERR(lp->sdma_regs);
+			return -ENOMEM;
 		}
 		if (pdata->dma_little_endian) {
 			lp->dma_in = temac_dma_in32_le;
-- 
cgit v1.2.3


From 97fff7c8de1e54e5326dfeb66085796864bceb64 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 27 Apr 2020 10:43:22 +0000
Subject: dpaa2-eth: fix error return code in setup_dpni()

Fix to return negative error code -ENOMEM from the error handling
case instead of 0, as done elsewhere in this function.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 8ec435ba7d27..11accab81ea1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2702,8 +2702,10 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
-	if (!priv->cls_rules)
+	if (!priv->cls_rules) {
+		err = -ENOMEM;
 		goto close;
+	}
 
 	return 0;
 
-- 
cgit v1.2.3


From b410439ca371334cd9e5772e411b5e2b6b2d0c9a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 28 Apr 2020 22:54:12 +0200
Subject: r8169: improve max jumbo packet size definition

Sync definition of max jumbo packet size with vendor driver and reserve
22 bytes for VLAN ethernet header plus checksum.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index aa3e63e031da..82f2ae7b6cf7 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -88,10 +88,10 @@
 #define RTL_R16(tp, reg)		readw(tp->mmio_addr + (reg))
 #define RTL_R32(tp, reg)		readl(tp->mmio_addr + (reg))
 
-#define JUMBO_4K	(4*1024 - ETH_HLEN - 2)
-#define JUMBO_6K	(6*1024 - ETH_HLEN - 2)
-#define JUMBO_7K	(7*1024 - ETH_HLEN - 2)
-#define JUMBO_9K	(9*1024 - ETH_HLEN - 2)
+#define JUMBO_4K	(4 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define JUMBO_6K	(6 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define JUMBO_7K	(7 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define JUMBO_9K	(9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 
 static const struct {
 	const char *name;
-- 
cgit v1.2.3


From 838974e1e08a9724525fa13ef15d6e021c23c99d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 28 Apr 2020 22:55:59 +0200
Subject: r8169: configure PME_SIGNAL for RTL8125 too

RTL8125 supports the same PME_SIGNAL handling as all later RTL8168
chip variants.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 82f2ae7b6cf7..0ac3976e3204 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1429,7 +1429,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_52:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_61:
 		options = RTL_R8(tp, Config2) & ~PME_SIGNAL;
 		if (wolopts)
 			options |= PME_SIGNAL;
-- 
cgit v1.2.3


From 2597912514925f6f06e85807cc9fc0fdfa630d11 Mon Sep 17 00:00:00 2001
From: Zheng Bin <zhengbin13@huawei.com>
Date: Wed, 29 Apr 2020 09:58:24 +0800
Subject: hinic: make symbol 'dump_mox_reg' static

Fix sparse warnings:

drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c:601:6: warning: symbol 'dump_mox_reg' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
index f8626dfd192e..d5cf31529dbf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -598,7 +598,7 @@ static void write_mbox_msg_attr(struct hinic_mbox_func_to_func *func_to_func,
 			     HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF, mbox_ctrl);
 }
 
-void dump_mox_reg(struct hinic_hwdev *hwdev)
+static void dump_mox_reg(struct hinic_hwdev *hwdev)
 {
 	u32 val;
 
-- 
cgit v1.2.3


From 37ecb5b8b8cd3156e739fd1c56a8e3842b72ebad Mon Sep 17 00:00:00 2001
From: Zou Wei <zou_wei@huawei.com>
Date: Wed, 29 Apr 2020 11:35:28 +0800
Subject: hinic: Use kmemdup instead of kzalloc and memcpy

Fixes coccicheck warnings:

 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c:452:17-24: WARNING opportunity for kmemdup
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c:458:23-30: WARNING opportunity for kmemdup

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
index d5cf31529dbf..564fb2294a29 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -449,18 +449,15 @@ static void recv_mbox_handler(struct hinic_mbox_func_to_func *func_to_func,
 		return;
 	}
 
-	rcv_mbox_temp = kzalloc(sizeof(*rcv_mbox_temp), GFP_KERNEL);
+	rcv_mbox_temp = kmemdup(recv_mbox, sizeof(*rcv_mbox_temp), GFP_KERNEL);
 	if (!rcv_mbox_temp)
 		return;
 
-	memcpy(rcv_mbox_temp, recv_mbox, sizeof(*rcv_mbox_temp));
-
-	rcv_mbox_temp->mbox = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
+	rcv_mbox_temp->mbox = kmemdup(recv_mbox->mbox, MBOX_MAX_BUF_SZ,
+				      GFP_KERNEL);
 	if (!rcv_mbox_temp->mbox)
 		goto err_alloc_rcv_mbox_msg;
 
-	memcpy(rcv_mbox_temp->mbox, recv_mbox->mbox, MBOX_MAX_BUF_SZ);
-
 	rcv_mbox_temp->buf_out = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL);
 	if (!rcv_mbox_temp->buf_out)
 		goto err_alloc_rcv_mbox_buf;
-- 
cgit v1.2.3


From ef891284b130c365a7b60afaf7fe3c92c4260bfb Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 10:11:28 +0200
Subject: r8169: remove not needed parameter in rtl8169_set_magic_reg

Remove a not needed parameter in rtl8169_set_magic_reg.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0ac3976e3204..0f869a761d8c 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2608,7 +2608,7 @@ static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp)
 	RTL_W32(tp, RxDescAddrLow, ((u64) tp->RxPhyAddr) & DMA_BIT_MASK(32));
 }
 
-static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_version)
+static void rtl8169_set_magic_reg(struct rtl8169_private *tp)
 {
 	u32 val;
 
@@ -3811,7 +3811,7 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp)
 
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	rtl8169_set_magic_reg(tp, tp->mac_version);
+	rtl8169_set_magic_reg(tp);
 
 	/* disable interrupt coalescing */
 	RTL_W16(tp, IntrMitigate, 0x0000);
-- 
cgit v1.2.3


From 64363e61c7bbcfa4c7d6697d96ef2e18fc311cf3 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Thu, 30 Apr 2020 22:21:40 +0300
Subject: net/mlx5: Change lag mutex lock to spin lock

The lag lock could be a spin lock, the critical section is short
and there is no need that the thread will sleep.
Change the lock that protects the LAG structure from mutex
to spin lock. It is required for next patch that need to
access this structure from context that we can't sleep.
In addition there is no need to hold this lock when query the
congestion counters.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 42 +++++++++++++--------------
 1 file changed, 21 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index c6ad5ca46877..b17b80bcd045 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -42,7 +42,7 @@
  * Beware of lock dependencies (preferably, no locks should be acquired
  * under it).
  */
-static DEFINE_MUTEX(lag_mutex);
+static DEFINE_SPINLOCK(lag_lock);
 
 static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1,
 			       u8 remap_port2)
@@ -274,9 +274,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	if (!dev0 || !dev1)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	tracker = ldev->tracker;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
@@ -458,9 +458,9 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 		break;
 	}
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev->tracker = tracker;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	if (changed)
 		mlx5_queue_bond_work(ldev, 0);
@@ -502,7 +502,7 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 	if (fn >= MLX5_MAX_PORTS)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev->pf[fn].dev    = dev;
 	ldev->pf[fn].netdev = netdev;
 	ldev->tracker.netdev_state[fn].link_up = 0;
@@ -510,7 +510,7 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 
 	dev->priv.lag = ldev;
 
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 }
 
 static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
@@ -525,11 +525,11 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
 	if (i == MLX5_MAX_PORTS)
 		return;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
 
 	dev->priv.lag = NULL;
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 }
 
 /* Must be called with intf_mutex held */
@@ -607,10 +607,10 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_roce(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -621,10 +621,10 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_active(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -635,10 +635,10 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 	struct mlx5_lag *ldev;
 	bool res;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	res  = ldev && __mlx5_lag_is_sriov(ldev);
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return res;
 }
@@ -664,7 +664,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	struct net_device *ndev = NULL;
 	struct mlx5_lag *ldev;
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
@@ -681,7 +681,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 		dev_hold(ndev);
 
 unlock:
-	mutex_unlock(&lag_mutex);
+	spin_unlock(&lag_lock);
 
 	return ndev;
 }
@@ -723,7 +723,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	memset(values, 0, sizeof(*values) * num_counters);
 
-	mutex_lock(&lag_mutex);
+	spin_lock(&lag_lock);
 	ldev = mlx5_lag_dev_get(dev);
 	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
@@ -733,6 +733,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		num_ports = 1;
 		mdev[MLX5_LAG_P1] = dev;
 	}
+	spin_unlock(&lag_lock);
 
 	for (i = 0; i < num_ports; ++i) {
 		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
@@ -742,14 +743,13 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		ret = mlx5_cmd_exec_inout(mdev[i], query_cong_statistics, in,
 					  out);
 		if (ret)
-			goto unlock;
+			goto free;
 
 		for (j = 0; j < num_counters; ++j)
 			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
 	}
 
-unlock:
-	mutex_unlock(&lag_mutex);
+free:
 	kvfree(out);
 	return ret;
 }
-- 
cgit v1.2.3


From c6bc6041b10f70b617f2d13894311fe62027d292 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Thu, 30 Apr 2020 22:21:41 +0300
Subject: net/mlx5: Add support to get lag physical port

Add function to get the device physical port of the lag slave.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 24 ++++++++++++++++++++++++
 include/linux/mlx5/driver.h                   |  2 ++
 2 files changed, 26 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index b17b80bcd045..874c70e8cc54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -687,6 +687,30 @@ unlock:
 }
 EXPORT_SYMBOL(mlx5_lag_get_roce_netdev);
 
+u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
+			   struct net_device *slave)
+{
+	struct mlx5_lag *ldev;
+	u8 port = 0;
+
+	spin_lock(&lag_lock);
+	ldev = mlx5_lag_dev_get(dev);
+	if (!(ldev && __mlx5_lag_is_roce(ldev)))
+		goto unlock;
+
+	if (ldev->pf[MLX5_LAG_P1].netdev == slave)
+		port = MLX5_LAG_P1;
+	else
+		port = MLX5_LAG_P2;
+
+	port = ldev->v2p_map[port];
+
+unlock:
+	spin_unlock(&lag_lock);
+	return port;
+}
+EXPORT_SYMBOL(mlx5_lag_get_slave_port);
+
 bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 {
 	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d82dbbab8179..267dfcc5493e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1074,6 +1074,8 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
+u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
+			   struct net_device *slave);
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 u64 *values,
 				 int num_counters,
-- 
cgit v1.2.3


From 9ea2af8d16f5612168ed52cb0ec6752bac0877a9 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:35 +0200
Subject: docs: networking: device drivers: convert 3com/vortex.txt to ReST

- add SPDX header;
- add a document title;
- mark code blocks and literals as such;
- mark tables as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/3com/vortex.rst      | 461 +++++++++++++++++++++
 .../networking/device_drivers/3com/vortex.txt      | 448 --------------------
 Documentation/networking/device_drivers/index.rst  |   1 +
 MAINTAINERS                                        |   2 +-
 drivers/net/ethernet/3com/3c59x.c                  |   4 +-
 drivers/net/ethernet/3com/Kconfig                  |   2 +-
 6 files changed, 466 insertions(+), 452 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/3com/vortex.rst
 delete mode 100644 Documentation/networking/device_drivers/3com/vortex.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/3com/vortex.rst b/Documentation/networking/device_drivers/3com/vortex.rst
new file mode 100644
index 000000000000..800add5be338
--- /dev/null
+++ b/Documentation/networking/device_drivers/3com/vortex.rst
@@ -0,0 +1,461 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+3Com Vortex device driver
+=========================
+
+Documentation/networking/device_drivers/3com/vortex.rst
+
+Andrew Morton
+
+30 April 2000
+
+
+This document describes the usage and errata of the 3Com "Vortex" device
+driver for Linux, 3c59x.c.
+
+The driver was written by Donald Becker <becker@scyld.com>
+
+Don is no longer the prime maintainer of this version of the driver.
+Please report problems to one or more of:
+
+- Andrew Morton
+- Netdev mailing list <netdev@vger.kernel.org>
+- Linux kernel mailing list <linux-kernel@vger.kernel.org>
+
+Please note the 'Reporting and Diagnosing Problems' section at the end
+of this file.
+
+
+Since kernel 2.3.99-pre6, this driver incorporates the support for the
+3c575-series Cardbus cards which used to be handled by 3c575_cb.c.
+
+This driver supports the following hardware:
+
+	- 3c590 Vortex 10Mbps
+	- 3c592 EISA 10Mbps Demon/Vortex
+	- 3c597 EISA Fast Demon/Vortex
+	- 3c595 Vortex 100baseTx
+	- 3c595 Vortex 100baseT4
+	- 3c595 Vortex 100base-MII
+	- 3c900 Boomerang 10baseT
+	- 3c900 Boomerang 10Mbps Combo
+	- 3c900 Cyclone 10Mbps TPO
+	- 3c900 Cyclone 10Mbps Combo
+	- 3c900 Cyclone 10Mbps TPC
+	- 3c900B-FL Cyclone 10base-FL
+	- 3c905 Boomerang 100baseTx
+	- 3c905 Boomerang 100baseT4
+	- 3c905B Cyclone 100baseTx
+	- 3c905B Cyclone 10/100/BNC
+	- 3c905B-FX Cyclone 100baseFx
+	- 3c905C Tornado
+	- 3c920B-EMB-WNM (ATI Radeon 9100 IGP)
+	- 3c980 Cyclone
+	- 3c980C Python-T
+	- 3cSOHO100-TX Hurricane
+	- 3c555 Laptop Hurricane
+	- 3c556 Laptop Tornado
+	- 3c556B Laptop Hurricane
+	- 3c575 [Megahertz] 10/100 LAN  CardBus
+	- 3c575 Boomerang CardBus
+	- 3CCFE575BT Cyclone CardBus
+	- 3CCFE575CT Tornado CardBus
+	- 3CCFE656 Cyclone CardBus
+	- 3CCFEM656B Cyclone+Winmodem CardBus
+	- 3CXFEM656C Tornado+Winmodem CardBus
+	- 3c450 HomePNA Tornado
+	- 3c920 Tornado
+	- 3c982 Hydra Dual Port A
+	- 3c982 Hydra Dual Port B
+	- 3c905B-T4
+	- 3c920B-EMB-WNM Tornado
+
+Module parameters
+=================
+
+There are several parameters which may be provided to the driver when
+its module is loaded.  These are usually placed in ``/etc/modprobe.d/*.conf``
+configuration files.  Example::
+
+    options 3c59x debug=3 rx_copybreak=300
+
+If you are using the PCMCIA tools (cardmgr) then the options may be
+placed in /etc/pcmcia/config.opts::
+
+    module "3c59x" opts "debug=3 rx_copybreak=300"
+
+
+The supported parameters are:
+
+debug=N
+
+  Where N is a number from 0 to 7.  Anything above 3 produces a lot
+  of output in your system logs.  debug=1 is default.
+
+options=N1,N2,N3,...
+
+  Each number in the list provides an option to the corresponding
+  network card.  So if you have two 3c905's and you wish to provide
+  them with option 0x204 you would use::
+
+    options=0x204,0x204
+
+  The individual options are composed of a number of bitfields which
+  have the following meanings:
+
+  Possible media type settings
+
+	==	=================================
+	0	10baseT
+	1	10Mbs AUI
+	2	undefined
+	3	10base2 (BNC)
+	4	100base-TX
+	5	100base-FX
+	6	MII (Media Independent Interface)
+	7	Use default setting from EEPROM
+	8       Autonegotiate
+	9       External MII
+	10      Use default setting from EEPROM
+	==	=================================
+
+  When generating a value for the 'options' setting, the above media
+  selection values may be OR'ed (or added to) the following:
+
+  ======  =============================================
+  0x8000  Set driver debugging level to 7
+  0x4000  Set driver debugging level to 2
+  0x0400  Enable Wake-on-LAN
+  0x0200  Force full duplex mode.
+  0x0010  Bus-master enable bit (Old Vortex cards only)
+  ======  =============================================
+
+  For example::
+
+    insmod 3c59x options=0x204
+
+  will force full-duplex 100base-TX, rather than allowing the usual
+  autonegotiation.
+
+global_options=N
+
+  Sets the ``options`` parameter for all 3c59x NICs in the machine.
+  Entries in the ``options`` array above will override any setting of
+  this.
+
+full_duplex=N1,N2,N3...
+
+  Similar to bit 9 of 'options'.  Forces the corresponding card into
+  full-duplex mode.  Please use this in preference to the ``options``
+  parameter.
+
+  In fact, please don't use this at all! You're better off getting
+  autonegotiation working properly.
+
+global_full_duplex=N1
+
+  Sets full duplex mode for all 3c59x NICs in the machine.  Entries
+  in the ``full_duplex`` array above will override any setting of this.
+
+flow_ctrl=N1,N2,N3...
+
+  Use 802.3x MAC-layer flow control.  The 3com cards only support the
+  PAUSE command, which means that they will stop sending packets for a
+  short period if they receive a PAUSE frame from the link partner.
+
+  The driver only allows flow control on a link which is operating in
+  full duplex mode.
+
+  This feature does not appear to work on the 3c905 - only 3c905B and
+  3c905C have been tested.
+
+  The 3com cards appear to only respond to PAUSE frames which are
+  sent to the reserved destination address of 01:80:c2:00:00:01.  They
+  do not honour PAUSE frames which are sent to the station MAC address.
+
+rx_copybreak=M
+
+  The driver preallocates 32 full-sized (1536 byte) network buffers
+  for receiving.  When a packet arrives, the driver has to decide
+  whether to leave the packet in its full-sized buffer, or to allocate
+  a smaller buffer and copy the packet across into it.
+
+  This is a speed/space tradeoff.
+
+  The value of rx_copybreak is used to decide when to make the copy.
+  If the packet size is less than rx_copybreak, the packet is copied.
+  The default value for rx_copybreak is 200 bytes.
+
+max_interrupt_work=N
+
+  The driver's interrupt service routine can handle many receive and
+  transmit packets in a single invocation.  It does this in a loop.
+  The value of max_interrupt_work governs how many times the interrupt
+  service routine will loop.  The default value is 32 loops.  If this
+  is exceeded the interrupt service routine gives up and generates a
+  warning message "eth0: Too much work in interrupt".
+
+hw_checksums=N1,N2,N3,...
+
+  Recent 3com NICs are able to generate IPv4, TCP and UDP checksums
+  in hardware.  Linux has used the Rx checksumming for a long time.
+  The "zero copy" patch which is planned for the 2.4 kernel series
+  allows you to make use of the NIC's DMA scatter/gather and transmit
+  checksumming as well.
+
+  The driver is set up so that, when the zerocopy patch is applied,
+  all Tornado and Cyclone devices will use S/G and Tx checksums.
+
+  This module parameter has been provided so you can override this
+  decision.  If you think that Tx checksums are causing a problem, you
+  may disable the feature with ``hw_checksums=0``.
+
+  If you think your NIC should be performing Tx checksumming and the
+  driver isn't enabling it, you can force the use of hardware Tx
+  checksumming with ``hw_checksums=1``.
+
+  The driver drops a message in the logfiles to indicate whether or
+  not it is using hardware scatter/gather and hardware Tx checksums.
+
+  Scatter/gather and hardware checksums provide considerable
+  performance improvement for the sendfile() system call, but a small
+  decrease in throughput for send().  There is no effect upon receive
+  efficiency.
+
+compaq_ioaddr=N,
+compaq_irq=N,
+compaq_device_id=N
+
+  "Variables to work-around the Compaq PCI BIOS32 problem"....
+
+watchdog=N
+
+  Sets the time duration (in milliseconds) after which the kernel
+  decides that the transmitter has become stuck and needs to be reset.
+  This is mainly for debugging purposes, although it may be advantageous
+  to increase this value on LANs which have very high collision rates.
+  The default value is 5000 (5.0 seconds).
+
+enable_wol=N1,N2,N3,...
+
+  Enable Wake-on-LAN support for the relevant interface.  Donald
+  Becker's ``ether-wake`` application may be used to wake suspended
+  machines.
+
+  Also enables the NIC's power management support.
+
+global_enable_wol=N
+
+  Sets enable_wol mode for all 3c59x NICs in the machine.  Entries in
+  the ``enable_wol`` array above will override any setting of this.
+
+Media selection
+---------------
+
+A number of the older NICs such as the 3c590 and 3c900 series have
+10base2 and AUI interfaces.
+
+Prior to January, 2001 this driver would autoeselect the 10base2 or AUI
+port if it didn't detect activity on the 10baseT port.  It would then
+get stuck on the 10base2 port and a driver reload was necessary to
+switch back to 10baseT.  This behaviour could not be prevented with a
+module option override.
+
+Later (current) versions of the driver _do_ support locking of the
+media type.  So if you load the driver module with
+
+	modprobe 3c59x options=0
+
+it will permanently select the 10baseT port.  Automatic selection of
+other media types does not occur.
+
+
+Transmit error, Tx status register 82
+-------------------------------------
+
+This is a common error which is almost always caused by another host on
+the same network being in full-duplex mode, while this host is in
+half-duplex mode.  You need to find that other host and make it run in
+half-duplex mode or fix this host to run in full-duplex mode.
+
+As a last resort, you can force the 3c59x driver into full-duplex mode
+with
+
+	options 3c59x full_duplex=1
+
+but this has to be viewed as a workaround for broken network gear and
+should only really be used for equipment which cannot autonegotiate.
+
+
+Additional resources
+--------------------
+
+Details of the device driver implementation are at the top of the source file.
+
+Additional documentation is available at Don Becker's Linux Drivers site:
+
+     http://www.scyld.com/vortex.html
+
+Donald Becker's driver development site:
+
+     http://www.scyld.com/network.html
+
+Donald's vortex-diag program is useful for inspecting the NIC's state:
+
+     http://www.scyld.com/ethercard_diag.html
+
+Donald's mii-diag program may be used for inspecting and manipulating
+the NIC's Media Independent Interface subsystem:
+
+     http://www.scyld.com/ethercard_diag.html#mii-diag
+
+Donald's wake-on-LAN page:
+
+     http://www.scyld.com/wakeonlan.html
+
+3Com's DOS-based application for setting up the NICs EEPROMs:
+
+	ftp://ftp.3com.com/pub/nic/3c90x/3c90xx2.exe
+
+
+Autonegotiation notes
+---------------------
+
+  The driver uses a one-minute heartbeat for adapting to changes in
+  the external LAN environment if link is up and 5 seconds if link is down.
+  This means that when, for example, a machine is unplugged from a hubbed
+  10baseT LAN plugged into a  switched 100baseT LAN, the throughput
+  will be quite dreadful for up to sixty seconds.  Be patient.
+
+  Cisco interoperability note from Walter Wong <wcw+@CMU.EDU>:
+
+  On a side note, adding HAS_NWAY seems to share a problem with the
+  Cisco 6509 switch.  Specifically, you need to change the spanning
+  tree parameter for the port the machine is plugged into to 'portfast'
+  mode.  Otherwise, the negotiation fails.  This has been an issue
+  we've noticed for a while but haven't had the time to track down.
+
+  Cisco switches    (Jeff Busch <jbusch@deja.com>)
+
+    My "standard config" for ports to which PC's/servers connect directly::
+
+	interface FastEthernet0/N
+	description machinename
+	load-interval 30
+	spanning-tree portfast
+
+    If autonegotiation is a problem, you may need to specify "speed
+    100" and "duplex full" as well (or "speed 10" and "duplex half").
+
+    WARNING: DO NOT hook up hubs/switches/bridges to these
+    specially-configured ports! The switch will become very confused.
+
+
+Reporting and diagnosing problems
+---------------------------------
+
+Maintainers find that accurate and complete problem reports are
+invaluable in resolving driver problems.  We are frequently not able to
+reproduce problems and must rely on your patience and efforts to get to
+the bottom of the problem.
+
+If you believe you have a driver problem here are some of the
+steps you should take:
+
+- Is it really a driver problem?
+
+   Eliminate some variables: try different cards, different
+   computers, different cables, different ports on the switch/hub,
+   different versions of the kernel or of the driver, etc.
+
+- OK, it's a driver problem.
+
+   You need to generate a report.  Typically this is an email to the
+   maintainer and/or netdev@vger.kernel.org.  The maintainer's
+   email address will be in the driver source or in the MAINTAINERS file.
+
+- The contents of your report will vary a lot depending upon the
+  problem.  If it's a kernel crash then you should refer to the
+  admin-guide/reporting-bugs.rst file.
+
+  But for most problems it is useful to provide the following:
+
+   - Kernel version, driver version
+
+   - A copy of the banner message which the driver generates when
+     it is initialised.  For example:
+
+     eth0: 3Com PCI 3c905C Tornado at 0xa400,  00:50:da:6a:88:f0, IRQ 19
+     8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
+     MII transceiver found at address 24, status 782d.
+     Enabling bus-master transmits and whole-frame receives.
+
+     NOTE: You must provide the ``debug=2`` modprobe option to generate
+     a full detection message.  Please do this::
+
+	modprobe 3c59x debug=2
+
+   - If it is a PCI device, the relevant output from 'lspci -vx', eg::
+
+       00:09.0 Ethernet controller: 3Com Corporation 3c905C-TX [Fast Etherlink] (rev 74)
+	       Subsystem: 3Com Corporation: Unknown device 9200
+	       Flags: bus master, medium devsel, latency 32, IRQ 19
+	       I/O ports at a400 [size=128]
+	       Memory at db000000 (32-bit, non-prefetchable) [size=128]
+	       Expansion ROM at <unassigned> [disabled] [size=128K]
+	       Capabilities: [dc] Power Management version 2
+       00: b7 10 00 92 07 00 10 02 74 00 00 02 08 20 00 00
+       10: 01 a4 00 00 00 00 00 db 00 00 00 00 00 00 00 00
+       20: 00 00 00 00 00 00 00 00 00 00 00 00 b7 10 00 10
+       30: 00 00 00 00 dc 00 00 00 00 00 00 00 05 01 0a 0a
+
+   - A description of the environment: 10baseT? 100baseT?
+     full/half duplex? switched or hubbed?
+
+   - Any additional module parameters which you may be providing to the driver.
+
+   - Any kernel logs which are produced.  The more the merrier.
+     If this is a large file and you are sending your report to a
+     mailing list, mention that you have the logfile, but don't send
+     it.  If you're reporting direct to the maintainer then just send
+     it.
+
+     To ensure that all kernel logs are available, add the
+     following line to /etc/syslog.conf::
+
+	 kern.* /var/log/messages
+
+     Then restart syslogd with::
+
+	 /etc/rc.d/init.d/syslog restart
+
+     (The above may vary, depending upon which Linux distribution you use).
+
+    - If your problem is reproducible then that's great.  Try the
+      following:
+
+      1) Increase the debug level.  Usually this is done via:
+
+	 a) modprobe driver debug=7
+	 b) In /etc/modprobe.d/driver.conf:
+	    options driver debug=7
+
+      2) Recreate the problem with the higher debug level,
+	 send all logs to the maintainer.
+
+      3) Download you card's diagnostic tool from Donald
+	 Becker's website <http://www.scyld.com/ethercard_diag.html>.
+	 Download mii-diag.c as well.  Build these.
+
+	 a) Run 'vortex-diag -aaee' and 'mii-diag -v' when the card is
+	    working correctly.  Save the output.
+
+	 b) Run the above commands when the card is malfunctioning.  Send
+	    both sets of output.
+
+Finally, please be patient and be prepared to do some work.  You may
+end up working on this problem for a week or more as the maintainer
+asks more questions, asks for more tests, asks for patches to be
+applied, etc.  At the end of it all, the problem may even remain
+unresolved.
diff --git a/Documentation/networking/device_drivers/3com/vortex.txt b/Documentation/networking/device_drivers/3com/vortex.txt
deleted file mode 100644
index 587f3fcfbcae..000000000000
--- a/Documentation/networking/device_drivers/3com/vortex.txt
+++ /dev/null
@@ -1,448 +0,0 @@
-Documentation/networking/device_drivers/3com/vortex.txt
-Andrew Morton
-30 April 2000
-
-
-This document describes the usage and errata of the 3Com "Vortex" device
-driver for Linux, 3c59x.c.
-
-The driver was written by Donald Becker <becker@scyld.com>
-
-Don is no longer the prime maintainer of this version of the driver. 
-Please report problems to one or more of:
-
-  Andrew Morton
-  Netdev mailing list <netdev@vger.kernel.org>
-  Linux kernel mailing list <linux-kernel@vger.kernel.org>
-
-Please note the 'Reporting and Diagnosing Problems' section at the end
-of this file.
-
-
-Since kernel 2.3.99-pre6, this driver incorporates the support for the
-3c575-series Cardbus cards which used to be handled by 3c575_cb.c.
-
-This driver supports the following hardware:
-
-	3c590 Vortex 10Mbps
-	3c592 EISA 10Mbps Demon/Vortex
-	3c597 EISA Fast Demon/Vortex
-	3c595 Vortex 100baseTx
-	3c595 Vortex 100baseT4
-	3c595 Vortex 100base-MII
-	3c900 Boomerang 10baseT
-	3c900 Boomerang 10Mbps Combo
-	3c900 Cyclone 10Mbps TPO
-	3c900 Cyclone 10Mbps Combo
-	3c900 Cyclone 10Mbps TPC
-	3c900B-FL Cyclone 10base-FL
-	3c905 Boomerang 100baseTx
-	3c905 Boomerang 100baseT4
-	3c905B Cyclone 100baseTx
-	3c905B Cyclone 10/100/BNC
-	3c905B-FX Cyclone 100baseFx
-	3c905C Tornado
-	3c920B-EMB-WNM (ATI Radeon 9100 IGP)
-	3c980 Cyclone
-	3c980C Python-T
-	3cSOHO100-TX Hurricane
-	3c555 Laptop Hurricane
-	3c556 Laptop Tornado
-	3c556B Laptop Hurricane
-	3c575 [Megahertz] 10/100 LAN  CardBus
-	3c575 Boomerang CardBus
-	3CCFE575BT Cyclone CardBus
-	3CCFE575CT Tornado CardBus
-	3CCFE656 Cyclone CardBus
-	3CCFEM656B Cyclone+Winmodem CardBus
-	3CXFEM656C Tornado+Winmodem CardBus
-	3c450 HomePNA Tornado
-	3c920 Tornado
-	3c982 Hydra Dual Port A
-	3c982 Hydra Dual Port B
-	3c905B-T4
-	3c920B-EMB-WNM Tornado
-
-Module parameters
-=================
-
-There are several parameters which may be provided to the driver when
-its module is loaded.  These are usually placed in /etc/modprobe.d/*.conf
-configuration files.  Example:
-
-options 3c59x debug=3 rx_copybreak=300
-
-If you are using the PCMCIA tools (cardmgr) then the options may be
-placed in /etc/pcmcia/config.opts:
-
-module "3c59x" opts "debug=3 rx_copybreak=300"
-
-
-The supported parameters are:
-
-debug=N
-
-  Where N is a number from 0 to 7.  Anything above 3 produces a lot
-  of output in your system logs.  debug=1 is default.
-
-options=N1,N2,N3,...
-
-  Each number in the list provides an option to the corresponding
-  network card.  So if you have two 3c905's and you wish to provide
-  them with option 0x204 you would use:
-
-    options=0x204,0x204
-
-  The individual options are composed of a number of bitfields which
-  have the following meanings:
-
-  Possible media type settings
-	0	10baseT
-	1	10Mbs AUI
-	2	undefined
-	3	10base2 (BNC)
-	4	100base-TX
-	5	100base-FX
-	6	MII (Media Independent Interface)
-	7	Use default setting from EEPROM
-	8       Autonegotiate
-	9       External MII
-	10      Use default setting from EEPROM
-
-  When generating a value for the 'options' setting, the above media
-  selection values may be OR'ed (or added to) the following:
-
-  0x8000  Set driver debugging level to 7
-  0x4000  Set driver debugging level to 2
-  0x0400  Enable Wake-on-LAN
-  0x0200  Force full duplex mode.
-  0x0010  Bus-master enable bit (Old Vortex cards only)
-
-  For example:
-
-    insmod 3c59x options=0x204
-
-  will force full-duplex 100base-TX, rather than allowing the usual
-  autonegotiation.
-
-global_options=N
-
-  Sets the `options' parameter for all 3c59x NICs in the machine. 
-  Entries in the `options' array above will override any setting of
-  this.
-
-full_duplex=N1,N2,N3...
-
-  Similar to bit 9 of 'options'.  Forces the corresponding card into
-  full-duplex mode.  Please use this in preference to the `options'
-  parameter.
-
-  In fact, please don't use this at all! You're better off getting
-  autonegotiation working properly.
-
-global_full_duplex=N1
-
-  Sets full duplex mode for all 3c59x NICs in the machine.  Entries
-  in the `full_duplex' array above will override any setting of this.
-
-flow_ctrl=N1,N2,N3...
-
-  Use 802.3x MAC-layer flow control.  The 3com cards only support the
-  PAUSE command, which means that they will stop sending packets for a
-  short period if they receive a PAUSE frame from the link partner. 
-
-  The driver only allows flow control on a link which is operating in
-  full duplex mode.
-
-  This feature does not appear to work on the 3c905 - only 3c905B and
-  3c905C have been tested.
-
-  The 3com cards appear to only respond to PAUSE frames which are
-  sent to the reserved destination address of 01:80:c2:00:00:01.  They
-  do not honour PAUSE frames which are sent to the station MAC address.
-
-rx_copybreak=M
-
-  The driver preallocates 32 full-sized (1536 byte) network buffers
-  for receiving.  When a packet arrives, the driver has to decide
-  whether to leave the packet in its full-sized buffer, or to allocate
-  a smaller buffer and copy the packet across into it.
-
-  This is a speed/space tradeoff.
-
-  The value of rx_copybreak is used to decide when to make the copy. 
-  If the packet size is less than rx_copybreak, the packet is copied. 
-  The default value for rx_copybreak is 200 bytes.
-
-max_interrupt_work=N
-
-  The driver's interrupt service routine can handle many receive and
-  transmit packets in a single invocation.  It does this in a loop. 
-  The value of max_interrupt_work governs how many times the interrupt
-  service routine will loop.  The default value is 32 loops.  If this
-  is exceeded the interrupt service routine gives up and generates a
-  warning message "eth0: Too much work in interrupt".
-
-hw_checksums=N1,N2,N3,...
-
-  Recent 3com NICs are able to generate IPv4, TCP and UDP checksums
-  in hardware.  Linux has used the Rx checksumming for a long time. 
-  The "zero copy" patch which is planned for the 2.4 kernel series
-  allows you to make use of the NIC's DMA scatter/gather and transmit
-  checksumming as well.
-
-  The driver is set up so that, when the zerocopy patch is applied,
-  all Tornado and Cyclone devices will use S/G and Tx checksums.
-
-  This module parameter has been provided so you can override this
-  decision.  If you think that Tx checksums are causing a problem, you
-  may disable the feature with `hw_checksums=0'.
-
-  If you think your NIC should be performing Tx checksumming and the
-  driver isn't enabling it, you can force the use of hardware Tx
-  checksumming with `hw_checksums=1'.
-
-  The driver drops a message in the logfiles to indicate whether or
-  not it is using hardware scatter/gather and hardware Tx checksums.
-
-  Scatter/gather and hardware checksums provide considerable
-  performance improvement for the sendfile() system call, but a small
-  decrease in throughput for send().  There is no effect upon receive
-  efficiency.
-
-compaq_ioaddr=N
-compaq_irq=N
-compaq_device_id=N
-
-  "Variables to work-around the Compaq PCI BIOS32 problem"....
-
-watchdog=N
-
-  Sets the time duration (in milliseconds) after which the kernel
-  decides that the transmitter has become stuck and needs to be reset. 
-  This is mainly for debugging purposes, although it may be advantageous
-  to increase this value on LANs which have very high collision rates.
-  The default value is 5000 (5.0 seconds).
-
-enable_wol=N1,N2,N3,...
-
-  Enable Wake-on-LAN support for the relevant interface.  Donald
-  Becker's `ether-wake' application may be used to wake suspended
-  machines.
-
-  Also enables the NIC's power management support.
-
-global_enable_wol=N
-
-  Sets enable_wol mode for all 3c59x NICs in the machine.  Entries in
-  the `enable_wol' array above will override any setting of this.
-
-Media selection
----------------
-
-A number of the older NICs such as the 3c590 and 3c900 series have
-10base2 and AUI interfaces.
-
-Prior to January, 2001 this driver would autoeselect the 10base2 or AUI
-port if it didn't detect activity on the 10baseT port.  It would then
-get stuck on the 10base2 port and a driver reload was necessary to
-switch back to 10baseT.  This behaviour could not be prevented with a
-module option override.
-
-Later (current) versions of the driver _do_ support locking of the
-media type.  So if you load the driver module with
-
-	modprobe 3c59x options=0
-
-it will permanently select the 10baseT port.  Automatic selection of
-other media types does not occur.
-
-
-Transmit error, Tx status register 82
--------------------------------------
-
-This is a common error which is almost always caused by another host on
-the same network being in full-duplex mode, while this host is in
-half-duplex mode.  You need to find that other host and make it run in
-half-duplex mode or fix this host to run in full-duplex mode.
-
-As a last resort, you can force the 3c59x driver into full-duplex mode
-with
-
-	options 3c59x full_duplex=1
-
-but this has to be viewed as a workaround for broken network gear and
-should only really be used for equipment which cannot autonegotiate.
-
-
-Additional resources
---------------------
-
-Details of the device driver implementation are at the top of the source file.
-
-Additional documentation is available at Don Becker's Linux Drivers site:
-
-     http://www.scyld.com/vortex.html
-
-Donald Becker's driver development site:
-
-     http://www.scyld.com/network.html
-
-Donald's vortex-diag program is useful for inspecting the NIC's state:
-
-     http://www.scyld.com/ethercard_diag.html
-
-Donald's mii-diag program may be used for inspecting and manipulating
-the NIC's Media Independent Interface subsystem:
-
-     http://www.scyld.com/ethercard_diag.html#mii-diag
-
-Donald's wake-on-LAN page:
-
-     http://www.scyld.com/wakeonlan.html
-
-3Com's DOS-based application for setting up the NICs EEPROMs:
-
-	ftp://ftp.3com.com/pub/nic/3c90x/3c90xx2.exe
-
-
-Autonegotiation notes
----------------------
-
-  The driver uses a one-minute heartbeat for adapting to changes in
-  the external LAN environment if link is up and 5 seconds if link is down.
-  This means that when, for example, a machine is unplugged from a hubbed
-  10baseT LAN plugged into a  switched 100baseT LAN, the throughput
-  will be quite dreadful for up to sixty seconds.  Be patient.
-
-  Cisco interoperability note from Walter Wong <wcw+@CMU.EDU>:
-
-  On a side note, adding HAS_NWAY seems to share a problem with the
-  Cisco 6509 switch.  Specifically, you need to change the spanning
-  tree parameter for the port the machine is plugged into to 'portfast'
-  mode.  Otherwise, the negotiation fails.  This has been an issue
-  we've noticed for a while but haven't had the time to track down.
-
-  Cisco switches    (Jeff Busch <jbusch@deja.com>)
-
-    My "standard config" for ports to which PC's/servers connect directly:
-
-        interface FastEthernet0/N
-        description machinename
-        load-interval 30
-        spanning-tree portfast
-
-    If autonegotiation is a problem, you may need to specify "speed
-    100" and "duplex full" as well (or "speed 10" and "duplex half").
-
-    WARNING: DO NOT hook up hubs/switches/bridges to these
-    specially-configured ports! The switch will become very confused.
-
-
-Reporting and diagnosing problems
----------------------------------
-
-Maintainers find that accurate and complete problem reports are
-invaluable in resolving driver problems.  We are frequently not able to
-reproduce problems and must rely on your patience and efforts to get to
-the bottom of the problem.
-
-If you believe you have a driver problem here are some of the
-steps you should take:
-
-- Is it really a driver problem?
-
-   Eliminate some variables: try different cards, different
-   computers, different cables, different ports on the switch/hub,
-   different versions of the kernel or of the driver, etc.
-
-- OK, it's a driver problem.
-
-   You need to generate a report.  Typically this is an email to the
-   maintainer and/or netdev@vger.kernel.org.  The maintainer's
-   email address will be in the driver source or in the MAINTAINERS file.
-
-- The contents of your report will vary a lot depending upon the
-  problem.  If it's a kernel crash then you should refer to the
-  admin-guide/reporting-bugs.rst file.
-
-  But for most problems it is useful to provide the following:
-
-   o Kernel version, driver version
-
-   o A copy of the banner message which the driver generates when
-     it is initialised.  For example:
-
-     eth0: 3Com PCI 3c905C Tornado at 0xa400,  00:50:da:6a:88:f0, IRQ 19
-     8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
-     MII transceiver found at address 24, status 782d.
-     Enabling bus-master transmits and whole-frame receives.
-
-     NOTE: You must provide the `debug=2' modprobe option to generate
-     a full detection message.  Please do this:
-
-	modprobe 3c59x debug=2
-
-   o If it is a PCI device, the relevant output from 'lspci -vx', eg:
-
-     00:09.0 Ethernet controller: 3Com Corporation 3c905C-TX [Fast Etherlink] (rev 74)
-             Subsystem: 3Com Corporation: Unknown device 9200
-             Flags: bus master, medium devsel, latency 32, IRQ 19
-             I/O ports at a400 [size=128]
-             Memory at db000000 (32-bit, non-prefetchable) [size=128]
-             Expansion ROM at <unassigned> [disabled] [size=128K]
-             Capabilities: [dc] Power Management version 2
-     00: b7 10 00 92 07 00 10 02 74 00 00 02 08 20 00 00
-     10: 01 a4 00 00 00 00 00 db 00 00 00 00 00 00 00 00
-     20: 00 00 00 00 00 00 00 00 00 00 00 00 b7 10 00 10
-     30: 00 00 00 00 dc 00 00 00 00 00 00 00 05 01 0a 0a
-
-   o A description of the environment: 10baseT? 100baseT?
-     full/half duplex? switched or hubbed?
-
-   o Any additional module parameters which you may be providing to the driver.
-
-   o Any kernel logs which are produced.  The more the merrier. 
-     If this is a large file and you are sending your report to a
-     mailing list, mention that you have the logfile, but don't send
-     it.  If you're reporting direct to the maintainer then just send
-     it.
-
-     To ensure that all kernel logs are available, add the
-     following line to /etc/syslog.conf:
-
-         kern.* /var/log/messages
-
-     Then restart syslogd with:
-
-         /etc/rc.d/init.d/syslog restart
-
-     (The above may vary, depending upon which Linux distribution you use).
-
-    o If your problem is reproducible then that's great.  Try the
-      following:
-
-      1) Increase the debug level.  Usually this is done via:
-
-         a) modprobe driver debug=7
-         b) In /etc/modprobe.d/driver.conf:
-            options driver debug=7
-
-      2) Recreate the problem with the higher debug level,
-         send all logs to the maintainer.
-
-      3) Download you card's diagnostic tool from Donald
-         Becker's website <http://www.scyld.com/ethercard_diag.html>.
-         Download mii-diag.c as well.  Build these.
-
-         a) Run 'vortex-diag -aaee' and 'mii-diag -v' when the card is
-            working correctly.  Save the output.
-
-         b) Run the above commands when the card is malfunctioning.  Send
-            both sets of output.
-
-Finally, please be patient and be prepared to do some work.  You may
-end up working on this problem for a week or more as the maintainer
-asks more questions, asks for more tests, asks for patches to be
-applied, etc.  At the end of it all, the problem may even remain
-unresolved.
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 402a9188f446..aaac502b81ea 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -28,6 +28,7 @@ Contents:
    pensando/ionic
    stmicro/stmmac
    3com/3c509
+   3com/vortex
 
 .. only::  subproject and html
 
diff --git a/MAINTAINERS b/MAINTAINERS
index bee65ebdc67e..eaea5f1994c9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -147,7 +147,7 @@ Maintainers List
 M:	Steffen Klassert <klassert@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Odd Fixes
-F:	Documentation/networking/device_drivers/3com/vortex.txt
+F:	Documentation/networking/device_drivers/3com/vortex.rst
 F:	drivers/net/ethernet/3com/3c59x.c
 
 3CR990 NETWORK DRIVER
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index a2b7f7ab8170..5984b7033999 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1149,7 +1149,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 
 	print_info = (vortex_debug > 1);
 	if (print_info)
-		pr_info("See Documentation/networking/device_drivers/3com/vortex.txt\n");
+		pr_info("See Documentation/networking/device_drivers/3com/vortex.rst\n");
 
 	pr_info("%s: 3Com %s %s at %p.\n",
 	       print_name,
@@ -1954,7 +1954,7 @@ vortex_error(struct net_device *dev, int status)
 				   dev->name, tx_status);
 			if (tx_status == 0x82) {
 				pr_err("Probably a duplex mismatch.  See "
-						"Documentation/networking/device_drivers/3com/vortex.txt\n");
+						"Documentation/networking/device_drivers/3com/vortex.rst\n");
 			}
 			dump_tx_ring(dev);
 		}
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 3a6fc99c6f32..7cc259893cb9 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -76,7 +76,7 @@ config VORTEX
 	  "Hurricane" (3c555/3cSOHO)                           PCI
 
 	  If you have such a card, say Y here.  More specific information is in
-	  <file:Documentation/networking/device_drivers/3com/vortex.txt> and
+	  <file:Documentation/networking/device_drivers/3com/vortex.rst> and
 	  in the comments at the beginning of
 	  <file:drivers/net/ethernet/3com/3c59x.c>.
 
-- 
cgit v1.2.3


From c839ce557b35de084d06f91c4e37948bdcef9709 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:38 +0200
Subject: docs: networking: device drivers: convert chelsio/cxgb.txt to ReST

- add SPDX header;
- use copyright symbol;
- adjust titles and chapters, adding proper markups;
- comment out text-only TOC from html/pdf output;
- mark code blocks and literals as such;
- add notes markups;
- mark tables as such;
- mark lists as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/chelsio/cxgb.rst     | 393 +++++++++++++++++++++
 .../networking/device_drivers/chelsio/cxgb.txt     | 352 ------------------
 Documentation/networking/device_drivers/index.rst  |   1 +
 drivers/net/ethernet/chelsio/Kconfig               |   2 +-
 4 files changed, 395 insertions(+), 353 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/chelsio/cxgb.rst
 delete mode 100644 Documentation/networking/device_drivers/chelsio/cxgb.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/chelsio/cxgb.rst b/Documentation/networking/device_drivers/chelsio/cxgb.rst
new file mode 100644
index 000000000000..435dce5fa2c7
--- /dev/null
+++ b/Documentation/networking/device_drivers/chelsio/cxgb.rst
@@ -0,0 +1,393 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=============================================
+Chelsio N210 10Gb Ethernet Network Controller
+=============================================
+
+Driver Release Notes for Linux
+
+Version 2.1.1
+
+June 20, 2005
+
+.. Contents
+
+ INTRODUCTION
+ FEATURES
+ PERFORMANCE
+ DRIVER MESSAGES
+ KNOWN ISSUES
+ SUPPORT
+
+
+Introduction
+============
+
+ This document describes the Linux driver for Chelsio 10Gb Ethernet Network
+ Controller. This driver supports the Chelsio N210 NIC and is backward
+ compatible with the Chelsio N110 model 10Gb NICs.
+
+
+Features
+========
+
+Adaptive Interrupts (adaptive-rx)
+---------------------------------
+
+  This feature provides an adaptive algorithm that adjusts the interrupt
+  coalescing parameters, allowing the driver to dynamically adapt the latency
+  settings to achieve the highest performance during various types of network
+  load.
+
+  The interface used to control this feature is ethtool. Please see the
+  ethtool manpage for additional usage information.
+
+  By default, adaptive-rx is disabled.
+  To enable adaptive-rx::
+
+      ethtool -C <interface> adaptive-rx on
+
+  To disable adaptive-rx, use ethtool::
+
+      ethtool -C <interface> adaptive-rx off
+
+  After disabling adaptive-rx, the timer latency value will be set to 50us.
+  You may set the timer latency after disabling adaptive-rx::
+
+      ethtool -C <interface> rx-usecs <microseconds>
+
+  An example to set the timer latency value to 100us on eth0::
+
+      ethtool -C eth0 rx-usecs 100
+
+  You may also provide a timer latency value while disabling adaptive-rx::
+
+      ethtool -C <interface> adaptive-rx off rx-usecs <microseconds>
+
+  If adaptive-rx is disabled and a timer latency value is specified, the timer
+  will be set to the specified value until changed by the user or until
+  adaptive-rx is enabled.
+
+  To view the status of the adaptive-rx and timer latency values::
+
+      ethtool -c <interface>
+
+
+TCP Segmentation Offloading (TSO) Support
+-----------------------------------------
+
+  This feature, also known as "large send", enables a system's protocol stack
+  to offload portions of outbound TCP processing to a network interface card
+  thereby reducing system CPU utilization and enhancing performance.
+
+  The interface used to control this feature is ethtool version 1.8 or higher.
+  Please see the ethtool manpage for additional usage information.
+
+  By default, TSO is enabled.
+  To disable TSO::
+
+      ethtool -K <interface> tso off
+
+  To enable TSO::
+
+      ethtool -K <interface> tso on
+
+  To view the status of TSO::
+
+      ethtool -k <interface>
+
+
+Performance
+===========
+
+ The following information is provided as an example of how to change system
+ parameters for "performance tuning" an what value to use. You may or may not
+ want to change these system parameters, depending on your server/workstation
+ application. Doing so is not warranted in any way by Chelsio Communications,
+ and is done at "YOUR OWN RISK". Chelsio will not be held responsible for loss
+ of data or damage to equipment.
+
+ Your distribution may have a different way of doing things, or you may prefer
+ a different method. These commands are shown only to provide an example of
+ what to do and are by no means definitive.
+
+ Making any of the following system changes will only last until you reboot
+ your system. You may want to write a script that runs at boot-up which
+ includes the optimal settings for your system.
+
+  Setting PCI Latency Timer::
+
+      setpci -d 1425::
+
+* 0x0c.l=0x0000F800
+
+  Disabling TCP timestamp::
+
+      sysctl -w net.ipv4.tcp_timestamps=0
+
+  Disabling SACK::
+
+      sysctl -w net.ipv4.tcp_sack=0
+
+  Setting large number of incoming connection requests::
+
+      sysctl -w net.ipv4.tcp_max_syn_backlog=3000
+
+  Setting maximum receive socket buffer size::
+
+      sysctl -w net.core.rmem_max=1024000
+
+  Setting maximum send socket buffer size::
+
+      sysctl -w net.core.wmem_max=1024000
+
+  Set smp_affinity (on a multiprocessor system) to a single CPU::
+
+      echo 1 > /proc/irq/<interrupt_number>/smp_affinity
+
+  Setting default receive socket buffer size::
+
+      sysctl -w net.core.rmem_default=524287
+
+  Setting default send socket buffer size::
+
+      sysctl -w net.core.wmem_default=524287
+
+  Setting maximum option memory buffers::
+
+      sysctl -w net.core.optmem_max=524287
+
+  Setting maximum backlog (# of unprocessed packets before kernel drops)::
+
+      sysctl -w net.core.netdev_max_backlog=300000
+
+  Setting TCP read buffers (min/default/max)::
+
+      sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
+
+  Setting TCP write buffers (min/pressure/max)::
+
+      sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
+
+  Setting TCP buffer space (min/pressure/max)::
+
+      sysctl -w net.ipv4.tcp_mem="10000000 10000000 10000000"
+
+  TCP window size for single connections:
+
+   The receive buffer (RX_WINDOW) size must be at least as large as the
+   Bandwidth-Delay Product of the communication link between the sender and
+   receiver. Due to the variations of RTT, you may want to increase the buffer
+   size up to 2 times the Bandwidth-Delay Product. Reference page 289 of
+   "TCP/IP Illustrated, Volume 1, The Protocols" by W. Richard Stevens.
+
+   At 10Gb speeds, use the following formula::
+
+       RX_WINDOW >= 1.25MBytes * RTT(in milliseconds)
+       Example for RTT with 100us: RX_WINDOW = (1,250,000 * 0.1) = 125,000
+
+   RX_WINDOW sizes of 256KB - 512KB should be sufficient.
+
+   Setting the min, max, and default receive buffer (RX_WINDOW) size::
+
+       sysctl -w net.ipv4.tcp_rmem="<min> <default> <max>"
+
+  TCP window size for multiple connections:
+   The receive buffer (RX_WINDOW) size may be calculated the same as single
+   connections, but should be divided by the number of connections. The
+   smaller window prevents congestion and facilitates better pacing,
+   especially if/when MAC level flow control does not work well or when it is
+   not supported on the machine. Experimentation may be necessary to attain
+   the correct value. This method is provided as a starting point for the
+   correct receive buffer size.
+
+   Setting the min, max, and default receive buffer (RX_WINDOW) size is
+   performed in the same manner as single connection.
+
+
+Driver Messages
+===============
+
+ The following messages are the most common messages logged by syslog. These
+ may be found in /var/log/messages.
+
+  Driver up::
+
+     Chelsio Network Driver - version 2.1.1
+
+  NIC detected::
+
+     eth#: Chelsio N210 1x10GBaseX NIC (rev #), PCIX 133MHz/64-bit
+
+  Link up::
+
+     eth#: link is up at 10 Gbps, full duplex
+
+  Link down::
+
+     eth#: link is down
+
+
+Known Issues
+============
+
+ These issues have been identified during testing. The following information
+ is provided as a workaround to the problem. In some cases, this problem is
+ inherent to Linux or to a particular Linux Distribution and/or hardware
+ platform.
+
+  1. Large number of TCP retransmits on a multiprocessor (SMP) system.
+
+      On a system with multiple CPUs, the interrupt (IRQ) for the network
+      controller may be bound to more than one CPU. This will cause TCP
+      retransmits if the packet data were to be split across different CPUs
+      and re-assembled in a different order than expected.
+
+      To eliminate the TCP retransmits, set smp_affinity on the particular
+      interrupt to a single CPU. You can locate the interrupt (IRQ) used on
+      the N110/N210 by using ifconfig::
+
+	  ifconfig <dev_name> | grep Interrupt
+
+      Set the smp_affinity to a single CPU::
+
+	  echo 1 > /proc/irq/<interrupt_number>/smp_affinity
+
+      It is highly suggested that you do not run the irqbalance daemon on your
+      system, as this will change any smp_affinity setting you have applied.
+      The irqbalance daemon runs on a 10 second interval and binds interrupts
+      to the least loaded CPU determined by the daemon. To disable this daemon::
+
+	  chkconfig --level 2345 irqbalance off
+
+      By default, some Linux distributions enable the kernel feature,
+      irqbalance, which performs the same function as the daemon. To disable
+      this feature, add the following line to your bootloader::
+
+	  noirqbalance
+
+	  Example using the Grub bootloader::
+
+	      title Red Hat Enterprise Linux AS (2.4.21-27.ELsmp)
+	      root (hd0,0)
+	      kernel /vmlinuz-2.4.21-27.ELsmp ro root=/dev/hda3 noirqbalance
+	      initrd /initrd-2.4.21-27.ELsmp.img
+
+  2. After running insmod, the driver is loaded and the incorrect network
+     interface is brought up without running ifup.
+
+      When using 2.4.x kernels, including RHEL kernels, the Linux kernel
+      invokes a script named "hotplug". This script is primarily used to
+      automatically bring up USB devices when they are plugged in, however,
+      the script also attempts to automatically bring up a network interface
+      after loading the kernel module. The hotplug script does this by scanning
+      the ifcfg-eth# config files in /etc/sysconfig/network-scripts, looking
+      for HWADDR=<mac_address>.
+
+      If the hotplug script does not find the HWADDRR within any of the
+      ifcfg-eth# files, it will bring up the device with the next available
+      interface name. If this interface is already configured for a different
+      network card, your new interface will have incorrect IP address and
+      network settings.
+
+      To solve this issue, you can add the HWADDR=<mac_address> key to the
+      interface config file of your network controller.
+
+      To disable this "hotplug" feature, you may add the driver (module name)
+      to the "blacklist" file located in /etc/hotplug. It has been noted that
+      this does not work for network devices because the net.agent script
+      does not use the blacklist file. Simply remove, or rename, the net.agent
+      script located in /etc/hotplug to disable this feature.
+
+  3. Transport Protocol (TP) hangs when running heavy multi-connection traffic
+     on an AMD Opteron system with HyperTransport PCI-X Tunnel chipset.
+
+      If your AMD Opteron system uses the AMD-8131 HyperTransport PCI-X Tunnel
+      chipset, you may experience the "133-Mhz Mode Split Completion Data
+      Corruption" bug identified by AMD while using a 133Mhz PCI-X card on the
+      bus PCI-X bus.
+
+      AMD states, "Under highly specific conditions, the AMD-8131 PCI-X Tunnel
+      can provide stale data via split completion cycles to a PCI-X card that
+      is operating at 133 Mhz", causing data corruption.
+
+      AMD's provides three workarounds for this problem, however, Chelsio
+      recommends the first option for best performance with this bug:
+
+	For 133Mhz secondary bus operation, limit the transaction length and
+	the number of outstanding transactions, via BIOS configuration
+	programming of the PCI-X card, to the following:
+
+	   Data Length (bytes): 1k
+
+	   Total allowed outstanding transactions: 2
+
+      Please refer to AMD 8131-HT/PCI-X Errata 26310 Rev 3.08 August 2004,
+      section 56, "133-MHz Mode Split Completion Data Corruption" for more
+      details with this bug and workarounds suggested by AMD.
+
+      It may be possible to work outside AMD's recommended PCI-X settings, try
+      increasing the Data Length to 2k bytes for increased performance. If you
+      have issues with these settings, please revert to the "safe" settings
+      and duplicate the problem before submitting a bug or asking for support.
+
+      .. note::
+
+	    The default setting on most systems is 8 outstanding transactions
+	    and 2k bytes data length.
+
+  4. On multiprocessor systems, it has been noted that an application which
+     is handling 10Gb networking can switch between CPUs causing degraded
+     and/or unstable performance.
+
+      If running on an SMP system and taking performance measurements, it
+      is suggested you either run the latest netperf-2.4.0+ or use a binding
+      tool such as Tim Hockin's procstate utilities (runon)
+      <http://www.hockin.org/~thockin/procstate/>.
+
+      Binding netserver and netperf (or other applications) to particular
+      CPUs will have a significant difference in performance measurements.
+      You may need to experiment which CPU to bind the application to in
+      order to achieve the best performance for your system.
+
+      If you are developing an application designed for 10Gb networking,
+      please keep in mind you may want to look at kernel functions
+      sched_setaffinity & sched_getaffinity to bind your application.
+
+      If you are just running user-space applications such as ftp, telnet,
+      etc., you may want to try the runon tool provided by Tim Hockin's
+      procstate utility. You could also try binding the interface to a
+      particular CPU: runon 0 ifup eth0
+
+
+Support
+=======
+
+ If you have problems with the software or hardware, please contact our
+ customer support team via email at support@chelsio.com or check our website
+ at http://www.chelsio.com
+
+-------------------------------------------------------------------------------
+
+::
+
+ Chelsio Communications
+ 370 San Aleso Ave.
+ Suite 100
+ Sunnyvale, CA 94085
+ http://www.chelsio.com
+
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License, version 2, as
+published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License along
+with this program; if not, write to the Free Software Foundation, Inc.,
+59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+THIS SOFTWARE IS PROVIDED ``AS IS`` AND WITHOUT ANY EXPRESS OR IMPLIED
+WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+Copyright |copy| 2003-2005 Chelsio Communications. All rights reserved.
diff --git a/Documentation/networking/device_drivers/chelsio/cxgb.txt b/Documentation/networking/device_drivers/chelsio/cxgb.txt
deleted file mode 100644
index 20a887615c4a..000000000000
--- a/Documentation/networking/device_drivers/chelsio/cxgb.txt
+++ /dev/null
@@ -1,352 +0,0 @@
-                 Chelsio N210 10Gb Ethernet Network Controller
-
-                         Driver Release Notes for Linux
-
-                                 Version 2.1.1
-
-                                 June 20, 2005
-
-CONTENTS
-========
- INTRODUCTION
- FEATURES
- PERFORMANCE
- DRIVER MESSAGES
- KNOWN ISSUES
- SUPPORT
-
-
-INTRODUCTION
-============
-
- This document describes the Linux driver for Chelsio 10Gb Ethernet Network
- Controller. This driver supports the Chelsio N210 NIC and is backward
- compatible with the Chelsio N110 model 10Gb NICs.
-
-
-FEATURES
-========
-
- Adaptive Interrupts (adaptive-rx)
- ---------------------------------
-
-  This feature provides an adaptive algorithm that adjusts the interrupt
-  coalescing parameters, allowing the driver to dynamically adapt the latency
-  settings to achieve the highest performance during various types of network
-  load.
-
-  The interface used to control this feature is ethtool. Please see the
-  ethtool manpage for additional usage information.
-
-  By default, adaptive-rx is disabled.
-  To enable adaptive-rx:
-
-      ethtool -C <interface> adaptive-rx on
-
-  To disable adaptive-rx, use ethtool:
-
-      ethtool -C <interface> adaptive-rx off
-
-  After disabling adaptive-rx, the timer latency value will be set to 50us.
-  You may set the timer latency after disabling adaptive-rx:
-
-      ethtool -C <interface> rx-usecs <microseconds>
-
-  An example to set the timer latency value to 100us on eth0:
-
-      ethtool -C eth0 rx-usecs 100
-
-  You may also provide a timer latency value while disabling adaptive-rx:
-
-      ethtool -C <interface> adaptive-rx off rx-usecs <microseconds>
-
-  If adaptive-rx is disabled and a timer latency value is specified, the timer
-  will be set to the specified value until changed by the user or until
-  adaptive-rx is enabled.
-
-  To view the status of the adaptive-rx and timer latency values:
-
-      ethtool -c <interface>
-
-
- TCP Segmentation Offloading (TSO) Support
- -----------------------------------------
-
-  This feature, also known as "large send", enables a system's protocol stack
-  to offload portions of outbound TCP processing to a network interface card
-  thereby reducing system CPU utilization and enhancing performance.
-
-  The interface used to control this feature is ethtool version 1.8 or higher.
-  Please see the ethtool manpage for additional usage information.
-
-  By default, TSO is enabled.
-  To disable TSO:
-
-      ethtool -K <interface> tso off
-
-  To enable TSO:
-
-      ethtool -K <interface> tso on
-
-  To view the status of TSO:
-
-      ethtool -k <interface>
-
-
-PERFORMANCE
-===========
-
- The following information is provided as an example of how to change system
- parameters for "performance tuning" an what value to use. You may or may not
- want to change these system parameters, depending on your server/workstation
- application. Doing so is not warranted in any way by Chelsio Communications,
- and is done at "YOUR OWN RISK". Chelsio will not be held responsible for loss
- of data or damage to equipment.
-
- Your distribution may have a different way of doing things, or you may prefer
- a different method. These commands are shown only to provide an example of
- what to do and are by no means definitive.
-
- Making any of the following system changes will only last until you reboot
- your system. You may want to write a script that runs at boot-up which
- includes the optimal settings for your system.
-
-  Setting PCI Latency Timer:
-      setpci -d 1425:* 0x0c.l=0x0000F800
-
-  Disabling TCP timestamp:
-      sysctl -w net.ipv4.tcp_timestamps=0
-
-  Disabling SACK:
-      sysctl -w net.ipv4.tcp_sack=0
-
-  Setting large number of incoming connection requests:
-      sysctl -w net.ipv4.tcp_max_syn_backlog=3000
-
-  Setting maximum receive socket buffer size:
-      sysctl -w net.core.rmem_max=1024000
-
-  Setting maximum send socket buffer size:
-      sysctl -w net.core.wmem_max=1024000
-
-  Set smp_affinity (on a multiprocessor system) to a single CPU:
-      echo 1 > /proc/irq/<interrupt_number>/smp_affinity
-
-  Setting default receive socket buffer size:
-      sysctl -w net.core.rmem_default=524287
-
-  Setting default send socket buffer size:
-      sysctl -w net.core.wmem_default=524287
-
-  Setting maximum option memory buffers:
-      sysctl -w net.core.optmem_max=524287
-
-  Setting maximum backlog (# of unprocessed packets before kernel drops):
-      sysctl -w net.core.netdev_max_backlog=300000
-
-  Setting TCP read buffers (min/default/max):
-      sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
-
-  Setting TCP write buffers (min/pressure/max):
-      sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
-
-  Setting TCP buffer space (min/pressure/max):
-      sysctl -w net.ipv4.tcp_mem="10000000 10000000 10000000"
-
-  TCP window size for single connections:
-   The receive buffer (RX_WINDOW) size must be at least as large as the
-   Bandwidth-Delay Product of the communication link between the sender and
-   receiver. Due to the variations of RTT, you may want to increase the buffer
-   size up to 2 times the Bandwidth-Delay Product. Reference page 289 of
-   "TCP/IP Illustrated, Volume 1, The Protocols" by W. Richard Stevens.
-   At 10Gb speeds, use the following formula:
-       RX_WINDOW >= 1.25MBytes * RTT(in milliseconds)
-       Example for RTT with 100us: RX_WINDOW = (1,250,000 * 0.1) = 125,000
-   RX_WINDOW sizes of 256KB - 512KB should be sufficient.
-   Setting the min, max, and default receive buffer (RX_WINDOW) size:
-       sysctl -w net.ipv4.tcp_rmem="<min> <default> <max>"
-
-  TCP window size for multiple connections:
-   The receive buffer (RX_WINDOW) size may be calculated the same as single
-   connections, but should be divided by the number of connections. The
-   smaller window prevents congestion and facilitates better pacing,
-   especially if/when MAC level flow control does not work well or when it is
-   not supported on the machine. Experimentation may be necessary to attain
-   the correct value. This method is provided as a starting point for the
-   correct receive buffer size.
-   Setting the min, max, and default receive buffer (RX_WINDOW) size is
-   performed in the same manner as single connection.
-
-
-DRIVER MESSAGES
-===============
-
- The following messages are the most common messages logged by syslog. These
- may be found in /var/log/messages.
-
-  Driver up:
-     Chelsio Network Driver - version 2.1.1
-
-  NIC detected:
-     eth#: Chelsio N210 1x10GBaseX NIC (rev #), PCIX 133MHz/64-bit
-
-  Link up:
-     eth#: link is up at 10 Gbps, full duplex
-
-  Link down:
-     eth#: link is down
-
-
-KNOWN ISSUES
-============
-
- These issues have been identified during testing. The following information
- is provided as a workaround to the problem. In some cases, this problem is
- inherent to Linux or to a particular Linux Distribution and/or hardware
- platform.
-
-  1. Large number of TCP retransmits on a multiprocessor (SMP) system.
-
-      On a system with multiple CPUs, the interrupt (IRQ) for the network
-      controller may be bound to more than one CPU. This will cause TCP
-      retransmits if the packet data were to be split across different CPUs
-      and re-assembled in a different order than expected.
-
-      To eliminate the TCP retransmits, set smp_affinity on the particular
-      interrupt to a single CPU. You can locate the interrupt (IRQ) used on
-      the N110/N210 by using ifconfig:
-          ifconfig <dev_name> | grep Interrupt
-      Set the smp_affinity to a single CPU:
-          echo 1 > /proc/irq/<interrupt_number>/smp_affinity
-
-      It is highly suggested that you do not run the irqbalance daemon on your
-      system, as this will change any smp_affinity setting you have applied.
-      The irqbalance daemon runs on a 10 second interval and binds interrupts
-      to the least loaded CPU determined by the daemon. To disable this daemon:
-          chkconfig --level 2345 irqbalance off
-
-      By default, some Linux distributions enable the kernel feature,
-      irqbalance, which performs the same function as the daemon. To disable
-      this feature, add the following line to your bootloader:
-          noirqbalance
-
-          Example using the Grub bootloader:
-              title Red Hat Enterprise Linux AS (2.4.21-27.ELsmp)
-              root (hd0,0)
-              kernel /vmlinuz-2.4.21-27.ELsmp ro root=/dev/hda3 noirqbalance
-              initrd /initrd-2.4.21-27.ELsmp.img
-
-  2. After running insmod, the driver is loaded and the incorrect network
-     interface is brought up without running ifup.
-
-      When using 2.4.x kernels, including RHEL kernels, the Linux kernel
-      invokes a script named "hotplug". This script is primarily used to
-      automatically bring up USB devices when they are plugged in, however,
-      the script also attempts to automatically bring up a network interface
-      after loading the kernel module. The hotplug script does this by scanning
-      the ifcfg-eth# config files in /etc/sysconfig/network-scripts, looking
-      for HWADDR=<mac_address>.
-
-      If the hotplug script does not find the HWADDRR within any of the
-      ifcfg-eth# files, it will bring up the device with the next available
-      interface name. If this interface is already configured for a different
-      network card, your new interface will have incorrect IP address and
-      network settings.
-
-      To solve this issue, you can add the HWADDR=<mac_address> key to the
-      interface config file of your network controller.
-
-      To disable this "hotplug" feature, you may add the driver (module name)
-      to the "blacklist" file located in /etc/hotplug. It has been noted that
-      this does not work for network devices because the net.agent script
-      does not use the blacklist file. Simply remove, or rename, the net.agent
-      script located in /etc/hotplug to disable this feature.
-
-  3. Transport Protocol (TP) hangs when running heavy multi-connection traffic
-     on an AMD Opteron system with HyperTransport PCI-X Tunnel chipset.
-
-      If your AMD Opteron system uses the AMD-8131 HyperTransport PCI-X Tunnel
-      chipset, you may experience the "133-Mhz Mode Split Completion Data
-      Corruption" bug identified by AMD while using a 133Mhz PCI-X card on the
-      bus PCI-X bus.
-
-      AMD states, "Under highly specific conditions, the AMD-8131 PCI-X Tunnel
-      can provide stale data via split completion cycles to a PCI-X card that
-      is operating at 133 Mhz", causing data corruption.
-
-      AMD's provides three workarounds for this problem, however, Chelsio
-      recommends the first option for best performance with this bug:
-
-        For 133Mhz secondary bus operation, limit the transaction length and
-        the number of outstanding transactions, via BIOS configuration
-        programming of the PCI-X card, to the following:
-
-           Data Length (bytes): 1k
-           Total allowed outstanding transactions: 2
-
-      Please refer to AMD 8131-HT/PCI-X Errata 26310 Rev 3.08 August 2004,
-      section 56, "133-MHz Mode Split Completion Data Corruption" for more
-      details with this bug and workarounds suggested by AMD.
-
-      It may be possible to work outside AMD's recommended PCI-X settings, try
-      increasing the Data Length to 2k bytes for increased performance. If you
-      have issues with these settings, please revert to the "safe" settings
-      and duplicate the problem before submitting a bug or asking for support.
-
-      NOTE: The default setting on most systems is 8 outstanding transactions
-            and 2k bytes data length.
-
-  4. On multiprocessor systems, it has been noted that an application which
-     is handling 10Gb networking can switch between CPUs causing degraded
-     and/or unstable performance.
-
-      If running on an SMP system and taking performance measurements, it
-      is suggested you either run the latest netperf-2.4.0+ or use a binding
-      tool such as Tim Hockin's procstate utilities (runon)
-      <http://www.hockin.org/~thockin/procstate/>.
-
-      Binding netserver and netperf (or other applications) to particular
-      CPUs will have a significant difference in performance measurements.
-      You may need to experiment which CPU to bind the application to in
-      order to achieve the best performance for your system.
-
-      If you are developing an application designed for 10Gb networking,
-      please keep in mind you may want to look at kernel functions
-      sched_setaffinity & sched_getaffinity to bind your application.
-
-      If you are just running user-space applications such as ftp, telnet,
-      etc., you may want to try the runon tool provided by Tim Hockin's
-      procstate utility. You could also try binding the interface to a
-      particular CPU: runon 0 ifup eth0
-
-
-SUPPORT
-=======
-
- If you have problems with the software or hardware, please contact our
- customer support team via email at support@chelsio.com or check our website
- at http://www.chelsio.com
-
-===============================================================================
-
- Chelsio Communications
- 370 San Aleso Ave.
- Suite 100
- Sunnyvale, CA 94085
- http://www.chelsio.com
-
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License, version 2, as
-published by the Free Software Foundation.
-
-You should have received a copy of the GNU General Public License along
-with this program; if not, write to the Free Software Foundation, Inc.,
-59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
-
-THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR IMPLIED
-WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
-MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
-
- Copyright (c) 2003-2005 Chelsio Communications. All rights reserved.
-
-===============================================================================
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 7dde314fc957..23c4ec9c9125 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -31,6 +31,7 @@ Contents:
    3com/vortex
    amazon/ena
    aquantia/atlantic
+   chelsio/cxgb
 
 .. only::  subproject and html
 
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index 9909bfda167e..82cdfa51ce37 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -26,7 +26,7 @@ config CHELSIO_T1
 	  This driver supports Chelsio gigabit and 10-gigabit
 	  Ethernet cards. More information about adapter features and
 	  performance tuning is in
-	  <file:Documentation/networking/device_drivers/chelsio/cxgb.txt>.
+	  <file:Documentation/networking/device_drivers/chelsio/cxgb.rst>.
 
 	  For general information about Chelsio and our products, visit
 	  our website at <http://www.chelsio.com>.
-- 
cgit v1.2.3


From 714a4da450c03bdc53a0d5fa6a4b3192b30c5cda Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:39 +0200
Subject: docs: networking: device drivers: convert cirrus/cs89x0.txt to ReST

- add SPDX header;
- adjust title markup;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/cirrus/cs89x0.rst    | 647 +++++++++++++++++++++
 .../networking/device_drivers/cirrus/cs89x0.txt    | 624 --------------------
 Documentation/networking/device_drivers/index.rst  |   1 +
 drivers/net/ethernet/cirrus/Kconfig                |   2 +-
 4 files changed, 649 insertions(+), 625 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/cirrus/cs89x0.rst
 delete mode 100644 Documentation/networking/device_drivers/cirrus/cs89x0.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/cirrus/cs89x0.rst b/Documentation/networking/device_drivers/cirrus/cs89x0.rst
new file mode 100644
index 000000000000..e5c283940ac5
--- /dev/null
+++ b/Documentation/networking/device_drivers/cirrus/cs89x0.rst
@@ -0,0 +1,647 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================================
+Cirrus Logic LAN CS8900/CS8920 Ethernet Adapters
+================================================
+
+.. note::
+
+   This document was contributed by Cirrus Logic for kernel 2.2.5.  This version
+   has been updated for 2.3.48 by Andrew Morton.
+
+   Still, this is too outdated! A major cleanup is needed here.
+
+Cirrus make a copy of this driver available at their website, as
+described below.  In general, you should use the driver version which
+comes with your Linux distribution.
+
+
+Linux Network Interface Driver ver. 2.00 <kernel 2.3.48>
+
+
+.. TABLE OF CONTENTS
+
+   1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
+	1.1 Product Overview
+	1.2 Driver Description
+	    1.2.1 Driver Name
+	    1.2.2 File in the Driver Package
+	1.3 System Requirements
+	1.4 Licensing Information
+
+   2.0 ADAPTER INSTALLATION and CONFIGURATION
+	2.1 CS8900-based Adapter Configuration
+	2.2 CS8920-based Adapter Configuration
+
+   3.0 LOADING THE DRIVER AS A MODULE
+
+   4.0 COMPILING THE DRIVER
+	4.1 Compiling the Driver as a Loadable Module
+	4.2 Compiling the driver to support memory mode
+	4.3 Compiling the driver to support Rx DMA
+
+   5.0 TESTING AND TROUBLESHOOTING
+	5.1 Known Defects and Limitations
+	5.2 Testing the Adapter
+	    5.2.1 Diagnostic Self-Test
+	    5.2.2 Diagnostic Network Test
+	5.3 Using the Adapter's LEDs
+	5.4 Resolving I/O Conflicts
+
+   6.0 TECHNICAL SUPPORT
+	6.1 Contacting Cirrus Logic's Technical Support
+	6.2 Information Required Before Contacting Technical Support
+	6.3 Obtaining the Latest Driver Version
+	6.4 Current maintainer
+	6.5 Kernel boot parameters
+
+
+1. Cirrus Logic LAN CS8900/CS8920 Ethernet Adapters
+===================================================
+
+
+1.1. Product Overview
+=====================
+
+The CS8900-based ISA Ethernet Adapters from Cirrus Logic follow
+IEEE 802.3 standards and support half or full-duplex operation in ISA bus
+computers on 10 Mbps Ethernet networks.  The adapters are designed for operation
+in 16-bit ISA or EISA bus expansion slots and are available in
+10BaseT-only or 3-media configurations (10BaseT, 10Base2, and AUI for 10Base-5
+or fiber networks).
+
+CS8920-based adapters are similar to the CS8900-based adapter with additional
+features for Plug and Play (PnP) support and Wakeup Frame recognition.  As
+such, the configuration procedures differ somewhat between the two types of
+adapters.  Refer to the "Adapter Configuration" section for details on
+configuring both types of adapters.
+
+
+1.2. Driver Description
+=======================
+
+The CS8900/CS8920 Ethernet Adapter driver for Linux supports the Linux
+v2.3.48 or greater kernel.  It can be compiled directly into the kernel
+or loaded at run-time as a device driver module.
+
+1.2.1 Driver Name: cs89x0
+
+1.2.2 Files in the Driver Archive:
+
+The files in the driver at Cirrus' website include:
+
+  ===================  ====================================================
+  readme.txt           this file
+  build                batch file to compile cs89x0.c.
+  cs89x0.c             driver C code
+  cs89x0.h             driver header file
+  cs89x0.o             pre-compiled module (for v2.2.5 kernel)
+  config/Config.in     sample file to include cs89x0 driver in the kernel.
+  config/Makefile      sample file to include cs89x0 driver in the kernel.
+  config/Space.c       sample file to include cs89x0 driver in the kernel.
+  ===================  ====================================================
+
+
+
+1.3. System Requirements
+------------------------
+
+The following hardware is required:
+
+   * Cirrus Logic LAN (CS8900/20-based) Ethernet ISA Adapter
+
+   * IBM or IBM-compatible PC with:
+     * An 80386 or higher processor
+     * 16 bytes of contiguous IO space available between 210h - 370h
+     * One available IRQ (5,10,11,or 12 for the CS8900, 3-7,9-15 for CS8920).
+
+   * Appropriate cable (and connector for AUI, 10BASE-2) for your network
+     topology.
+
+The following software is required:
+
+* LINUX kernel version 2.3.48 or higher
+
+   * CS8900/20 Setup Utility (DOS-based)
+
+   * LINUX kernel sources for your kernel (if compiling into kernel)
+
+   * GNU Toolkit (gcc and make) v2.6 or above (if compiling into kernel
+     or a module)
+
+
+
+1.4. Licensing Information
+--------------------------
+
+This program is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free Software
+Foundation, version 1.
+
+This program is distributed in the hope that it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+more details.
+
+For a full copy of the GNU General Public License, write to the Free Software
+Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+
+2. Adapter Installation and Configuration
+=========================================
+
+Both the CS8900 and CS8920-based adapters can be configured using parameters
+stored in an on-board EEPROM. You must use the DOS-based CS8900/20 Setup
+Utility if you want to change the adapter's configuration in EEPROM.
+
+When loading the driver as a module, you can specify many of the adapter's
+configuration parameters on the command-line to override the EEPROM's settings
+or for interface configuration when an EEPROM is not used. (CS8920-based
+adapters must use an EEPROM.) See Section 3.0 LOADING THE DRIVER AS A MODULE.
+
+Since the CS8900/20 Setup Utility is a DOS-based application, you must install
+and configure the adapter in a DOS-based system using the CS8900/20 Setup
+Utility before installation in the target LINUX system.  (Not required if
+installing a CS8900-based adapter and the default configuration is acceptable.)
+
+
+2.1. CS8900-based Adapter Configuration
+---------------------------------------
+
+CS8900-based adapters shipped from Cirrus Logic have been configured
+with the following "default" settings::
+
+  Operation Mode:      Memory Mode
+  IRQ:                 10
+  Base I/O Address:    300
+  Memory Base Address: D0000
+  Optimization:	       DOS Client
+  Transmission Mode:   Half-duplex
+  BootProm:            None
+  Media Type:	       Autodetect (3-media cards) or
+		       10BASE-T (10BASE-T only adapter)
+
+You should only change the default configuration settings if conflicts with
+another adapter exists. To change the adapter's configuration, run the
+CS8900/20 Setup Utility.
+
+
+2.2. CS8920-based Adapter Configuration
+---------------------------------------
+
+CS8920-based adapters are shipped from Cirrus Logic configured as Plug
+and Play (PnP) enabled.  However, since the cs89x0 driver does NOT
+support PnP, you must install the CS8920 adapter in a DOS-based PC and
+run the CS8900/20 Setup Utility to disable PnP and configure the
+adapter before installation in the target Linux system.  Failure to do
+this will leave the adapter inactive and the driver will be unable to
+communicate with the adapter.
+
+::
+
+	****************************************************************
+	*                    CS8920-BASED ADAPTERS:                    *
+	*                                                              *
+	* CS8920-BASED ADAPTERS ARE PLUG and PLAY ENABLED BY DEFAULT.  *
+	* THE CS89X0 DRIVER DOES NOT SUPPORT PnP. THEREFORE, YOU MUST  *
+	* RUN THE CS8900/20 SETUP UTILITY TO DISABLE PnP SUPPORT AND   *
+	* TO ACTIVATE THE ADAPTER.                                     *
+	****************************************************************
+
+
+
+
+3. Loading the Driver as a Module
+=================================
+
+If the driver is compiled as a loadable module, you can load the driver module
+with the 'modprobe' command.  Many of the adapter's configuration parameters can
+be specified as command-line arguments to the load command.  This facility
+provides a means to override the EEPROM's settings or for interface
+configuration when an EEPROM is not used.
+
+Example::
+
+    insmod cs89x0.o io=0x200 irq=0xA media=aui
+
+This example loads the module and configures the adapter to use an IO port base
+address of 200h, interrupt 10, and use the AUI media connection.  The following
+configuration options are available on the command line::
+
+  io=###               - specify IO address (200h-360h)
+  irq=##               - specify interrupt level
+  use_dma=1            - Enable DMA
+  dma=#                - specify dma channel (Driver is compiled to support
+			 Rx DMA only)
+  dmasize=# (16 or 64) - DMA size 16K or 64K.  Default value is set to 16.
+  media=rj45           - specify media type
+   or media=bnc
+   or media=aui
+   or media=auto
+  duplex=full          - specify forced half/full/autonegotiate duplex
+   or duplex=half
+   or duplex=auto
+  debug=#              - debug level (only available if the driver was compiled
+			 for debugging)
+
+**Notes:**
+
+a) If an EEPROM is present, any specified command-line parameter
+   will override the corresponding configuration value stored in
+   EEPROM.
+
+b) The "io" parameter must be specified on the command-line.
+
+c) The driver's hardware probe routine is designed to avoid
+   writing to I/O space until it knows that there is a cs89x0
+   card at the written addresses.  This could cause problems
+   with device probing.  To avoid this behaviour, add one
+   to the ``io=`` module parameter.  This doesn't actually change
+   the I/O address, but it is a flag to tell the driver
+   to partially initialise the hardware before trying to
+   identify the card.  This could be dangerous if you are
+   not sure that there is a cs89x0 card at the provided address.
+
+   For example, to scan for an adapter located at IO base 0x300,
+   specify an IO address of 0x301.
+
+d) The "duplex=auto" parameter is only supported for the CS8920.
+
+e) The minimum command-line configuration required if an EEPROM is
+   not present is:
+
+   io
+   irq
+   media type (no autodetect)
+
+f) The following additional parameters are CS89XX defaults (values
+   used with no EEPROM or command-line argument).
+
+   * DMA Burst = enabled
+   * IOCHRDY Enabled = enabled
+   * UseSA = enabled
+   * CS8900 defaults to half-duplex if not specified on command-line
+   * CS8920 defaults to autoneg if not specified on command-line
+   * Use reset defaults for other config parameters
+   * dma_mode = 0
+
+g) You can use ifconfig to set the adapter's Ethernet address.
+
+h) Many Linux distributions use the 'modprobe' command to load
+   modules.  This program uses the '/etc/conf.modules' file to
+   determine configuration information which is passed to a driver
+   module when it is loaded.  All the configuration options which are
+   described above may be placed within /etc/conf.modules.
+
+   For example::
+
+     > cat /etc/conf.modules
+     ...
+     alias eth0 cs89x0
+     options cs89x0 io=0x0200 dma=5 use_dma=1
+     ...
+
+   In this example we are telling the module system that the
+   ethernet driver for this machine should use the cs89x0 driver.  We
+   are asking 'modprobe' to pass the 'io', 'dma' and 'use_dma'
+   arguments to the driver when it is loaded.
+
+i) Cirrus recommend that the cs89x0 use the ISA DMA channels 5, 6 or
+   7.  You will probably find that other DMA channels will not work.
+
+j) The cs89x0 supports DMA for receiving only.  DMA mode is
+   significantly more efficient.  Flooding a 400 MHz Celeron machine
+   with large ping packets consumes 82% of its CPU capacity in non-DMA
+   mode.  With DMA this is reduced to 45%.
+
+k) If your Linux kernel was compiled with inbuilt plug-and-play
+   support you will be able to find information about the cs89x0 card
+   with the command::
+
+     cat /proc/isapnp
+
+l) If during DMA operation you find erratic behavior or network data
+   corruption you should use your PC's BIOS to slow the EISA bus clock.
+
+m) If the cs89x0 driver is compiled directly into the kernel
+   (non-modular) then its I/O address is automatically determined by
+   ISA bus probing.  The IRQ number, media options, etc are determined
+   from the card's EEPROM.
+
+n) If the cs89x0 driver is compiled directly into the kernel, DMA
+   mode may be selected by providing the kernel with a boot option
+   'cs89x0_dma=N' where 'N' is the desired DMA channel number (5, 6 or 7).
+
+   Kernel boot options may be provided on the LILO command line::
+
+	LILO boot: linux cs89x0_dma=5
+
+   or they may be placed in /etc/lilo.conf::
+
+	image=/boot/bzImage-2.3.48
+	  append="cs89x0_dma=5"
+	  label=linux
+	  root=/dev/hda5
+	  read-only
+
+   The DMA Rx buffer size is hardwired to 16 kbytes in this mode.
+   (64k mode is not available).
+
+
+4. Compiling the Driver
+=======================
+
+The cs89x0 driver can be compiled directly into the kernel or compiled into
+a loadable device driver module.
+
+Just use the standard way to configure the driver and compile the Kernel.
+
+
+4.1. Compiling the Driver to Support Rx DMA
+-------------------------------------------
+
+The compile-time optionality for DMA was removed in the 2.3 kernel
+series.  DMA support is now unconditionally part of the driver.  It is
+enabled by the 'use_dma=1' module option.
+
+
+5. Testing and Troubleshooting
+==============================
+
+5.1. Known Defects and Limitations
+----------------------------------
+
+Refer to the RELEASE.TXT file distributed as part of this archive for a list of
+known defects, driver limitations, and work arounds.
+
+
+5.2. Testing the Adapter
+------------------------
+
+Once the adapter has been installed and configured, the diagnostic option of
+the CS8900/20 Setup Utility can be used to test the functionality of the
+adapter and its network connection.  Use the diagnostics 'Self Test' option to
+test the functionality of the adapter with the hardware configuration you have
+assigned. You can use the diagnostics 'Network Test' to test the ability of the
+adapter to communicate across the Ethernet with another PC equipped with a
+CS8900/20-based adapter card (it must also be running the CS8900/20 Setup
+Utility).
+
+.. note::
+
+	 The Setup Utility's diagnostics are designed to run in a
+	 DOS-only operating system environment.  DO NOT run the diagnostics
+	 from a DOS or command prompt session under Windows 95, Windows NT,
+	 OS/2, or other operating system.
+
+To run the diagnostics tests on the CS8900/20 adapter:
+
+   1.  Boot DOS on the PC and start the CS8900/20 Setup Utility.
+
+   2.  The adapter's current configuration is displayed.  Hit the ENTER key to
+       get to the main menu.
+
+   4.  Select 'Diagnostics' (ALT-G) from the main menu.
+       * Select 'Self-Test' to test the adapter's basic functionality.
+       * Select 'Network Test' to test the network connection and cabling.
+
+
+5.2.1. Diagnostic Self-test
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The diagnostic self-test checks the adapter's basic functionality as well as
+its ability to communicate across the ISA bus based on the system resources
+assigned during hardware configuration.  The following tests are performed:
+
+   * IO Register Read/Write Test
+
+     The IO Register Read/Write test insures that the CS8900/20 can be
+     accessed in IO mode, and that the IO base address is correct.
+
+   * Shared Memory Test
+
+     The Shared Memory test insures the CS8900/20 can be accessed in memory
+     mode and that the range of memory addresses assigned does not conflict
+     with other devices in the system.
+
+   * Interrupt Test
+
+     The Interrupt test insures there are no conflicts with the assigned IRQ
+     signal.
+
+   * EEPROM Test
+
+     The EEPROM test insures the EEPROM can be read.
+
+   * Chip RAM Test
+
+     The Chip RAM test insures the 4K of memory internal to the CS8900/20 is
+     working properly.
+
+   * Internal Loop-back Test
+
+     The Internal Loop Back test insures the adapter's transmitter and
+     receiver are operating properly.  If this test fails, make sure the
+     adapter's cable is connected to the network (check for LED activity for
+     example).
+
+   * Boot PROM Test
+
+     The Boot PROM  test insures the Boot PROM is present, and can be read.
+     Failure indicates the Boot PROM  was not successfully read due to a
+     hardware problem or due to a conflicts on the Boot PROM address
+     assignment. (Test only applies if the adapter is configured to use the
+     Boot PROM option.)
+
+Failure of a test item indicates a possible system resource conflict with
+another device on the ISA bus.  In this case, you should use the Manual Setup
+option to reconfigure the adapter by selecting a different value for the system
+resource that failed.
+
+
+5.2.2. Diagnostic Network Test
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The Diagnostic Network Test verifies a working network connection by
+transferring data between two CS8900/20 adapters installed in different PCs
+on the same network. (Note: the diagnostic network test should not be run
+between two nodes across a router.)
+
+This test requires that each of the two PCs have a CS8900/20-based adapter
+installed and have the CS8900/20 Setup Utility running.  The first PC is
+configured as a Responder and the other PC is configured as an Initiator.
+Once the Initiator is started, it sends data frames to the Responder which
+returns the frames to the Initiator.
+
+The total number of frames received and transmitted are displayed on the
+Initiator's display, along with a count of the number of frames received and
+transmitted OK or in error.  The test can be terminated anytime by the user at
+either PC.
+
+To setup the Diagnostic Network Test:
+
+    1.  Select a PC with a CS8900/20-based adapter and a known working network
+	connection to act as the Responder.  Run the CS8900/20 Setup Utility
+	and select 'Diagnostics -> Network Test -> Responder' from the main
+	menu.  Hit ENTER to start the Responder.
+
+    2.  Return to the PC with the CS8900/20-based adapter you want to test and
+	start the CS8900/20 Setup Utility.
+
+    3.  From the main menu, Select 'Diagnostic -> Network Test -> Initiator'.
+	Hit ENTER to start the test.
+
+You may stop the test on the Initiator at any time while allowing the Responder
+to continue running.  In this manner, you can move to additional PCs and test
+them by starting the Initiator on another PC without having to stop/start the
+Responder.
+
+
+
+5.3. Using the Adapter's LEDs
+-----------------------------
+
+The 2 and 3-media adapters have two LEDs visible on the back end of the board
+located near the 10Base-T connector.
+
+Link Integrity LED: A "steady" ON of the green LED indicates a valid 10Base-T
+connection.  (Only applies to 10Base-T.  The green LED has no significance for
+a 10Base-2 or AUI connection.)
+
+TX/RX LED: The yellow LED lights briefly each time the adapter transmits or
+receives data. (The yellow LED will appear to "flicker" on a typical network.)
+
+
+5.4. Resolving I/O Conflicts
+----------------------------
+
+An IO conflict occurs when two or more adapter use the same ISA resource (IO
+address, memory address or IRQ).  You can usually detect an IO conflict in one
+of four ways after installing and or configuring the CS8900/20-based adapter:
+
+    1.  The system does not boot properly (or at all).
+
+    2.  The driver cannot communicate with the adapter, reporting an "Adapter
+	not found" error message.
+
+    3.  You cannot connect to the network or the driver will not load.
+
+    4.  If you have configured the adapter to run in memory mode but the driver
+	reports it is using IO mode when loading, this is an indication of a
+	memory address conflict.
+
+If an IO conflict occurs, run the CS8900/20 Setup Utility and perform a
+diagnostic self-test.  Normally, the ISA resource in conflict will fail the
+self-test.  If so, reconfigure the adapter selecting another choice for the
+resource in conflict.  Run the diagnostics again to check for further IO
+conflicts.
+
+In some cases, such as when the PC will not boot, it may be necessary to remove
+the adapter and reconfigure it by installing it in another PC to run the
+CS8900/20 Setup Utility.  Once reinstalled in the target system, run the
+diagnostics self-test to ensure the new configuration is free of conflicts
+before loading the driver again.
+
+When manually configuring the adapter, keep in mind the typical ISA system
+resource usage as indicated in the tables below.
+
+::
+
+  I/O Address    	Device                        IRQ      Device
+  -----------    	--------                      ---      --------
+     200-20F       	Game I/O adapter               3       COM2, Bus Mouse
+     230-23F       	Bus Mouse                      4       COM1
+     270-27F       	LPT3: third parallel port      5       LPT2
+     2F0-2FF       	COM2: second serial port       6       Floppy Disk controller
+     320-32F       	Fixed disk controller          7       LPT1
+							 8       Real-time Clock
+						     9       EGA/VGA display adapter
+						    12       Mouse (PS/2)
+  Memory Address  Device                          13       Math Coprocessor
+  --------------  ---------------------           14       Hard Disk controller
+  A000-BFFF	EGA Graphics Adapter
+  A000-C7FF	VGA Graphics Adapter
+  B000-BFFF	Mono Graphics Adapter
+  B800-BFFF	Color Graphics Adapter
+  E000-FFFF	AT BIOS
+
+
+
+
+6. Technical Support
+====================
+
+6.1. Contacting Cirrus Logic's Technical Support
+------------------------------------------------
+
+Cirrus Logic's CS89XX Technical Application Support can be reached at::
+
+  Telephone  :(800) 888-5016 (from inside U.S. and Canada)
+	     :(512) 442-7555 (from outside the U.S. and Canada)
+  Fax        :(512) 912-3871
+  Email      :ethernet@crystal.cirrus.com
+  WWW        :http://www.cirrus.com
+
+
+6.2. Information Required before Contacting Technical Support
+-------------------------------------------------------------
+
+Before contacting Cirrus Logic for technical support, be prepared to provide as
+Much of the following information as possible.
+
+1.) Adapter type (CRD8900, CDB8900, CDB8920, etc.)
+
+2.) Adapter configuration
+
+    * IO Base, Memory Base, IO or memory mode enabled, IRQ, DMA channel
+    * Plug and Play enabled/disabled (CS8920-based adapters only)
+    * Configured for media auto-detect or specific media type (which type).
+
+3.) PC System's Configuration
+
+    * Plug and Play system (yes/no)
+    * BIOS (make and version)
+    * System make and model
+    * CPU (type and speed)
+    * System RAM
+    * SCSI Adapter
+
+4.) Software
+
+    * CS89XX driver and version
+    * Your network operating system and version
+    * Your system's OS version
+    * Version of all protocol support files
+
+5.) Any Error Message displayed.
+
+
+
+6.3 Obtaining the Latest Driver Version
+---------------------------------------
+
+You can obtain the latest CS89XX drivers and support software from Cirrus Logic's
+Web site.  You can also contact Cirrus Logic's Technical Support (email:
+ethernet@crystal.cirrus.com) and request that you be registered for automatic
+software-update notification.
+
+Cirrus Logic maintains a web page at http://www.cirrus.com with the
+latest drivers and technical publications.
+
+
+6.4. Current maintainer
+-----------------------
+
+In February 2000 the maintenance of this driver was assumed by Andrew
+Morton.
+
+6.5 Kernel module parameters
+----------------------------
+
+For use in embedded environments with no cs89x0 EEPROM, the kernel boot
+parameter ``cs89x0_media=`` has been implemented.  Usage is::
+
+	cs89x0_media=rj45    or
+	cs89x0_media=aui     or
+	cs89x0_media=bnc
diff --git a/Documentation/networking/device_drivers/cirrus/cs89x0.txt b/Documentation/networking/device_drivers/cirrus/cs89x0.txt
deleted file mode 100644
index 0e190180eec8..000000000000
--- a/Documentation/networking/device_drivers/cirrus/cs89x0.txt
+++ /dev/null
@@ -1,624 +0,0 @@
-
-NOTE
-----
-
-This document was contributed by Cirrus Logic for kernel 2.2.5.  This version
-has been updated for 2.3.48 by Andrew Morton.
-
-Cirrus make a copy of this driver available at their website, as
-described below.  In general, you should use the driver version which
-comes with your Linux distribution.
-
-
-
-CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-Linux Network Interface Driver ver. 2.00 <kernel 2.3.48>
-===============================================================================
- 
-
-TABLE OF CONTENTS
-
-1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-    1.1 Product Overview 
-    1.2 Driver Description
-	1.2.1 Driver Name
-	1.2.2 File in the Driver Package
-    1.3 System Requirements
-    1.4 Licensing Information
-
-2.0 ADAPTER INSTALLATION and CONFIGURATION
-    2.1 CS8900-based Adapter Configuration
-    2.2 CS8920-based Adapter Configuration 
-
-3.0 LOADING THE DRIVER AS A MODULE
-
-4.0 COMPILING THE DRIVER
-    4.1 Compiling the Driver as a Loadable Module
-    4.2 Compiling the driver to support memory mode
-    4.3 Compiling the driver to support Rx DMA 
-
-5.0 TESTING AND TROUBLESHOOTING
-    5.1 Known Defects and Limitations
-    5.2 Testing the Adapter
-        5.2.1 Diagnostic Self-Test
-        5.2.2 Diagnostic Network Test
-    5.3 Using the Adapter's LEDs
-    5.4 Resolving I/O Conflicts
-
-6.0 TECHNICAL SUPPORT
-    6.1 Contacting Cirrus Logic's Technical Support
-    6.2 Information Required Before Contacting Technical Support
-    6.3 Obtaining the Latest Driver Version
-    6.4 Current maintainer
-    6.5 Kernel boot parameters
-
-
-1.0 CIRRUS LOGIC LAN CS8900/CS8920 ETHERNET ADAPTERS
-===============================================================================
-
-
-1.1 PRODUCT OVERVIEW
-
-The CS8900-based ISA Ethernet Adapters from Cirrus Logic follow 
-IEEE 802.3 standards and support half or full-duplex operation in ISA bus 
-computers on 10 Mbps Ethernet networks.  The adapters are designed for operation 
-in 16-bit ISA or EISA bus expansion slots and are available in 
-10BaseT-only or 3-media configurations (10BaseT, 10Base2, and AUI for 10Base-5 
-or fiber networks).  
-
-CS8920-based adapters are similar to the CS8900-based adapter with additional 
-features for Plug and Play (PnP) support and Wakeup Frame recognition.  As 
-such, the configuration procedures differ somewhat between the two types of 
-adapters.  Refer to the "Adapter Configuration" section for details on 
-configuring both types of adapters.
-
-
-1.2 DRIVER DESCRIPTION
-
-The CS8900/CS8920 Ethernet Adapter driver for Linux supports the Linux
-v2.3.48 or greater kernel.  It can be compiled directly into the kernel
-or loaded at run-time as a device driver module.
-
-1.2.1 Driver Name: cs89x0
-
-1.2.2 Files in the Driver Archive:
-
-The files in the driver at Cirrus' website include:
-
-  readme.txt         - this file
-  build              - batch file to compile cs89x0.c.
-  cs89x0.c           - driver C code
-  cs89x0.h           - driver header file
-  cs89x0.o           - pre-compiled module (for v2.2.5 kernel)
-  config/Config.in   - sample file to include cs89x0 driver in the kernel.
-  config/Makefile    - sample file to include cs89x0 driver in the kernel.
-  config/Space.c     - sample file to include cs89x0 driver in the kernel.
-
-
-
-1.3 SYSTEM REQUIREMENTS
-
-The following hardware is required:
-
-   * Cirrus Logic LAN (CS8900/20-based) Ethernet ISA Adapter   
-
-   * IBM or IBM-compatible PC with:
-     * An 80386 or higher processor
-     * 16 bytes of contiguous IO space available between 210h - 370h
-     * One available IRQ (5,10,11,or 12 for the CS8900, 3-7,9-15 for CS8920).
-
-   * Appropriate cable (and connector for AUI, 10BASE-2) for your network
-     topology.
-
-The following software is required:
-
-* LINUX kernel version 2.3.48 or higher
-
-   * CS8900/20 Setup Utility (DOS-based)
-
-   * LINUX kernel sources for your kernel (if compiling into kernel)
-
-   * GNU Toolkit (gcc and make) v2.6 or above (if compiling into kernel 
-     or a module)   
-
-
-
-1.4 LICENSING INFORMATION
-
-This program is free software; you can redistribute it and/or modify it under
-the terms of the GNU General Public License as published by the Free Software
-Foundation, version 1.
-
-This program is distributed in the hope that it will be useful, but WITHOUT
-ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 
-FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for 
-more details.
-
-For a full copy of the GNU General Public License, write to the Free Software
-Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
-
-2.0 ADAPTER INSTALLATION and CONFIGURATION
-===============================================================================
-
-Both the CS8900 and CS8920-based adapters can be configured using parameters 
-stored in an on-board EEPROM. You must use the DOS-based CS8900/20 Setup 
-Utility if you want to change the adapter's configuration in EEPROM.  
-
-When loading the driver as a module, you can specify many of the adapter's 
-configuration parameters on the command-line to override the EEPROM's settings 
-or for interface configuration when an EEPROM is not used. (CS8920-based 
-adapters must use an EEPROM.) See Section 3.0 LOADING THE DRIVER AS A MODULE.
-
-Since the CS8900/20 Setup Utility is a DOS-based application, you must install 
-and configure the adapter in a DOS-based system using the CS8900/20 Setup 
-Utility before installation in the target LINUX system.  (Not required if 
-installing a CS8900-based adapter and the default configuration is acceptable.)
-     
-
-2.1 CS8900-BASED ADAPTER CONFIGURATION
-
-CS8900-based adapters shipped from Cirrus Logic have been configured 
-with the following "default" settings:
-
-  Operation Mode:      Memory Mode
-  IRQ:                 10
-  Base I/O Address:    300
-  Memory Base Address: D0000
-  Optimization:	       DOS Client
-  Transmission Mode:   Half-duplex
-  BootProm:            None
-  Media Type:	       Autodetect (3-media cards) or 
-                       10BASE-T (10BASE-T only adapter)
-
-You should only change the default configuration settings if conflicts with 
-another adapter exists. To change the adapter's configuration, run the 
-CS8900/20 Setup Utility. 
-
-
-2.2 CS8920-BASED ADAPTER CONFIGURATION
-
-CS8920-based adapters are shipped from Cirrus Logic configured as Plug
-and Play (PnP) enabled.  However, since the cs89x0 driver does NOT
-support PnP, you must install the CS8920 adapter in a DOS-based PC and
-run the CS8900/20 Setup Utility to disable PnP and configure the
-adapter before installation in the target Linux system.  Failure to do
-this will leave the adapter inactive and the driver will be unable to
-communicate with the adapter.  
-
-
-        **************************************************************** 
-        *                    CS8920-BASED ADAPTERS:                    *
-        *                                                              * 
-        * CS8920-BASED ADAPTERS ARE PLUG and PLAY ENABLED BY DEFAULT.  * 
-        * THE CS89X0 DRIVER DOES NOT SUPPORT PnP. THEREFORE, YOU MUST  *
-        * RUN THE CS8900/20 SETUP UTILITY TO DISABLE PnP SUPPORT AND   *
-        * TO ACTIVATE THE ADAPTER.                                     *
-        ****************************************************************
-
-
-
-
-3.0 LOADING THE DRIVER AS A MODULE
-===============================================================================
-
-If the driver is compiled as a loadable module, you can load the driver module
-with the 'modprobe' command.  Many of the adapter's configuration parameters can 
-be specified as command-line arguments to the load command.  This facility 
-provides a means to override the EEPROM's settings or for interface 
-configuration when an EEPROM is not used.
-
-Example:
-
-    insmod cs89x0.o io=0x200 irq=0xA media=aui
-
-This example loads the module and configures the adapter to use an IO port base
-address of 200h, interrupt 10, and use the AUI media connection.  The following
-configuration options are available on the command line:
-
-* io=###               - specify IO address (200h-360h)
-* irq=##               - specify interrupt level
-* use_dma=1            - Enable DMA
-* dma=#                - specify dma channel (Driver is compiled to support
-                         Rx DMA only)
-* dmasize=# (16 or 64) - DMA size 16K or 64K.  Default value is set to 16.
-* media=rj45           - specify media type
-   or media=bnc
-   or media=aui
-   or media=auto
-* duplex=full          - specify forced half/full/autonegotiate duplex
-   or duplex=half
-   or duplex=auto
-* debug=#              - debug level (only available if the driver was compiled
-                         for debugging)
-
-NOTES:
-
-a) If an EEPROM is present, any specified command-line parameter
-   will override the corresponding configuration value stored in
-   EEPROM.
-
-b) The "io" parameter must be specified on the command-line.  
-
-c) The driver's hardware probe routine is designed to avoid
-   writing to I/O space until it knows that there is a cs89x0
-   card at the written addresses.  This could cause problems
-   with device probing.  To avoid this behaviour, add one
-   to the `io=' module parameter.  This doesn't actually change
-   the I/O address, but it is a flag to tell the driver
-   to partially initialise the hardware before trying to
-   identify the card.  This could be dangerous if you are
-   not sure that there is a cs89x0 card at the provided address.
-
-   For example, to scan for an adapter located at IO base 0x300,
-   specify an IO address of 0x301.  
-
-d) The "duplex=auto" parameter is only supported for the CS8920.
-
-e) The minimum command-line configuration required if an EEPROM is
-   not present is:
-
-   io 
-   irq 
-   media type (no autodetect)
-
-f) The following additional parameters are CS89XX defaults (values
-   used with no EEPROM or command-line argument).
-
-   * DMA Burst = enabled
-   * IOCHRDY Enabled = enabled
-   * UseSA = enabled
-   * CS8900 defaults to half-duplex if not specified on command-line
-   * CS8920 defaults to autoneg if not specified on command-line
-   * Use reset defaults for other config parameters
-   * dma_mode = 0
-
-g) You can use ifconfig to set the adapter's Ethernet address.
-
-h) Many Linux distributions use the 'modprobe' command to load
-   modules.  This program uses the '/etc/conf.modules' file to
-   determine configuration information which is passed to a driver
-   module when it is loaded.  All the configuration options which are
-   described above may be placed within /etc/conf.modules.
-
-   For example:
-
-   > cat /etc/conf.modules
-   ...
-   alias eth0 cs89x0
-   options cs89x0 io=0x0200 dma=5 use_dma=1
-   ...
-
-   In this example we are telling the module system that the
-   ethernet driver for this machine should use the cs89x0 driver.  We
-   are asking 'modprobe' to pass the 'io', 'dma' and 'use_dma'
-   arguments to the driver when it is loaded.
-
-i) Cirrus recommend that the cs89x0 use the ISA DMA channels 5, 6 or
-   7.  You will probably find that other DMA channels will not work.
-
-j) The cs89x0 supports DMA for receiving only.  DMA mode is
-   significantly more efficient.  Flooding a 400 MHz Celeron machine
-   with large ping packets consumes 82% of its CPU capacity in non-DMA
-   mode.  With DMA this is reduced to 45%.
-
-k) If your Linux kernel was compiled with inbuilt plug-and-play
-   support you will be able to find information about the cs89x0 card
-   with the command
-
-   cat /proc/isapnp
-
-l) If during DMA operation you find erratic behavior or network data
-   corruption you should use your PC's BIOS to slow the EISA bus clock.
-
-m) If the cs89x0 driver is compiled directly into the kernel
-   (non-modular) then its I/O address is automatically determined by
-   ISA bus probing.  The IRQ number, media options, etc are determined
-   from the card's EEPROM.
-
-n) If the cs89x0 driver is compiled directly into the kernel, DMA
-   mode may be selected by providing the kernel with a boot option
-   'cs89x0_dma=N' where 'N' is the desired DMA channel number (5, 6 or 7).
-
-   Kernel boot options may be provided on the LILO command line:
-
-	LILO boot: linux cs89x0_dma=5
-
-   or they may be placed in /etc/lilo.conf:
-
-	image=/boot/bzImage-2.3.48
-	  append="cs89x0_dma=5"
-	  label=linux
-	  root=/dev/hda5
-	  read-only
-
-   The DMA Rx buffer size is hardwired to 16 kbytes in this mode.
-   (64k mode is not available).
-
-
-4.0 COMPILING THE DRIVER
-===============================================================================
-
-The cs89x0 driver can be compiled directly into the kernel or compiled into
-a loadable device driver module.
-
-
-4.1 COMPILING THE DRIVER AS A LOADABLE MODULE
-
-To compile the driver into a loadable module, use the following command 
-(single command line, without quotes):
-
-"gcc -D__KERNEL__ -I/usr/src/linux/include -I/usr/src/linux/net/inet -Wall 
--Wstrict-prototypes -O2 -fomit-frame-pointer -DMODULE -DCONFIG_MODVERSIONS 
--c cs89x0.c"
-
-4.2 COMPILING THE DRIVER TO SUPPORT MEMORY MODE
-
-Support for memory mode was not carried over into the 2.3 series kernels.
-
-4.3 COMPILING THE DRIVER TO SUPPORT Rx DMA
-
-The compile-time optionality for DMA was removed in the 2.3 kernel
-series.  DMA support is now unconditionally part of the driver.  It is
-enabled by the 'use_dma=1' module option.
-
-
-5.0 TESTING AND TROUBLESHOOTING
-===============================================================================
-
-5.1 KNOWN DEFECTS and LIMITATIONS
-
-Refer to the RELEASE.TXT file distributed as part of this archive for a list of 
-known defects, driver limitations, and work arounds.
-
-
-5.2 TESTING THE ADAPTER
-
-Once the adapter has been installed and configured, the diagnostic option of 
-the CS8900/20 Setup Utility can be used to test the functionality of the 
-adapter and its network connection.  Use the diagnostics 'Self Test' option to
-test the functionality of the adapter with the hardware configuration you have
-assigned. You can use the diagnostics 'Network Test' to test the ability of the
-adapter to communicate across the Ethernet with another PC equipped with a 
-CS8900/20-based adapter card (it must also be running the CS8900/20 Setup 
-Utility).
-
-         NOTE: The Setup Utility's diagnostics are designed to run in a
-         DOS-only operating system environment.  DO NOT run the diagnostics 
-         from a DOS or command prompt session under Windows 95, Windows NT, 
-         OS/2, or other operating system.
-
-To run the diagnostics tests on the CS8900/20 adapter:
-
-   1.) Boot DOS on the PC and start the CS8900/20 Setup Utility.
-
-   2.) The adapter's current configuration is displayed.  Hit the ENTER key to
-       get to the main menu.
-
-   4.) Select 'Diagnostics' (ALT-G) from the main menu.  
-       * Select 'Self-Test' to test the adapter's basic functionality.
-       * Select 'Network Test' to test the network connection and cabling.
-
-
-5.2.1 DIAGNOSTIC SELF-TEST
-
-The diagnostic self-test checks the adapter's basic functionality as well as 
-its ability to communicate across the ISA bus based on the system resources 
-assigned during hardware configuration.  The following tests are performed:
-
-   * IO Register Read/Write Test
-     The IO Register Read/Write test insures that the CS8900/20 can be 
-     accessed in IO mode, and that the IO base address is correct.
-
-   * Shared Memory Test
-     The Shared Memory test insures the CS8900/20 can be accessed in memory 
-     mode and that the range of memory addresses assigned does not conflict 
-     with other devices in the system.
-
-   * Interrupt Test
-     The Interrupt test insures there are no conflicts with the assigned IRQ
-     signal.
-
-   * EEPROM Test
-     The EEPROM test insures the EEPROM can be read.
-
-   * Chip RAM Test
-     The Chip RAM test insures the 4K of memory internal to the CS8900/20 is
-     working properly.
-
-   * Internal Loop-back Test
-     The Internal Loop Back test insures the adapter's transmitter and 
-     receiver are operating properly.  If this test fails, make sure the 
-     adapter's cable is connected to the network (check for LED activity for 
-     example).
-
-   * Boot PROM Test
-     The Boot PROM  test insures the Boot PROM is present, and can be read.
-     Failure indicates the Boot PROM  was not successfully read due to a
-     hardware problem or due to a conflicts on the Boot PROM address
-     assignment. (Test only applies if the adapter is configured to use the
-     Boot PROM option.)
-
-Failure of a test item indicates a possible system resource conflict with 
-another device on the ISA bus.  In this case, you should use the Manual Setup 
-option to reconfigure the adapter by selecting a different value for the system
-resource that failed.
-
-
-5.2.2 DIAGNOSTIC NETWORK TEST
-
-The Diagnostic Network Test verifies a working network connection by 
-transferring data between two CS8900/20 adapters installed in different PCs 
-on the same network. (Note: the diagnostic network test should not be run 
-between two nodes across a router.) 
-
-This test requires that each of the two PCs have a CS8900/20-based adapter
-installed and have the CS8900/20 Setup Utility running.  The first PC is 
-configured as a Responder and the other PC is configured as an Initiator.  
-Once the Initiator is started, it sends data frames to the Responder which 
-returns the frames to the Initiator.
-
-The total number of frames received and transmitted are displayed on the 
-Initiator's display, along with a count of the number of frames received and 
-transmitted OK or in error.  The test can be terminated anytime by the user at 
-either PC.
-
-To setup the Diagnostic Network Test:
-
-    1.) Select a PC with a CS8900/20-based adapter and a known working network
-        connection to act as the Responder.  Run the CS8900/20 Setup Utility 
-        and select 'Diagnostics -> Network Test -> Responder' from the main 
-        menu.  Hit ENTER to start the Responder.
-
-    2.) Return to the PC with the CS8900/20-based adapter you want to test and
-        start the CS8900/20 Setup Utility. 
-
-    3.) From the main menu, Select 'Diagnostic -> Network Test -> Initiator'.
-        Hit ENTER to start the test.
- 
-You may stop the test on the Initiator at any time while allowing the Responder
-to continue running.  In this manner, you can move to additional PCs and test 
-them by starting the Initiator on another PC without having to stop/start the 
-Responder.
- 
-
-
-5.3 USING THE ADAPTER'S LEDs
-
-The 2 and 3-media adapters have two LEDs visible on the back end of the board 
-located near the 10Base-T connector.  
-
-Link Integrity LED: A "steady" ON of the green LED indicates a valid 10Base-T 
-connection.  (Only applies to 10Base-T.  The green LED has no significance for
-a 10Base-2 or AUI connection.)
-
-TX/RX LED: The yellow LED lights briefly each time the adapter transmits or 
-receives data. (The yellow LED will appear to "flicker" on a typical network.)
-
-
-5.4 RESOLVING I/O CONFLICTS
-
-An IO conflict occurs when two or more adapter use the same ISA resource (IO 
-address, memory address or IRQ).  You can usually detect an IO conflict in one 
-of four ways after installing and or configuring the CS8900/20-based adapter:
-
-    1.) The system does not boot properly (or at all).
-
-    2.) The driver cannot communicate with the adapter, reporting an "Adapter
-        not found" error message.
-
-    3.) You cannot connect to the network or the driver will not load.
-
-    4.) If you have configured the adapter to run in memory mode but the driver
-        reports it is using IO mode when loading, this is an indication of a
-        memory address conflict.
-
-If an IO conflict occurs, run the CS8900/20 Setup Utility and perform a 
-diagnostic self-test.  Normally, the ISA resource in conflict will fail the 
-self-test.  If so, reconfigure the adapter selecting another choice for the 
-resource in conflict.  Run the diagnostics again to check for further IO 
-conflicts.
-
-In some cases, such as when the PC will not boot, it may be necessary to remove
-the adapter and reconfigure it by installing it in another PC to run the 
-CS8900/20 Setup Utility.  Once reinstalled in the target system, run the 
-diagnostics self-test to ensure the new configuration is free of conflicts 
-before loading the driver again.
-
-When manually configuring the adapter, keep in mind the typical ISA system 
-resource usage as indicated in the tables below.
-
-I/O Address    	Device                        IRQ      Device
------------    	--------                      ---      --------
- 200-20F       	Game I/O adapter               3       COM2, Bus Mouse
- 230-23F       	Bus Mouse                      4       COM1
- 270-27F       	LPT3: third parallel port      5       LPT2
- 2F0-2FF       	COM2: second serial port       6       Floppy Disk controller
- 320-32F       	Fixed disk controller          7       LPT1
-                                      	       8       Real-time Clock
-                                                 9       EGA/VGA display adapter    
-                                                12       Mouse (PS/2)                              
-Memory Address  Device                          13       Math Coprocessor
---------------  ---------------------           14       Hard Disk controller
-A000-BFFF	EGA Graphics Adapter
-A000-C7FF	VGA Graphics Adapter
-B000-BFFF	Mono Graphics Adapter
-B800-BFFF	Color Graphics Adapter
-E000-FFFF	AT BIOS
-
-
-
-
-6.0 TECHNICAL SUPPORT
-===============================================================================
-
-6.1 CONTACTING CIRRUS LOGIC'S TECHNICAL SUPPORT
-
-Cirrus Logic's CS89XX Technical Application Support can be reached at:
-
-Telephone  :(800) 888-5016 (from inside U.S. and Canada)
-           :(512) 442-7555 (from outside the U.S. and Canada)
-Fax        :(512) 912-3871
-Email      :ethernet@crystal.cirrus.com
-WWW        :http://www.cirrus.com
-
-
-6.2 INFORMATION REQUIRED BEFORE CONTACTING TECHNICAL SUPPORT
-
-Before contacting Cirrus Logic for technical support, be prepared to provide as 
-Much of the following information as possible. 
-
-1.) Adapter type (CRD8900, CDB8900, CDB8920, etc.)
-
-2.) Adapter configuration
-
-    * IO Base, Memory Base, IO or memory mode enabled, IRQ, DMA channel
-    * Plug and Play enabled/disabled (CS8920-based adapters only)
-    * Configured for media auto-detect or specific media type (which type).    
-
-3.) PC System's Configuration
-
-    * Plug and Play system (yes/no)
-    * BIOS (make and version)
-    * System make and model
-    * CPU (type and speed)
-    * System RAM
-    * SCSI Adapter
-
-4.) Software
-
-    * CS89XX driver and version
-    * Your network operating system and version
-    * Your system's OS version 
-    * Version of all protocol support files
-
-5.) Any Error Message displayed.
-
-
-
-6.3 OBTAINING THE LATEST DRIVER VERSION
-
-You can obtain the latest CS89XX drivers and support software from Cirrus Logic's 
-Web site.  You can also contact Cirrus Logic's Technical Support (email:
-ethernet@crystal.cirrus.com) and request that you be registered for automatic 
-software-update notification.
-
-Cirrus Logic maintains a web page at http://www.cirrus.com with the
-latest drivers and technical publications.
-
-
-6.4 Current maintainer
-
-In February 2000 the maintenance of this driver was assumed by Andrew
-Morton.
-
-6.5 Kernel module parameters
-
-For use in embedded environments with no cs89x0 EEPROM, the kernel boot
-parameter `cs89x0_media=' has been implemented.  Usage is:
-
-	cs89x0_media=rj45    or
-	cs89x0_media=aui     or
-	cs89x0_media=bnc
-
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 23c4ec9c9125..0b39342e2a1f 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -32,6 +32,7 @@ Contents:
    amazon/ena
    aquantia/atlantic
    chelsio/cxgb
+   cirrus/cs89x0
 
 .. only::  subproject and html
 
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 48f3198381bc..8d845f5ee0c5 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -24,7 +24,7 @@ config CS89x0
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
-	  <file:Documentation/networking/device_drivers/cirrus/cs89x0.txt>.
+	  <file:Documentation/networking/device_drivers/cirrus/cs89x0.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called cs89x0.
-- 
cgit v1.2.3


From b6671d71ca811aed02f136a6cd812a542f88c483 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:41 +0200
Subject: docs: networking: device drivers: convert dec/de4x5.txt to ReST

- add SPDX header;
- add a document title;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/dec/de4x5.rst        | 189 +++++++++++++++++++++
 .../networking/device_drivers/dec/de4x5.txt        | 178 -------------------
 Documentation/networking/device_drivers/index.rst  |   1 +
 drivers/net/ethernet/dec/tulip/Kconfig             |   2 +-
 4 files changed, 191 insertions(+), 179 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/dec/de4x5.rst
 delete mode 100644 Documentation/networking/device_drivers/dec/de4x5.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/dec/de4x5.rst b/Documentation/networking/device_drivers/dec/de4x5.rst
new file mode 100644
index 000000000000..e03e9c631879
--- /dev/null
+++ b/Documentation/networking/device_drivers/dec/de4x5.rst
@@ -0,0 +1,189 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+DEC EtherWORKS Ethernet De4x5 cards
+===================================
+
+    Originally,   this  driver  was    written  for the  Digital   Equipment
+    Corporation series of EtherWORKS Ethernet cards:
+
+	 - DE425 TP/COAX EISA
+	 - DE434 TP PCI
+	 - DE435 TP/COAX/AUI PCI
+	 - DE450 TP/COAX/AUI PCI
+	 - DE500 10/100 PCI Fasternet
+
+    but it  will  now attempt  to  support all  cards which   conform to the
+    Digital Semiconductor   SROM   Specification.    The  driver   currently
+    recognises the following chips:
+
+	 - DC21040  (no SROM)
+	 - DC21041[A]
+	 - DC21140[A]
+	 - DC21142
+	 - DC21143
+
+    So far the driver is known to work with the following cards:
+
+	 - KINGSTON
+	 - Linksys
+	 - ZNYX342
+	 - SMC8432
+	 - SMC9332 (w/new SROM)
+	 - ZNYX31[45]
+	 - ZNYX346 10/100 4 port (can act as a 10/100 bridge!)
+
+    The driver has been tested on a relatively busy network using the DE425,
+    DE434, DE435 and DE500 cards and benchmarked with 'ttcp': it transferred
+    16M of data to a DECstation 5000/200 as follows::
+
+		  TCP           UDP
+	       TX     RX     TX     RX
+      DE425   1030k  997k   1170k  1128k
+      DE434   1063k  995k   1170k  1125k
+      DE435   1063k  995k   1170k  1125k
+      DE500   1063k  998k   1170k  1125k  in 10Mb/s mode
+
+    All  values are typical (in   kBytes/sec) from a  sample  of 4 for  each
+    measurement. Their error is +/-20k on a quiet (private) network and also
+    depend on what load the CPU has.
+
+----------------------------------------------------------------------------
+
+    The ability to load this  driver as a loadable  module has been included
+    and used extensively  during the driver development  (to save those long
+    reboot sequences).  Loadable module support  under PCI and EISA has been
+    achieved by letting the driver autoprobe as if it were compiled into the
+    kernel. Do make sure  you're not sharing  interrupts with anything  that
+    cannot accommodate  interrupt  sharing!
+
+    To utilise this ability, you have to do 8 things:
+
+    0) have a copy of the loadable modules code installed on your system.
+    1) copy de4x5.c from the  /linux/drivers/net directory to your favourite
+       temporary directory.
+    2) for fixed  autoprobes (not  recommended),  edit the source code  near
+       line 5594 to reflect the I/O address  you're using, or assign these when
+       loading by::
+
+		   insmod de4x5 io=0xghh           where g = bus number
+							hh = device number
+
+       .. note::
+
+	   autoprobing for modules is now supported by default. You may just
+	   use::
+
+		   insmod de4x5
+
+	   to load all available boards. For a specific board, still use
+	   the 'io=?' above.
+    3) compile  de4x5.c, but include -DMODULE in  the command line to ensure
+       that the correct bits are compiled (see end of source code).
+    4) if you are wanting to add a new  card, goto 5. Otherwise, recompile a
+       kernel with the de4x5 configuration turned off and reboot.
+    5) insmod de4x5 [io=0xghh]
+    6) run the net startup bits for your new eth?? interface(s) manually
+       (usually /etc/rc.inet[12] at boot time).
+    7) enjoy!
+
+    To unload a module, turn off the associated interface(s)
+    'ifconfig eth?? down' then 'rmmod de4x5'.
+
+    Automedia detection is included so that in  principle you can disconnect
+    from, e.g.  TP, reconnect  to BNC  and  things will still work  (after a
+    pause while the   driver figures out   where its media went).  My tests
+    using ping showed that it appears to work....
+
+    By  default,  the driver will  now   autodetect any  DECchip based card.
+    Should you have a need to restrict the driver to DIGITAL only cards, you
+    can compile with a  DEC_ONLY define, or if  loading as a module, use the
+    'dec_only=1'  parameter.
+
+    I've changed the timing routines to  use the kernel timer and scheduling
+    functions  so that the  hangs  and other assorted problems that occurred
+    while autosensing the  media  should be gone.  A  bonus  for the DC21040
+    auto  media sense algorithm is  that it can now  use one that is more in
+    line with the  rest (the DC21040  chip doesn't  have a hardware  timer).
+    The downside is the 1 'jiffies' (10ms) resolution.
+
+    IEEE 802.3u MII interface code has  been added in anticipation that some
+    products may use it in the future.
+
+    The SMC9332 card  has a non-compliant SROM  which needs fixing -  I have
+    patched this  driver to detect it  because the SROM format used complies
+    to a previous DEC-STD format.
+
+    I have removed the buffer copies needed for receive on Intels.  I cannot
+    remove them for   Alphas since  the  Tulip hardware   only does longword
+    aligned  DMA transfers  and  the  Alphas get   alignment traps with  non
+    longword aligned data copies (which makes them really slow). No comment.
+
+    I  have added SROM decoding  routines to make this  driver work with any
+    card that  supports the Digital  Semiconductor SROM spec. This will help
+    all  cards running the dc2114x  series chips in particular.  Cards using
+    the dc2104x  chips should run correctly with  the basic  driver.  I'm in
+    debt to <mjacob@feral.com> for the  testing and feedback that helped get
+    this feature working.  So far we have  tested KINGSTON, SMC8432, SMC9332
+    (with the latest SROM complying  with the SROM spec  V3: their first was
+    broken), ZNYX342  and  LinkSys. ZNYX314 (dual  21041  MAC) and  ZNYX 315
+    (quad 21041 MAC)  cards also  appear  to work despite their  incorrectly
+    wired IRQs.
+
+    I have added a temporary fix for interrupt problems when some SCSI cards
+    share the same interrupt as the DECchip based  cards. The problem occurs
+    because  the SCSI card wants to  grab the interrupt  as a fast interrupt
+    (runs the   service routine with interrupts turned   off) vs.  this card
+    which really needs to run the service routine with interrupts turned on.
+    This driver will  now   add the interrupt service   routine  as  a  fast
+    interrupt if it   is bounced from the   slow interrupt.  THIS IS NOT   A
+    RECOMMENDED WAY TO RUN THE DRIVER  and has been done  for a limited time
+    until  people   sort  out their  compatibility    issues and the  kernel
+    interrupt  service code  is  fixed.   YOU  SHOULD SEPARATE OUT  THE FAST
+    INTERRUPT CARDS FROM THE SLOW INTERRUPT CARDS to ensure that they do not
+    run on the same interrupt. PCMCIA/CardBus is another can of worms...
+
+    Finally, I think  I have really  fixed  the module  loading problem with
+    more than one DECchip based  card.  As a  side effect, I don't mess with
+    the  device structure any  more which means that  if more than 1 card in
+    2.0.x is    installed (4  in   2.1.x),  the  user   will have   to  edit
+    linux/drivers/net/Space.c  to make room for  them. Hence, module loading
+    is  the preferred way to use   this driver, since  it  doesn't have this
+    limitation.
+
+    Where SROM media  detection is used and  full duplex is specified in the
+    SROM,  the feature is  ignored unless  lp->params.fdx  is set at compile
+    time  OR during  a   module load  (insmod  de4x5   args='eth??:fdx' [see
+    below]).  This is because there  is no way  to automatically detect full
+    duplex   links  except through   autonegotiation.    When I  include the
+    autonegotiation feature in  the SROM autoconf  code, this detection will
+    occur automatically for that case.
+
+    Command line  arguments are  now allowed, similar to  passing  arguments
+    through LILO. This will allow a per adapter board set  up of full duplex
+    and media. The only lexical constraints are:  the board name (dev->name)
+    appears in  the list before its parameters.  The list of parameters ends
+    either at the end of the parameter list or with another board name.  The
+    following parameters are allowed:
+
+	    =========  ===============================================
+	    fdx        for full duplex
+	    autosense  to set the media/speed; with the following
+		       sub-parameters:
+		       TP, TP_NW, BNC, AUI, BNC_AUI, 100Mb, 10Mb, AUTO
+	    =========  ===============================================
+
+    Case sensitivity is important  for  the sub-parameters. They *must*   be
+    upper case. Examples::
+
+	insmod de4x5 args='eth1:fdx autosense=BNC eth0:autosense=100Mb'.
+
+    For a compiled in driver, in linux/drivers/net/CONFIG, place e.g.::
+
+	DE4X5_OPTS = -DDE4X5_PARM='"eth0:fdx autosense=AUI eth2:autosense=TP"'
+
+    Yes,  I know full duplex  isn't permissible on BNC  or AUI; they're just
+    examples. By default, full duplex is turned  off and AUTO is the default
+    autosense setting. In  reality, I expect only the  full duplex option to
+    be used. Note the use of single quotes in the two examples above and the
+    lack of commas to separate items.
diff --git a/Documentation/networking/device_drivers/dec/de4x5.txt b/Documentation/networking/device_drivers/dec/de4x5.txt
deleted file mode 100644
index 452aac58341d..000000000000
--- a/Documentation/networking/device_drivers/dec/de4x5.txt
+++ /dev/null
@@ -1,178 +0,0 @@
-    Originally,   this  driver  was    written  for the  Digital   Equipment
-    Corporation series of EtherWORKS Ethernet cards:
-
-        DE425 TP/COAX EISA
-	DE434 TP PCI
-	DE435 TP/COAX/AUI PCI
-	DE450 TP/COAX/AUI PCI
-	DE500 10/100 PCI Fasternet
-
-    but it  will  now attempt  to  support all  cards which   conform to the
-    Digital Semiconductor   SROM   Specification.    The  driver   currently
-    recognises the following chips:
-
-        DC21040  (no SROM) 
-	DC21041[A]  
-	DC21140[A] 
-	DC21142 
-	DC21143 
-
-    So far the driver is known to work with the following cards:
-
-        KINGSTON
-	Linksys
-	ZNYX342
-	SMC8432
-	SMC9332 (w/new SROM)
-	ZNYX31[45]
-	ZNYX346 10/100 4 port (can act as a 10/100 bridge!) 
-
-    The driver has been tested on a relatively busy network using the DE425,
-    DE434, DE435 and DE500 cards and benchmarked with 'ttcp': it transferred
-    16M of data to a DECstation 5000/200 as follows:
-
-                TCP           UDP
-             TX     RX     TX     RX
-    DE425   1030k  997k   1170k  1128k
-    DE434   1063k  995k   1170k  1125k
-    DE435   1063k  995k   1170k  1125k
-    DE500   1063k  998k   1170k  1125k  in 10Mb/s mode
-
-    All  values are typical (in   kBytes/sec) from a  sample  of 4 for  each
-    measurement. Their error is +/-20k on a quiet (private) network and also
-    depend on what load the CPU has.
-
-    =========================================================================
-
-    The ability to load this  driver as a loadable  module has been included
-    and used extensively  during the driver development  (to save those long
-    reboot sequences).  Loadable module support  under PCI and EISA has been
-    achieved by letting the driver autoprobe as if it were compiled into the
-    kernel. Do make sure  you're not sharing  interrupts with anything  that
-    cannot accommodate  interrupt  sharing!
-
-    To utilise this ability, you have to do 8 things:
-
-    0) have a copy of the loadable modules code installed on your system.
-    1) copy de4x5.c from the  /linux/drivers/net directory to your favourite
-    temporary directory.
-    2) for fixed  autoprobes (not  recommended),  edit the source code  near
-    line 5594 to reflect the I/O address  you're using, or assign these when
-    loading by:
-
-                   insmod de4x5 io=0xghh           where g = bus number
-		                                        hh = device number   
-
-       NB: autoprobing for modules is now supported by default. You may just
-           use:
-
-                   insmod de4x5
-
-           to load all available boards. For a specific board, still use
-	   the 'io=?' above.
-    3) compile  de4x5.c, but include -DMODULE in  the command line to ensure
-    that the correct bits are compiled (see end of source code).
-    4) if you are wanting to add a new  card, goto 5. Otherwise, recompile a
-    kernel with the de4x5 configuration turned off and reboot.
-    5) insmod de4x5 [io=0xghh]
-    6) run the net startup bits for your new eth?? interface(s) manually 
-    (usually /etc/rc.inet[12] at boot time). 
-    7) enjoy!
-
-    To unload a module, turn off the associated interface(s) 
-    'ifconfig eth?? down' then 'rmmod de4x5'.
-
-    Automedia detection is included so that in  principle you can disconnect
-    from, e.g.  TP, reconnect  to BNC  and  things will still work  (after a
-    pause while the   driver figures out   where its media went).  My tests
-    using ping showed that it appears to work....
-
-    By  default,  the driver will  now   autodetect any  DECchip based card.
-    Should you have a need to restrict the driver to DIGITAL only cards, you
-    can compile with a  DEC_ONLY define, or if  loading as a module, use the
-    'dec_only=1'  parameter. 
-
-    I've changed the timing routines to  use the kernel timer and scheduling
-    functions  so that the  hangs  and other assorted problems that occurred
-    while autosensing the  media  should be gone.  A  bonus  for the DC21040
-    auto  media sense algorithm is  that it can now  use one that is more in
-    line with the  rest (the DC21040  chip doesn't  have a hardware  timer).
-    The downside is the 1 'jiffies' (10ms) resolution.
-
-    IEEE 802.3u MII interface code has  been added in anticipation that some
-    products may use it in the future.
-
-    The SMC9332 card  has a non-compliant SROM  which needs fixing -  I have
-    patched this  driver to detect it  because the SROM format used complies
-    to a previous DEC-STD format.
-
-    I have removed the buffer copies needed for receive on Intels.  I cannot
-    remove them for   Alphas since  the  Tulip hardware   only does longword
-    aligned  DMA transfers  and  the  Alphas get   alignment traps with  non
-    longword aligned data copies (which makes them really slow). No comment.
-
-    I  have added SROM decoding  routines to make this  driver work with any
-    card that  supports the Digital  Semiconductor SROM spec. This will help
-    all  cards running the dc2114x  series chips in particular.  Cards using
-    the dc2104x  chips should run correctly with  the basic  driver.  I'm in
-    debt to <mjacob@feral.com> for the  testing and feedback that helped get
-    this feature working.  So far we have  tested KINGSTON, SMC8432, SMC9332
-    (with the latest SROM complying  with the SROM spec  V3: their first was
-    broken), ZNYX342  and  LinkSys. ZNYX314 (dual  21041  MAC) and  ZNYX 315
-    (quad 21041 MAC)  cards also  appear  to work despite their  incorrectly
-    wired IRQs.
-
-    I have added a temporary fix for interrupt problems when some SCSI cards
-    share the same interrupt as the DECchip based  cards. The problem occurs
-    because  the SCSI card wants to  grab the interrupt  as a fast interrupt
-    (runs the   service routine with interrupts turned   off) vs.  this card
-    which really needs to run the service routine with interrupts turned on.
-    This driver will  now   add the interrupt service   routine  as  a  fast
-    interrupt if it   is bounced from the   slow interrupt.  THIS IS NOT   A
-    RECOMMENDED WAY TO RUN THE DRIVER  and has been done  for a limited time
-    until  people   sort  out their  compatibility    issues and the  kernel
-    interrupt  service code  is  fixed.   YOU  SHOULD SEPARATE OUT  THE FAST
-    INTERRUPT CARDS FROM THE SLOW INTERRUPT CARDS to ensure that they do not
-    run on the same interrupt. PCMCIA/CardBus is another can of worms...
-
-    Finally, I think  I have really  fixed  the module  loading problem with
-    more than one DECchip based  card.  As a  side effect, I don't mess with
-    the  device structure any  more which means that  if more than 1 card in
-    2.0.x is    installed (4  in   2.1.x),  the  user   will have   to  edit
-    linux/drivers/net/Space.c  to make room for  them. Hence, module loading
-    is  the preferred way to use   this driver, since  it  doesn't have this
-    limitation.
-
-    Where SROM media  detection is used and  full duplex is specified in the
-    SROM,  the feature is  ignored unless  lp->params.fdx  is set at compile
-    time  OR during  a   module load  (insmod  de4x5   args='eth??:fdx' [see
-    below]).  This is because there  is no way  to automatically detect full
-    duplex   links  except through   autonegotiation.    When I  include the
-    autonegotiation feature in  the SROM autoconf  code, this detection will
-    occur automatically for that case.
-
-    Command line  arguments are  now allowed, similar to  passing  arguments
-    through LILO. This will allow a per adapter board set  up of full duplex
-    and media. The only lexical constraints are:  the board name (dev->name)
-    appears in  the list before its parameters.  The list of parameters ends
-    either at the end of the parameter list or with another board name.  The
-    following parameters are allowed:
-
-            fdx        for full duplex
-	    autosense  to set the media/speed; with the following 
-	               sub-parameters:
-		       TP, TP_NW, BNC, AUI, BNC_AUI, 100Mb, 10Mb, AUTO
-
-    Case sensitivity is important  for  the sub-parameters. They *must*   be
-    upper case. Examples:
-
-        insmod de4x5 args='eth1:fdx autosense=BNC eth0:autosense=100Mb'.
-
-    For a compiled in driver, in linux/drivers/net/CONFIG, place e.g.
-	DE4X5_OPTS = -DDE4X5_PARM='"eth0:fdx autosense=AUI eth2:autosense=TP"' 
-
-    Yes,  I know full duplex  isn't permissible on BNC  or AUI; they're just
-    examples. By default, full duplex is turned  off and AUTO is the default
-    autosense setting. In  reality, I expect only the  full duplex option to
-    be used. Note the use of single quotes in the two examples above and the
-    lack of commas to separate items.
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index e8db57fef2e9..4ad13ffb5800 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -34,6 +34,7 @@ Contents:
    chelsio/cxgb
    cirrus/cs89x0
    davicom/dm9000
+   dec/de4x5
 
 .. only::  subproject and html
 
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index 8ce6888ea722..8c4245d94bb2 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -114,7 +114,7 @@ config DE4X5
 	  These include the DE425, DE434, DE435, DE450 and DE500 models.  If
 	  you have a network card of this type, say Y.  More specific
 	  information is contained in
-	  <file:Documentation/networking/device_drivers/dec/de4x5.txt>.
+	  <file:Documentation/networking/device_drivers/dec/de4x5.rst>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called de4x5.
-- 
cgit v1.2.3


From c981977d3a5ce55c96b1b77f42d0a9df0a79244e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:42 +0200
Subject: docs: networking: device drivers: convert dec/dmfe.txt to ReST

- add SPDX header;
- adjust titles and chapters, adding proper markups;
- comment out text-only TOC from html/pdf output;
- mark code blocks and literals as such;
- mark tables as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/dec/dmfe.rst         | 71 ++++++++++++++++++++++
 .../networking/device_drivers/dec/dmfe.txt         | 66 --------------------
 Documentation/networking/device_drivers/index.rst  |  1 +
 MAINTAINERS                                        |  2 +-
 drivers/net/ethernet/dec/tulip/Kconfig             |  2 +-
 5 files changed, 74 insertions(+), 68 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/dec/dmfe.rst
 delete mode 100644 Documentation/networking/device_drivers/dec/dmfe.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/dec/dmfe.rst b/Documentation/networking/device_drivers/dec/dmfe.rst
new file mode 100644
index 000000000000..c4cf809cad84
--- /dev/null
+++ b/Documentation/networking/device_drivers/dec/dmfe.rst
@@ -0,0 +1,71 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================================
+Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux
+==============================================================
+
+Note: This driver doesn't have a maintainer.
+
+
+This program is free software; you can redistribute it and/or
+modify it under the terms of the GNU General   Public License
+as published by the Free Software Foundation; either version 2
+of the License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+
+This driver provides kernel support for Davicom DM9102(A)/DM9132/DM9801 ethernet cards ( CNET
+10/100 ethernet cards uses Davicom chipset too, so this driver supports CNET cards too ).If you
+didn't compile this driver as a module, it will automatically load itself on boot and print a
+line similar to::
+
+	dmfe: Davicom DM9xxx net driver, version 1.36.4 (2002-01-17)
+
+If you compiled this driver as a module, you have to load it on boot.You can load it with command::
+
+	insmod dmfe
+
+This way it will autodetect the device mode.This is the suggested way to load the module.Or you can pass
+a mode= setting to module while loading, like::
+
+	insmod dmfe mode=0 # Force 10M Half Duplex
+	insmod dmfe mode=1 # Force 100M Half Duplex
+	insmod dmfe mode=4 # Force 10M Full Duplex
+	insmod dmfe mode=5 # Force 100M Full Duplex
+
+Next you should configure your network interface with a command similar to::
+
+	ifconfig eth0 172.22.3.18
+		      ^^^^^^^^^^^
+		     Your IP Address
+
+Then you may have to modify the default routing table with command::
+
+	route add default eth0
+
+
+Now your ethernet card should be up and running.
+
+
+TODO:
+
+- Implement pci_driver::suspend() and pci_driver::resume() power management methods.
+- Check on 64 bit boxes.
+- Check and fix on big endian boxes.
+- Test and make sure PCI latency is now correct for all cases.
+
+
+Authors:
+
+Sten Wang <sten_wang@davicom.com.tw >   : Original Author
+
+Contributors:
+
+- Marcelo Tosatti <marcelo@conectiva.com.br>
+- Alan Cox <alan@lxorguk.ukuu.org.uk>
+- Jeff Garzik <jgarzik@pobox.com>
+- Vojtech Pavlik <vojtech@suse.cz>
diff --git a/Documentation/networking/device_drivers/dec/dmfe.txt b/Documentation/networking/device_drivers/dec/dmfe.txt
deleted file mode 100644
index 25320bf19c86..000000000000
--- a/Documentation/networking/device_drivers/dec/dmfe.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Note: This driver doesn't have a maintainer.
-
-Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver for Linux.
-
-This program is free software; you can redistribute it and/or
-modify it under the terms of the GNU General   Public License
-as published by the Free Software Foundation; either version 2
-of the License, or (at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-
-This driver provides kernel support for Davicom DM9102(A)/DM9132/DM9801 ethernet cards ( CNET
-10/100 ethernet cards uses Davicom chipset too, so this driver supports CNET cards too ).If you
-didn't compile this driver as a module, it will automatically load itself on boot and print a
-line similar to :
-
-	dmfe: Davicom DM9xxx net driver, version 1.36.4 (2002-01-17)
-
-If you compiled this driver as a module, you have to load it on boot.You can load it with command :
-
-	insmod dmfe
-
-This way it will autodetect the device mode.This is the suggested way to load the module.Or you can pass
-a mode= setting to module while loading, like :
-
-	insmod dmfe mode=0 # Force 10M Half Duplex
-	insmod dmfe mode=1 # Force 100M Half Duplex
-	insmod dmfe mode=4 # Force 10M Full Duplex
-	insmod dmfe mode=5 # Force 100M Full Duplex
-
-Next you should configure your network interface with a command similar to :
-
-	ifconfig eth0 172.22.3.18
-                      ^^^^^^^^^^^
-		     Your IP Address
-
-Then you may have to modify the default routing table with command :
-
-	route add default eth0
-
-
-Now your ethernet card should be up and running.
-
-
-TODO:
-
-Implement pci_driver::suspend() and pci_driver::resume() power management methods.
-Check on 64 bit boxes.
-Check and fix on big endian boxes.
-Test and make sure PCI latency is now correct for all cases.
-
-
-Authors:
-
-Sten Wang <sten_wang@davicom.com.tw >   : Original Author
-
-Contributors:
-
-Marcelo Tosatti <marcelo@conectiva.com.br>
-Alan Cox <alan@lxorguk.ukuu.org.uk>
-Jeff Garzik <jgarzik@pobox.com>
-Vojtech Pavlik <vojtech@suse.cz>
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 4ad13ffb5800..09728e964ce1 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -35,6 +35,7 @@ Contents:
    cirrus/cs89x0
    davicom/dm9000
    dec/de4x5
+   dec/dmfe
 
 .. only::  subproject and html
 
diff --git a/MAINTAINERS b/MAINTAINERS
index b5cfee17635e..f0b18c156176 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4694,7 +4694,7 @@ F:	net/ax25/sysctl_net_ax25.c
 DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
 L:	netdev@vger.kernel.org
 S:	Orphan
-F:	Documentation/networking/device_drivers/dec/dmfe.txt
+F:	Documentation/networking/device_drivers/dec/dmfe.rst
 F:	drivers/net/ethernet/dec/tulip/dmfe.c
 
 DC390/AM53C974 SCSI driver
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index 8c4245d94bb2..177f36f4b89d 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -138,7 +138,7 @@ config DM9102
 	  This driver is for DM9102(A)/DM9132/DM9801 compatible PCI cards from
 	  Davicom (<http://www.davicom.com.tw/>).  If you have such a network
 	  (Ethernet) card, say Y.  Some information is contained in the file
-	  <file:Documentation/networking/device_drivers/dec/dmfe.txt>.
+	  <file:Documentation/networking/device_drivers/dec/dmfe.rst>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called dmfe.
-- 
cgit v1.2.3


From ca705e4793f024afb8e86030e08b1e0f16dcc07c Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:43 +0200
Subject: docs: networking: device drivers: convert dlink/dl2k.txt to ReST

- add SPDX header;
- mark code blocks and literals as such;
- mark lists as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/dlink/dl2k.rst       | 314 +++++++++++++++++++++
 .../networking/device_drivers/dlink/dl2k.txt       | 282 ------------------
 Documentation/networking/device_drivers/index.rst  |   1 +
 drivers/net/ethernet/dlink/dl2k.c                  |   2 +-
 4 files changed, 316 insertions(+), 283 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/dlink/dl2k.rst
 delete mode 100644 Documentation/networking/device_drivers/dlink/dl2k.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/dlink/dl2k.rst b/Documentation/networking/device_drivers/dlink/dl2k.rst
new file mode 100644
index 000000000000..ccdb5d0d7460
--- /dev/null
+++ b/Documentation/networking/device_drivers/dlink/dl2k.rst
@@ -0,0 +1,314 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================================
+D-Link DL2000-based Gigabit Ethernet Adapter Installation
+=========================================================
+
+May 23, 2002
+
+.. Contents
+
+ - Compatibility List
+ - Quick Install
+ - Compiling the Driver
+ - Installing the Driver
+ - Option parameter
+ - Configuration Script Sample
+ - Troubleshooting
+
+
+Compatibility List
+==================
+
+Adapter Support:
+
+- D-Link DGE-550T Gigabit Ethernet Adapter.
+- D-Link DGE-550SX Gigabit Ethernet Adapter.
+- D-Link DL2000-based Gigabit Ethernet Adapter.
+
+
+The driver support Linux kernel 2.4.7 later. We had tested it
+on the environments below.
+
+ . Red Hat v6.2 (update kernel to 2.4.7)
+ . Red Hat v7.0 (update kernel to 2.4.7)
+ . Red Hat v7.1 (kernel 2.4.7)
+ . Red Hat v7.2 (kernel 2.4.7-10)
+
+
+Quick Install
+=============
+Install linux driver as following command::
+
+    1. make all
+    2. insmod dl2k.ko
+    3. ifconfig eth0 up 10.xxx.xxx.xxx netmask 255.0.0.0
+			^^^^^^^^^^^^^^^\	    ^^^^^^^^\
+					IP		     NETMASK
+
+Now eth0 should active, you can test it by "ping" or get more information by
+"ifconfig". If tested ok, continue the next step.
+
+4. ``cp dl2k.ko /lib/modules/`uname -r`/kernel/drivers/net``
+5. Add the following line to /etc/modprobe.d/dl2k.conf::
+
+	alias eth0 dl2k
+
+6. Run ``depmod`` to updated module indexes.
+7. Run ``netconfig`` or ``netconf`` to create configuration script ifcfg-eth0
+   located at /etc/sysconfig/network-scripts or create it manually.
+
+   [see - Configuration Script Sample]
+8. Driver will automatically load and configure at next boot time.
+
+Compiling the Driver
+====================
+In Linux, NIC drivers are most commonly configured as loadable modules.
+The approach of building a monolithic kernel has become obsolete. The driver
+can be compiled as part of a monolithic kernel, but is strongly discouraged.
+The remainder of this section assumes the driver is built as a loadable module.
+In the Linux environment, it is a good idea to rebuild the driver from the
+source instead of relying on a precompiled version. This approach provides
+better reliability since a precompiled driver might depend on libraries or
+kernel features that are not present in a given Linux installation.
+
+The 3 files necessary to build Linux device driver are dl2k.c, dl2k.h and
+Makefile. To compile, the Linux installation must include the gcc compiler,
+the kernel source, and the kernel headers. The Linux driver supports Linux
+Kernels 2.4.7. Copy the files to a directory and enter the following command
+to compile and link the driver:
+
+CD-ROM drive
+------------
+
+::
+
+    [root@XXX /] mkdir cdrom
+    [root@XXX /] mount -r -t iso9660 -o conv=auto /dev/cdrom /cdrom
+    [root@XXX /] cd root
+    [root@XXX /root] mkdir dl2k
+    [root@XXX /root] cd dl2k
+    [root@XXX dl2k] cp /cdrom/linux/dl2k.tgz /root/dl2k
+    [root@XXX dl2k] tar xfvz dl2k.tgz
+    [root@XXX dl2k] make all
+
+Floppy disc drive
+-----------------
+
+::
+
+    [root@XXX /] cd root
+    [root@XXX /root] mkdir dl2k
+    [root@XXX /root] cd dl2k
+    [root@XXX dl2k] mcopy a:/linux/dl2k.tgz /root/dl2k
+    [root@XXX dl2k] tar xfvz dl2k.tgz
+    [root@XXX dl2k] make all
+
+Installing the Driver
+=====================
+
+Manual Installation
+-------------------
+
+  Once the driver has been compiled, it must be loaded, enabled, and bound
+  to a protocol stack in order to establish network connectivity. To load a
+  module enter the command::
+
+    insmod dl2k.o
+
+  or::
+
+    insmod dl2k.o <optional parameter>	; add parameter
+
+---------------------------------------------------------
+
+  example::
+
+    insmod dl2k.o media=100mbps_hd
+
+   or::
+
+    insmod dl2k.o media=3
+
+   or::
+
+    insmod dl2k.o media=3,2	; for 2 cards
+
+---------------------------------------------------------
+
+  Please reference the list of the command line parameters supported by
+  the Linux device driver below.
+
+  The insmod command only loads the driver and gives it a name of the form
+  eth0, eth1, etc. To bring the NIC into an operational state,
+  it is necessary to issue the following command::
+
+    ifconfig eth0 up
+
+  Finally, to bind the driver to the active protocol (e.g., TCP/IP with
+  Linux), enter the following command::
+
+    ifup eth0
+
+  Note that this is meaningful only if the system can find a configuration
+  script that contains the necessary network information. A sample will be
+  given in the next paragraph.
+
+  The commands to unload a driver are as follows::
+
+    ifdown eth0
+    ifconfig eth0 down
+    rmmod dl2k.o
+
+  The following are the commands to list the currently loaded modules and
+  to see the current network configuration::
+
+    lsmod
+    ifconfig
+
+
+Automated Installation
+----------------------
+  This section describes how to install the driver such that it is
+  automatically loaded and configured at boot time. The following description
+  is based on a Red Hat 6.0/7.0 distribution, but it can easily be ported to
+  other distributions as well.
+
+Red Hat v6.x/v7.x
+-----------------
+  1. Copy dl2k.o to the network modules directory, typically
+     /lib/modules/2.x.x-xx/net or /lib/modules/2.x.x/kernel/drivers/net.
+  2. Locate the boot module configuration file, most commonly in the
+     /etc/modprobe.d/ directory. Add the following lines::
+
+	alias ethx dl2k
+	options dl2k <optional parameters>
+
+     where ethx will be eth0 if the NIC is the only ethernet adapter, eth1 if
+     one other ethernet adapter is installed, etc. Refer to the table in the
+     previous section for the list of optional parameters.
+  3. Locate the network configuration scripts, normally the
+     /etc/sysconfig/network-scripts directory, and create a configuration
+     script named ifcfg-ethx that contains network information.
+  4. Note that for most Linux distributions, Red Hat included, a configuration
+     utility with a graphical user interface is provided to perform steps 2
+     and 3 above.
+
+
+Parameter Description
+=====================
+You can install this driver without any additional parameter. However, if you
+are going to have extensive functions then it is necessary to set extra
+parameter. Below is a list of the command line parameters supported by the
+Linux device
+driver.
+
+
+===============================   ==============================================
+mtu=packet_size			  Specifies the maximum packet size. default
+				  is 1500.
+
+media=media_type		  Specifies the media type the NIC operates at.
+				  autosense	Autosensing active media.
+
+				  ===========	=========================
+				  10mbps_hd	10Mbps half duplex.
+				  10mbps_fd	10Mbps full duplex.
+				  100mbps_hd	100Mbps half duplex.
+				  100mbps_fd	100Mbps full duplex.
+				  1000mbps_fd	1000Mbps full duplex.
+				  1000mbps_hd	1000Mbps half duplex.
+				  0		Autosensing active media.
+				  1		10Mbps half duplex.
+				  2		10Mbps full duplex.
+				  3		100Mbps half duplex.
+				  4		100Mbps full duplex.
+				  5          	1000Mbps half duplex.
+				  6          	1000Mbps full duplex.
+				  ===========	=========================
+
+				  By default, the NIC operates at autosense.
+				  1000mbps_fd and 1000mbps_hd types are only
+				  available for fiber adapter.
+
+vlan=n				  Specifies the VLAN ID. If vlan=0, the
+				  Virtual Local Area Network (VLAN) function is
+				  disable.
+
+jumbo=[0|1]			  Specifies the jumbo frame support. If jumbo=1,
+				  the NIC accept jumbo frames. By default, this
+				  function is disabled.
+				  Jumbo frame usually improve the performance
+				  int gigabit.
+				  This feature need jumbo frame compatible
+				  remote.
+
+rx_coalesce=m			  Number of rx frame handled each interrupt.
+rx_timeout=n			  Rx DMA wait time for an interrupt.
+				  If set rx_coalesce > 0, hardware only assert
+				  an interrupt for m frames. Hardware won't
+				  assert rx interrupt until m frames received or
+				  reach timeout of n * 640 nano seconds.
+				  Set proper rx_coalesce and rx_timeout can
+				  reduce congestion collapse and overload which
+				  has been a bottleneck for high speed network.
+
+				  For example, rx_coalesce=10 rx_timeout=800.
+				  that is, hardware assert only 1 interrupt
+				  for 10 frames received or timeout of 512 us.
+
+tx_coalesce=n			  Number of tx frame handled each interrupt.
+				  Set n > 1 can reduce the interrupts
+				  congestion usually lower performance of
+				  high speed network card. Default is 16.
+
+tx_flow=[1|0]			  Specifies the Tx flow control. If tx_flow=0,
+				  the Tx flow control disable else driver
+				  autodetect.
+rx_flow=[1|0]			  Specifies the Rx flow control. If rx_flow=0,
+				  the Rx flow control enable else driver
+				  autodetect.
+===============================   ==============================================
+
+
+Configuration Script Sample
+===========================
+Here is a sample of a simple configuration script::
+
+    DEVICE=eth0
+    USERCTL=no
+    ONBOOT=yes
+    POOTPROTO=none
+    BROADCAST=207.200.5.255
+    NETWORK=207.200.5.0
+    NETMASK=255.255.255.0
+    IPADDR=207.200.5.2
+
+
+Troubleshooting
+===============
+Q1. Source files contain ^ M behind every line.
+
+    Make sure all files are Unix file format (no LF). Try the following
+    shell command to convert files::
+
+	cat dl2k.c | col -b > dl2k.tmp
+	mv dl2k.tmp dl2k.c
+
+    OR::
+
+	cat dl2k.c | tr -d "\r" > dl2k.tmp
+	mv dl2k.tmp dl2k.c
+
+Q2: Could not find header files (``*.h``)?
+
+    To compile the driver, you need kernel header files. After
+    installing the kernel source, the header files are usually located in
+    /usr/src/linux/include, which is the default include directory configured
+    in Makefile. For some distributions, there is a copy of header files in
+    /usr/src/include/linux and /usr/src/include/asm, that you can change the
+    INCLUDEDIR in Makefile to /usr/include without installing kernel source.
+
+    Note that RH 7.0 didn't provide correct header files in /usr/include,
+    including those files will make a wrong version driver.
+
diff --git a/Documentation/networking/device_drivers/dlink/dl2k.txt b/Documentation/networking/device_drivers/dlink/dl2k.txt
deleted file mode 100644
index cba74f7a3abc..000000000000
--- a/Documentation/networking/device_drivers/dlink/dl2k.txt
+++ /dev/null
@@ -1,282 +0,0 @@
-
-    D-Link DL2000-based Gigabit Ethernet Adapter Installation
-    for Linux
-    May 23, 2002
-
-Contents
-========
- - Compatibility List
- - Quick Install
- - Compiling the Driver
- - Installing the Driver
- - Option parameter
- - Configuration Script Sample
- - Troubleshooting
-
-
-Compatibility List
-=================
-Adapter Support:
-
-D-Link DGE-550T Gigabit Ethernet Adapter.
-D-Link DGE-550SX Gigabit Ethernet Adapter.
-D-Link DL2000-based Gigabit Ethernet Adapter.
-
-
-The driver support Linux kernel 2.4.7 later. We had tested it
-on the environments below.
-
- . Red Hat v6.2 (update kernel to 2.4.7)
- . Red Hat v7.0 (update kernel to 2.4.7)
- . Red Hat v7.1 (kernel 2.4.7)
- . Red Hat v7.2 (kernel 2.4.7-10)
-
-
-Quick Install
-=============
-Install linux driver as following command:
-
-1. make all
-2. insmod dl2k.ko
-3. ifconfig eth0 up 10.xxx.xxx.xxx netmask 255.0.0.0
-		    ^^^^^^^^^^^^^^^\	    ^^^^^^^^\
-				    IP		     NETMASK
-Now eth0 should active, you can test it by "ping" or get more information by
-"ifconfig". If tested ok, continue the next step.
-
-4. cp dl2k.ko /lib/modules/`uname -r`/kernel/drivers/net
-5. Add the following line to /etc/modprobe.d/dl2k.conf:
-	alias eth0 dl2k
-6. Run depmod to updated module indexes.
-7. Run "netconfig" or "netconf" to create configuration script ifcfg-eth0
-   located at /etc/sysconfig/network-scripts or create it manually.
-   [see - Configuration Script Sample]
-8. Driver will automatically load and configure at next boot time.
-
-Compiling the Driver
-====================
-  In Linux, NIC drivers are most commonly configured as loadable modules.
-The approach of building a monolithic kernel has become obsolete. The driver
-can be compiled as part of a monolithic kernel, but is strongly discouraged.
-The remainder of this section assumes the driver is built as a loadable module.
-In the Linux environment, it is a good idea to rebuild the driver from the
-source instead of relying on a precompiled version. This approach provides
-better reliability since a precompiled driver might depend on libraries or
-kernel features that are not present in a given Linux installation.
-
-The 3 files necessary to build Linux device driver are dl2k.c, dl2k.h and
-Makefile. To compile, the Linux installation must include the gcc compiler,
-the kernel source, and the kernel headers. The Linux driver supports Linux
-Kernels 2.4.7. Copy the files to a directory and enter the following command
-to compile and link the driver:
-
-CD-ROM drive
-------------
-
-[root@XXX /] mkdir cdrom
-[root@XXX /] mount -r -t iso9660 -o conv=auto /dev/cdrom /cdrom
-[root@XXX /] cd root
-[root@XXX /root] mkdir dl2k
-[root@XXX /root] cd dl2k
-[root@XXX dl2k] cp /cdrom/linux/dl2k.tgz /root/dl2k
-[root@XXX dl2k] tar xfvz dl2k.tgz
-[root@XXX dl2k] make all
-
-Floppy disc drive
------------------
-
-[root@XXX /] cd root
-[root@XXX /root] mkdir dl2k
-[root@XXX /root] cd dl2k
-[root@XXX dl2k] mcopy a:/linux/dl2k.tgz /root/dl2k
-[root@XXX dl2k] tar xfvz dl2k.tgz
-[root@XXX dl2k] make all
-
-Installing the Driver
-=====================
-
-  Manual Installation
-  -------------------
-  Once the driver has been compiled, it must be loaded, enabled, and bound
-  to a protocol stack in order to establish network connectivity. To load a
-  module enter the command:
-
-  insmod dl2k.o
-
-  or
-
-  insmod dl2k.o <optional parameter>	; add parameter
-
-  ===============================================================
-   example: insmod dl2k.o media=100mbps_hd
-   or	    insmod dl2k.o media=3
-   or	    insmod dl2k.o media=3,2	; for 2 cards
-  ===============================================================
-
-  Please reference the list of the command line parameters supported by
-  the Linux device driver below.
-
-  The insmod command only loads the driver and gives it a name of the form
-  eth0, eth1, etc. To bring the NIC into an operational state,
-  it is necessary to issue the following command:
-
-  ifconfig eth0 up
-
-  Finally, to bind the driver to the active protocol (e.g., TCP/IP with
-  Linux), enter the following command:
-
-  ifup eth0
-
-  Note that this is meaningful only if the system can find a configuration
-  script that contains the necessary network information. A sample will be
-  given in the next paragraph.
-
-  The commands to unload a driver are as follows:
-
-  ifdown eth0
-  ifconfig eth0 down
-  rmmod dl2k.o
-
-  The following are the commands to list the currently loaded modules and
-  to see the current network configuration.
-
-  lsmod
-  ifconfig
-
-
-  Automated Installation
-  ----------------------
-  This section describes how to install the driver such that it is
-  automatically loaded and configured at boot time. The following description
-  is based on a Red Hat 6.0/7.0 distribution, but it can easily be ported to
-  other distributions as well.
-
-  Red Hat v6.x/v7.x
-  -----------------
-  1. Copy dl2k.o to the network modules directory, typically
-     /lib/modules/2.x.x-xx/net or /lib/modules/2.x.x/kernel/drivers/net.
-  2. Locate the boot module configuration file, most commonly in the
-     /etc/modprobe.d/ directory. Add the following lines:
-
-     alias ethx dl2k
-     options dl2k <optional parameters>
-
-     where ethx will be eth0 if the NIC is the only ethernet adapter, eth1 if
-     one other ethernet adapter is installed, etc. Refer to the table in the
-     previous section for the list of optional parameters.
-  3. Locate the network configuration scripts, normally the
-     /etc/sysconfig/network-scripts directory, and create a configuration
-     script named ifcfg-ethx that contains network information.
-  4. Note that for most Linux distributions, Red Hat included, a configuration
-     utility with a graphical user interface is provided to perform steps 2
-     and 3 above.
-
-
-Parameter Description
-=====================
-You can install this driver without any additional parameter. However, if you
-are going to have extensive functions then it is necessary to set extra
-parameter. Below is a list of the command line parameters supported by the
-Linux device
-driver.
-
-mtu=packet_size			- Specifies the maximum packet size. default
-				  is 1500.
-
-media=media_type		- Specifies the media type the NIC operates at.
-				  autosense	Autosensing active media.
-				  10mbps_hd	10Mbps half duplex.
-				  10mbps_fd	10Mbps full duplex.
-				  100mbps_hd	100Mbps half duplex.
-				  100mbps_fd	100Mbps full duplex.
-				  1000mbps_fd	1000Mbps full duplex.
-				  1000mbps_hd	1000Mbps half duplex.
-				  0		Autosensing active media.
-				  1		10Mbps half duplex.
-				  2		10Mbps full duplex.
-				  3		100Mbps half duplex.
-				  4		100Mbps full duplex.
-				  5          	1000Mbps half duplex.
-				  6          	1000Mbps full duplex.
-
-				  By default, the NIC operates at autosense.
-				  1000mbps_fd and 1000mbps_hd types are only
-				  available for fiber adapter.
-
-vlan=n				- Specifies the VLAN ID. If vlan=0, the
-				  Virtual Local Area Network (VLAN) function is
-				  disable.
-
-jumbo=[0|1]			- Specifies the jumbo frame support. If jumbo=1,
-				  the NIC accept jumbo frames. By default, this
-				  function is disabled.
-				  Jumbo frame usually improve the performance
-				  int gigabit.
-				  This feature need jumbo frame compatible 
-				  remote.
-				  
-rx_coalesce=m			- Number of rx frame handled each interrupt.
-rx_timeout=n			- Rx DMA wait time for an interrupt. 
-				  If set rx_coalesce > 0, hardware only assert 
-				  an interrupt for m frames. Hardware won't 
-				  assert rx interrupt until m frames received or
-				  reach timeout of n * 640 nano seconds. 
-				  Set proper rx_coalesce and rx_timeout can 
-				  reduce congestion collapse and overload which
-				  has been a bottleneck for high speed network.
-				  
-				  For example, rx_coalesce=10 rx_timeout=800.
-				  that is, hardware assert only 1 interrupt 
-				  for 10 frames received or timeout of 512 us. 
-
-tx_coalesce=n			- Number of tx frame handled each interrupt.
-				  Set n > 1 can reduce the interrupts 
-				  congestion usually lower performance of
-				  high speed network card. Default is 16.
-				  
-tx_flow=[1|0]			- Specifies the Tx flow control. If tx_flow=0, 
-				  the Tx flow control disable else driver
-				  autodetect.
-rx_flow=[1|0]			- Specifies the Rx flow control. If rx_flow=0, 
-				  the Rx flow control enable else driver
-				  autodetect.
-
-
-Configuration Script Sample
-===========================
-Here is a sample of a simple configuration script:
-
-DEVICE=eth0
-USERCTL=no
-ONBOOT=yes
-POOTPROTO=none
-BROADCAST=207.200.5.255
-NETWORK=207.200.5.0
-NETMASK=255.255.255.0
-IPADDR=207.200.5.2
-
-
-Troubleshooting
-===============
-Q1. Source files contain ^ M behind every line.
-	Make sure all files are Unix file format (no LF). Try the following
-    shell command to convert files.
-
-	cat dl2k.c | col -b > dl2k.tmp
-	mv dl2k.tmp dl2k.c
-
-	OR
-
-	cat dl2k.c | tr -d "\r" > dl2k.tmp
-	mv dl2k.tmp dl2k.c
-
-Q2: Could not find header files (*.h) ?
-	To compile the driver, you need kernel header files. After
-    installing the kernel source, the header files are usually located in
-    /usr/src/linux/include, which is the default include directory configured
-    in Makefile. For some distributions, there is a copy of header files in
-    /usr/src/include/linux and /usr/src/include/asm, that you can change the
-    INCLUDEDIR in Makefile to /usr/include without installing kernel source.
-	Note that RH 7.0 didn't provide correct header files in /usr/include,
-    including those files will make a wrong version driver.
-
diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 09728e964ce1..e5d1863379cb 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -36,6 +36,7 @@ Contents:
    davicom/dm9000
    dec/de4x5
    dec/dmfe
+   dlink/dl2k
 
 .. only::  subproject and html
 
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 643090555cc7..5143722c4419 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1869,7 +1869,7 @@ Compile command:
 
 gcc -D__KERNEL__ -DMODULE -I/usr/src/linux/include -Wall -Wstrict-prototypes -O2 -c dl2k.c
 
-Read Documentation/networking/device_drivers/dlink/dl2k.txt for details.
+Read Documentation/networking/device_drivers/dlink/dl2k.rst for details.
 
 */
 
-- 
cgit v1.2.3


From 7762f5c514dce027ad2a2031390c0c19c24547af Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:49 +0200
Subject: docs: networking: device drivers: convert neterion/s2io.txt to ReST

- add SPDX header;
- add a document title;
- comment out text-only TOC from html/pdf output;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/index.rst  |   1 +
 .../networking/device_drivers/neterion/s2io.rst    | 196 +++++++++++++++++++++
 .../networking/device_drivers/neterion/s2io.txt    | 141 ---------------
 MAINTAINERS                                        |   2 +-
 drivers/net/ethernet/neterion/Kconfig              |   2 +-
 5 files changed, 199 insertions(+), 143 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/neterion/s2io.rst
 delete mode 100644 Documentation/networking/device_drivers/neterion/s2io.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 575f0043b03e..da1f8438d4ea 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -42,6 +42,7 @@ Contents:
    intel/ipw2100
    intel/ipw2200
    microsoft/netvsc
+   neterion/s2io
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/neterion/s2io.rst b/Documentation/networking/device_drivers/neterion/s2io.rst
new file mode 100644
index 000000000000..c5673ec4559b
--- /dev/null
+++ b/Documentation/networking/device_drivers/neterion/s2io.rst
@@ -0,0 +1,196 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================================
+Neterion's (Formerly S2io) Xframe I/II PCI-X 10GbE driver
+=========================================================
+
+Release notes for Neterion's (Formerly S2io) Xframe I/II PCI-X 10GbE driver.
+
+.. Contents
+  - 1.  Introduction
+  - 2.  Identifying the adapter/interface
+  - 3.  Features supported
+  - 4.  Command line parameters
+  - 5.  Performance suggestions
+  - 6.  Available Downloads
+
+
+1. Introduction
+===============
+This Linux driver supports Neterion's Xframe I PCI-X 1.0 and
+Xframe II PCI-X 2.0 adapters. It supports several features
+such as jumbo frames, MSI/MSI-X, checksum offloads, TSO, UFO and so on.
+See below for complete list of features.
+
+All features are supported for both IPv4 and IPv6.
+
+2. Identifying the adapter/interface
+====================================
+
+a. Insert the adapter(s) in your system.
+b. Build and load driver::
+
+	# insmod s2io.ko
+
+c. View log messages::
+
+	# dmesg | tail -40
+
+You will see messages similar to::
+
+	eth3: Neterion Xframe I 10GbE adapter (rev 3), Version 2.0.9.1, Intr type INTA
+	eth4: Neterion Xframe II 10GbE adapter (rev 2), Version 2.0.9.1, Intr type INTA
+	eth4: Device is on 64 bit 133MHz PCIX(M1) bus
+
+The above messages identify the adapter type(Xframe I/II), adapter revision,
+driver version, interface name(eth3, eth4), Interrupt type(INTA, MSI, MSI-X).
+In case of Xframe II, the PCI/PCI-X bus width and frequency are displayed
+as well.
+
+To associate an interface with a physical adapter use "ethtool -p <ethX>".
+The corresponding adapter's LED will blink multiple times.
+
+3. Features supported
+=====================
+a. Jumbo frames. Xframe I/II supports MTU up to 9600 bytes,
+   modifiable using ip command.
+
+b. Offloads. Supports checksum offload(TCP/UDP/IP) on transmit
+   and receive, TSO.
+
+c. Multi-buffer receive mode. Scattering of packet across multiple
+   buffers. Currently driver supports 2-buffer mode which yields
+   significant performance improvement on certain platforms(SGI Altix,
+   IBM xSeries).
+
+d. MSI/MSI-X. Can be enabled on platforms which support this feature
+   (IA64, Xeon) resulting in noticeable performance improvement(up to 7%
+   on certain platforms).
+
+e. Statistics. Comprehensive MAC-level and software statistics displayed
+   using "ethtool -S" option.
+
+f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
+   with multiple steering options.
+
+4. Command line parameters
+==========================
+
+a. tx_fifo_num
+	Number of transmit queues
+
+Valid range: 1-8
+
+Default: 1
+
+b. rx_ring_num
+	Number of receive rings
+
+Valid range: 1-8
+
+Default: 1
+
+c. tx_fifo_len
+	Size of each transmit queue
+
+Valid range: Total length of all queues should not exceed 8192
+
+Default: 4096
+
+d. rx_ring_sz
+	Size of each receive ring(in 4K blocks)
+
+Valid range: Limited by memory on system
+
+Default: 30
+
+e. intr_type
+	Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
+
+Valid values: 0, 2
+
+Default: 2
+
+5. Performance suggestions
+==========================
+
+General:
+
+a. Set MTU to maximum(9000 for switch setup, 9600 in back-to-back configuration)
+b. Set TCP windows size to optimal value.
+
+For instance, for MTU=1500 a value of 210K has been observed to result in
+good performance::
+
+	# sysctl -w net.ipv4.tcp_rmem="210000 210000 210000"
+	# sysctl -w net.ipv4.tcp_wmem="210000 210000 210000"
+
+For MTU=9000, TCP window size of 10 MB is recommended::
+
+	# sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
+	# sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
+
+Transmit performance:
+
+a. By default, the driver respects BIOS settings for PCI bus parameters.
+   However, you may want to experiment with PCI bus parameters
+   max-split-transactions(MOST) and MMRBC (use setpci command).
+
+   A MOST value of 2 has been found optimal for Opterons and 3 for Itanium.
+
+   It could be different for your hardware.
+
+   Set MMRBC to 4K**.
+
+   For example you can set
+
+   For opteron::
+
+	#setpci -d 17d5:* 62=1d
+
+   For Itanium::
+
+	#setpci -d 17d5:* 62=3d
+
+   For detailed description of the PCI registers, please see Xframe User Guide.
+
+b. Ensure Transmit Checksum offload is enabled. Use ethtool to set/verify this
+   parameter.
+
+c. Turn on TSO(using "ethtool -K")::
+
+	# ethtool -K <ethX> tso on
+
+Receive performance:
+
+a. By default, the driver respects BIOS settings for PCI bus parameters.
+   However, you may want to set PCI latency timer to 248::
+
+	#setpci -d 17d5:* LATENCY_TIMER=f8
+
+   For detailed description of the PCI registers, please see Xframe User Guide.
+
+b. Use 2-buffer mode. This results in large performance boost on
+   certain platforms(eg. SGI Altix, IBM xSeries).
+
+c. Ensure Receive Checksum offload is enabled. Use "ethtool -K ethX" command to
+   set/verify this option.
+
+d. Enable NAPI feature(in kernel configuration Device Drivers ---> Network
+   device support --->  Ethernet (10000 Mbit) ---> S2IO 10Gbe Xframe NIC) to
+   bring down CPU utilization.
+
+.. note::
+
+   For AMD opteron platforms with 8131 chipset, MMRBC=1 and MOST=1 are
+   recommended as safe parameters.
+
+For more information, please review the AMD8131 errata at
+http://vip.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/
+26310_AMD-8131_HyperTransport_PCI-X_Tunnel_Revision_Guide_rev_3_18.pdf
+
+6. Support
+==========
+
+For further support please contact either your 10GbE Xframe NIC vendor (IBM,
+HP, SGI etc.)
diff --git a/Documentation/networking/device_drivers/neterion/s2io.txt b/Documentation/networking/device_drivers/neterion/s2io.txt
deleted file mode 100644
index 0362a42f7cf4..000000000000
--- a/Documentation/networking/device_drivers/neterion/s2io.txt
+++ /dev/null
@@ -1,141 +0,0 @@
-Release notes for Neterion's (Formerly S2io) Xframe I/II PCI-X 10GbE driver.
-
-Contents
-=======
-- 1.  Introduction
-- 2.  Identifying the adapter/interface
-- 3.  Features supported
-- 4.  Command line parameters
-- 5.  Performance suggestions
-- 6.  Available Downloads 
-
-
-1.	Introduction:
-This Linux driver supports Neterion's Xframe I PCI-X 1.0 and
-Xframe II PCI-X 2.0 adapters. It supports several features 
-such as jumbo frames, MSI/MSI-X, checksum offloads, TSO, UFO and so on.
-See below for complete list of features.
-All features are supported for both IPv4 and IPv6.
-
-2.	Identifying the adapter/interface:
-a. Insert the adapter(s) in your system.
-b. Build and load driver 
-# insmod s2io.ko
-c. View log messages
-# dmesg | tail -40
-You will see messages similar to:
-eth3: Neterion Xframe I 10GbE adapter (rev 3), Version 2.0.9.1, Intr type INTA
-eth4: Neterion Xframe II 10GbE adapter (rev 2), Version 2.0.9.1, Intr type INTA
-eth4: Device is on 64 bit 133MHz PCIX(M1) bus
-
-The above messages identify the adapter type(Xframe I/II), adapter revision,
-driver version, interface name(eth3, eth4), Interrupt type(INTA, MSI, MSI-X).
-In case of Xframe II, the PCI/PCI-X bus width and frequency are displayed
-as well.
-
-To associate an interface with a physical adapter use "ethtool -p <ethX>".
-The corresponding adapter's LED will blink multiple times.
-
-3.	Features supported:
-a. Jumbo frames. Xframe I/II supports MTU up to 9600 bytes,
-modifiable using ip command.
-
-b. Offloads. Supports checksum offload(TCP/UDP/IP) on transmit
-and receive, TSO.
-
-c. Multi-buffer receive mode. Scattering of packet across multiple
-buffers. Currently driver supports 2-buffer mode which yields
-significant performance improvement on certain platforms(SGI Altix,
-IBM xSeries).
-
-d. MSI/MSI-X. Can be enabled on platforms which support this feature
-(IA64, Xeon) resulting in noticeable performance improvement(up to 7%
-on certain platforms).
-
-e. Statistics. Comprehensive MAC-level and software statistics displayed
-using "ethtool -S" option.
-
-f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
-with multiple steering options.
-
-4.  Command line parameters
-a. tx_fifo_num
-Number of transmit queues
-Valid range: 1-8
-Default: 1
-
-b. rx_ring_num
-Number of receive rings
-Valid range: 1-8
-Default: 1
-
-c. tx_fifo_len
-Size of each transmit queue
-Valid range: Total length of all queues should not exceed 8192
-Default: 4096
-
-d. rx_ring_sz 
-Size of each receive ring(in 4K blocks)
-Valid range: Limited by memory on system
-Default: 30 
-
-e. intr_type
-Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
-Valid values: 0, 2
-Default: 2
-
-5.  Performance suggestions
-General:
-a. Set MTU to maximum(9000 for switch setup, 9600 in back-to-back configuration)
-b. Set TCP windows size to optimal value. 
-For instance, for MTU=1500 a value of 210K has been observed to result in 
-good performance.
-# sysctl -w net.ipv4.tcp_rmem="210000 210000 210000"
-# sysctl -w net.ipv4.tcp_wmem="210000 210000 210000"
-For MTU=9000, TCP window size of 10 MB is recommended.
-# sysctl -w net.ipv4.tcp_rmem="10000000 10000000 10000000"
-# sysctl -w net.ipv4.tcp_wmem="10000000 10000000 10000000"
-
-Transmit performance:
-a. By default, the driver respects BIOS settings for PCI bus parameters. 
-However, you may want to experiment with PCI bus parameters 
-max-split-transactions(MOST) and MMRBC (use setpci command). 
-A MOST value of 2 has been found optimal for Opterons and 3 for Itanium.  
-It could be different for your hardware.  
-Set MMRBC to 4K**.
-
-For example you can set 
-For opteron
-#setpci -d 17d5:* 62=1d 
-For Itanium
-#setpci -d 17d5:* 62=3d 
-
-For detailed description of the PCI registers, please see Xframe User Guide.
-
-b. Ensure Transmit Checksum offload is enabled. Use ethtool to set/verify this 
-parameter.
-c. Turn on TSO(using "ethtool -K")
-# ethtool -K <ethX> tso on
-
-Receive performance:
-a. By default, the driver respects BIOS settings for PCI bus parameters. 
-However, you may want to set PCI latency timer to 248.
-#setpci -d 17d5:* LATENCY_TIMER=f8
-For detailed description of the PCI registers, please see Xframe User Guide.
-b. Use 2-buffer mode. This results in large performance boost on
-certain platforms(eg. SGI Altix, IBM xSeries).
-c. Ensure Receive Checksum offload is enabled. Use "ethtool -K ethX" command to 
-set/verify this option.
-d. Enable NAPI feature(in kernel configuration Device Drivers ---> Network 
-device support --->  Ethernet (10000 Mbit) ---> S2IO 10Gbe Xframe NIC) to 
-bring down CPU utilization.
-
-** For AMD opteron platforms with 8131 chipset, MMRBC=1 and MOST=1 are 
-recommended as safe parameters.
-For more information, please review the AMD8131 errata at
-http://vip.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/
-26310_AMD-8131_HyperTransport_PCI-X_Tunnel_Revision_Guide_rev_3_18.pdf
-
-6. Support
-For further support please contact either your 10GbE Xframe NIC vendor (IBM, 
-HP, SGI etc.)
diff --git a/MAINTAINERS b/MAINTAINERS
index ba8bb932e3da..4e3f96ee0d98 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11656,7 +11656,7 @@ NETERION 10GbE DRIVERS (s2io/vxge)
 M:	Jon Mason <jdmason@kudzu.us>
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	Documentation/networking/device_drivers/neterion/s2io.txt
+F:	Documentation/networking/device_drivers/neterion/s2io.rst
 F:	Documentation/networking/device_drivers/neterion/vxge.txt
 F:	drivers/net/ethernet/neterion/
 
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index 5e630f3a0189..c375ee08f6ea 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -27,7 +27,7 @@ config S2IO
 	  on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/device_drivers/neterion/s2io.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/s2io.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called s2io.
-- 
cgit v1.2.3


From f10727d3b68c8e03111436de94c922ffe304e21e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:50 +0200
Subject: docs: networking: device drivers: convert neterion/vxge.txt to ReST

- add SPDX header;
- adjust titles and chapters, adding proper markups;
- comment out text-only TOC from html/pdf output;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/index.rst  |   1 +
 .../networking/device_drivers/neterion/vxge.rst    | 115 +++++++++++++++++++++
 .../networking/device_drivers/neterion/vxge.txt    |  93 -----------------
 MAINTAINERS                                        |   2 +-
 drivers/net/ethernet/neterion/Kconfig              |   2 +-
 5 files changed, 118 insertions(+), 95 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/neterion/vxge.rst
 delete mode 100644 Documentation/networking/device_drivers/neterion/vxge.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index da1f8438d4ea..55837244eaad 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -43,6 +43,7 @@ Contents:
    intel/ipw2200
    microsoft/netvsc
    neterion/s2io
+   neterion/vxge
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/neterion/vxge.rst b/Documentation/networking/device_drivers/neterion/vxge.rst
new file mode 100644
index 000000000000..589c6b15c63d
--- /dev/null
+++ b/Documentation/networking/device_drivers/neterion/vxge.rst
@@ -0,0 +1,115 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================================================
+Neterion's (Formerly S2io) X3100 Series 10GbE PCIe Server Adapter Linux driver
+==============================================================================
+
+.. Contents
+
+  1) Introduction
+  2) Features supported
+  3) Configurable driver parameters
+  4) Troubleshooting
+
+1. Introduction
+===============
+
+This Linux driver supports all Neterion's X3100 series 10 GbE PCIe I/O
+Virtualized Server adapters.
+
+The X3100 series supports four modes of operation, configurable via
+firmware:
+
+	- Single function mode
+	- Multi function mode
+	- SRIOV mode
+	- MRIOV mode
+
+The functions share a 10GbE link and the pci-e bus, but hardly anything else
+inside the ASIC. Features like independent hw reset, statistics, bandwidth/
+priority allocation and guarantees, GRO, TSO, interrupt moderation etc are
+supported independently on each function.
+
+(See below for a complete list of features supported for both IPv4 and IPv6)
+
+2. Features supported
+=====================
+
+i)   Single function mode (up to 17 queues)
+
+ii)  Multi function mode (up to 17 functions)
+
+iii) PCI-SIG's I/O Virtualization
+
+       - Single Root mode: v1.0 (up to 17 functions)
+       - Multi-Root mode: v1.0 (up to 17 functions)
+
+iv)  Jumbo frames
+
+       X3100 Series supports MTU up to 9600 bytes, modifiable using
+       ip command.
+
+v)   Offloads supported: (Enabled by default)
+
+       - Checksum offload (TCP/UDP/IP) on transmit and receive paths
+       - TCP Segmentation Offload (TSO) on transmit path
+       - Generic Receive Offload (GRO) on receive path
+
+vi)  MSI-X: (Enabled by default)
+
+       Resulting in noticeable performance improvement (up to 7% on certain
+       platforms).
+
+vii) NAPI: (Enabled by default)
+
+       For better Rx interrupt moderation.
+
+viii)RTH (Receive Traffic Hash): (Enabled by default)
+
+       Receive side steering for better scaling.
+
+ix)  Statistics
+
+       Comprehensive MAC-level and software statistics displayed using
+       "ethtool -S" option.
+
+x)   Multiple hardware queues: (Enabled by default)
+
+       Up to 17 hardware based transmit and receive data channels, with
+       multiple steering options (transmit multiqueue enabled by default).
+
+3) Configurable driver parameters:
+----------------------------------
+
+i)  max_config_dev
+       Specifies maximum device functions to be enabled.
+
+       Valid range: 1-8
+
+ii) max_config_port
+       Specifies number of ports to be enabled.
+
+       Valid range: 1,2
+
+       Default: 1
+
+iii) max_config_vpath
+       Specifies maximum VPATH(s) configured for each device function.
+
+       Valid range: 1-17
+
+iv) vlan_tag_strip
+       Enables/disables vlan tag stripping from all received tagged frames that
+       are not replicated at the internal L2 switch.
+
+       Valid range: 0,1 (disabled, enabled respectively)
+
+       Default: 1
+
+v)  addr_learn_en
+       Enable learning the mac address of the guest OS interface in
+       virtualization environment.
+
+       Valid range: 0,1 (disabled, enabled respectively)
+
+       Default: 0
diff --git a/Documentation/networking/device_drivers/neterion/vxge.txt b/Documentation/networking/device_drivers/neterion/vxge.txt
deleted file mode 100644
index abfec245f97c..000000000000
--- a/Documentation/networking/device_drivers/neterion/vxge.txt
+++ /dev/null
@@ -1,93 +0,0 @@
-Neterion's (Formerly S2io) X3100 Series 10GbE PCIe Server Adapter Linux driver
-==============================================================================
-
-Contents
---------
-
-1) Introduction
-2) Features supported
-3) Configurable driver parameters
-4) Troubleshooting
-
-1) Introduction:
-----------------
-This Linux driver supports all Neterion's X3100 series 10 GbE PCIe I/O
-Virtualized Server adapters.
-The X3100 series supports four modes of operation, configurable via
-firmware -
-	Single function mode
-	Multi function mode
-	SRIOV mode
-	MRIOV mode
-The functions share a 10GbE link and the pci-e bus, but hardly anything else
-inside the ASIC. Features like independent hw reset, statistics, bandwidth/
-priority allocation and guarantees, GRO, TSO, interrupt moderation etc are
-supported independently on each function.
-
-(See below for a complete list of features supported for both IPv4 and IPv6)
-
-2) Features supported:
-----------------------
-
-i)   Single function mode (up to 17 queues)
-
-ii)  Multi function mode (up to 17 functions)
-
-iii) PCI-SIG's I/O Virtualization
-       - Single Root mode: v1.0 (up to 17 functions)
-       - Multi-Root mode: v1.0 (up to 17 functions)
-
-iv)  Jumbo frames
-       X3100 Series supports MTU up to 9600 bytes, modifiable using
-       ip command.
-
-v)   Offloads supported: (Enabled by default)
-       Checksum offload (TCP/UDP/IP) on transmit and receive paths
-       TCP Segmentation Offload (TSO) on transmit path
-       Generic Receive Offload (GRO) on receive path
-
-vi)  MSI-X: (Enabled by default)
-       Resulting in noticeable performance improvement (up to 7% on certain
-       platforms).
-
-vii) NAPI: (Enabled by default)
-       For better Rx interrupt moderation.
-
-viii)RTH (Receive Traffic Hash): (Enabled by default)
-       Receive side steering for better scaling.
-
-ix)  Statistics
-       Comprehensive MAC-level and software statistics displayed using
-       "ethtool -S" option.
-
-x)   Multiple hardware queues: (Enabled by default)
-       Up to 17 hardware based transmit and receive data channels, with
-       multiple steering options (transmit multiqueue enabled by default).
-
-3) Configurable driver parameters:
-----------------------------------
-
-i)  max_config_dev
-       Specifies maximum device functions to be enabled.
-       Valid range: 1-8
-
-ii) max_config_port
-       Specifies number of ports to be enabled.
-       Valid range: 1,2
-       Default: 1
-
-iii)max_config_vpath
-       Specifies maximum VPATH(s) configured for each device function.
-       Valid range: 1-17
-
-iv) vlan_tag_strip
-       Enables/disables vlan tag stripping from all received tagged frames that
-       are not replicated at the internal L2 switch.
-       Valid range: 0,1 (disabled, enabled respectively)
-       Default: 1
-
-v)  addr_learn_en
-       Enable learning the mac address of the guest OS interface in
-       virtualization environment.
-       Valid range: 0,1 (disabled, enabled respectively)
-       Default: 0
diff --git a/MAINTAINERS b/MAINTAINERS
index 4e3f96ee0d98..88e9e8430581 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11657,7 +11657,7 @@ M:	Jon Mason <jdmason@kudzu.us>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/neterion/s2io.rst
-F:	Documentation/networking/device_drivers/neterion/vxge.txt
+F:	Documentation/networking/device_drivers/neterion/vxge.rst
 F:	drivers/net/ethernet/neterion/
 
 NETFILTER
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index c375ee08f6ea..a82a37094579 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -42,7 +42,7 @@ config VXGE
 	  labeled as either one, depending on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/device_drivers/neterion/vxge.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/vxge.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called vxge.
-- 
cgit v1.2.3


From d6a998732b6d00b365c157a5f5ec321f3ac20cf0 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:53 +0200
Subject: docs: networking: device drivers: convert smsc/smc9.txt to ReST

- add SPDX header;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/index.rst  |  1 +
 .../networking/device_drivers/smsc/smc9.rst        | 48 ++++++++++++++++++++++
 .../networking/device_drivers/smsc/smc9.txt        | 42 -------------------
 drivers/net/ethernet/smsc/Kconfig                  |  4 +-
 4 files changed, 51 insertions(+), 44 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/smsc/smc9.rst
 delete mode 100644 Documentation/networking/device_drivers/smsc/smc9.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 77270d59943b..3479e6f576c3 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -46,6 +46,7 @@ Contents:
    neterion/vxge
    qualcomm/rmnet
    sb1000
+   smsc/smc9
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/smsc/smc9.rst b/Documentation/networking/device_drivers/smsc/smc9.rst
new file mode 100644
index 000000000000..e5eac896a631
--- /dev/null
+++ b/Documentation/networking/device_drivers/smsc/smc9.rst
@@ -0,0 +1,48 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================
+SMC 9xxxx Driver
+================
+
+Revision 0.12
+
+3/5/96
+
+Copyright 1996  Erik Stahlman
+
+Released under terms of the GNU General Public License.
+
+This file contains the instructions and caveats for my SMC9xxx driver.  You
+should not be using the driver without reading this file.
+
+Things to note about installation:
+
+  1. The driver should work on all kernels from 1.2.13 until 1.3.71.
+     (A kernel patch is supplied for 1.3.71 )
+
+  2. If you include this into the kernel, you might need to change some
+     options, such as for forcing IRQ.
+
+
+  3.  To compile as a module, run 'make'.
+      Make will give you the appropriate options for various kernel support.
+
+  4.  Loading the driver as a module::
+
+	use:   insmod smc9194.o
+	optional parameters:
+		io=xxxx    : your base address
+		irq=xx	   : your irq
+		ifport=x   :	0 for whatever is default
+				1 for twisted pair
+				2 for AUI  ( or BNC on some cards )
+
+How to obtain the latest version?
+
+FTP:
+	ftp://fenris.campus.vt.edu/smc9/smc9-12.tar.gz
+	ftp://sfbox.vt.edu/filebox/F/fenris/smc9/smc9-12.tar.gz
+
+
+Contacting me:
+    erik@mail.vt.edu
diff --git a/Documentation/networking/device_drivers/smsc/smc9.txt b/Documentation/networking/device_drivers/smsc/smc9.txt
deleted file mode 100644
index d1e15074e43d..000000000000
--- a/Documentation/networking/device_drivers/smsc/smc9.txt
+++ /dev/null
@@ -1,42 +0,0 @@
-
-SMC 9xxxx Driver 
-Revision 0.12 
-3/5/96
-Copyright 1996  Erik Stahlman 
-Released under terms of the GNU General Public License. 
-
-This file contains the instructions and caveats for my SMC9xxx driver.  You
-should not be using the driver without reading this file.  
-
-Things to note about installation:
-
-  1. The driver should work on all kernels from 1.2.13 until 1.3.71.
-	(A kernel patch is supplied for 1.3.71 )
-
-  2. If you include this into the kernel, you might need to change some
-	options, such as for forcing IRQ.   
-
- 
-  3.  To compile as a module, run 'make' .   
-	Make will give you the appropriate options for various kernel support.
- 
-  4.  Loading the driver as a module :
-
-	use:   insmod smc9194.o 
-	optional parameters:
-		io=xxxx    : your base address
-		irq=xx	   : your irq 
-		ifport=x   :	0 for whatever is default
-				1 for twisted pair
-				2 for AUI  ( or BNC on some cards )
-
-How to obtain the latest version? 
-	
-FTP:  
-	ftp://fenris.campus.vt.edu/smc9/smc9-12.tar.gz
-	ftp://sfbox.vt.edu/filebox/F/fenris/smc9/smc9-12.tar.gz 
-   
-
-Contacting me:
-    erik@mail.vt.edu
- 
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 9e1c3752b200..4d2d91ec8b41 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -28,7 +28,7 @@ config SMC9194
 	  option if you have a DELL laptop with the docking station, or
 	  another SMC9192/9194 based chipset.  Say Y if you want it compiled
 	  into the kernel, and read the file
-	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called smc9194.
@@ -44,7 +44,7 @@ config SMC91X
 	  This is a driver for SMC's 91x series of Ethernet chipsets,
 	  including the SMC91C94 and the SMC91C111. Say Y if you want it
 	  compiled into the kernel, and read the file
-	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.rst>.
 
 	  This driver is also available as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want).
-- 
cgit v1.2.3


From e9a5475e735c9603b870c6ee5189de7cd32bb080 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 1 May 2020 16:44:56 +0200
Subject: docs: networking: device drivers: convert ti/tlan.txt to ReST

- add SPDX header;
- adjust titles and chapters, adding proper markups;
- mark tables as such;
- mark code blocks and literals as such;
- adjust identation, whitespaces and blank lines where needed;
- add to networking/index.rst.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/index.rst  |   1 +
 .../networking/device_drivers/ti/tlan.rst          | 140 +++++++++++++++++++++
 .../networking/device_drivers/ti/tlan.txt          | 117 -----------------
 MAINTAINERS                                        |   2 +-
 drivers/net/ethernet/ti/Kconfig                    |   2 +-
 drivers/net/ethernet/ti/tlan.c                     |   2 +-
 6 files changed, 144 insertions(+), 120 deletions(-)
 create mode 100644 Documentation/networking/device_drivers/ti/tlan.rst
 delete mode 100644 Documentation/networking/device_drivers/ti/tlan.txt

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index 1d3b664e6921..adc0bf65fb02 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -49,6 +49,7 @@ Contents:
    smsc/smc9
    ti/cpsw_switchdev
    ti/cpsw
+   ti/tlan
 
 .. only::  subproject and html
 
diff --git a/Documentation/networking/device_drivers/ti/tlan.rst b/Documentation/networking/device_drivers/ti/tlan.rst
new file mode 100644
index 000000000000..4fdc0907f4fc
--- /dev/null
+++ b/Documentation/networking/device_drivers/ti/tlan.rst
@@ -0,0 +1,140 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+TLAN driver for Linux
+=====================
+
+:Version: 1.14a
+
+(C) 1997-1998 Caldera, Inc.
+
+(C) 1998 James Banks
+
+(C) 1999-2001 Torben Mathiasen <tmm@image.dk, torben.mathiasen@compaq.com>
+
+For driver information/updates visit http://www.compaq.com
+
+
+
+
+
+I. Supported Devices
+====================
+
+    Only PCI devices will work with this driver.
+
+    Supported:
+
+    =========	=========	===========================================
+    Vendor ID	Device ID	Name
+    =========	=========	===========================================
+    0e11	ae32		Compaq Netelligent 10/100 TX PCI UTP
+    0e11	ae34		Compaq Netelligent 10 T PCI UTP
+    0e11	ae35		Compaq Integrated NetFlex 3/P
+    0e11	ae40		Compaq Netelligent Dual 10/100 TX PCI UTP
+    0e11	ae43		Compaq Netelligent Integrated 10/100 TX UTP
+    0e11	b011		Compaq Netelligent 10/100 TX Embedded UTP
+    0e11	b012		Compaq Netelligent 10 T/2 PCI UTP/Coax
+    0e11	b030		Compaq Netelligent 10/100 TX UTP
+    0e11	f130		Compaq NetFlex 3/P
+    0e11	f150		Compaq NetFlex 3/P
+    108d	0012		Olicom OC-2325
+    108d	0013		Olicom OC-2183
+    108d	0014		Olicom OC-2326
+    =========	=========	===========================================
+
+
+    Caveats:
+
+    I am not sure if 100BaseTX daughterboards (for those cards which
+    support such things) will work.  I haven't had any solid evidence
+    either way.
+
+    However, if a card supports 100BaseTx without requiring an add
+    on daughterboard, it should work with 100BaseTx.
+
+    The "Netelligent 10 T/2 PCI UTP/Coax" (b012) device is untested,
+    but I do not expect any problems.
+
+
+II. Driver Options
+==================
+
+	1. You can append debug=x to the end of the insmod line to get
+	   debug messages, where x is a bit field where the bits mean
+	   the following:
+
+	   ====		=====================================
+	   0x01		Turn on general debugging messages.
+	   0x02		Turn on receive debugging messages.
+	   0x04		Turn on transmit debugging messages.
+	   0x08		Turn on list debugging messages.
+	   ====		=====================================
+
+	2. You can append aui=1 to the end of the insmod line to cause
+	   the adapter to use the AUI interface instead of the 10 Base T
+	   interface.  This is also what to do if you want to use the BNC
+	   connector on a TLAN based device.  (Setting this option on a
+	   device that does not have an AUI/BNC connector will probably
+	   cause it to not function correctly.)
+
+	3. You can set duplex=1 to force half duplex, and duplex=2 to
+	   force full duplex.
+
+	4. You can set speed=10 to force 10Mbs operation, and speed=100
+	   to force 100Mbs operation. (I'm not sure what will happen
+	   if a card which only supports 10Mbs is forced into 100Mbs
+	   mode.)
+
+	5. You have to use speed=X duplex=Y together now. If you just
+	   do "insmod tlan.o speed=100" the driver will do Auto-Neg.
+	   To force a 10Mbps Half-Duplex link do "insmod tlan.o speed=10
+	   duplex=1".
+
+	6. If the driver is built into the kernel, you can use the 3rd
+	   and 4th parameters to set aui and debug respectively.  For
+	   example::
+
+		ether=0,0,0x1,0x7,eth0
+
+	   This sets aui to 0x1 and debug to 0x7, assuming eth0 is a
+	   supported TLAN device.
+
+	   The bits in the third byte are assigned as follows:
+
+		====   ===============
+		0x01   aui
+		0x02   use half duplex
+		0x04   use full duplex
+		0x08   use 10BaseT
+		0x10   use 100BaseTx
+		====   ===============
+
+	   You also need to set both speed and duplex settings when forcing
+	   speeds with kernel-parameters.
+	   ether=0,0,0x12,0,eth0 will force link to 100Mbps Half-Duplex.
+
+	7. If you have more than one tlan adapter in your system, you can
+	   use the above options on a per adapter basis. To force a 100Mbit/HD
+	   link with your eth1 adapter use::
+
+		insmod tlan speed=0,100 duplex=0,1
+
+	   Now eth0 will use auto-neg and eth1 will be forced to 100Mbit/HD.
+	   Note that the tlan driver supports a maximum of 8 adapters.
+
+
+III. Things to try if you have problems
+=======================================
+
+	1. Make sure your card's PCI id is among those listed in
+	   section I, above.
+	2. Make sure routing is correct.
+	3. Try forcing different speed/duplex settings
+
+
+There is also a tlan mailing list which you can join by sending "subscribe tlan"
+in the body of an email to majordomo@vuser.vu.union.edu.
+
+There is also a tlan website at http://www.compaq.com
+
diff --git a/Documentation/networking/device_drivers/ti/tlan.txt b/Documentation/networking/device_drivers/ti/tlan.txt
deleted file mode 100644
index 34550dfcef74..000000000000
--- a/Documentation/networking/device_drivers/ti/tlan.txt
+++ /dev/null
@@ -1,117 +0,0 @@
-(C) 1997-1998 Caldera, Inc.
-(C) 1998 James Banks
-(C) 1999-2001 Torben Mathiasen <tmm@image.dk, torben.mathiasen@compaq.com>
-
-For driver information/updates visit http://www.compaq.com
-
-
-TLAN driver for Linux, version 1.14a
-README
-
-
-I.  Supported Devices.
-
-    Only PCI devices will work with this driver.
-
-    Supported:
-    Vendor ID	Device ID	Name
-    0e11	ae32		Compaq Netelligent 10/100 TX PCI UTP
-    0e11	ae34		Compaq Netelligent 10 T PCI UTP
-    0e11	ae35		Compaq Integrated NetFlex 3/P
-    0e11	ae40		Compaq Netelligent Dual 10/100 TX PCI UTP
-    0e11	ae43		Compaq Netelligent Integrated 10/100 TX UTP
-    0e11	b011		Compaq Netelligent 10/100 TX Embedded UTP
-    0e11	b012		Compaq Netelligent 10 T/2 PCI UTP/Coax
-    0e11	b030		Compaq Netelligent 10/100 TX UTP
-    0e11	f130		Compaq NetFlex 3/P
-    0e11	f150		Compaq NetFlex 3/P
-    108d	0012		Olicom OC-2325	
-    108d	0013		Olicom OC-2183
-    108d	0014		Olicom OC-2326	
-
-
-    Caveats:
-    
-    I am not sure if 100BaseTX daughterboards (for those cards which
-    support such things) will work.  I haven't had any solid evidence
-    either way.
-
-    However, if a card supports 100BaseTx without requiring an add
-    on daughterboard, it should work with 100BaseTx.
-
-    The "Netelligent 10 T/2 PCI UTP/Coax" (b012) device is untested,
-    but I do not expect any problems.
-    
-
-II.   Driver Options
-	1. You can append debug=x to the end of the insmod line to get
-           debug messages, where x is a bit field where the bits mean
-	   the following:
-	   
-	   0x01		Turn on general debugging messages.
-	   0x02		Turn on receive debugging messages.
-	   0x04		Turn on transmit debugging messages.
-	   0x08		Turn on list debugging messages.
-
-	2. You can append aui=1 to the end of the insmod line to cause
-           the adapter to use the AUI interface instead of the 10 Base T
-           interface.  This is also what to do if you want to use the BNC
-	   connector on a TLAN based device.  (Setting this option on a
-	   device that does not have an AUI/BNC connector will probably
-	   cause it to not function correctly.)
-
-	3. You can set duplex=1 to force half duplex, and duplex=2 to
-	   force full duplex.
-
-	4. You can set speed=10 to force 10Mbs operation, and speed=100
-	   to force 100Mbs operation. (I'm not sure what will happen
-	   if a card which only supports 10Mbs is forced into 100Mbs
-	   mode.)
-
-	5. You have to use speed=X duplex=Y together now. If you just
-	   do "insmod tlan.o speed=100" the driver will do Auto-Neg.
-	   To force a 10Mbps Half-Duplex link do "insmod tlan.o speed=10 
-	   duplex=1".
-
-	6. If the driver is built into the kernel, you can use the 3rd
-	   and 4th parameters to set aui and debug respectively.  For
-	   example:
-
-	   ether=0,0,0x1,0x7,eth0
-
-	   This sets aui to 0x1 and debug to 0x7, assuming eth0 is a
-	   supported TLAN device.
-
-	   The bits in the third byte are assigned as follows:
-
-		0x01 = aui
-		0x02 = use half duplex
-		0x04 = use full duplex
-		0x08 = use 10BaseT
-		0x10 = use 100BaseTx
-
-	   You also need to set both speed and duplex settings when forcing
-	   speeds with kernel-parameters. 
-	   ether=0,0,0x12,0,eth0 will force link to 100Mbps Half-Duplex.
-
-	7. If you have more than one tlan adapter in your system, you can
-	   use the above options on a per adapter basis. To force a 100Mbit/HD
-	   link with your eth1 adapter use:
-	   
-	   insmod tlan speed=0,100 duplex=0,1
-
-	   Now eth0 will use auto-neg and eth1 will be forced to 100Mbit/HD.
-	   Note that the tlan driver supports a maximum of 8 adapters.
-
-
-III.  Things to try if you have problems.
-	1. Make sure your card's PCI id is among those listed in
-	   section I, above.
-	2. Make sure routing is correct.
-	3. Try forcing different speed/duplex settings
-
-
-There is also a tlan mailing list which you can join by sending "subscribe tlan"
-in the body of an email to majordomo@vuser.vu.union.edu.
-There is also a tlan website at http://www.compaq.com
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 94afbf577a06..38dbfbfccb5e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16971,7 +16971,7 @@ M:	Samuel Chessman <chessman@tux.org>
 L:	tlan-devel@lists.sourceforge.net (subscribers-only)
 S:	Maintained
 W:	http://sourceforge.net/projects/tlan/
-F:	Documentation/networking/device_drivers/ti/tlan.txt
+F:	Documentation/networking/device_drivers/ti/tlan.rst
 F:	drivers/net/ethernet/ti/tlan.*
 
 TM6000 VIDEO4LINUX DRIVER
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 89cec778cf2d..7b0ad777828d 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -138,7 +138,7 @@ config TLAN
 
 	  Devices currently supported by this driver are Compaq Netelligent,
 	  Compaq NetFlex and Olicom cards.  Please read the file
-	  <file:Documentation/networking/device_drivers/ti/tlan.txt>
+	  <file:Documentation/networking/device_drivers/ti/tlan.rst>
 	  for more details.
 
 	  To compile this driver as a module, choose M here. The module
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index ad465202980a..857709828058 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -70,7 +70,7 @@ MODULE_DESCRIPTION("Driver for TI ThunderLAN based ethernet PCI adapters");
 MODULE_LICENSE("GPL");
 
 /* Turn on debugging.
- * See Documentation/networking/device_drivers/ti/tlan.txt for details
+ * See Documentation/networking/device_drivers/ti/tlan.rst for details
  */
 static  int		debug;
 module_param(debug, int, 0);
-- 
cgit v1.2.3


From f773d5118b6ce63d645d404bf29075252b890c66 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 19:22:29 +0200
Subject: r8169: remove redundant driver message when entering promiscuous mode

Net core -  __dev_set_promiscuity - prints a message already when
promiscuous mode in entered/left, therefore we don't have to do this
in the driver too. Also the driver message would be misleading
(would be because "link" message level is disabled per default)
because it would print "promisc mode enabled" even if it's being
left. Reason is that __dev_change_flags() calls dev_set_rx_mode()
before touching the promisc flag.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0f869a761d8c..bfa199b36652 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2634,8 +2634,6 @@ static void rtl_set_rx_mode(struct net_device *dev)
 	u32 tmp;
 
 	if (dev->flags & IFF_PROMISC) {
-		/* Unconditionally log net taps. */
-		netif_notice(tp, link, dev, "Promiscuous mode enabled\n");
 		rx_mode |= AcceptAllPhys;
 	} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
 		   dev->flags & IFF_ALLMULTI ||
-- 
cgit v1.2.3


From d56f58cec90d46a60d1acb15954b96d89aa154ee Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 19:23:36 +0200
Subject: r8169: simplify counter handling

The counter handling functions can only fail if rtl8169_do_counters()
times out. In the poll function we emit an error message in case of
timeout, therefore we don't have to propagate the timeout all the
way up just to print another message basically saying the same.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 38 +++++++++++--------------------
 1 file changed, 13 insertions(+), 25 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index bfa199b36652..1c2ea7506784 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1625,7 +1625,7 @@ DECLARE_RTL_COND(rtl_counters_cond)
 	return RTL_R32(tp, CounterAddrLow) & (CounterReset | CounterDump);
 }
 
-static bool rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd)
+static void rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd)
 {
 	dma_addr_t paddr = tp->counters_phys_addr;
 	u32 cmd;
@@ -1636,22 +1636,20 @@ static bool rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd)
 	RTL_W32(tp, CounterAddrLow, cmd);
 	RTL_W32(tp, CounterAddrLow, cmd | counter_cmd);
 
-	return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
+	rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
 }
 
-static bool rtl8169_reset_counters(struct rtl8169_private *tp)
+static void rtl8169_reset_counters(struct rtl8169_private *tp)
 {
 	/*
 	 * Versions prior to RTL_GIGA_MAC_VER_19 don't support resetting the
 	 * tally counters.
 	 */
-	if (tp->mac_version < RTL_GIGA_MAC_VER_19)
-		return true;
-
-	return rtl8169_do_counters(tp, CounterReset);
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_19)
+		rtl8169_do_counters(tp, CounterReset);
 }
 
-static bool rtl8169_update_counters(struct rtl8169_private *tp)
+static void rtl8169_update_counters(struct rtl8169_private *tp)
 {
 	u8 val = RTL_R8(tp, ChipCmd);
 
@@ -1659,16 +1657,13 @@ static bool rtl8169_update_counters(struct rtl8169_private *tp)
 	 * Some chips are unable to dump tally counters when the receiver
 	 * is disabled. If 0xff chip may be in a PCI power-save state.
 	 */
-	if (!(val & CmdRxEnb) || val == 0xff)
-		return true;
-
-	return rtl8169_do_counters(tp, CounterDump);
+	if (val & CmdRxEnb && val != 0xff)
+		rtl8169_do_counters(tp, CounterDump);
 }
 
-static bool rtl8169_init_counter_offsets(struct rtl8169_private *tp)
+static void rtl8169_init_counter_offsets(struct rtl8169_private *tp)
 {
 	struct rtl8169_counters *counters = tp->counters;
-	bool ret = false;
 
 	/*
 	 * rtl8169_init_counter_offsets is called from rtl_open.  On chip
@@ -1686,22 +1681,16 @@ static bool rtl8169_init_counter_offsets(struct rtl8169_private *tp)
 	 */
 
 	if (tp->tc_offset.inited)
-		return true;
-
-	/* If both, reset and update fail, propagate to caller. */
-	if (rtl8169_reset_counters(tp))
-		ret = true;
+		return;
 
-	if (rtl8169_update_counters(tp))
-		ret = true;
+	rtl8169_reset_counters(tp);
+	rtl8169_update_counters(tp);
 
 	tp->tc_offset.tx_errors = counters->tx_errors;
 	tp->tc_offset.tx_multi_collision = counters->tx_multi_collision;
 	tp->tc_offset.tx_aborted = counters->tx_aborted;
 	tp->tc_offset.rx_missed = counters->rx_missed;
 	tp->tc_offset.inited = true;
-
-	return ret;
 }
 
 static void rtl8169_get_ethtool_stats(struct net_device *dev,
@@ -4759,8 +4748,7 @@ static int rtl_open(struct net_device *dev)
 
 	rtl_hw_start(tp);
 
-	if (!rtl8169_init_counter_offsets(tp))
-		netif_warn(tp, hw, dev, "counter reset/update failed\n");
+	rtl8169_init_counter_offsets(tp);
 
 	phy_start(tp->phydev);
 	netif_start_queue(dev);
-- 
cgit v1.2.3


From 3bf6ff3cec5d2b1d8185e76c7fae48ff7021ebd0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 19:24:47 +0200
Subject: r8169: remove "out of memory" error message from rtl_request_firmware

When preparing an unrelated change, checkpatch complained about this
redundant out-of-memory message. Therefore remove it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1c2ea7506784..768721d565ae 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2507,10 +2507,8 @@ static void rtl_request_firmware(struct rtl8169_private *tp)
 		return;
 
 	rtl_fw = kzalloc(sizeof(*rtl_fw), GFP_KERNEL);
-	if (!rtl_fw) {
-		netif_warn(tp, ifup, tp->dev, "Unable to load firmware, out of memory\n");
+	if (!rtl_fw)
 		return;
-	}
 
 	rtl_fw->phy_write = rtl_writephy;
 	rtl_fw->phy_read = rtl_readphy;
-- 
cgit v1.2.3


From 93882c6f210af5e318cdbe40b320053cff0fa033 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 19:26:22 +0200
Subject: r8169: switch from netif_xxx message functions to netdev_xxx

Considering the few messages we have in the driver, there's not really
a benefit in being able to control them on a message type level.
Therefore simplify the code and switch to the netdev_xxx message
functions. In addition add net_ratelimit() to messages that can be
printed from a hot path.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 68 ++++++++++---------------------
 1 file changed, 22 insertions(+), 46 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 768721d565ae..8b665f2ec21f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -59,9 +59,6 @@
 #define FIRMWARE_8107E_2	"rtl_nic/rtl8107e-2.fw"
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 
-#define R8169_MSG_DEFAULT \
-	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
-
 /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
    The RTL chips use a 64 element hash table based on the Ethernet CRC. */
 #define	MC_FILTER_LIMIT	32
@@ -179,10 +176,6 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl);
 
-static struct {
-	u32 msg_enable;
-} debug = { -1 };
-
 enum rtl_registers {
 	MAC0		= 0,	/* Ethernet hardware address. */
 	MAC4		= 4,
@@ -604,7 +597,6 @@ struct rtl8169_private {
 	struct net_device *dev;
 	struct phy_device *phydev;
 	struct napi_struct napi;
-	u32 msg_enable;
 	enum mac_version mac_version;
 	u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */
 	u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */
@@ -646,8 +638,6 @@ typedef void (*rtl_generic_fct)(struct rtl8169_private *tp);
 
 MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
 MODULE_DESCRIPTION("RealTek RTL-8169 Gigabit Ethernet driver");
-module_param_named(debug, debug.msg_enable, int, 0);
-MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
 MODULE_SOFTDEP("pre: realtek");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
@@ -751,8 +741,10 @@ static bool rtl_loop_wait(struct rtl8169_private *tp, const struct rtl_cond *c,
 			return true;
 		delay(d);
 	}
-	netif_err(tp, drv, tp->dev, "%s == %d (loop: %d, delay: %d).\n",
-		  c->msg, !high, n, d);
+
+	if (net_ratelimit())
+		netdev_err(tp->dev, "%s == %d (loop: %d, delay: %d).\n",
+			   c->msg, !high, n, d);
 	return false;
 }
 
@@ -797,7 +789,8 @@ static bool name ## _check(struct rtl8169_private *tp)
 static bool rtl_ocp_reg_failure(struct rtl8169_private *tp, u32 reg)
 {
 	if (reg & 0xffff0001) {
-		netif_err(tp, drv, tp->dev, "Invalid ocp reg %x!\n", reg);
+		if (net_ratelimit())
+			netdev_err(tp->dev, "Invalid ocp reg %x!\n", reg);
 		return true;
 	}
 	return false;
@@ -1580,20 +1573,6 @@ static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	rtl_unlock_work(tp);
 }
 
-static u32 rtl8169_get_msglevel(struct net_device *dev)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	return tp->msg_enable;
-}
-
-static void rtl8169_set_msglevel(struct net_device *dev, u32 value)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	tp->msg_enable = value;
-}
-
 static const char rtl8169_gstrings[][ETH_GSTRING_LEN] = {
 	"tx_packets",
 	"rx_packets",
@@ -1985,8 +1964,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_link		= ethtool_op_get_link,
 	.get_coalesce		= rtl_get_coalesce,
 	.set_coalesce		= rtl_set_coalesce,
-	.get_msglevel		= rtl8169_get_msglevel,
-	.set_msglevel		= rtl8169_set_msglevel,
 	.get_regs		= rtl8169_get_regs,
 	.get_wol		= rtl8169_get_wol,
 	.set_wol		= rtl8169_set_wol,
@@ -3868,8 +3845,7 @@ static struct page *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
 
 	mapping = dma_map_page(d, data, 0, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(d, mapping))) {
-		if (net_ratelimit())
-			netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n");
+		netdev_err(tp->dev, "Failed to map RX DMA!\n");
 		__free_pages(data, get_order(R8169_RX_BUF_SIZE));
 		return NULL;
 	}
@@ -4006,7 +3982,7 @@ static int rtl8169_tx_map(struct rtl8169_private *tp, const u32 *opts, u32 len,
 	ret = dma_mapping_error(d, mapping);
 	if (unlikely(ret)) {
 		if (net_ratelimit())
-			netif_err(tp, drv, tp->dev, "Failed to map TX data!\n");
+			netdev_err(tp->dev, "Failed to map TX data!\n");
 		return ret;
 	}
 
@@ -4172,7 +4148,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	txd_first = tp->TxDescArray + entry;
 
 	if (unlikely(!rtl_tx_slots_avail(tp, frags))) {
-		netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n");
+		if (net_ratelimit())
+			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
 		goto err_stop_0;
 	}
 
@@ -4334,9 +4311,9 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 
 	pci_status_errs = pci_status_get_and_clear_errors(pdev);
 
-	netif_err(tp, intr, dev, "PCI error (cmd = 0x%04x, status_errs = 0x%04x)\n",
-		  pci_cmd, pci_status_errs);
-
+	if (net_ratelimit())
+		netdev_err(dev, "PCI error (cmd = 0x%04x, status_errs = 0x%04x)\n",
+			   pci_cmd, pci_status_errs);
 	/*
 	 * The recovery sequence below admits a very elaborated explanation:
 	 * - it seems to work;
@@ -4454,8 +4431,9 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
 		dma_rmb();
 
 		if (unlikely(status & RxRES)) {
-			netif_info(tp, rx_err, dev, "Rx ERROR. status = %08x\n",
-				   status);
+			if (net_ratelimit())
+				netdev_warn(dev, "Rx ERROR. status = %08x\n",
+					    status);
 			dev->stats.rx_errors++;
 			if (status & (RxRWT | RxRUNT))
 				dev->stats.rx_length_errors++;
@@ -5326,7 +5304,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp = netdev_priv(dev);
 	tp->dev = dev;
 	tp->pci_dev = pdev;
-	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
 	tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1;
 	tp->eee_adv = -1;
 	tp->ocp_base = OCP_STD_PHY_BASE;
@@ -5484,15 +5461,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
-	netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n",
-		   rtl_chip_infos[chipset].name, dev->dev_addr, xid,
-		   pci_irq_vector(pdev, 0));
+	netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
+		    rtl_chip_infos[chipset].name, dev->dev_addr, xid,
+		    pci_irq_vector(pdev, 0));
 
 	if (jumbo_max)
-		netif_info(tp, probe, dev,
-			   "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
-			   jumbo_max, tp->mac_version <= RTL_GIGA_MAC_VER_06 ?
-			   "ok" : "ko");
+		netdev_info(dev, "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
+			    jumbo_max, tp->mac_version <= RTL_GIGA_MAC_VER_06 ?
+			    "ok" : "ko");
 
 	if (r8168_check_dash(tp))
 		rtl8168_driver_start(tp);
-- 
cgit v1.2.3


From 1bb694e208395816fee278ca46d2796727d3f4a9 Mon Sep 17 00:00:00 2001
From: Christophe Roullier <christophe.roullier@st.com>
Date: Mon, 27 Apr 2020 12:00:38 +0200
Subject: net: ethernet: stmmac: simplify phy modes management for stm32

No new feature, just to simplify stm32 part to be easier to use.
Add by default all Ethernet clocks in DT, and activate or not in function
of phy mode, clock frequency, if property "st,ext-phyclk" is set or not.
Keep backward compatibility
--------------------------------------------------------------------------
|PHY_MODE |    Normal | PHY wo crystal|   PHY wo crystal   |  No 125Mhz  |
|         |	      |      25MHz    |        50MHz       |  from PHY   |
--------------------------------------------------------------------------
|  MII    |	 -    |     eth-ck    |       n/a          |	    n/a  |
|         |	      | st,ext-phyclk |                    |             |
--------------------------------------------------------------------------
|  GMII   |	 -    |     eth-ck    |       n/a          |	    n/a  |
|         |	      | st,ext-phyclk |                    |             |
--------------------------------------------------------------------------
| RGMII   |	 -    |     eth-ck    |       n/a          |     eth-ck  |
|         |	     | st,ext-phyclk |                    |st,eth-clk-sel|
|         |	     |               |                    |       or     |
|         |	     |               |                    | st,ext-phyclk|
----------------==--------------------------------------------------------
| RMII    |	 -   |     eth-ck    |      eth-ck        |       n/a    |
|         | 	     | st,ext-phyclk | st,eth-ref-clk-sel |              |
|         | 	     |               | or st,ext-phyclk   |              |
--------------------------------------------------------------------------

Signed-off-by: Christophe Roullier <christophe.roullier@st.com>
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c | 74 ++++++++++++++---------
 1 file changed, 44 insertions(+), 30 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index b2dc99289687..5d4df4c5254e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -29,6 +29,11 @@
 #define SYSCFG_PMCR_ETH_CLK_SEL		BIT(16)
 #define SYSCFG_PMCR_ETH_REF_CLK_SEL	BIT(17)
 
+/* CLOCK feed to PHY*/
+#define ETH_CK_F_25M	25000000
+#define ETH_CK_F_50M	50000000
+#define ETH_CK_F_125M	125000000
+
 /*  Ethernet PHY interface selection in register SYSCFG Configuration
  *------------------------------------------
  * src	 |BIT(23)| BIT(22)| BIT(21)|BIT(20)|
@@ -58,33 +63,20 @@
  *|         |        |      25MHz    |        50MHz       |                  |
  * ---------------------------------------------------------------------------
  *|  MII    |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
- *|         |        |		     |                    |		     |
+ *|         |        | st,ext-phyclk |                    |		     |
  * ---------------------------------------------------------------------------
  *|  GMII   |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
- *|         |        |               |                    |		     |
+ *|         |        | st,ext-phyclk |                    |		     |
  * ---------------------------------------------------------------------------
- *| RGMII   |	 -   |     eth-ck    |	      n/a	  |  eth-ck (no pin) |
- *|         |        |               |                    |  st,eth-clk-sel  |
+ *| RGMII   |	 -   |     eth-ck    |	      n/a	  |      eth-ck      |
+ *|         |        | st,ext-phyclk |                    | st,eth-clk-sel or|
+ *|         |        |               |                    | st,ext-phyclk    |
  * ---------------------------------------------------------------------------
  *| RMII    |	 -   |     eth-ck    |	    eth-ck        |	  n/a        |
- *|         |        |		     | st,eth-ref-clk-sel |		     |
+ *|         |        | st,ext-phyclk | st,eth-ref-clk-sel |		     |
+ *|         |        |               | or st,ext-phyclk   |		     |
  * ---------------------------------------------------------------------------
  *
- * BIT(17) : set this bit in RMII mode when you have PHY without crystal 50MHz
- * BIT(16) : set this bit in GMII/RGMII PHY when you do not want use 125Mhz
- * from PHY
- *-----------------------------------------------------
- * src	 |         BIT(17)       |       BIT(16)      |
- *-----------------------------------------------------
- * MII   |           n/a	 |         n/a        |
- *-----------------------------------------------------
- * GMII  |           n/a         |   st,eth-clk-sel   |
- *-----------------------------------------------------
- * RGMII |           n/a         |   st,eth-clk-sel   |
- *-----------------------------------------------------
- * RMII  |   st,eth-ref-clk-sel	 |         n/a        |
- *-----------------------------------------------------
- *
  */
 
 struct stm32_dwmac {
@@ -93,6 +85,8 @@ struct stm32_dwmac {
 	struct clk *clk_eth_ck;
 	struct clk *clk_ethstp;
 	struct clk *syscfg_clk;
+	int ext_phyclk;
+	int enable_eth_ck;
 	int eth_clk_sel_reg;
 	int eth_ref_clk_sel_reg;
 	int irq_pwr_wakeup;
@@ -155,14 +149,17 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 		ret = clk_prepare_enable(dwmac->syscfg_clk);
 		if (ret)
 			return ret;
-		ret = clk_prepare_enable(dwmac->clk_eth_ck);
-		if (ret) {
-			clk_disable_unprepare(dwmac->syscfg_clk);
-			return ret;
+		if (dwmac->enable_eth_ck) {
+			ret = clk_prepare_enable(dwmac->clk_eth_ck);
+			if (ret) {
+				clk_disable_unprepare(dwmac->syscfg_clk);
+				return ret;
+			}
 		}
 	} else {
 		clk_disable_unprepare(dwmac->syscfg_clk);
-		clk_disable_unprepare(dwmac->clk_eth_ck);
+		if (dwmac->enable_eth_ck)
+			clk_disable_unprepare(dwmac->clk_eth_ck);
 	}
 	return ret;
 }
@@ -170,24 +167,34 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct stm32_dwmac *dwmac = plat_dat->bsp_priv;
-	u32 reg = dwmac->mode_reg;
+	u32 reg = dwmac->mode_reg, clk_rate;
 	int val;
 
+	clk_rate = clk_get_rate(dwmac->clk_eth_ck);
+	dwmac->enable_eth_ck = false;
 	switch (plat_dat->interface) {
 	case PHY_INTERFACE_MODE_MII:
+		if (clk_rate == ETH_CK_F_25M && dwmac->ext_phyclk)
+			dwmac->enable_eth_ck = true;
 		val = SYSCFG_PMCR_ETH_SEL_MII;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_MII\n");
 		break;
 	case PHY_INTERFACE_MODE_GMII:
 		val = SYSCFG_PMCR_ETH_SEL_GMII;
-		if (dwmac->eth_clk_sel_reg)
+		if (clk_rate == ETH_CK_F_25M &&
+		    (dwmac->eth_clk_sel_reg || dwmac->ext_phyclk)) {
+			dwmac->enable_eth_ck = true;
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
+		}
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_GMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RMII:
 		val = SYSCFG_PMCR_ETH_SEL_RMII;
-		if (dwmac->eth_ref_clk_sel_reg)
+		if ((clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_50M) &&
+		    (dwmac->eth_ref_clk_sel_reg || dwmac->ext_phyclk)) {
+			dwmac->enable_eth_ck = true;
 			val |= SYSCFG_PMCR_ETH_REF_CLK_SEL;
+		}
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
@@ -195,8 +202,11 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val = SYSCFG_PMCR_ETH_SEL_RGMII;
-		if (dwmac->eth_clk_sel_reg)
+		if ((clk_rate == ETH_CK_F_25M || clk_rate == ETH_CK_F_125M) &&
+		    (dwmac->eth_clk_sel_reg || dwmac->ext_phyclk)) {
+			dwmac->enable_eth_ck = true;
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
+		}
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RGMII\n");
 		break;
 	default:
@@ -294,6 +304,9 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 	struct device_node *np = dev->of_node;
 	int err = 0;
 
+	/* Ethernet PHY have no crystal */
+	dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
+
 	/* Gigabit Ethernet 125MHz clock selection. */
 	dwmac->eth_clk_sel_reg = of_property_read_bool(np, "st,eth-clk-sel");
 
@@ -431,7 +444,8 @@ static int stm32mp1_suspend(struct stm32_dwmac *dwmac)
 
 	clk_disable_unprepare(dwmac->clk_tx);
 	clk_disable_unprepare(dwmac->syscfg_clk);
-	clk_disable_unprepare(dwmac->clk_eth_ck);
+	if (dwmac->enable_eth_ck)
+		clk_disable_unprepare(dwmac->clk_eth_ck);
 
 	return ret;
 }
-- 
cgit v1.2.3


From e00edb4efbbc07425441a3be2aa87abaf5800d96 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 29 Apr 2020 02:52:20 +0000
Subject: drivers: net: davinci_mdio: fix potential NULL dereference in
 davinci_mdio_probe()

platform_get_resource() may fail and return NULL, so we should
better check it's return value to avoid a NULL pointer dereference
since devm_ioremap() does not check input parameters for null.

This is detected by Coccinelle semantic patch.

@@
expression pdev, res, n, t, e, e1, e2;
@@

res = \(platform_get_resource\|platform_get_resource_byname\)(pdev, t, n);
+ if (!res)
+   return -EINVAL;
... when != res == NULL
e = devm_ioremap(e1, res->start, e2);

Fixes: 03f66f067560 ("net: ethernet: ti: davinci_mdio: use devm_ioremap()")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_mdio.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 38b7f6d35759..702fdc393da0 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -397,6 +397,8 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	data->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	data->regs = devm_ioremap(dev, res->start, resource_size(res));
 	if (!data->regs)
 		return -ENOMEM;
-- 
cgit v1.2.3


From fe677b057e33a0345570064c0d82ef6956b005d6 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:29 +0300
Subject: net: atlantic: update company name in the driver description

Aquantia is now part of Marvell. Thus, update the driver description.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_cfg.h    | 4 ++--
 drivers/net/ethernet/aquantia/atlantic/aq_common.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 7560f5506e55..52b9833fda99 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -80,8 +80,8 @@
 
 #define AQ_CFG_LOCK_TRYS   100U
 
-#define AQ_CFG_DRV_AUTHOR      "aQuantia"
-#define AQ_CFG_DRV_DESC        "aQuantia Corporation(R) Network Driver"
+#define AQ_CFG_DRV_AUTHOR      "Marvell"
+#define AQ_CFG_DRV_DESC        "Marvell (Aquantia) Corporation(R) Network Driver"
 #define AQ_CFG_DRV_NAME        "atlantic"
 
 #endif /* AQ_CFG_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index c8c402b013bb..d5beb798bab6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -37,7 +37,7 @@
 #define AQ_DEVICE_ID_AQC111S	0x91B1
 #define AQ_DEVICE_ID_AQC112S	0x92B1
 
-#define HW_ATL_NIC_NAME "aQuantia AQtion 10Gbit Network Adapter"
+#define HW_ATL_NIC_NAME "Marvell (aQuantia) AQtion 10Gbit Network Adapter"
 
 #define AQ_HWREV_ANY	0
 #define AQ_HWREV_1	1
-- 
cgit v1.2.3


From 98c4353c5add3cb2bbb3c2da1cbd7fd2d09f396b Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:30 +0300
Subject: net: atlantic: add A2 device IDs

Adding device ids for the new generation of atlantic nic.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_common.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index d5beb798bab6..1261e7c7a01e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -37,6 +37,13 @@
 #define AQ_DEVICE_ID_AQC111S	0x91B1
 #define AQ_DEVICE_ID_AQC112S	0x92B1
 
+#define AQ_DEVICE_ID_AQC113DEV	0x00C0
+#define AQ_DEVICE_ID_AQC113CS	0x94C0
+#define AQ_DEVICE_ID_AQC114CS	0x93C0
+#define AQ_DEVICE_ID_AQC113	0x04C0
+#define AQ_DEVICE_ID_AQC113C	0x14C0
+#define AQ_DEVICE_ID_AQC115C	0x12C0
+
 #define HW_ATL_NIC_NAME "Marvell (aQuantia) AQtion 10Gbit Network Adapter"
 
 #define AQ_HWREV_ANY	0
-- 
cgit v1.2.3


From 3d464aadef75415c55a5a4feb611a9bbf034d7d3 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:31 +0300
Subject: net: atlantic: add defines for 10M and EEE 100M link mode

This patch adds defines for 10M and EEE 100M link modes, which are
supported by A2.

10M support is added in this patch series.
EEE is out of scope, but will be added in a follow-up series.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_common.h | 22 ++++++++++++----------
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    |  3 +++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 12 ++++++++++++
 3 files changed, 27 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index 1261e7c7a01e..53620ba6d7a6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -50,16 +50,18 @@
 #define AQ_HWREV_1	1
 #define AQ_HWREV_2	2
 
-#define AQ_NIC_RATE_10G        BIT(0)
-#define AQ_NIC_RATE_5G         BIT(1)
-#define AQ_NIC_RATE_5GSR       BIT(2)
-#define AQ_NIC_RATE_2GS        BIT(3)
-#define AQ_NIC_RATE_1G         BIT(4)
-#define AQ_NIC_RATE_100M       BIT(5)
+#define AQ_NIC_RATE_10G		BIT(0)
+#define AQ_NIC_RATE_5G		BIT(1)
+#define AQ_NIC_RATE_5GSR	BIT(2)
+#define AQ_NIC_RATE_2GS		BIT(3)
+#define AQ_NIC_RATE_1G		BIT(4)
+#define AQ_NIC_RATE_100M	BIT(5)
+#define AQ_NIC_RATE_10M		BIT(6)
 
-#define AQ_NIC_RATE_EEE_10G	BIT(6)
-#define AQ_NIC_RATE_EEE_5G	BIT(7)
-#define AQ_NIC_RATE_EEE_2GS	BIT(8)
-#define AQ_NIC_RATE_EEE_1G	BIT(9)
+#define AQ_NIC_RATE_EEE_10G	BIT(7)
+#define AQ_NIC_RATE_EEE_5G	BIT(8)
+#define AQ_NIC_RATE_EEE_2GS	BIT(9)
+#define AQ_NIC_RATE_EEE_1G	BIT(10)
+#define AQ_NIC_RATE_EEE_100M	BIT(11)
 
 #endif /* AQ_COMMON_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 7241cf92b43a..0c9dd8edc062 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -611,6 +611,9 @@ static enum hw_atl_fw2x_rate eee_mask_to_ethtool_mask(u32 speed)
 	if (speed & AQ_NIC_RATE_EEE_1G)
 		rate |= SUPPORTED_1000baseT_Full;
 
+	if (speed & AQ_NIC_RATE_EEE_100M)
+		rate |= SUPPORTED_100baseT_Full;
+
 	return rate;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index a369705a786a..80dd744dcbd1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -885,6 +885,10 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     100baseT_Full);
 
+	if (self->aq_nic_cfg.aq_hw_caps->link_speed_msk & AQ_NIC_RATE_10M)
+		ethtool_link_ksettings_add_link_mode(cmd, supported,
+						     10baseT_Full);
+
 	if (self->aq_nic_cfg.aq_hw_caps->flow_control) {
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     Pause);
@@ -924,6 +928,10 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     100baseT_Full);
 
+	if (self->aq_nic_cfg.link_speed_msk  & AQ_NIC_RATE_10M)
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     10baseT_Full);
+
 	if (self->aq_nic_cfg.fc.cur & AQ_NIC_FC_RX)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     Pause);
@@ -954,6 +962,10 @@ int aq_nic_set_link_ksettings(struct aq_nic_s *self,
 		speed = cmd->base.speed;
 
 		switch (speed) {
+		case SPEED_10:
+			rate = AQ_NIC_RATE_10M;
+			break;
+
 		case SPEED_100:
 			rate = AQ_NIC_RATE_100M;
 			break;
-- 
cgit v1.2.3


From 099d074e3f0cd3f48e57e3349b9f8a25b0e3feb8 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:32 +0300
Subject: net: atlantic: add hw_soft_reset, hw_prepare to hw_ops

A2 will have a different implementation of these 2 APIs, so
this patch moves them to hw_ops in preparation for A2.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Co-developed-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Signed-off-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h           |  5 +++++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c          | 16 +++++++++++++++-
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c    |  2 ++
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c    |  2 ++
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c |  4 ----
 5 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 7d71bc7dc500..84abce29d590 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -182,6 +182,11 @@ struct aq_hw_ops {
 
 	int (*hw_set_mac_address)(struct aq_hw_s *self, u8 *mac_addr);
 
+	int (*hw_soft_reset)(struct aq_hw_s *self);
+
+	int (*hw_prepare)(struct aq_hw_s *self,
+			  const struct aq_fw_ops **fw_ops);
+
 	int (*hw_reset)(struct aq_hw_s *self);
 
 	int (*hw_init)(struct aq_hw_s *self, u8 *mac_addr);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 80dd744dcbd1..7f4d8abab951 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -257,6 +257,20 @@ static void aq_nic_polling_timer_cb(struct timer_list *t)
 		  AQ_CFG_POLLING_TIMER_INTERVAL);
 }
 
+static int aq_nic_hw_prepare(struct aq_nic_s *self)
+{
+	int err = 0;
+
+	err = self->aq_hw_ops->hw_soft_reset(self->aq_hw);
+	if (err)
+		goto exit;
+
+	err = self->aq_hw_ops->hw_prepare(self->aq_hw, &self->aq_fw_ops);
+
+exit:
+	return err;
+}
+
 int aq_nic_ndev_register(struct aq_nic_s *self)
 {
 	int err = 0;
@@ -266,7 +280,7 @@ int aq_nic_ndev_register(struct aq_nic_s *self)
 		goto err_exit;
 	}
 
-	err = hw_atl_utils_initfw(self->aq_hw, &self->aq_fw_ops);
+	err = aq_nic_hw_prepare(self);
 	if (err)
 		goto err_exit;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 9b1062b8af64..2dba8c277ecb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -886,6 +886,8 @@ static int hw_atl_a0_hw_ring_rx_stop(struct aq_hw_s *self,
 }
 
 const struct aq_hw_ops hw_atl_ops_a0 = {
+	.hw_soft_reset        = hw_atl_utils_soft_reset,
+	.hw_prepare           = hw_atl_utils_initfw,
 	.hw_set_mac_address   = hw_atl_a0_hw_mac_addr_set,
 	.hw_init              = hw_atl_a0_hw_init,
 	.hw_reset             = hw_atl_a0_hw_reset,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index d20d91cdece8..4e2e4eef028d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1478,6 +1478,8 @@ static int hw_atl_b0_set_loopback(struct aq_hw_s *self, u32 mode, bool enable)
 }
 
 const struct aq_hw_ops hw_atl_ops_b0 = {
+	.hw_soft_reset        = hw_atl_utils_soft_reset,
+	.hw_prepare           = hw_atl_utils_initfw,
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
 	.hw_reset             = hw_atl_b0_hw_reset,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 354705f9bc49..7259bcb81e9b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -67,10 +67,6 @@ int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
 	int err = 0;
 
-	err = hw_atl_utils_soft_reset(self);
-	if (err)
-		return err;
-
 	hw_atl_utils_hw_chip_features_init(self,
 					   &self->chip_features);
 
-- 
cgit v1.2.3


From 36e90a5297ea02c67c0f17d8b39eb9ceb93dd6f0 Mon Sep 17 00:00:00 2001
From: Nikita Danilov <ndanilov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:33 +0300
Subject: net: atlantic: simplify hw_get_fw_version() usage

hw_get_fw_version() never fails, so this patch simplifies its
usage by utilizing return value instead of output argument.

Signed-off-by: Nikita Danilov <ndanilov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h               | 2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c              | 6 +-----
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 8 +++-----
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h | 2 +-
 4 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 84abce29d590..c0dada1075cf 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -259,7 +259,7 @@ struct aq_hw_ops {
 
 	struct aq_stats_s *(*hw_get_hw_stats)(struct aq_hw_s *self);
 
-	int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version);
+	u32 (*hw_get_fw_version)(struct aq_hw_s *self);
 
 	int (*hw_set_offload)(struct aq_hw_s *self,
 			      struct aq_nic_cfg_s *aq_nic_cfg);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 7f4d8abab951..57102f35e9f3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1032,11 +1032,7 @@ struct aq_nic_cfg_s *aq_nic_get_cfg(struct aq_nic_s *self)
 
 u32 aq_nic_get_fw_version(struct aq_nic_s *self)
 {
-	u32 fw_version = 0U;
-
-	self->aq_hw_ops->hw_get_fw_version(self->aq_hw, &fw_version);
-
-	return fw_version;
+	return self->aq_hw_ops->hw_get_fw_version(self->aq_hw);
 }
 
 int aq_nic_set_loopback(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 7259bcb81e9b..bd1712ca9ef2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -70,7 +70,7 @@ int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 	hw_atl_utils_hw_chip_features_init(self,
 					   &self->chip_features);
 
-	hw_atl_utils_get_fw_version(self, &self->fw_ver_actual);
+	self->fw_ver_actual = hw_atl_utils_get_fw_version(self);
 
 	if (hw_atl_utils_ver_match(HW_ATL_FW_VER_1X,
 				   self->fw_ver_actual) == 0) {
@@ -915,11 +915,9 @@ int hw_atl_utils_hw_get_regs(struct aq_hw_s *self,
 	return 0;
 }
 
-int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version)
+u32 hw_atl_utils_get_fw_version(struct aq_hw_s *self)
 {
-	*fw_version = aq_hw_read_reg(self, 0x18U);
-
-	return 0;
+	return aq_hw_read_reg(self, HW_ATL_MPI_FW_VERSION);
 }
 
 static int aq_fw1x_set_wake_magic(struct aq_hw_s *self, bool wol_enabled,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index b15513914636..086627a96746 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -622,7 +622,7 @@ int hw_atl_utils_hw_set_power(struct aq_hw_s *self,
 
 int hw_atl_utils_hw_deinit(struct aq_hw_s *self);
 
-int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version);
+u32 hw_atl_utils_get_fw_version(struct aq_hw_s *self);
 
 int hw_atl_utils_update_stats(struct aq_hw_s *self);
 
-- 
cgit v1.2.3


From d0f23741c202c685447050713907f3be39a985ee Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:34 +0300
Subject: net: atlantic: make hw_get_regs optional

This patch fixes potential crash in case if hw_get_regs is NULL.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 57102f35e9f3..2dbea5cd7684 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -778,6 +778,9 @@ int aq_nic_get_regs(struct aq_nic_s *self, struct ethtool_regs *regs, void *p)
 	u32 *regs_buff = p;
 	int err = 0;
 
+	if (unlikely(!self->aq_hw_ops->hw_get_regs))
+		return -EOPNOTSUPP;
+
 	regs->version = 1;
 
 	err = self->aq_hw_ops->hw_get_regs(self->aq_hw,
@@ -792,6 +795,9 @@ err_exit:
 
 int aq_nic_get_regs_count(struct aq_nic_s *self)
 {
+	if (unlikely(!self->aq_hw_ops->hw_get_regs))
+		return 0;
+
 	return self->aq_nic_cfg.aq_hw_caps->mac_regs_count;
 }
 
-- 
cgit v1.2.3


From d1ad88fe9fa9f5c3e4ecf509efb579852b44cc79 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:35 +0300
Subject: net: atlantic: move IS_CHIP_FEATURE to aq_hw.h

IS_CHIP feature will be used to differentiate between A1 and A2,
where necessary. Thus, move it to aq_hw.h, rename it and make
it accept the 'hw' pointer.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     | 13 ++++++++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c  |  2 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  6 ++--
 .../aquantia/atlantic/hw_atl/hw_atl_utils.c        | 36 ++++++++++++----------
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        | 11 -------
 5 files changed, 36 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index c0dada1075cf..f420ef40b627 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -136,6 +136,19 @@ enum aq_priv_flags {
 				 BIT(AQ_HW_LOOPBACK_PHYINT_SYS) |\
 				 BIT(AQ_HW_LOOPBACK_PHYEXT_SYS))
 
+#define ATL_HW_CHIP_MIPS         0x00000001U
+#define ATL_HW_CHIP_TPO2         0x00000002U
+#define ATL_HW_CHIP_RPF2         0x00000004U
+#define ATL_HW_CHIP_MPI_AQ       0x00000010U
+#define ATL_HW_CHIP_ATLANTIC     0x00800000U
+#define ATL_HW_CHIP_REVISION_A0  0x01000000U
+#define ATL_HW_CHIP_REVISION_B0  0x02000000U
+#define ATL_HW_CHIP_REVISION_B1  0x04000000U
+#define ATL_HW_CHIP_ANTIGUA      0x08000000U
+
+#define ATL_HW_IS_CHIP_FEATURE(_HW_, _F_) (!!(ATL_HW_CHIP_##_F_ & \
+	(_HW_)->chip_features))
+
 struct aq_hw_s {
 	atomic_t flags;
 	u8 rbl_enabled:1;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 2dba8c277ecb..eee265b4415a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -267,7 +267,7 @@ static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self)
 	hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
 
 	/* misc */
-	aq_hw_write_reg(self, 0x00007040U, IS_CHIP_FEATURE(TPO2) ?
+	aq_hw_write_reg(self, 0x00007040U, ATL_HW_IS_CHIP_FEATURE(self, TPO2) ?
 			0x00010000U : 0x00000000U);
 	hw_atl_tdm_tx_dca_en_set(self, 0U);
 	hw_atl_tdm_tx_dca_mode_set(self, 0U);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 4e2e4eef028d..3b42045b9c7d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -324,7 +324,7 @@ static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 	hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
 
 	/* misc */
-	aq_hw_write_reg(self, 0x00007040U, IS_CHIP_FEATURE(TPO2) ?
+	aq_hw_write_reg(self, 0x00007040U, ATL_HW_IS_CHIP_FEATURE(self, TPO2) ?
 			0x00010000U : 0x00000000U);
 	hw_atl_tdm_tx_dca_en_set(self, 0U);
 	hw_atl_tdm_tx_dca_mode_set(self, 0U);
@@ -372,8 +372,8 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
 
 	/* misc */
-	aq_hw_write_reg(self, 0x00005040U,
-			IS_CHIP_FEATURE(RPF2) ? 0x000F0000U : 0x00000000U);
+	aq_hw_write_reg(self, 0x00005040U, ATL_HW_IS_CHIP_FEATURE(self, RPF2) ?
+			0x000F0000U : 0x00000000U);
 
 	hw_atl_rpfl2broadcast_flr_act_set(self, 1U);
 	hw_atl_rpfl2broadcast_count_threshold_set(self, 0xFFFFU & (~0U / 256U));
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index bd1712ca9ef2..20655a2170cc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -309,7 +309,7 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a,
 	for (++cnt; --cnt && !err;) {
 		aq_hw_write_reg(self, HW_ATL_MIF_CMD, 0x00008000U);
 
-		if (IS_CHIP_FEATURE(REVISION_B1))
+		if (ATL_HW_IS_CHIP_FEATURE(self, REVISION_B1))
 			err = readx_poll_timeout_atomic(hw_atl_utils_mif_addr_get,
 							self, val, val != a,
 							1U, 1000U);
@@ -405,7 +405,7 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 addr, u32 *p,
 	if (err < 0)
 		goto err_exit;
 
-	if (IS_CHIP_FEATURE(REVISION_B1))
+	if (ATL_HW_IS_CHIP_FEATURE(self, REVISION_B1))
 		err = hw_atl_utils_write_b1_mbox(self, addr, p, cnt, area);
 	else
 		err = hw_atl_utils_write_b0_mbox(self, addr, p, cnt);
@@ -497,7 +497,7 @@ int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size)
 	struct aq_hw_atl_utils_fw_rpc_tid_s sw;
 	int err = 0;
 
-	if (!IS_CHIP_FEATURE(MIPS)) {
+	if (!ATL_HW_IS_CHIP_FEATURE(self, MIPS)) {
 		err = -1;
 		goto err_exit;
 	}
@@ -603,7 +603,7 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 	if (err < 0)
 		goto err_exit;
 
-	if (IS_CHIP_FEATURE(REVISION_A0)) {
+	if (ATL_HW_IS_CHIP_FEATURE(self, REVISION_A0)) {
 		unsigned int mtu = self->aq_nic_cfg ?
 					self->aq_nic_cfg->mtu : 1514U;
 		pmbox->stats.ubrc = pmbox->stats.uprc * mtu;
@@ -802,22 +802,24 @@ void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p)
 	u32 mif_rev = val & 0xFFU;
 	u32 chip_features = 0U;
 
+	chip_features |= ATL_HW_CHIP_ATLANTIC;
+
 	if ((0xFU & mif_rev) == 1U) {
-		chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_A0 |
-			HAL_ATLANTIC_UTILS_CHIP_MPI_AQ |
-			HAL_ATLANTIC_UTILS_CHIP_MIPS;
+		chip_features |= ATL_HW_CHIP_REVISION_A0 |
+			ATL_HW_CHIP_MPI_AQ |
+			ATL_HW_CHIP_MIPS;
 	} else if ((0xFU & mif_rev) == 2U) {
-		chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_B0 |
-			HAL_ATLANTIC_UTILS_CHIP_MPI_AQ |
-			HAL_ATLANTIC_UTILS_CHIP_MIPS |
-			HAL_ATLANTIC_UTILS_CHIP_TPO2 |
-			HAL_ATLANTIC_UTILS_CHIP_RPF2;
+		chip_features |= ATL_HW_CHIP_REVISION_B0 |
+			ATL_HW_CHIP_MPI_AQ |
+			ATL_HW_CHIP_MIPS |
+			ATL_HW_CHIP_TPO2 |
+			ATL_HW_CHIP_RPF2;
 	} else if ((0xFU & mif_rev) == 0xAU) {
-		chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_B1 |
-			HAL_ATLANTIC_UTILS_CHIP_MPI_AQ |
-			HAL_ATLANTIC_UTILS_CHIP_MIPS |
-			HAL_ATLANTIC_UTILS_CHIP_TPO2 |
-			HAL_ATLANTIC_UTILS_CHIP_RPF2;
+		chip_features |= ATL_HW_CHIP_REVISION_B1 |
+			ATL_HW_CHIP_MPI_AQ |
+			ATL_HW_CHIP_MIPS |
+			ATL_HW_CHIP_TPO2 |
+			ATL_HW_CHIP_RPF2;
 	}
 
 	*p = chip_features;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 086627a96746..5513254642b3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -406,17 +406,6 @@ enum hw_atl_rx_ctrl_registers_l3l4 {
 #define HW_ATL_GET_REG_LOCATION_FL3L4(location) \
 	((location) - AQ_RX_FIRST_LOC_FL3L4)
 
-#define HAL_ATLANTIC_UTILS_CHIP_MIPS         0x00000001U
-#define HAL_ATLANTIC_UTILS_CHIP_TPO2         0x00000002U
-#define HAL_ATLANTIC_UTILS_CHIP_RPF2         0x00000004U
-#define HAL_ATLANTIC_UTILS_CHIP_MPI_AQ       0x00000010U
-#define HAL_ATLANTIC_UTILS_CHIP_REVISION_A0  0x01000000U
-#define HAL_ATLANTIC_UTILS_CHIP_REVISION_B0  0x02000000U
-#define HAL_ATLANTIC_UTILS_CHIP_REVISION_B1  0x04000000U
-
-#define IS_CHIP_FEATURE(_F_) (HAL_ATLANTIC_UTILS_CHIP_##_F_ & \
-	self->chip_features)
-
 enum hal_atl_utils_fw_state_e {
 	MPI_DEINIT = 0,
 	MPI_RESET = 1,
-- 
cgit v1.2.3


From f67619611b4ce0e3b2bbc2cd75b9c2ce2035ef1e Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:36 +0300
Subject: net: atlantic: A2 driver-firmware interface

This patch adds the driver<->firmware interface for A2

Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils.h      | 593 +++++++++++++++++++++
 1 file changed, 593 insertions(+)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
new file mode 100644
index 000000000000..7d4ac65440c9
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -0,0 +1,593 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#ifndef HW_ATL2_UTILS_H
+#define HW_ATL2_UTILS_H
+
+/* F W    A P I */
+
+struct link_options_s {
+	u8 link_up:1;
+	u8 link_renegotiate:1;
+	u8 minimal_link_speed:1;
+	u8 internal_loopback:1;
+	u8 external_loopback:1;
+	u8 rate_10M_hd:1;
+	u8 rate_100M_hd:1;
+	u8 rate_1G_hd:1;
+
+	u8 rate_10M:1;
+	u8 rate_100M:1;
+	u8 rate_1G:1;
+	u8 rate_2P5G:1;
+	u8 rate_N2P5G:1;
+	u8 rate_5G:1;
+	u8 rate_N5G:1;
+	u8 rate_10G:1;
+
+	u8 eee_100M:1;
+	u8 eee_1G:1;
+	u8 eee_2P5G:1;
+	u8 eee_5G:1;
+	u8 eee_10G:1;
+	u8 rsvd3:3;
+
+	u8 pause_rx:1;
+	u8 pause_tx:1;
+	u8 rsvd4:1;
+	u8 downshift:1;
+	u8 downshift_retry:4;
+};
+
+struct link_control_s {
+	u8 mode:4;
+	u8 disable_crc_corruption:1;
+	u8 discard_short_frames:1;
+	u8 flow_control_mode:1;
+	u8 disable_length_check:1;
+
+	u8 discard_errored_frames:1;
+	u8 control_frame_enable:1;
+	u8 enable_tx_padding:1;
+	u8 enable_crc_forwarding:1;
+	u8 enable_frame_padding_removal_rx: 1;
+	u8 promiscuous_mode: 1;
+	u8 rsvd:2;
+
+	u16 rsvd2;
+};
+
+struct thermal_shutdown_s {
+	u8 enable:1;
+	u8 warning_enable:1;
+	u8 rsvd:6;
+
+	u8 shutdown_temperature;
+	u8 cold_temperature;
+	u8 warning_temperature;
+};
+
+struct mac_address_s {
+	u8 mac_address[6];
+};
+
+struct mac_address_aligned_s {
+	struct mac_address_s aligned;
+	u16 rsvd;
+};
+
+struct sleep_proxy_s {
+	struct wake_on_lan_s {
+		u8 wake_on_magic_packet:1;
+		u8 wake_on_pattern:1;
+		u8 wake_on_link_up:1;
+		u8 wake_on_link_down:1;
+		u8 wake_on_ping:1;
+		u8 wake_on_timer:1;
+		u8 rsvd:2;
+
+		u8 rsvd2;
+		u16 rsvd3;
+
+		u32 link_up_timeout;
+		u32 link_down_timeout;
+		u32 timer;
+	} wake_on_lan;
+
+	struct {
+		u32 mask[4];
+		u32 crc32;
+	} wake_up_pattern[8];
+
+	struct __attribute__ ((__packed__)) {
+		u8 arp_responder:1;
+		u8 echo_responder:1;
+		u8 igmp_client:1;
+		u8 echo_truncate:1;
+		u8 address_guard:1;
+		u8 ignore_fragmented:1;
+		u8 rsvd:2;
+
+		u16 echo_max_len;
+		u8 rsvd2;
+	} ipv4_offload;
+
+	u32 ipv4_offload_addr[8];
+	u32 reserved[8];
+
+	struct __attribute__ ((__packed__)) {
+		u8 ns_responder:1;
+		u8 echo_responder:1;
+		u8 mld_client:1;
+		u8 echo_truncate:1;
+		u8 address_guard:1;
+		u8 rsvd:3;
+
+		u16 echo_max_len;
+		u8 rsvd2;
+	} ipv6_offload;
+
+	u32 ipv6_offload_addr[16][4];
+
+	struct {
+		u16 port[16];
+	} tcp_port_offload;
+
+	struct {
+		u16 port[16];
+	} udp_port_offload;
+
+	struct {
+		u32 retry_count;
+		u32 retry_interval;
+	} ka4_offload;
+
+	struct {
+		u32 timeout;
+		u16 local_port;
+		u16 remote_port;
+		u8 remote_mac_addr[6];
+		u16 rsvd;
+		u32 rsvd2;
+		u32 rsvd3;
+		u16 rsvd4;
+		u16 win_size;
+		u32 seq_num;
+		u32 ack_num;
+		u32 local_ip;
+		u32 remote_ip;
+	} ka4_connection[16];
+
+	struct {
+		u32 retry_count;
+		u32 retry_interval;
+	} ka6_offload;
+
+	struct {
+		u32 timeout;
+		u16 local_port;
+		u16 remote_port;
+		u8 remote_mac_addr[6];
+		u16 rsvd;
+		u32 rsvd2;
+		u32 rsvd3;
+		u16 rsvd4;
+		u16 win_size;
+		u32 seq_num;
+		u32 ack_num;
+		u32 local_ip[4];
+		u32 remote_ip[4];
+	} ka6_connection[16];
+
+	struct {
+		u32 rr_count;
+		u32 rr_buf_len;
+		u32 idx_offset;
+		u32 rr__offset;
+	} mdns_offload;
+};
+
+struct pause_quanta_s {
+	u16 quanta_10M;
+	u16 threshold_10M;
+	u16 quanta_100M;
+	u16 threshold_100M;
+	u16 quanta_1G;
+	u16 threshold_1G;
+	u16 quanta_2P5G;
+	u16 threshold_2P5G;
+	u16 quanta_5G;
+	u16 threshold_5G;
+	u16 quanta_10G;
+	u16 threshold_10G;
+};
+
+struct data_buffer_status_s {
+	u32 data_offset;
+	u32 data_length;
+};
+
+struct device_caps_s {
+	u8 finite_flashless:1;
+	u8 cable_diag:1;
+	u8 ncsi:1;
+	u8 avb:1;
+	u8 rsvd:4;
+
+	u8 rsvd2;
+	u16 rsvd3;
+	u32 rsvd4;
+};
+
+struct version_s {
+	struct bundle_version_t {
+		u8 major;
+		u8 minor;
+		u16 build;
+	} bundle;
+	struct mac_version_t {
+		u8 major;
+		u8 minor;
+		u16 build;
+	} mac;
+	struct phy_version_t {
+		u8 major;
+		u8 minor;
+		u16 build;
+	} phy;
+	u32 rsvd;
+};
+
+struct link_status_s {
+	u8 link_state:4;
+	u8 link_rate:4;
+
+	u8 pause_tx:1;
+	u8 pause_rx:1;
+	u8 eee:1;
+	u8 duplex:1;
+	u8 rsvd:4;
+
+	u16 rsvd2;
+};
+
+struct wol_status_s {
+	u8 wake_count;
+	u8 wake_reason;
+
+	u16 wake_up_packet_length :12;
+	u16 wake_up_pattern_number :3;
+	u16 rsvd:1;
+
+	u32 wake_up_packet[379];
+};
+
+struct mac_health_monitor_s {
+	u8 mac_ready:1;
+	u8 mac_fault:1;
+	u8 mac_flashless_finished:1;
+	u8 rsvd:5;
+
+	u8 mac_temperature;
+	u16 mac_heart_beat;
+	u16 mac_fault_code;
+	u16 rsvd2;
+};
+
+struct phy_health_monitor_s {
+	u8 phy_ready:1;
+	u8 phy_fault:1;
+	u8 phy_hot_warning:1;
+	u8 rsvd:5;
+
+	u8 phy_temperature;
+	u16 phy_heart_beat;
+	u16 phy_fault_code;
+	u16 rsvd2;
+};
+
+struct device_link_caps_s {
+	u8 rsvd:3;
+	u8 internal_loopback:1;
+	u8 external_loopback:1;
+	u8 rate_10M_hd:1;
+	u8 rate_100M_hd:1;
+	u8 rate_1G_hd:1;
+
+	u8 rate_10M:1;
+	u8 rate_100M:1;
+	u8 rate_1G:1;
+	u8 rate_2P5G:1;
+	u8 rate_N2P5G:1;
+	u8 rate_5G:1;
+	u8 rate_N5G:1;
+	u8 rate_10G:1;
+
+	u8 rsvd3:1;
+	u8 eee_100M:1;
+	u8 eee_1G:1;
+	u8 eee_2P5G:1;
+	u8 rsvd4:1;
+	u8 eee_5G:1;
+	u8 rsvd5:1;
+	u8 eee_10G:1;
+
+	u8 pause_rx:1;
+	u8 pause_tx:1;
+	u8 pfc:1;
+	u8 downshift:1;
+	u8 downshift_retry:4;
+};
+
+struct sleep_proxy_caps_s {
+	u8 ipv4_offload:1;
+	u8 ipv6_offload:1;
+	u8 tcp_port_offload:1;
+	u8 udp_port_offload:1;
+	u8 ka4_offload:1;
+	u8 ka6_offload:1;
+	u8 mdns_offload:1;
+	u8 wake_on_ping:1;
+
+	u8 wake_on_magic_packet:1;
+	u8 wake_on_pattern:1;
+	u8 wake_on_timer:1;
+	u8 wake_on_link:1;
+	u8 wake_patterns_count:4;
+
+	u8 ipv4_count;
+	u8 ipv6_count;
+
+	u8 tcp_port_offload_count;
+	u8 udp_port_offload_count;
+
+	u8 tcp4_ka_count;
+	u8 tcp6_ka_count;
+
+	u8 igmp_offload:1;
+	u8 mld_offload:1;
+	u8 rsvd:6;
+
+	u8 rsvd2;
+	u16 rsvd3;
+};
+
+struct lkp_link_caps_s {
+	u8 rsvd:5;
+	u8 rate_10M_hd:1;
+	u8 rate_100M_hd:1;
+	u8 rate_1G_hd:1;
+
+	u8 rate_10M:1;
+	u8 rate_100M:1;
+	u8 rate_1G:1;
+	u8 rate_2P5G:1;
+	u8 rate_N2P5G:1;
+	u8 rate_5G:1;
+	u8 rate_N5G:1;
+	u8 rate_10G:1;
+
+	u8 rsvd2:1;
+	u8 eee_100M:1;
+	u8 eee_1G:1;
+	u8 eee_2P5G:1;
+	u8 rsvd3:1;
+	u8 eee_5G:1;
+	u8 rsvd4:1;
+	u8 eee_10G:1;
+
+	u8 pause_rx:1;
+	u8 pause_tx:1;
+	u8 rsvd5:6;
+};
+
+struct core_dump_s {
+	u32 reg0;
+	u32 reg1;
+	u32 reg2;
+
+	u32 hi;
+	u32 lo;
+
+	u32 regs[32];
+};
+
+struct trace_s {
+	u32 sync_counter;
+	u32 mem_buffer[0x1ff];
+};
+
+struct cable_diag_control_s {
+	u8 toggle :1;
+	u8 rsvd:7;
+
+	u8 wait_timeout_sec;
+	u16 rsvd2;
+};
+
+struct cable_diag_lane_data_s {
+	u8 result_code;
+	u8 dist;
+	u8 far_dist;
+	u8 rsvd;
+};
+
+struct cable_diag_status_s {
+	struct cable_diag_lane_data_s lane_data[4];
+	u8 transact_id;
+	u8 status:4;
+	u8 rsvd:4;
+	u16 rsvd2;
+};
+
+struct statistics_s {
+	struct {
+		u32 link_up;
+		u32 link_down;
+	} link;
+
+	struct {
+		u64 tx_unicast_octets;
+		u64 tx_multicast_octets;
+		u64 tx_broadcast_octets;
+		u64 rx_unicast_octets;
+		u64 rx_multicast_octets;
+		u64 rx_broadcast_octets;
+
+		u32 tx_unicast_frames;
+		u32 tx_multicast_frames;
+		u32 tx_broadcast_frames;
+		u32 tx_errors;
+
+		u32 rx_unicast_frames;
+		u32 rx_multicast_frames;
+		u32 rx_broadcast_frames;
+		u32 rx_dropped_frames;
+		u32 rx_error_frames;
+
+		u32 tx_good_frames;
+		u32 rx_good_frames;
+		u32 reserve_fw_gap;
+	} msm;
+	u32 main_loop_cycles;
+	u32 reserve_fw_gap;
+};
+
+struct filter_caps_s {
+	u8 l2_filters_base_index:6;
+	u8 flexible_filter_mask:2;
+	u8 l2_filter_count;
+	u8 ethertype_filter_base_index;
+	u8 ethertype_filter_count;
+
+	u8 vlan_filter_base_index;
+	u8 vlan_filter_count;
+	u8 l3_ip4_filter_base_index:4;
+	u8 l3_ip4_filter_count:4;
+	u8 l3_ip6_filter_base_index:4;
+	u8 l3_ip6_filter_count:4;
+
+	u8 l4_filter_base_index:4;
+	u8 l4_filter_count:4;
+	u8 l4_flex_filter_base_index:4;
+	u8 l4_flex_filter_count:4;
+	u8 rslv_tbl_base_index;
+	u8 rslv_tbl_count;
+};
+
+struct request_policy_s {
+	struct {
+		u8 all:1;
+		u8 mcast:1;
+		u8 rx_queue_tc_index:5;
+		u8 queue_or_tc:1;
+	} promisc;
+
+	struct {
+		u8 accept:1;
+		u8 rsvd:1;
+		u8 rx_queue_tc_index:5;
+		u8 queue_or_tc:1;
+	} bcast;
+
+	struct {
+		u8 accept:1;
+		u8 rsvd:1;
+		u8 rx_queue_tc_index:5;
+		u8 queue_or_tc:1;
+	} mcast;
+
+	u8 rsvd:8;
+};
+
+struct fw_interface_in {
+	u32 mtu;
+	u32 rsvd1;
+	struct mac_address_aligned_s mac_address;
+	struct link_control_s link_control;
+	u32 rsvd2;
+	struct link_options_s link_options;
+	u32 rsvd3;
+	struct thermal_shutdown_s thermal_shutdown;
+	u32 rsvd4;
+	struct sleep_proxy_s sleep_proxy;
+	u32 rsvd5;
+	struct pause_quanta_s pause_quanta[8];
+	struct cable_diag_control_s cable_diag_control;
+	u32 rsvd6;
+	struct data_buffer_status_s data_buffer_status;
+	u32 rsvd7;
+	struct request_policy_s request_policy;
+};
+
+struct transaction_counter_s {
+	u16 transaction_cnt_a;
+	u16 transaction_cnt_b;
+};
+
+struct management_status_s {
+	struct mac_address_s mac_address;
+	u16 vlan;
+
+	struct{
+		u32 enable : 1;
+		u32 rsvd:31;
+	} flags;
+
+	u32 rsvd1;
+	u32 rsvd2;
+	u32 rsvd3;
+	u32 rsvd4;
+	u32 rsvd5;
+};
+
+struct fw_interface_out {
+	struct transaction_counter_s transaction_id;
+	struct version_s version;
+	struct link_status_s link_status;
+	struct wol_status_s wol_status;
+	u32 rsvd;
+	u32 rsvd2;
+	struct mac_health_monitor_s mac_health_monitor;
+	u32 rsvd3;
+	u32 rsvd4;
+	struct phy_health_monitor_s phy_health_monitor;
+	u32 rsvd5;
+	u32 rsvd6;
+	struct cable_diag_status_s cable_diag_status;
+	u32 rsvd7;
+	struct device_link_caps_s device_link_caps;
+	u32 rsvd8;
+	struct sleep_proxy_caps_s sleep_proxy_caps;
+	u32 rsvd9;
+	struct lkp_link_caps_s lkp_link_caps;
+	u32 rsvd10;
+	struct core_dump_s core_dump;
+	u32 rsvd11;
+	struct statistics_s stats;
+	u32 rsvd12;
+	struct filter_caps_s filter_caps;
+	struct device_caps_s device_caps;
+	u32 rsvd13;
+	struct management_status_s management_status;
+	u32 reserve[21];
+	struct trace_s trace;
+};
+
+#define  AQ_A2_FW_LINK_RATE_INVALID 0
+#define  AQ_A2_FW_LINK_RATE_10M     1
+#define  AQ_A2_FW_LINK_RATE_100M    2
+#define  AQ_A2_FW_LINK_RATE_1G      3
+#define  AQ_A2_FW_LINK_RATE_2G5     4
+#define  AQ_A2_FW_LINK_RATE_5G      5
+#define  AQ_A2_FW_LINK_RATE_10G     6
+
+#define  AQ_HOST_MODE_INVALID      0U
+#define  AQ_HOST_MODE_ACTIVE       1U
+#define  AQ_HOST_MODE_SLEEP_PROXY  2U
+#define  AQ_HOST_MODE_LOW_POWER    3U
+#define  AQ_HOST_MODE_SHUTDOWN     4U
+
+#endif /* HW_ATL2_UTILS_H */
-- 
cgit v1.2.3


From 258ff0cf61d607e17f2e273aae3e50c1dd251dec Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:37 +0300
Subject: net: atlantic: minimal A2 HW bindings required for fw_ops

This patch adds the bare minimum of A2 HW bindings required to
get fw_ops working.

Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/Makefile    |  1 +
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  1 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        | 56 ++++++++++++++++++++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        | 31 ++++++++++++
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        | 48 +++++++++++++++++++
 5 files changed, 137 insertions(+)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 8b555665a33a..86824f1868ab 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -25,6 +25,7 @@ atlantic-objs := aq_main.o \
 	hw_atl/hw_atl_utils.o \
 	hw_atl/hw_atl_utils_fw2x.o \
 	hw_atl/hw_atl_llh.o \
+	hw_atl2/hw_atl2_llh.o \
 	macsec/macsec_api.o
 
 atlantic-$(CONFIG_MACSEC) += aq_macsec.o
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index f420ef40b627..e770d91e0876 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -172,6 +172,7 @@ struct aq_hw_s {
 	struct hw_atl_utils_fw_rpc rpc;
 	s64 ptp_clk_offset;
 	u16 phy_id;
+	void *priv;
 };
 
 struct aq_ring_s;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
new file mode 100644
index 000000000000..b6164bc5fffd
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#include "hw_atl2_llh.h"
+#include "hw_atl2_llh_internal.h"
+#include "aq_hw_utils.h"
+
+void hw_atl2_mif_shared_buf_get(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				int len)
+{
+	int j = 0;
+	int i;
+
+	for (i = offset; i < offset + len; i++, j++)
+		data[j] = aq_hw_read_reg(aq_hw,
+					 HW_ATL2_MIF_SHARED_BUFFER_IN_ADR(i));
+}
+
+void hw_atl2_mif_shared_buf_write(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				  int len)
+{
+	int j = 0;
+	int i;
+
+	for (i = offset; i < offset + len; i++, j++)
+		aq_hw_write_reg(aq_hw, HW_ATL2_MIF_SHARED_BUFFER_IN_ADR(i),
+				data[j]);
+}
+
+void hw_atl2_mif_shared_buf_read(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				 int len)
+{
+	int j = 0;
+	int i;
+
+	for (i = offset; i < offset + len; i++, j++)
+		data[j] = aq_hw_read_reg(aq_hw,
+					 HW_ATL2_MIF_SHARED_BUFFER_OUT_ADR(i));
+}
+
+void hw_atl2_mif_host_finished_write_set(struct aq_hw_s *aq_hw, u32 finish)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_MIF_HOST_FINISHED_WRITE_ADR,
+			    HW_ATL2_MIF_HOST_FINISHED_WRITE_MSK,
+			    HW_ATL2_MIF_HOST_FINISHED_WRITE_SHIFT,
+			    finish);
+}
+
+u32 hw_atl2_mif_mcp_finished_read_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, HW_ATL2_MIF_MCP_FINISHED_READ_ADR,
+				  HW_ATL2_MIF_MCP_FINISHED_READ_MSK,
+				  HW_ATL2_MIF_MCP_FINISHED_READ_SHIFT);
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
new file mode 100644
index 000000000000..8ef8bd6b2534
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#ifndef HW_ATL2_LLH_H
+#define HW_ATL2_LLH_H
+
+#include <linux/types.h>
+
+struct aq_hw_s;
+
+/* get data from firmware shared input buffer */
+void hw_atl2_mif_shared_buf_get(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				int len);
+
+/* set data into firmware shared input buffer */
+void hw_atl2_mif_shared_buf_write(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				  int len);
+
+/* get data from firmware shared output buffer */
+void hw_atl2_mif_shared_buf_read(struct aq_hw_s *aq_hw, int offset, u32 *data,
+				 int len);
+
+/* set host finished write shared buffer indication */
+void hw_atl2_mif_host_finished_write_set(struct aq_hw_s *aq_hw, u32 finish);
+
+/* get mcp finished read shared buffer indication */
+u32 hw_atl2_mif_mcp_finished_read_get(struct aq_hw_s *aq_hw);
+
+#endif /* HW_ATL2_LLH_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
new file mode 100644
index 000000000000..835deb2d1950
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#ifndef HW_ATL2_LLH_INTERNAL_H
+#define HW_ATL2_LLH_INTERNAL_H
+
+/* Register address for firmware shared input buffer */
+#define HW_ATL2_MIF_SHARED_BUFFER_IN_ADR(dword) (0x00012000U + (dword) * 0x4U)
+/* Register address for firmware shared output buffer */
+#define HW_ATL2_MIF_SHARED_BUFFER_OUT_ADR(dword) (0x00013000U + (dword) * 0x4U)
+
+/* pif_host_finished_buf_wr_i Bitfield Definitions
+ * Preprocessor definitions for the bitfield "pif_host_finished_buf_wr_i".
+ * PORT="pif_host_finished_buf_wr_i"
+ */
+/* Register address for bitfield rpif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_ADR 0x00000e00u
+/* Bitmask for bitfield pif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_MSK 0x00000001u
+/* Inverted bitmask for bitfield pif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_MSKN 0xFFFFFFFEu
+/* Lower bit position of bitfield pif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_SHIFT 0
+/* Width of bitfield pif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_WIDTH 1
+/* Default value of bitfield pif_host_finished_buf_wr_i */
+#define HW_ATL2_MIF_HOST_FINISHED_WRITE_DEFAULT 0x0
+
+/* pif_mcp_finished_buf_rd_i Bitfield Definitions
+ * Preprocessor definitions for the bitfield "pif_mcp_finished_buf_rd_i".
+ * PORT="pif_mcp_finished_buf_rd_i"
+ */
+/* Register address for bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_ADR 0x00000e04u
+/* Bitmask for bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_MSK 0x00000001u
+/* Inverted bitmask for bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_MSKN 0xFFFFFFFEu
+/* Lower bit position of bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_SHIFT 0
+/* Width of bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_WIDTH 1
+/* Default value of bitfield pif_mcp_finished_buf_rd_i */
+#define HW_ATL2_MIF_MCP_FINISHED_READ_DEFAULT 0x0
+
+#endif /* HW_ATL2_LLH_INTERNAL_H */
-- 
cgit v1.2.3


From 5cfd54d7dc186a368af92aba0dcb8b4d4bbe8658 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:38 +0300
Subject: net: atlantic: minimal A2 fw_ops

This patch adds the minimum set of FW ops for A2.

Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Co-developed-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/Makefile    |   1 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |  17 ++
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils.h      |   5 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c   | 329 +++++++++++++++++++++
 4 files changed, 352 insertions(+)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 86824f1868ab..fa845c15d0e1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -25,6 +25,7 @@ atlantic-objs := aq_main.o \
 	hw_atl/hw_atl_utils.o \
 	hw_atl/hw_atl_utils_fw2x.o \
 	hw_atl/hw_atl_llh.o \
+	hw_atl2/hw_atl2_utils_fw.o \
 	hw_atl2/hw_atl2_llh.o \
 	macsec/macsec_api.o
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
new file mode 100644
index 000000000000..233db3222bb8
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#ifndef HW_ATL2_INTERNAL_H
+#define HW_ATL2_INTERNAL_H
+
+#include "hw_atl2_utils.h"
+
+#define HW_ATL2_MTU_JUMBO  16352U
+
+struct hw_atl2_priv {
+	struct statistics_s last_stats;
+};
+
+#endif /* HW_ATL2_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
index 7d4ac65440c9..5421fbed3db5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -590,4 +590,9 @@ struct fw_interface_out {
 #define  AQ_HOST_MODE_LOW_POWER    3U
 #define  AQ_HOST_MODE_SHUTDOWN     4U
 
+int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
+						u8 *base_index, u8 *count);
+
+extern const struct aq_fw_ops aq_a2_fw_ops;
+
 #endif /* HW_ATL2_UTILS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
new file mode 100644
index 000000000000..c3e0e5575810
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#include <linux/iopoll.h>
+
+#include "aq_hw.h"
+#include "hw_atl/hw_atl_llh.h"
+#include "hw_atl2_utils.h"
+#include "hw_atl2_llh.h"
+#include "hw_atl2_internal.h"
+
+#define AQ_A2_FW_READ_TRY_MAX 1000
+
+#define hw_atl2_shared_buffer_write(HW, ITEM, VARIABLE) \
+	hw_atl2_mif_shared_buf_write(HW,\
+		(offsetof(struct fw_interface_in, ITEM) / sizeof(u32)),\
+		(u32 *)&(VARIABLE), sizeof(VARIABLE) / sizeof(u32))
+
+#define hw_atl2_shared_buffer_get(HW, ITEM, VARIABLE) \
+	hw_atl2_mif_shared_buf_get(HW, \
+		(offsetof(struct fw_interface_in, ITEM) / sizeof(u32)),\
+		(u32 *)&(VARIABLE), \
+		sizeof(VARIABLE) / sizeof(u32))
+
+/* This should never be used on non atomic fields,
+ * treat any > u32 read as non atomic.
+ */
+#define hw_atl2_shared_buffer_read(HW, ITEM, VARIABLE) \
+{\
+	BUILD_BUG_ON_MSG((offsetof(struct fw_interface_out, ITEM) % \
+			 sizeof(u32)) != 0,\
+			 "Non aligned read " # ITEM);\
+	BUILD_BUG_ON_MSG(sizeof(VARIABLE) > sizeof(u32),\
+			 "Non atomic read " # ITEM);\
+	hw_atl2_mif_shared_buf_read(HW, \
+		(offsetof(struct fw_interface_out, ITEM) / sizeof(u32)),\
+		(u32 *)&(VARIABLE), sizeof(VARIABLE) / sizeof(u32));\
+}
+
+#define hw_atl2_shared_buffer_read_safe(HW, ITEM, DATA) \
+	hw_atl2_shared_buffer_read_block((HW), \
+		(offsetof(struct fw_interface_out, ITEM) / sizeof(u32)),\
+		sizeof(((struct fw_interface_out *)0)->ITEM) / sizeof(u32),\
+		(DATA))
+
+static int hw_atl2_shared_buffer_read_block(struct aq_hw_s *self,
+					    u32 offset, u32 dwords, void *data)
+{
+	struct transaction_counter_s tid1, tid2;
+	int cnt = 0;
+
+	do {
+		do {
+			hw_atl2_shared_buffer_read(self, transaction_id, tid1);
+			cnt++;
+			if (cnt > AQ_A2_FW_READ_TRY_MAX)
+				return -ETIME;
+			if (tid1.transaction_cnt_a != tid1.transaction_cnt_b)
+				udelay(1);
+		} while (tid1.transaction_cnt_a != tid1.transaction_cnt_b);
+
+		hw_atl2_mif_shared_buf_read(self, offset, (u32 *)data, dwords);
+
+		hw_atl2_shared_buffer_read(self, transaction_id, tid2);
+
+		cnt++;
+		if (cnt > AQ_A2_FW_READ_TRY_MAX)
+			return -ETIME;
+	} while (tid2.transaction_cnt_a != tid2.transaction_cnt_b ||
+		 tid1.transaction_cnt_a != tid2.transaction_cnt_a);
+
+	return 0;
+}
+
+static inline int hw_atl2_shared_buffer_finish_ack(struct aq_hw_s *self)
+{
+	u32 val;
+	int err;
+
+	hw_atl2_mif_host_finished_write_set(self, 1U);
+	err = readx_poll_timeout_atomic(hw_atl2_mif_mcp_finished_read_get,
+					self, val, val == 0U,
+					100, 100000U);
+	WARN(err, "hw_atl2_shared_buffer_finish_ack");
+
+	return err;
+}
+
+static int aq_a2_fw_init(struct aq_hw_s *self)
+{
+	struct link_control_s link_control;
+	u32 mtu;
+	u32 val;
+	int err;
+
+	hw_atl2_shared_buffer_get(self, link_control, link_control);
+	link_control.mode = AQ_HOST_MODE_ACTIVE;
+	hw_atl2_shared_buffer_write(self, link_control, link_control);
+
+	hw_atl2_shared_buffer_get(self, mtu, mtu);
+	mtu = HW_ATL2_MTU_JUMBO;
+	hw_atl2_shared_buffer_write(self, mtu, mtu);
+
+	hw_atl2_mif_host_finished_write_set(self, 1U);
+	err = readx_poll_timeout_atomic(hw_atl2_mif_mcp_finished_read_get,
+					self, val, val == 0U,
+					100, 5000000U);
+	WARN(err, "hw_atl2_shared_buffer_finish_ack");
+
+	return err;
+}
+
+static int aq_a2_fw_deinit(struct aq_hw_s *self)
+{
+	struct link_control_s link_control;
+
+	hw_atl2_shared_buffer_get(self, link_control, link_control);
+	link_control.mode = AQ_HOST_MODE_SHUTDOWN;
+	hw_atl2_shared_buffer_write(self, link_control, link_control);
+
+	return hw_atl2_shared_buffer_finish_ack(self);
+}
+
+static void a2_link_speed_mask2fw(u32 speed,
+				  struct link_options_s *link_options)
+{
+	link_options->rate_10G = !!(speed & AQ_NIC_RATE_10G);
+	link_options->rate_5G = !!(speed & AQ_NIC_RATE_5G);
+	link_options->rate_N5G = !!(speed & AQ_NIC_RATE_5GSR);
+	link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2GS);
+	link_options->rate_N2P5G = link_options->rate_2P5G;
+	link_options->rate_1G = !!(speed & AQ_NIC_RATE_1G);
+	link_options->rate_100M = !!(speed & AQ_NIC_RATE_100M);
+	link_options->rate_10M = !!(speed & AQ_NIC_RATE_10M);
+}
+
+static int aq_a2_fw_set_link_speed(struct aq_hw_s *self, u32 speed)
+{
+	struct link_options_s link_options;
+
+	hw_atl2_shared_buffer_get(self, link_options, link_options);
+	link_options.link_up = 1U;
+	a2_link_speed_mask2fw(speed, &link_options);
+	hw_atl2_shared_buffer_write(self, link_options, link_options);
+
+	return hw_atl2_shared_buffer_finish_ack(self);
+}
+
+static int aq_a2_fw_set_state(struct aq_hw_s *self,
+			      enum hal_atl_utils_fw_state_e state)
+{
+	struct link_options_s link_options;
+
+	hw_atl2_shared_buffer_get(self, link_options, link_options);
+
+	switch (state) {
+	case MPI_INIT:
+		link_options.link_up = 1U;
+		break;
+	case MPI_DEINIT:
+		link_options.link_up = 0U;
+		break;
+	case MPI_RESET:
+	case MPI_POWER:
+		/* No actions */
+		break;
+	}
+
+	hw_atl2_shared_buffer_write(self, link_options, link_options);
+
+	return hw_atl2_shared_buffer_finish_ack(self);
+}
+
+static int aq_a2_fw_update_link_status(struct aq_hw_s *self)
+{
+	struct link_status_s link_status;
+
+	hw_atl2_shared_buffer_read(self, link_status, link_status);
+
+	switch (link_status.link_rate) {
+	case AQ_A2_FW_LINK_RATE_10G:
+		self->aq_link_status.mbps = 10000;
+		break;
+	case AQ_A2_FW_LINK_RATE_5G:
+		self->aq_link_status.mbps = 5000;
+		break;
+	case AQ_A2_FW_LINK_RATE_2G5:
+		self->aq_link_status.mbps = 2500;
+		break;
+	case AQ_A2_FW_LINK_RATE_1G:
+		self->aq_link_status.mbps = 1000;
+		break;
+	case AQ_A2_FW_LINK_RATE_100M:
+		self->aq_link_status.mbps = 100;
+		break;
+	case AQ_A2_FW_LINK_RATE_10M:
+		self->aq_link_status.mbps = 10;
+		break;
+	default:
+		self->aq_link_status.mbps = 0;
+	}
+
+	return 0;
+}
+
+static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
+{
+	struct mac_address_aligned_s mac_address;
+
+	hw_atl2_shared_buffer_get(self, mac_address, mac_address);
+	ether_addr_copy(mac, (u8 *)mac_address.aligned.mac_address);
+
+	if ((mac[0] & 0x01U) || ((mac[0] | mac[1] | mac[2]) == 0x00U)) {
+		unsigned int rnd = 0;
+		u32 h;
+		u32 l;
+
+		get_random_bytes(&rnd, sizeof(unsigned int));
+
+		l = 0xE3000000U | (0xFFFFU & rnd) | (0x00 << 16);
+		h = 0x8001300EU;
+
+		mac[5] = (u8)(0xFFU & l);
+		l >>= 8;
+		mac[4] = (u8)(0xFFU & l);
+		l >>= 8;
+		mac[3] = (u8)(0xFFU & l);
+		l >>= 8;
+		mac[2] = (u8)(0xFFU & l);
+		mac[1] = (u8)(0xFFU & h);
+		h >>= 8;
+		mac[0] = (u8)(0xFFU & h);
+	}
+
+	return 0;
+}
+
+static int aq_a2_fw_update_stats(struct aq_hw_s *self)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct statistics_s stats;
+
+	hw_atl2_shared_buffer_read_safe(self, stats, &stats);
+
+#define AQ_SDELTA(_N_, _F_) (self->curr_stats._N_ += \
+			stats.msm._F_ - priv->last_stats.msm._F_)
+
+	if (self->aq_link_status.mbps) {
+		AQ_SDELTA(uprc, rx_unicast_frames);
+		AQ_SDELTA(mprc, rx_multicast_frames);
+		AQ_SDELTA(bprc, rx_broadcast_frames);
+		AQ_SDELTA(erpr, rx_error_frames);
+
+		AQ_SDELTA(uptc, tx_unicast_frames);
+		AQ_SDELTA(mptc, tx_multicast_frames);
+		AQ_SDELTA(bptc, tx_broadcast_frames);
+		AQ_SDELTA(erpt, tx_errors);
+
+		AQ_SDELTA(ubrc, rx_unicast_octets);
+		AQ_SDELTA(ubtc, tx_unicast_octets);
+		AQ_SDELTA(mbrc, rx_multicast_octets);
+		AQ_SDELTA(mbtc, tx_multicast_octets);
+		AQ_SDELTA(bbrc, rx_broadcast_octets);
+		AQ_SDELTA(bbtc, tx_broadcast_octets);
+	}
+#undef AQ_SDELTA
+	self->curr_stats.dma_pkt_rc =
+		hw_atl_stats_rx_dma_good_pkt_counter_get(self);
+	self->curr_stats.dma_pkt_tc =
+		hw_atl_stats_tx_dma_good_pkt_counter_get(self);
+	self->curr_stats.dma_oct_rc =
+		hw_atl_stats_rx_dma_good_octet_counter_get(self);
+	self->curr_stats.dma_oct_tc =
+		hw_atl_stats_tx_dma_good_octet_counter_get(self);
+	self->curr_stats.dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
+
+	memcpy(&priv->last_stats, &stats, sizeof(stats));
+
+	return 0;
+}
+
+static int aq_a2_fw_renegotiate(struct aq_hw_s *self)
+{
+	struct link_options_s link_options;
+	int err;
+
+	hw_atl2_shared_buffer_get(self, link_options, link_options);
+	link_options.link_renegotiate = 1U;
+	hw_atl2_shared_buffer_write(self, link_options, link_options);
+
+	err = hw_atl2_shared_buffer_finish_ack(self);
+
+	/* We should put renegotiate status back to zero
+	 * after command completes
+	 */
+	link_options.link_renegotiate = 0U;
+	hw_atl2_shared_buffer_write(self, link_options, link_options);
+
+	return err;
+}
+
+int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
+						u8 *base_index, u8 *count)
+{
+	struct filter_caps_s filter_caps;
+	int err;
+
+	err = hw_atl2_shared_buffer_read_safe(self, filter_caps, &filter_caps);
+	if (err)
+		return err;
+
+	*base_index = filter_caps.rslv_tbl_base_index;
+	*count = filter_caps.rslv_tbl_count;
+	return 0;
+}
+
+const struct aq_fw_ops aq_a2_fw_ops = {
+	.init               = aq_a2_fw_init,
+	.deinit             = aq_a2_fw_deinit,
+	.reset              = NULL,
+	.renegotiate        = aq_a2_fw_renegotiate,
+	.get_mac_permanent  = aq_a2_fw_get_mac_permanent,
+	.set_link_speed     = aq_a2_fw_set_link_speed,
+	.set_state          = aq_a2_fw_set_state,
+	.update_link_status = aq_a2_fw_update_link_status,
+	.update_stats       = aq_a2_fw_update_stats,
+};
-- 
cgit v1.2.3


From b3f0c79cba2060c1af37b32d60eff8598391519e Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:39 +0300
Subject: net: atlantic: A2 hw_ops skeleton

This patch adds basic hw_ops layout for A2.

Actual implementation will be added in the follow-up patches.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/Makefile    |   1 +
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |   1 +
 .../net/ethernet/aquantia/atlantic/aq_pci_func.c   |  39 +++-
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 226 +++++++++++++++++++++
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h   |  14 ++
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |  20 ++
 6 files changed, 294 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index fa845c15d0e1..23f0e5b5fcdb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -25,6 +25,7 @@ atlantic-objs := aq_main.o \
 	hw_atl/hw_atl_utils.o \
 	hw_atl/hw_atl_utils_fw2x.o \
 	hw_atl/hw_atl_llh.o \
+	hw_atl2/hw_atl2.o \
 	hw_atl2/hw_atl2_utils_fw.o \
 	hw_atl2/hw_atl2_llh.o \
 	macsec/macsec_api.o
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index e770d91e0876..03fea9469f01 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -55,6 +55,7 @@ struct aq_hw_caps_s {
 	u8 rx_rings;
 	bool flow_control;
 	bool is_64_dma;
+	u32 priv_data_len;
 };
 
 struct aq_hw_link_status_s {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 2edf137a7030..ce46cdbc69e6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -16,6 +16,7 @@
 #include "aq_pci_func.h"
 #include "hw_atl/hw_atl_a0.h"
 #include "hw_atl/hw_atl_b0.h"
+#include "hw_atl2/hw_atl2.h"
 #include "aq_filters.h"
 #include "aq_drvinfo.h"
 #include "aq_macsec.h"
@@ -41,6 +42,13 @@ static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC111S), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC112S), },
 
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113DEV), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113CS), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC114CS), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113C), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC115C), },
+
 	{}
 };
 
@@ -70,6 +78,13 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_AQC109S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc109s, },
 	{ AQ_DEVICE_ID_AQC111S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc111s, },
 	{ AQ_DEVICE_ID_AQC112S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc112s, },
+
+	{ AQ_DEVICE_ID_AQC113DEV,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC113,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC113CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC114CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC113C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC115C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
 };
 
 MODULE_DEVICE_TABLE(pci, aq_pci_tbl);
@@ -104,10 +119,8 @@ int aq_pci_func_init(struct pci_dev *pdev)
 	int err;
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (!err) {
+	if (!err)
 		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-
-	}
 	if (err) {
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (!err)
@@ -237,6 +250,15 @@ static int aq_pci_probe(struct pci_dev *pdev,
 		goto err_ioremap;
 	}
 	self->aq_hw->aq_nic_cfg = aq_nic_get_cfg(self);
+	if (self->aq_hw->aq_nic_cfg->aq_hw_caps->priv_data_len) {
+		int len = self->aq_hw->aq_nic_cfg->aq_hw_caps->priv_data_len;
+
+		self->aq_hw->priv = kzalloc(len, GFP_KERNEL);
+		if (!self->aq_hw->priv) {
+			err = -ENOMEM;
+			goto err_free_aq_hw;
+		}
+	}
 
 	for (bar = 0; bar < 4; ++bar) {
 		if (IORESOURCE_MEM & pci_resource_flags(pdev, bar)) {
@@ -245,19 +267,19 @@ static int aq_pci_probe(struct pci_dev *pdev,
 			mmio_pa = pci_resource_start(pdev, bar);
 			if (mmio_pa == 0U) {
 				err = -EIO;
-				goto err_free_aq_hw;
+				goto err_free_aq_hw_priv;
 			}
 
 			reg_sz = pci_resource_len(pdev, bar);
 			if ((reg_sz <= 24 /*ATL_REGS_SIZE*/)) {
 				err = -EIO;
-				goto err_free_aq_hw;
+				goto err_free_aq_hw_priv;
 			}
 
 			self->aq_hw->mmio = ioremap(mmio_pa, reg_sz);
 			if (!self->aq_hw->mmio) {
 				err = -EIO;
-				goto err_free_aq_hw;
+				goto err_free_aq_hw_priv;
 			}
 			break;
 		}
@@ -265,7 +287,7 @@ static int aq_pci_probe(struct pci_dev *pdev,
 
 	if (bar == 4) {
 		err = -EIO;
-		goto err_free_aq_hw;
+		goto err_free_aq_hw_priv;
 	}
 
 	numvecs = min((u8)AQ_CFG_VECS_DEF,
@@ -305,6 +327,8 @@ err_register:
 	aq_pci_free_irq_vectors(self);
 err_hwinit:
 	iounmap(self->aq_hw->mmio);
+err_free_aq_hw_priv:
+	kfree(self->aq_hw->priv);
 err_free_aq_hw:
 	kfree(self->aq_hw);
 err_ioremap:
@@ -332,6 +356,7 @@ static void aq_pci_remove(struct pci_dev *pdev)
 		aq_nic_free_vectors(self);
 		aq_pci_free_irq_vectors(self);
 		iounmap(self->aq_hw->mmio);
+		kfree(self->aq_hw->priv);
 		kfree(self->aq_hw);
 		pci_release_regions(pdev);
 		free_netdev(self->ndev);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
new file mode 100644
index 000000000000..58c74a73b6cf
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#include "aq_hw.h"
+#include "hw_atl2_utils.h"
+#include "hw_atl2_internal.h"
+
+#define DEFAULT_BOARD_BASIC_CAPABILITIES \
+	.is_64_dma = true,		  \
+	.msix_irqs = 8U,		  \
+	.irq_mask = ~0U,		  \
+	.vecs = HW_ATL2_RSS_MAX,	  \
+	.tcs = HW_ATL2_TC_MAX,	  \
+	.rxd_alignment = 1U,		  \
+	.rxd_size = HW_ATL2_RXD_SIZE,   \
+	.rxds_max = HW_ATL2_MAX_RXD,    \
+	.rxds_min = HW_ATL2_MIN_RXD,    \
+	.txd_alignment = 1U,		  \
+	.txd_size = HW_ATL2_TXD_SIZE,   \
+	.txds_max = HW_ATL2_MAX_TXD,    \
+	.txds_min = HW_ATL2_MIN_TXD,    \
+	.txhwb_alignment = 4096U,	  \
+	.tx_rings = HW_ATL2_TX_RINGS,   \
+	.rx_rings = HW_ATL2_RX_RINGS,   \
+	.hw_features = NETIF_F_HW_CSUM |  \
+			NETIF_F_RXCSUM |  \
+			NETIF_F_RXHASH |  \
+			NETIF_F_SG |      \
+			NETIF_F_TSO |     \
+			NETIF_F_TSO6 |    \
+			NETIF_F_LRO |     \
+			NETIF_F_NTUPLE |  \
+			NETIF_F_HW_VLAN_CTAG_FILTER | \
+			NETIF_F_HW_VLAN_CTAG_RX |     \
+			NETIF_F_HW_VLAN_CTAG_TX |     \
+			NETIF_F_GSO_UDP_L4      |     \
+			NETIF_F_GSO_PARTIAL,          \
+	.hw_priv_flags = IFF_UNICAST_FLT, \
+	.flow_control = true,		  \
+	.mtu = HW_ATL2_MTU_JUMBO,	  \
+	.mac_regs_count = 72,		  \
+	.hw_alive_check_addr = 0x10U,     \
+	.priv_data_len = sizeof(struct hw_atl2_priv)
+
+const struct aq_hw_caps_s hw_atl2_caps_aqc113 = {
+	DEFAULT_BOARD_BASIC_CAPABILITIES,
+	.media_type = AQ_HW_MEDIA_TYPE_TP,
+	.link_speed_msk = AQ_NIC_RATE_10G |
+			  AQ_NIC_RATE_5G  |
+			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_1G  |
+			  AQ_NIC_RATE_100M      |
+			  AQ_NIC_RATE_10M,
+};
+
+static int hw_atl2_hw_reset(struct aq_hw_s *self)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_rss_hash_set(struct aq_hw_s *self,
+				   struct aq_rss_parameters *rss_params)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
+			      struct aq_rss_parameters *rss_params)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_offload_set(struct aq_hw_s *self,
+				  struct aq_nic_cfg_s *aq_nic_cfg)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u8 base_index, count;
+	int err;
+
+	err = hw_atl2_utils_get_action_resolve_table_caps(self, &base_index,
+							  &count);
+	if (err)
+		return err;
+
+	priv->art_base_index = 8 * base_index;
+
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_tx_start(struct aq_hw_s *self,
+				    struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_rx_start(struct aq_hw_s *self,
+				    struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_start(struct aq_hw_s *self)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_tx_xmit(struct aq_hw_s *self,
+				   struct aq_ring_s *ring,
+				   unsigned int frags)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_rx_init(struct aq_hw_s *self,
+				   struct aq_ring_s *aq_ring,
+				   struct aq_ring_param_s *aq_ring_param)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_tx_init(struct aq_hw_s *self,
+				   struct aq_ring_s *aq_ring,
+				   struct aq_ring_param_s *aq_ring_param)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_rx_fill(struct aq_hw_s *self, struct aq_ring_s *ring,
+				   unsigned int sw_tail_old)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_tx_head_update(struct aq_hw_s *self,
+					  struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_rx_receive(struct aq_hw_s *self,
+				      struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_irq_enable(struct aq_hw_s *self, u64 mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_irq_disable(struct aq_hw_s *self, u64 mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_irq_read(struct aq_hw_s *self, u64 *mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_interrupt_moderation_set(struct aq_hw_s *self)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_stop(struct aq_hw_s *self)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hw_atl2_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self)
+{
+	return &self->curr_stats;
+}
+
+const struct aq_hw_ops hw_atl2_ops = {
+	.hw_set_mac_address   = hw_atl2_hw_mac_addr_set,
+	.hw_init              = hw_atl2_hw_init,
+	.hw_reset             = hw_atl2_hw_reset,
+	.hw_start             = hw_atl2_hw_start,
+	.hw_ring_tx_start     = hw_atl2_hw_ring_tx_start,
+	.hw_ring_tx_stop      = hw_atl2_hw_ring_tx_stop,
+	.hw_ring_rx_start     = hw_atl2_hw_ring_rx_start,
+	.hw_ring_rx_stop      = hw_atl2_hw_ring_rx_stop,
+	.hw_stop              = hw_atl2_hw_stop,
+
+	.hw_ring_tx_xmit         = hw_atl2_hw_ring_tx_xmit,
+	.hw_ring_tx_head_update  = hw_atl2_hw_ring_tx_head_update,
+
+	.hw_ring_rx_receive      = hw_atl2_hw_ring_rx_receive,
+	.hw_ring_rx_fill         = hw_atl2_hw_ring_rx_fill,
+
+	.hw_irq_enable           = hw_atl2_hw_irq_enable,
+	.hw_irq_disable          = hw_atl2_hw_irq_disable,
+	.hw_irq_read             = hw_atl2_hw_irq_read,
+
+	.hw_ring_rx_init             = hw_atl2_hw_ring_rx_init,
+	.hw_ring_tx_init             = hw_atl2_hw_ring_tx_init,
+	.hw_interrupt_moderation_set = hw_atl2_hw_interrupt_moderation_set,
+	.hw_rss_set                  = hw_atl2_hw_rss_set,
+	.hw_rss_hash_set             = hw_atl2_hw_rss_hash_set,
+	.hw_get_hw_stats             = hw_atl2_utils_get_hw_stats,
+	.hw_set_offload              = hw_atl2_hw_offload_set,
+};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
new file mode 100644
index 000000000000..de8723f1c28a
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#ifndef HW_ATL2_H
+#define HW_ATL2_H
+
+#include "aq_common.h"
+
+extern const struct aq_hw_caps_s hw_atl2_caps_aqc113;
+extern const struct aq_hw_ops hw_atl2_ops;
+
+#endif /* HW_ATL2_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index 233db3222bb8..f82058484332 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -9,9 +9,29 @@
 #include "hw_atl2_utils.h"
 
 #define HW_ATL2_MTU_JUMBO  16352U
+#define HW_ATL2_MTU        1514U
+
+#define HW_ATL2_TX_RINGS 4U
+#define HW_ATL2_RX_RINGS 4U
+
+#define HW_ATL2_RINGS_MAX 32U
+#define HW_ATL2_TXD_SIZE       (16U)
+#define HW_ATL2_RXD_SIZE       (16U)
+
+#define HW_ATL2_TC_MAX 1U
+#define HW_ATL2_RSS_MAX 8U
+
+#define HW_ATL2_MIN_RXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL2_MIN_TXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL2_MAX_RXD 8184U
+#define HW_ATL2_MAX_TXD 8184U
 
 struct hw_atl2_priv {
 	struct statistics_s last_stats;
+	unsigned int art_base_index;
 };
 
 #endif /* HW_ATL2_INTERNAL_H */
-- 
cgit v1.2.3


From 57fe8fd2255cd97d2c2a9b69cb5172c0f15343b8 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:40 +0300
Subject: net: atlantic: HW bindings for A2 RFP

RPF is one of the modules which has been significantly
changed/extended on A2.

This patch adds the necessary A2 register definitions
for RPF, which are used in follow-up patches.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Co-developed-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c |  14 ++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h |   6 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |  74 ++++++++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |  26 ++++
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        | 164 +++++++++++++++++++++
 5 files changed, 284 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index d1f68fc16291..8dd3232d72c4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -693,6 +693,13 @@ void hw_atl_rpfl2multicast_flr_en_set(struct aq_hw_s *aq_hw,
 			    HW_ATL_RPFL2MC_ENF_SHIFT, l2multicast_flr_en);
 }
 
+u32 hw_atl_rpfl2promiscuous_mode_en_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, HW_ATL_RPFL2PROMIS_MODE_ADR,
+				  HW_ATL_RPFL2PROMIS_MODE_MSK,
+				  HW_ATL_RPFL2PROMIS_MODE_SHIFT);
+}
+
 void hw_atl_rpfl2promiscuous_mode_en_set(struct aq_hw_s *aq_hw,
 					 u32 l2promiscuous_mode_en)
 {
@@ -867,6 +874,13 @@ void hw_atl_rpf_vlan_prom_mode_en_set(struct aq_hw_s *aq_hw,
 			    vlan_prom_mode_en);
 }
 
+u32 hw_atl_rpf_vlan_prom_mode_en_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, HW_ATL_RPF_VL_PROMIS_MODE_ADR,
+				  HW_ATL_RPF_VL_PROMIS_MODE_MSK,
+				  HW_ATL_RPF_VL_PROMIS_MODE_SHIFT);
+}
+
 void hw_atl_rpf_vlan_accept_untagged_packets_set(struct aq_hw_s *aq_hw,
 						 u32 vlan_acc_untagged_packets)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 62992b23c0e8..a4699a682973 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -349,6 +349,9 @@ void hw_atl_rpfl2multicast_flr_en_set(struct aq_hw_s *aq_hw,
 				      u32 l2multicast_flr_en,
 				      u32 filter);
 
+/* get l2 promiscuous mode enable */
+u32 hw_atl_rpfl2promiscuous_mode_en_get(struct aq_hw_s *aq_hw);
+
 /* set l2 promiscuous mode enable */
 void hw_atl_rpfl2promiscuous_mode_en_set(struct aq_hw_s *aq_hw,
 					 u32 l2promiscuous_mode_en);
@@ -420,6 +423,9 @@ void hw_atl_rpf_vlan_outer_etht_set(struct aq_hw_s *aq_hw, u32 vlan_outer_etht);
 void hw_atl_rpf_vlan_prom_mode_en_set(struct aq_hw_s *aq_hw,
 				      u32 vlan_prom_mode_en);
 
+/* Get VLAN promiscuous mode enable */
+u32 hw_atl_rpf_vlan_prom_mode_en_get(struct aq_hw_s *aq_hw);
+
 /* Set VLAN untagged action */
 void hw_atl_rpf_vlan_untagged_act_set(struct aq_hw_s *aq_hw,
 				      u32 vlan_untagged_act);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index b6164bc5fffd..67f46a7bdcda 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -7,6 +7,80 @@
 #include "hw_atl2_llh_internal.h"
 #include "aq_hw_utils.h"
 
+void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR,
+			    HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_MSK,
+			    HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_SHIFT,
+			    rss_hash_type);
+}
+
+/* rpf */
+
+void hw_atl2_rpf_new_enable_set(struct aq_hw_s *aq_hw, u32 enable)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_NEW_EN_ADR,
+			    HW_ATL2_RPF_NEW_EN_MSK,
+			    HW_ATL2_RPF_NEW_EN_SHIFT,
+			    enable);
+}
+
+void hw_atl2_rpfl2_uc_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPFL2UC_TAG_ADR(filter),
+			    HW_ATL2_RPFL2UC_TAG_MSK,
+			    HW_ATL2_RPFL2UC_TAG_SHIFT,
+			    tag);
+}
+
+void hw_atl2_rpfl2_bc_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_L2_BC_TAG_ADR,
+			    HW_ATL2_RPF_L2_BC_TAG_MSK,
+			    HW_ATL2_RPF_L2_BC_TAG_SHIFT,
+			    tag);
+}
+
+void hw_atl2_new_rpf_rss_redir_set(struct aq_hw_s *aq_hw, u32 tc, u32 index,
+				   u32 queue)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_RSS_REDIR_ADR(tc, index),
+			    HW_ATL2_RPF_RSS_REDIR_MSK(tc),
+			    HW_ATL2_RPF_RSS_REDIR_SHIFT(tc),
+			    queue);
+}
+
+void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_VL_TAG_ADR(filter),
+			    HW_ATL2_RPF_VL_TAG_MSK,
+			    HW_ATL2_RPF_VL_TAG_SHIFT,
+			    tag);
+}
+
+/* set action resolver record */
+void hw_atl2_rpf_act_rslvr_record_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 tag, u32 mask, u32 action)
+{
+	aq_hw_write_reg(aq_hw,
+			HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_ADR(location),
+			tag);
+	aq_hw_write_reg(aq_hw,
+			HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_ADR(location),
+			mask);
+	aq_hw_write_reg(aq_hw,
+			HW_ATL2_RPF_ACT_RSLVR_ACTN_ADR(location),
+			action);
+}
+
+void hw_atl2_rpf_act_rslvr_section_en_set(struct aq_hw_s *aq_hw, u32 sections)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_REC_TAB_EN_ADR,
+			    HW_ATL2_RPF_REC_TAB_EN_MSK,
+			    HW_ATL2_RPF_REC_TAB_EN_SHIFT,
+			    sections);
+}
+
 void hw_atl2_mif_shared_buf_get(struct aq_hw_s *aq_hw, int offset, u32 *data,
 				int len)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index 8ef8bd6b2534..bd5b0d5a8084 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -10,6 +10,32 @@
 
 struct aq_hw_s;
 
+/** Set RSS HASH type */
+void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type);
+
+/* set new RPF enable */
+void hw_atl2_rpf_new_enable_set(struct aq_hw_s *aq_hw, u32 enable);
+
+/* set l2 unicast filter tag */
+void hw_atl2_rpfl2_uc_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter);
+
+/* set l2 broadcast filter tag */
+void hw_atl2_rpfl2_bc_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag);
+
+/* set new rss redirection table */
+void hw_atl2_new_rpf_rss_redir_set(struct aq_hw_s *aq_hw, u32 tc, u32 index,
+				   u32 queue);
+
+/* Set VLAN filter tag */
+void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter);
+
+/* set action resolver record */
+void hw_atl2_rpf_act_rslvr_record_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 tag, u32 mask, u32 action);
+
+/* set enable action resolver section */
+void hw_atl2_rpf_act_rslvr_section_en_set(struct aq_hw_s *aq_hw, u32 sections);
+
 /* get data from firmware shared input buffer */
 void hw_atl2_mif_shared_buf_get(struct aq_hw_s *aq_hw, int offset, u32 *data,
 				int len);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index 835deb2d1950..886491b6ab73 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -6,6 +6,170 @@
 #ifndef HW_ATL2_LLH_INTERNAL_H
 #define HW_ATL2_LLH_INTERNAL_H
 
+/* RX pif_rpf_rss_hash_type_i Bitfield Definitions
+ */
+#define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR 0x000054C8
+#define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_MSK 0x000001FF
+#define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_MSKN 0xFFFFFE00
+#define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_SHIFT 0
+#define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_WIDTH 9
+
+/* rx rpf_new_rpf_en bitfield definitions
+ * preprocessor definitions for the bitfield "rpf_new_rpf_en_i".
+ * port="pif_rpf_new_rpf_en_i
+ */
+
+/* register address for bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_ADR 0x00005104
+/* bitmask for bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_MSK 0x00000800
+/* inverted bitmask for bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_MSKN 0xfffff7ff
+/* lower bit position of bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_SHIFT 11
+/* width of bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_WIDTH 1
+/* default value of bitfield rpf_new_rpf_en */
+#define HW_ATL2_RPF_NEW_EN_DEFAULT 0x0
+
+/* rx l2_uc_req_tag0{f}[5:0] bitfield definitions
+ * preprocessor definitions for the bitfield "l2_uc_req_tag0{f}[7:0]".
+ * parameter: filter {f} | stride size 0x8 | range [0, 37]
+ * port="pif_rpf_l2_uc_req_tag0[5:0]"
+ */
+
+/* register address for bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_ADR(filter) (0x00005114 + (filter) * 0x8)
+/* bitmask for bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_MSK 0x0FC00000
+/* inverted bitmask for bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_MSKN 0xF03FFFFF
+/* lower bit position of bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_SHIFT 22
+/* width of bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_WIDTH 6
+/* default value of bitfield l2_uc_req_tag0{f}[2:0] */
+#define HW_ATL2_RPFL2UC_TAG_DEFAULT 0x0
+
+/* rpf_l2_bc_req_tag[5:0] bitfield definitions
+ * preprocessor definitions for the bitfield "rpf_l2_bc_req_tag[5:0]".
+ * port="pifrpf_l2_bc_req_tag_i[5:0]"
+ */
+
+/* register address for bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_ADR 0x000050F0
+/* bitmask for bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_MSK 0x0000003F
+/* inverted bitmask for bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_MSKN 0xffffffc0
+/* lower bit position of bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_SHIFT 0
+/* width of bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_WIDTH 6
+/* default value of bitfield rpf_l2_bc_req_tag */
+#define HW_ATL2_RPF_L2_BC_TAG_DEFAULT 0x0
+
+/* rx rpf_rss_red1_data_[4:0] bitfield definitions
+ * preprocessor definitions for the bitfield "rpf_rss_red1_data[4:0]".
+ * port="pif_rpf_rss_red1_data_i[4:0]"
+ */
+
+/* register address for bitfield rpf_rss_red1_data[4:0] */
+#define HW_ATL2_RPF_RSS_REDIR_ADR(TC, INDEX) (0x00006200 + \
+					(0x100 * !!((TC) > 3)) + (INDEX) * 4)
+/* bitmask for bitfield rpf_rss_red1_data[4:0] */
+#define HW_ATL2_RPF_RSS_REDIR_MSK(TC)  (0x00000001F << (5 * ((TC) % 4)))
+/* lower bit position of bitfield rpf_rss_red1_data[4:0] */
+#define HW_ATL2_RPF_RSS_REDIR_SHIFT(TC) (5 * ((TC) % 4))
+/* width of bitfield rpf_rss_red1_data[4:0] */
+#define HW_ATL2_RPF_RSS_REDIR_WIDTH 5
+/* default value of bitfield rpf_rss_red1_data[4:0] */
+#define HW_ATL2_RPF_RSS_REDIR_DEFAULT 0x0
+
+/* rx vlan_req_tag0{f}[3:0] bitfield definitions
+ * preprocessor definitions for the bitfield "vlan_req_tag0{f}[3:0]".
+ * parameter: filter {f} | stride size 0x4 | range [0, 15]
+ * port="pif_rpf_vlan_req_tag0[3:0]"
+ */
+
+/* register address for bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_ADR(filter) (0x00005290 + (filter) * 0x4)
+/* bitmask for bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_MSK 0x0000F000
+/* inverted bitmask for bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_MSKN 0xFFFF0FFF
+/* lower bit position of bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_SHIFT 12
+/* width of bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_WIDTH 4
+/* default value of bitfield vlan_req_tag0{f}[3:0] */
+#define HW_ATL2_RPF_VL_TAG_DEFAULT 0x0
+
+/* ahb_mem_addr{f}[31:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "ahb_mem_addr{f}[31:0]".
+ * Parameter: filter {f} | stride size 0x10 | range [0, 127]
+ * PORT="ahb_mem_addr{f}[31:0]"
+ */
+
+/* Register address for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_ADR(filter) \
+	(0x00014000u + (filter) * 0x10)
+/* Bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_MSKN 0x00000000u
+/* Lower bit position of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_SHIFT 0
+/* Width of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_WIDTH 31
+/* Default value of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_REQ_TAG_DEFAULT 0x0
+
+/* Register address for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_ADR(filter) \
+	(0x00014004u + (filter) * 0x10)
+/* Bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_MSKN 0x00000000u
+/* Lower bit position of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_SHIFT 0
+/* Width of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_WIDTH 31
+/* Default value of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_TAG_MASK_DEFAULT 0x0
+
+/* Register address for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_ADR(filter) \
+	(0x00014008u + (filter) * 0x10)
+/* Bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_MSK 0x000007FFu
+/* Inverted bitmask for bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_MSKN 0xFFFFF800u
+/* Lower bit position of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_SHIFT 0
+/* Width of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_WIDTH 10
+/* Default value of bitfield ahb_mem_addr{f}[31:0] */
+#define HW_ATL2_RPF_ACT_RSLVR_ACTN_DEFAULT 0x0
+
+/* rpf_rec_tab_en[15:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "rpf_rec_tab_en[15:0]".
+ * PORT="pif_rpf_rec_tab_en[15:0]"
+ */
+/* Register address for bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_ADR 0x00006ff0u
+/* Bitmask for bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_MSK 0x0000FFFFu
+/* Inverted bitmask for bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_MSKN 0xFFFF0000u
+/* Lower bit position of bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_SHIFT 0
+/* Width of bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_WIDTH 16
+/* Default value of bitfield rpf_rec_tab_en[15:0] */
+#define HW_ATL2_RPF_REC_TAB_EN_DEFAULT 0x0
+
 /* Register address for firmware shared input buffer */
 #define HW_ATL2_MIF_SHARED_BUFFER_IN_ADR(dword) (0x00012000U + (dword) * 0x4U)
 /* Register address for firmware shared output buffer */
-- 
cgit v1.2.3


From 3417368494db497c0426d1dcc46c4c459ff43ca7 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:41 +0300
Subject: net: atlantic: add A2 RPF hw_ops

This patch adds RPF-related hw_ops, which are needed for basic
functionality.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Co-developed-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        |   2 +
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 208 +++++++++++++++++++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |  49 +++++
 3 files changed, 259 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 5513254642b3..5db57ea9a5bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -360,6 +360,8 @@ struct aq_rx_filter_vlan {
 	u8 queue;
 };
 
+#define HW_ATL_VLAN_MAX_FILTERS         16U
+
 struct aq_rx_filter_l2 {
 	s8 queue;
 	u8 location;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 58c74a73b6cf..7dd5f9a1c505 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -4,9 +4,17 @@
  */
 
 #include "aq_hw.h"
+#include "aq_hw_utils.h"
+#include "aq_nic.h"
+#include "hw_atl/hw_atl_utils.h"
+#include "hw_atl/hw_atl_llh.h"
 #include "hw_atl2_utils.h"
+#include "hw_atl2_llh.h"
 #include "hw_atl2_internal.h"
 
+static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
+				       u32 tag, u32 mask, u32 action);
+
 #define DEFAULT_BOARD_BASIC_CAPABILITIES \
 	.is_64_dma = true,		  \
 	.msix_irqs = 8U,		  \
@@ -55,6 +63,11 @@ const struct aq_hw_caps_s hw_atl2_caps_aqc113 = {
 			  AQ_NIC_RATE_10M,
 };
 
+static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self)
+{
+	return hw_atl_reg_glb_cpu_sem_get(self, HW_ATL2_FW_SM_ACT_RSLVR);
+}
+
 static int hw_atl2_hw_reset(struct aq_hw_s *self)
 {
 	return -EOPNOTSUPP;
@@ -78,6 +91,60 @@ static int hw_atl2_hw_offload_set(struct aq_hw_s *self,
 	return -EOPNOTSUPP;
 }
 
+static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
+						  bool promisc)
+{
+	u16 off_action = (!promisc &&
+			  !hw_atl_rpfl2promiscuous_mode_en_get(self)) ?
+				HW_ATL2_ACTION_DROP : HW_ATL2_ACTION_DISABLE;
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u8 index;
+
+	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_OFF_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0,
+				    HW_ATL2_RPF_TAG_VLAN_MASK |
+				    HW_ATL2_RPF_TAG_UNTAG_MASK, off_action);
+}
+
+static void hw_atl2_hw_new_rx_filter_promisc(struct aq_hw_s *self, bool promisc)
+{
+	u16 off_action = promisc ? HW_ATL2_ACTION_DISABLE : HW_ATL2_ACTION_DROP;
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	bool vlan_promisc_enable;
+	u8 index;
+
+	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_OFF_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0,
+				    HW_ATL2_RPF_TAG_UC_MASK |
+				    HW_ATL2_RPF_TAG_ALLMC_MASK,
+				    off_action);
+
+	/* turn VLAN promisc mode too */
+	vlan_promisc_enable = hw_atl_rpf_vlan_prom_mode_en_get(self);
+	hw_atl2_hw_new_rx_filter_vlan_promisc(self, promisc |
+					      vlan_promisc_enable);
+}
+
+static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
+				       u32 tag, u32 mask, u32 action)
+{
+	u32 val;
+	int err;
+
+	err = readx_poll_timeout_atomic(hw_atl2_sem_act_rslvr_get,
+					self, val, val == 1,
+					1, 10000U);
+	if (err)
+		return err;
+
+	hw_atl2_rpf_act_rslvr_record_set(self, location, tag, mask,
+					 action);
+
+	hw_atl_reg_glb_cpu_sem_set(self, 1, HW_ATL2_FW_SM_ACT_RSLVR);
+
+	return err;
+}
+
 static int hw_atl2_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
 {
 	return -EOPNOTSUPP;
@@ -170,6 +237,88 @@ static int hw_atl2_hw_irq_read(struct aq_hw_s *self, u64 *mask)
 	return -EOPNOTSUPP;
 }
 
+#define IS_FILTER_ENABLED(_F_) ((packet_filter & (_F_)) ? 1U : 0U)
+
+static int hw_atl2_hw_packet_filter_set(struct aq_hw_s *self,
+					unsigned int packet_filter)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	u32 vlan_promisc;
+	u32 l2_promisc;
+	unsigned int i;
+
+	l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) ||
+		     !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET));
+	vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc;
+
+	hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc);
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc);
+
+	hw_atl2_hw_new_rx_filter_promisc(self, IS_FILTER_ENABLED(IFF_PROMISC));
+
+	hw_atl_rpfl2multicast_flr_en_set(self,
+					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+
+	hw_atl_rpfl2_accept_all_mc_packets_set(self,
+					      IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					      IS_FILTER_ENABLED(IFF_MULTICAST));
+
+	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
+
+	for (i = HW_ATL2_MAC_MIN; i < HW_ATL2_MAC_MAX; ++i)
+		hw_atl_rpfl2_uc_flr_en_set(self,
+					   (cfg->is_mc_list_enabled &&
+					    (i <= cfg->mc_list_count)) ?
+				    1U : 0U, i);
+
+	return aq_hw_err_from_flags(self);
+}
+
+#undef IS_FILTER_ENABLED
+
+static int hw_atl2_hw_multicast_list_set(struct aq_hw_s *self,
+					 u8 ar_mac
+					 [AQ_HW_MULTICAST_ADDRESS_MAX]
+					 [ETH_ALEN],
+					 u32 count)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	int err = 0;
+
+	if (count > (HW_ATL2_MAC_MAX - HW_ATL2_MAC_MIN)) {
+		err = -EBADRQC;
+		goto err_exit;
+	}
+	for (cfg->mc_list_count = 0U;
+			cfg->mc_list_count < count;
+			++cfg->mc_list_count) {
+		u32 i = cfg->mc_list_count;
+		u32 h = (ar_mac[i][0] << 8) | (ar_mac[i][1]);
+		u32 l = (ar_mac[i][2] << 24) | (ar_mac[i][3] << 16) |
+					(ar_mac[i][4] << 8) | ar_mac[i][5];
+
+		hw_atl_rpfl2_uc_flr_en_set(self, 0U, HW_ATL2_MAC_MIN + i);
+
+		hw_atl_rpfl2unicast_dest_addresslsw_set(self, l,
+							HW_ATL2_MAC_MIN + i);
+
+		hw_atl_rpfl2unicast_dest_addressmsw_set(self, h,
+							HW_ATL2_MAC_MIN + i);
+
+		hw_atl2_rpfl2_uc_flr_tag_set(self, 1, HW_ATL2_MAC_MIN + i);
+
+		hw_atl_rpfl2_uc_flr_en_set(self, (cfg->is_mc_list_enabled),
+					   HW_ATL2_MAC_MIN + i);
+	}
+
+	err = aq_hw_err_from_flags(self);
+
+err_exit:
+	return err;
+}
+
 static int hw_atl2_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
 	return -EOPNOTSUPP;
@@ -195,6 +344,61 @@ static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self)
 	return &self->curr_stats;
 }
 
+static int hw_atl2_hw_vlan_set(struct aq_hw_s *self,
+			       struct aq_rx_filter_vlan *aq_vlans)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u32 queue;
+	u8 index;
+	int i;
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self, 1U);
+
+	for (i = 0; i < HW_ATL_VLAN_MAX_FILTERS; i++) {
+		queue = HW_ATL2_ACTION_ASSIGN_QUEUE(aq_vlans[i].queue);
+
+		hw_atl_rpf_vlan_flr_en_set(self, 0U, i);
+		hw_atl_rpf_vlan_rxq_en_flr_set(self, 0U, i);
+		index = priv->art_base_index + HW_ATL2_RPF_VLAN_USER_INDEX + i;
+		hw_atl2_act_rslvr_table_set(self, index, 0, 0,
+					    HW_ATL2_ACTION_DISABLE);
+		if (aq_vlans[i].enable) {
+			hw_atl_rpf_vlan_id_flr_set(self,
+						   aq_vlans[i].vlan_id, i);
+			hw_atl_rpf_vlan_flr_act_set(self, 1U, i);
+			hw_atl_rpf_vlan_flr_en_set(self, 1U, i);
+
+			if (aq_vlans[i].queue != 0xFF) {
+				hw_atl_rpf_vlan_rxq_flr_set(self,
+							    aq_vlans[i].queue,
+							    i);
+				hw_atl_rpf_vlan_rxq_en_flr_set(self, 1U, i);
+
+				hw_atl2_rpf_vlan_flr_tag_set(self, i + 2, i);
+
+				index = priv->art_base_index +
+					HW_ATL2_RPF_VLAN_USER_INDEX + i;
+				hw_atl2_act_rslvr_table_set(self, index,
+					(i + 2) << HW_ATL2_RPF_TAG_VLAN_OFFSET,
+					HW_ATL2_RPF_TAG_VLAN_MASK, queue);
+			} else {
+				hw_atl2_rpf_vlan_flr_tag_set(self, 1, i);
+			}
+		}
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl2_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
+{
+	/* set promisc in case of disabing the vlan filter */
+	hw_atl_rpf_vlan_prom_mode_en_set(self, !enable);
+	hw_atl2_hw_new_rx_filter_vlan_promisc(self, !enable);
+
+	return aq_hw_err_from_flags(self);
+}
+
 const struct aq_hw_ops hw_atl2_ops = {
 	.hw_set_mac_address   = hw_atl2_hw_mac_addr_set,
 	.hw_init              = hw_atl2_hw_init,
@@ -218,6 +422,10 @@ const struct aq_hw_ops hw_atl2_ops = {
 
 	.hw_ring_rx_init             = hw_atl2_hw_ring_rx_init,
 	.hw_ring_tx_init             = hw_atl2_hw_ring_tx_init,
+	.hw_packet_filter_set        = hw_atl2_hw_packet_filter_set,
+	.hw_filter_vlan_set          = hw_atl2_hw_vlan_set,
+	.hw_filter_vlan_ctrl         = hw_atl2_hw_vlan_ctrl,
+	.hw_multicast_list_set       = hw_atl2_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl2_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl2_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl2_hw_rss_hash_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index f82058484332..dccc89df2223 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -18,6 +18,10 @@
 #define HW_ATL2_TXD_SIZE       (16U)
 #define HW_ATL2_RXD_SIZE       (16U)
 
+#define HW_ATL2_MAC_UC   0U
+#define HW_ATL2_MAC_MIN  1U
+#define HW_ATL2_MAC_MAX  38U
+
 #define HW_ATL2_TC_MAX 1U
 #define HW_ATL2_RSS_MAX 8U
 
@@ -29,6 +33,51 @@
 #define HW_ATL2_MAX_RXD 8184U
 #define HW_ATL2_MAX_TXD 8184U
 
+#define HW_ATL2_FW_SM_ACT_RSLVR  0x3U
+
+#define HW_ATL2_RPF_TAG_UC_OFFSET      0x0
+#define HW_ATL2_RPF_TAG_ALLMC_OFFSET   0x6
+#define HW_ATL2_RPF_TAG_ET_OFFSET      0x7
+#define HW_ATL2_RPF_TAG_VLAN_OFFSET    0xA
+#define HW_ATL2_RPF_TAG_UNTAG_OFFSET   0xE
+#define HW_ATL2_RPF_TAG_L3_V4_OFFSET   0xF
+#define HW_ATL2_RPF_TAG_L3_V6_OFFSET   0x12
+#define HW_ATL2_RPF_TAG_L4_OFFSET      0x15
+#define HW_ATL2_RPF_TAG_L4_FLEX_OFFSET 0x18
+#define HW_ATL2_RPF_TAG_FLEX_OFFSET    0x1B
+#define HW_ATL2_RPF_TAG_PCP_OFFSET     0x1D
+
+#define HW_ATL2_RPF_TAG_UC_MASK    (0x0000003F << HW_ATL2_RPF_TAG_UC_OFFSET)
+#define HW_ATL2_RPF_TAG_ALLMC_MASK (0x00000001 << HW_ATL2_RPF_TAG_ALLMC_OFFSET)
+#define HW_ATL2_RPF_TAG_UNTAG_MASK (0x00000001 << HW_ATL2_RPF_TAG_UNTAG_OFFSET)
+#define HW_ATL2_RPF_TAG_VLAN_MASK  (0x0000000F << HW_ATL2_RPF_TAG_VLAN_OFFSET)
+#define HW_ATL2_RPF_TAG_ET_MASK    (0x00000007 << HW_ATL2_RPF_TAG_ET_OFFSET)
+#define HW_ATL2_RPF_TAG_L3_V4_MASK (0x00000007 << HW_ATL2_RPF_TAG_L3_V4_OFFSET)
+#define HW_ATL2_RPF_TAG_L3_V6_MASK (0x00000007 << HW_ATL2_RPF_TAG_L3_V6_OFFSET)
+#define HW_ATL2_RPF_TAG_L4_MASK    (0x00000007 << HW_ATL2_RPF_TAG_L4_OFFSET)
+#define HW_ATL2_RPF_TAG_PCP_MASK   (0x00000007 << HW_ATL2_RPF_TAG_PCP_OFFSET)
+
+enum HW_ATL2_RPF_ART_INDEX {
+	HW_ATL2_RPF_L2_PROMISC_OFF_INDEX,
+	HW_ATL2_RPF_VLAN_PROMISC_OFF_INDEX,
+	HW_ATL2_RPF_L3L4_USER_INDEX	= 8,
+	HW_ATL2_RPF_ET_PCP_USER_INDEX	= HW_ATL2_RPF_L3L4_USER_INDEX + 16,
+	HW_ATL2_RPF_VLAN_USER_INDEX	= HW_ATL2_RPF_ET_PCP_USER_INDEX + 16,
+	HW_ATL2_RPF_PCP_TO_TC_INDEX	= HW_ATL2_RPF_VLAN_USER_INDEX +
+					  HW_ATL_VLAN_MAX_FILTERS,
+};
+
+#define HW_ATL2_ACTION(ACTION, RSS, INDEX, VALID) \
+	((((ACTION) & 0x3U) << 8) | \
+	(((RSS) & 0x1U) << 7) | \
+	(((INDEX) & 0x3FU) << 2) | \
+	(((VALID) & 0x1U) << 0))
+
+#define HW_ATL2_ACTION_DROP HW_ATL2_ACTION(0, 0, 0, 1)
+#define HW_ATL2_ACTION_DISABLE HW_ATL2_ACTION(0, 0, 0, 0)
+#define HW_ATL2_ACTION_ASSIGN_QUEUE(QUEUE) HW_ATL2_ACTION(1, 0, (QUEUE), 1)
+#define HW_ATL2_ACTION_ASSIGN_TC(TC) HW_ATL2_ACTION(1, 1, (TC), 1)
+
 struct hw_atl2_priv {
 	struct statistics_s last_stats;
 	unsigned int art_base_index;
-- 
cgit v1.2.3


From ec7629e0c2217963eedb886026a71040c9d32aa9 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:42 +0300
Subject: net: atlantic: HW bindings for basic A2 init/deinit hw_ops

This patch adds A2 register definitions for basic A2 HW
initialization / deinitialization.

Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Co-developed-by: Egor Pomozov <epomozov@marvell.com>
Signed-off-by: Egor Pomozov <epomozov@marvell.com>
Co-developed-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Co-developed-by: Nikita Danilov <ndanilov@marvell.com>
Signed-off-by: Nikita Danilov <ndanilov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |  70 +++++++++++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |  29 ++++++
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        | 108 +++++++++++++++++++++
 3 files changed, 207 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index 67f46a7bdcda..af176e1e5a18 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -58,6 +58,55 @@ void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter)
 			    tag);
 }
 
+/* TX */
+
+void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_ADR,
+			    HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_MSK,
+			    HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_SHIFT,
+			    clk_gate_en);
+}
+
+void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
+						    u32 max_credit,
+						    u32 tc)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc),
+			    HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK,
+			    HW_ATL2_TPS_DATA_TCTCREDIT_MAX_SHIFT,
+			    max_credit);
+}
+
+void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
+						u32 tx_pkt_shed_tc_data_weight,
+						u32 tc)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc),
+			    HW_ATL2_TPS_DATA_TCTWEIGHT_MSK,
+			    HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT,
+			    tx_pkt_shed_tc_data_weight);
+}
+
+u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg(aq_hw, HW_ATL2_FPGA_VER_ADR);
+}
+
+void hw_atl2_init_launchtime(struct aq_hw_s *aq_hw)
+{
+	u32 hw_ver = hw_atl2_get_hw_version(aq_hw);
+
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_LT_CTRL_ADR,
+			    HW_ATL2_LT_CTRL_CLK_RATIO_MSK,
+			    HW_ATL2_LT_CTRL_CLK_RATIO_SHIFT,
+			    hw_ver  < HW_ATL2_FPGA_VER_U32(1, 0, 0, 0) ?
+			    HW_ATL2_LT_CTRL_CLK_RATIO_FULL_SPEED :
+			    hw_ver >= HW_ATL2_FPGA_VER_U32(1, 0, 85, 2) ?
+			    HW_ATL2_LT_CTRL_CLK_RATIO_HALF_SPEED :
+			    HW_ATL2_LT_CTRL_CLK_RATIO_QUATER_SPEED);
+}
+
 /* set action resolver record */
 void hw_atl2_rpf_act_rslvr_record_set(struct aq_hw_s *aq_hw, u8 location,
 				      u32 tag, u32 mask, u32 action)
@@ -128,3 +177,24 @@ u32 hw_atl2_mif_mcp_finished_read_get(struct aq_hw_s *aq_hw)
 				  HW_ATL2_MIF_MCP_FINISHED_READ_MSK,
 				  HW_ATL2_MIF_MCP_FINISHED_READ_SHIFT);
 }
+
+u32 hw_atl2_mif_mcp_boot_reg_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg(aq_hw, HW_ATL2_MIF_BOOT_REG_ADR);
+}
+
+void hw_atl2_mif_mcp_boot_reg_set(struct aq_hw_s *aq_hw, u32 val)
+{
+	return aq_hw_write_reg(aq_hw, HW_ATL2_MIF_BOOT_REG_ADR, val);
+}
+
+u32 hw_atl2_mif_host_req_int_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg(aq_hw, HW_ATL2_MCP_HOST_REQ_INT_ADR);
+}
+
+void hw_atl2_mif_host_req_int_clr(struct aq_hw_s *aq_hw, u32 val)
+{
+	return aq_hw_write_reg(aq_hw, HW_ATL2_MCP_HOST_REQ_INT_CLR_ADR,
+			       val);
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index bd5b0d5a8084..4acbbceb623f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -29,6 +29,23 @@ void hw_atl2_new_rpf_rss_redir_set(struct aq_hw_s *aq_hw, u32 tc, u32 index,
 /* Set VLAN filter tag */
 void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter);
 
+/* set tx buffer clock gate enable */
+void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en);
+
+/* set tx packet scheduler tc data max credit */
+void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
+						    u32 max_credit,
+						    u32 tc);
+
+/* set tx packet scheduler tc data weight */
+void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
+						u32 tx_pkt_shed_tc_data_weight,
+						u32 tc);
+
+u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw);
+
+void hw_atl2_init_launchtime(struct aq_hw_s *aq_hw);
+
 /* set action resolver record */
 void hw_atl2_rpf_act_rslvr_record_set(struct aq_hw_s *aq_hw, u8 location,
 				      u32 tag, u32 mask, u32 action);
@@ -54,4 +71,16 @@ void hw_atl2_mif_host_finished_write_set(struct aq_hw_s *aq_hw, u32 finish);
 /* get mcp finished read shared buffer indication */
 u32 hw_atl2_mif_mcp_finished_read_get(struct aq_hw_s *aq_hw);
 
+/* get mcp boot register */
+u32 hw_atl2_mif_mcp_boot_reg_get(struct aq_hw_s *aq_hw);
+
+/* set mcp boot register */
+void hw_atl2_mif_mcp_boot_reg_set(struct aq_hw_s *aq_hw, u32 val);
+
+/* get host interrupt request */
+u32 hw_atl2_mif_host_req_int_get(struct aq_hw_s *aq_hw);
+
+/* clear host interrupt request */
+void hw_atl2_mif_host_req_int_clr(struct aq_hw_s *aq_hw, u32 val);
+
 #endif /* HW_ATL2_LLH_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index 886491b6ab73..14b78e090950 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -105,6 +105,105 @@
 /* default value of bitfield vlan_req_tag0{f}[3:0] */
 #define HW_ATL2_RPF_VL_TAG_DEFAULT 0x0
 
+/* RX rx_q{Q}_tc_map[2:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "rx_q{Q}_tc_map[2:0]".
+ * Parameter: Queue {Q} | bit-level stride | range [0, 31]
+ * PORT="pif_rx_q0_tc_map_i[2:0]"
+ */
+
+/* Register address for bitfield rx_q{Q}_tc_map[2:0] */
+#define HW_ATL2_RX_Q_TC_MAP_ADR(queue) \
+	(((queue) < 32) ? 0x00005900 + ((queue) / 8) * 4 : 0)
+/* Lower bit position of bitfield rx_q{Q}_tc_map[2:0] */
+#define HW_ATL2_RX_Q_TC_MAP_SHIFT(queue) \
+	(((queue) < 32) ? ((queue) * 4) % 32 : 0)
+/* Width of bitfield rx_q{Q}_tc_map[2:0] */
+#define HW_ATL2_RX_Q_TC_MAP_WIDTH 3
+/* Default value of bitfield rx_q{Q}_tc_map[2:0] */
+#define HW_ATL2_RX_Q_TC_MAP_DEFAULT 0x0
+
+/* tx tx_buffer_clk_gate_en bitfield definitions
+ * preprocessor definitions for the bitfield "tx_buffer_clk_gate_en".
+ * port="pif_tpb_tx_buffer_clk_gate_en_i"
+ */
+
+/* register address for bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_ADR 0x00007900
+/* bitmask for bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_MSK 0x00000020
+/* inverted bitmask for bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_MSKN 0xffffffdf
+/* lower bit position of bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_SHIFT 5
+/* width of bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_WIDTH 1
+/* default value of bitfield tx_buffer_clk_gate_en */
+#define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_DEFAULT 0x0
+
+/* tx data_tc{t}_credit_max[b:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_credit_max[b:0]".
+ * parameter: tc {t} | stride size 0x4 | range [0, 7]
+ * port="pif_tps_data_tc0_credit_max_i[11:0]"
+ */
+
+/* register address for bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc) (0x00007110 + (tc) * 0x4)
+/* bitmask for bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK 0x0fff0000
+/* inverted bitmask for bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSKN 0xf000ffff
+/* lower bit position of bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_SHIFT 16
+/* width of bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_WIDTH 12
+/* default value of bitfield data_tc{t}_credit_max[b:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_DEFAULT 0x0
+
+/* tx data_tc{t}_weight[8:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_weight[8:0]".
+ * parameter: tc {t} | stride size 0x4 | range [0, 7]
+ * port="pif_tps_data_tc0_weight_i[8:0]"
+ */
+
+/* register address for bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc) (0x00007110 + (tc) * 0x4)
+/* bitmask for bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSK 0x000001ff
+/* inverted bitmask for bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSKN 0xfffffe00
+/* lower bit position of bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT 0
+/* width of bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH 9
+/* default value of bitfield data_tc{t}_weight[8:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_DEFAULT 0x0
+
+/* Launch time control register */
+#define HW_ATL2_LT_CTRL_ADR 0x00007a1c
+
+#define HW_ATL2_LT_CTRL_AVB_LEN_CMP_TRSHLD_MSK 0xFFFF0000
+#define HW_ATL2_LT_CTRL_AVB_LEN_CMP_TRSHLD_SHIFT 16
+
+#define HW_ATL2_LT_CTRL_CLK_RATIO_MSK 0x0000FF00
+#define HW_ATL2_LT_CTRL_CLK_RATIO_SHIFT 8
+#define HW_ATL2_LT_CTRL_CLK_RATIO_QUATER_SPEED 4
+#define HW_ATL2_LT_CTRL_CLK_RATIO_HALF_SPEED 2
+#define HW_ATL2_LT_CTRL_CLK_RATIO_FULL_SPEED 1
+
+#define HW_ATL2_LT_CTRL_25G_MODE_SUPPORT_MSK 0x00000008
+#define HW_ATL2_LT_CTRL_25G_MODE_SUPPORT_SHIFT 3
+
+#define HW_ATL2_LT_CTRL_LINK_SPEED_MSK 0x00000007
+#define HW_ATL2_LT_CTRL_LINK_SPEED_SHIFT 0
+
+/* FPGA VER register */
+#define HW_ATL2_FPGA_VER_ADR 0x000000f4
+#define HW_ATL2_FPGA_VER_U32(mj, mi, bl, rv) \
+	((((mj) & 0xff) << 24) | \
+	 (((mi) & 0xff) << 16) | \
+	 (((bl) & 0xff) << 8) | \
+	 (((rv) & 0xff) << 0))
+
 /* ahb_mem_addr{f}[31:0] Bitfield Definitions
  * Preprocessor definitions for the bitfield "ahb_mem_addr{f}[31:0]".
  * Parameter: filter {f} | stride size 0x10 | range [0, 127]
@@ -209,4 +308,13 @@
 /* Default value of bitfield pif_mcp_finished_buf_rd_i */
 #define HW_ATL2_MIF_MCP_FINISHED_READ_DEFAULT 0x0
 
+/* Register address for bitfield pif_mcp_boot_reg */
+#define HW_ATL2_MIF_BOOT_REG_ADR 0x00003040u
+
+#define HW_ATL2_MCP_HOST_REQ_INT_READY BIT(0)
+
+#define HW_ATL2_MCP_HOST_REQ_INT_ADR 0x00000F00u
+#define HW_ATL2_MCP_HOST_REQ_INT_SET_ADR 0x00000F04u
+#define HW_ATL2_MCP_HOST_REQ_INT_CLR_ADR 0x00000F08u
+
 #endif /* HW_ATL2_LLH_INTERNAL_H */
-- 
cgit v1.2.3


From c1be0bf092bd292ee617622c116f5981a34cce96 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Thu, 30 Apr 2020 11:04:43 +0300
Subject: net: atlantic: common functions needed for basic A2 init/deinit
 hw_ops

This patch adds common functions (mostly FW-related), which are
needed for basic A2 HW initialization / deinitialization.

Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Co-developed-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/Makefile    |   1 +
 .../aquantia/atlantic/hw_atl/hw_atl_utils.c        |   3 +-
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        |   2 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils.c      | 139 +++++++++++++++++++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils.h      |   8 ++
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c   |  12 ++
 6 files changed, 163 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 23f0e5b5fcdb..130a105d03f3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -26,6 +26,7 @@ atlantic-objs := aq_main.o \
 	hw_atl/hw_atl_utils_fw2x.o \
 	hw_atl/hw_atl_llh.o \
 	hw_atl2/hw_atl2.o \
+	hw_atl2/hw_atl2_utils.o \
 	hw_atl2/hw_atl2_utils_fw.o \
 	hw_atl2/hw_atl2_llh.o \
 	macsec/macsec_api.o
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 20655a2170cc..1100d40a0302 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -53,7 +53,6 @@ enum mcp_area {
 	MCP_AREA_SETTINGS = 0x20000000,
 };
 
-static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
 static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
@@ -434,7 +433,7 @@ int hw_atl_write_fwsettings_dwords(struct aq_hw_s *self, u32 offset, u32 *p,
 					     p, cnt, MCP_AREA_SETTINGS);
 }
 
-static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual)
+int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual)
 {
 	const u32 dw_major_mask = 0xff000000U;
 	const u32 dw_minor_mask = 0x00ffffffU;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 5db57ea9a5bd..99c1b6644ec3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -634,6 +634,8 @@ int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size);
 int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 			     struct hw_atl_utils_fw_rpc **rpc);
 
+int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
+
 extern const struct aq_fw_ops aq_fw_1x_ops;
 extern const struct aq_fw_ops aq_fw_2x_ops;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c
new file mode 100644
index 000000000000..85ccc9a011a0
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Atlantic Network Driver
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#include <linux/iopoll.h>
+
+#include "aq_hw_utils.h"
+#include "hw_atl/hw_atl_utils.h"
+#include "hw_atl2_utils.h"
+#include "hw_atl2_llh.h"
+#include "hw_atl2_llh_internal.h"
+
+#define HW_ATL2_FW_VER_1X          0x01000000U
+
+#define AQ_A2_BOOT_STARTED         BIT(0x18)
+#define AQ_A2_CRASH_INIT           BIT(0x1B)
+#define AQ_A2_BOOT_CODE_FAILED     BIT(0x1C)
+#define AQ_A2_FW_INIT_FAILED       BIT(0x1D)
+#define AQ_A2_FW_INIT_COMP_SUCCESS BIT(0x1F)
+
+#define AQ_A2_FW_BOOT_FAILED_MASK (AQ_A2_CRASH_INIT | \
+				   AQ_A2_BOOT_CODE_FAILED | \
+				   AQ_A2_FW_INIT_FAILED)
+#define AQ_A2_FW_BOOT_COMPLETE_MASK (AQ_A2_FW_BOOT_FAILED_MASK | \
+				     AQ_A2_FW_INIT_COMP_SUCCESS)
+
+#define AQ_A2_FW_BOOT_REQ_REBOOT        BIT(0x0)
+#define AQ_A2_FW_BOOT_REQ_HOST_BOOT     BIT(0x8)
+#define AQ_A2_FW_BOOT_REQ_MAC_FAST_BOOT BIT(0xA)
+#define AQ_A2_FW_BOOT_REQ_PHY_FAST_BOOT BIT(0xB)
+
+int hw_atl2_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
+{
+	int err;
+
+	self->fw_ver_actual = hw_atl2_utils_get_fw_version(self);
+
+	if (hw_atl_utils_ver_match(HW_ATL2_FW_VER_1X,
+				   self->fw_ver_actual) == 0) {
+		*fw_ops = &aq_a2_fw_ops;
+	} else {
+		aq_pr_err("Bad FW version detected: %x, but continue\n",
+			  self->fw_ver_actual);
+		*fw_ops = &aq_a2_fw_ops;
+	}
+	aq_pr_trace("Detect ATL2FW %x\n", self->fw_ver_actual);
+	self->aq_fw_ops = *fw_ops;
+	err = self->aq_fw_ops->init(self);
+
+	self->chip_features |= ATL_HW_CHIP_ANTIGUA;
+
+	return err;
+}
+
+static bool hw_atl2_mcp_boot_complete(struct aq_hw_s *self)
+{
+	u32 rbl_status;
+
+	rbl_status = hw_atl2_mif_mcp_boot_reg_get(self);
+	if (rbl_status & AQ_A2_FW_BOOT_COMPLETE_MASK)
+		return true;
+
+	/* Host boot requested */
+	if (hw_atl2_mif_host_req_int_get(self) & HW_ATL2_MCP_HOST_REQ_INT_READY)
+		return true;
+
+	return false;
+}
+
+int hw_atl2_utils_soft_reset(struct aq_hw_s *self)
+{
+	bool rbl_complete = false;
+	u32 rbl_status = 0;
+	u32 rbl_request;
+	int err;
+
+	err = readx_poll_timeout_atomic(hw_atl2_mif_mcp_boot_reg_get, self,
+				rbl_status,
+				((rbl_status & AQ_A2_BOOT_STARTED) &&
+				 (rbl_status != 0xFFFFFFFFu)),
+				10, 500000);
+	if (err)
+		aq_pr_trace("Boot code probably hanged, reboot anyway");
+
+	hw_atl2_mif_host_req_int_clr(self, 0x01);
+	rbl_request = AQ_A2_FW_BOOT_REQ_REBOOT;
+#ifdef AQ_CFG_FAST_START
+	rbl_request |= AQ_A2_FW_BOOT_REQ_MAC_FAST_BOOT;
+#endif
+	hw_atl2_mif_mcp_boot_reg_set(self, rbl_request);
+
+	/* Wait for RBL boot */
+	err = readx_poll_timeout_atomic(hw_atl2_mif_mcp_boot_reg_get, self,
+				rbl_status,
+				((rbl_status & AQ_A2_BOOT_STARTED) &&
+				 (rbl_status != 0xFFFFFFFFu)),
+				10, 200000);
+	if (err) {
+		aq_pr_err("Boot code hanged");
+		goto err_exit;
+	}
+
+	err = readx_poll_timeout_atomic(hw_atl2_mcp_boot_complete, self,
+					rbl_complete,
+					rbl_complete,
+					10, 2000000);
+
+	if (err) {
+		aq_pr_err("FW Restart timed out");
+		goto err_exit;
+	}
+
+	rbl_status = hw_atl2_mif_mcp_boot_reg_get(self);
+
+	if (rbl_status & AQ_A2_FW_BOOT_FAILED_MASK) {
+		err = -EIO;
+		aq_pr_err("FW Restart failed");
+		goto err_exit;
+	}
+
+	if (hw_atl2_mif_host_req_int_get(self) &
+	    HW_ATL2_MCP_HOST_REQ_INT_READY) {
+		err = -EIO;
+		aq_pr_err("No FW detected. Dynamic FW load not implemented");
+		goto err_exit;
+	}
+
+	if (self->aq_fw_ops) {
+		err = self->aq_fw_ops->init(self);
+		if (err) {
+			aq_pr_err("FW Init failed");
+			goto err_exit;
+		}
+	}
+
+err_exit:
+	return err;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
index 5421fbed3db5..2317dd8459d0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -6,6 +6,8 @@
 #ifndef HW_ATL2_UTILS_H
 #define HW_ATL2_UTILS_H
 
+#include "aq_hw.h"
+
 /* F W    A P I */
 
 struct link_options_s {
@@ -590,6 +592,12 @@ struct fw_interface_out {
 #define  AQ_HOST_MODE_LOW_POWER    3U
 #define  AQ_HOST_MODE_SHUTDOWN     4U
 
+int hw_atl2_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops);
+
+int hw_atl2_utils_soft_reset(struct aq_hw_s *self);
+
+u32 hw_atl2_utils_get_fw_version(struct aq_hw_s *self);
+
 int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
 						u8 *base_index, u8 *count);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index c3e0e5575810..f5fb4b11f51a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -301,6 +301,18 @@ static int aq_a2_fw_renegotiate(struct aq_hw_s *self)
 	return err;
 }
 
+u32 hw_atl2_utils_get_fw_version(struct aq_hw_s *self)
+{
+	struct version_s version;
+
+	hw_atl2_shared_buffer_read_safe(self, version, &version);
+
+	/* A2 FW version is stored in reverse order */
+	return version.mac.major << 24 |
+	       version.mac.minor << 16 |
+	       version.mac.build;
+}
+
 int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
 						u8 *base_index, u8 *count)
 {
-- 
cgit v1.2.3


From e54dcf4bba3e2c36b3eb89cd9063753c2a3ef459 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:44 +0300
Subject: net: atlantic: basic A2 init/deinit hw_ops

This patch adds basic A2 HW initialization / deinitialization.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Co-developed-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |   3 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  24 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h  |  14 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c |   4 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h |   4 +-
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 344 +++++++++++++++++----
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |  48 +++
 7 files changed, 362 insertions(+), 79 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 2dbea5cd7684..f97b073efd8e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -378,7 +378,8 @@ int aq_nic_init(struct aq_nic_s *self)
 	if (err < 0)
 		goto err_exit;
 
-	if (self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_TP) {
+	if (ATL_HW_IS_CHIP_FEATURE(self->aq_hw, ATLANTIC) &&
+	    self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_TP) {
 		self->aq_hw->phy_id = HW_ATL_PHY_ID_MAX;
 		err = aq_phy_init(self->aq_hw);
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 3b42045b9c7d..c46199f14ec4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -187,8 +187,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
-				     struct aq_rss_parameters *rss_params)
+int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
+			      struct aq_rss_parameters *rss_params)
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	unsigned int addr = 0U;
@@ -215,8 +215,8 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
-				struct aq_rss_parameters *rss_params)
+int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
+			 struct aq_rss_parameters *rss_params)
 {
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	u8 *indirection_table =	rss_params->indirection_table;
@@ -314,7 +314,7 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
 	/* Tx TC/Queue number config */
-	hw_atl_rpb_tps_tx_tc_mode_set(self, 1U);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
@@ -495,7 +495,7 @@ static int hw_atl_b0_hw_ring_rx_start(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_start(struct aq_hw_s *self)
+int hw_atl_b0_hw_start(struct aq_hw_s *self)
 {
 	hw_atl_tpb_tx_buff_en_set(self, 1);
 	hw_atl_rpb_rx_buff_en_set(self, 1);
@@ -854,14 +854,14 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_irq_enable(struct aq_hw_s *self, u64 mask)
+int hw_atl_b0_hw_irq_enable(struct aq_hw_s *self, u64 mask)
 {
 	hw_atl_itr_irq_msk_setlsw_set(self, LODWORD(mask));
 
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask)
+int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask)
 {
 	hw_atl_itr_irq_msk_clearlsw_set(self, LODWORD(mask));
 	hw_atl_itr_irq_status_clearlsw_set(self, LODWORD(mask));
@@ -871,7 +871,7 @@ static int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask)
+int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask)
 {
 	*mask = hw_atl_itr_irq_statuslsw_get(self);
 
@@ -880,8 +880,8 @@ static int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask)
 
 #define IS_FILTER_ENABLED(_F_) ((packet_filter & (_F_)) ? 1U : 0U)
 
-static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
-					  unsigned int packet_filter)
+int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
+				   unsigned int packet_filter)
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	unsigned int i = 0U;
@@ -1089,7 +1089,7 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
 
 static int hw_atl_b0_tx_tc_mode_get(struct aq_hw_s *self, u32 *tc_mode)
 {
-	*tc_mode = hw_atl_rpb_tps_tx_tc_mode_get(self);
+	*tc_mode = hw_atl_tpb_tps_tx_tc_mode_get(self);
 	return aq_hw_err_from_flags(self);
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index 09af1683034b..ea7136b06b32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -33,4 +33,18 @@ extern const struct aq_hw_ops hw_atl_ops_b0;
 
 #define hw_atl_ops_b1 hw_atl_ops_b0
 
+int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
+			      struct aq_rss_parameters *rss_params);
+int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
+			 struct aq_rss_parameters *rss_params);
+
+int hw_atl_b0_hw_start(struct aq_hw_s *self);
+
+int hw_atl_b0_hw_irq_enable(struct aq_hw_s *self, u64 mask);
+int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask);
+int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask);
+
+int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
+				   unsigned int packet_filter);
+
 #endif /* HW_ATL_B0_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 8dd3232d72c4..9e2d01a6aac8 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1318,14 +1318,14 @@ void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en)
 			    HW_ATL_TPB_TX_BUF_EN_SHIFT, tx_buff_en);
 }
 
-u32 hw_atl_rpb_tps_tx_tc_mode_get(struct aq_hw_s *aq_hw)
+u32 hw_atl_tpb_tps_tx_tc_mode_get(struct aq_hw_s *aq_hw)
 {
 	return aq_hw_read_reg_bit(aq_hw, HW_ATL_TPB_TX_TC_MODE_ADDR,
 			HW_ATL_TPB_TX_TC_MODE_MSK,
 			HW_ATL_TPB_TX_TC_MODE_SHIFT);
 }
 
-void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+void hw_atl_tpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
 				   u32 tx_traf_class_mode)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPB_TX_TC_MODE_ADDR,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index a4699a682973..b88cb84805d5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -616,11 +616,11 @@ void hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(struct aq_hw_s *aq_hw,
 /* tpb */
 
 /* set TX Traffic Class Mode */
-void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+void hw_atl_tpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
 				   u32 tx_traf_class_mode);
 
 /* get TX Traffic Class Mode */
-u32 hw_atl_rpb_tps_tx_tc_mode_get(struct aq_hw_s *aq_hw);
+u32 hw_atl_tpb_tps_tx_tc_mode_get(struct aq_hw_s *aq_hw);
 
 /* set tx buffer enable */
 void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 7dd5f9a1c505..ad0b22b3c01f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -6,11 +6,13 @@
 #include "aq_hw.h"
 #include "aq_hw_utils.h"
 #include "aq_nic.h"
+#include "hw_atl/hw_atl_b0.h"
 #include "hw_atl/hw_atl_utils.h"
 #include "hw_atl/hw_atl_llh.h"
 #include "hw_atl2_utils.h"
 #include "hw_atl2_llh.h"
 #include "hw_atl2_internal.h"
+#include "hw_atl2_llh_internal.h"
 
 static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 				       u32 tag, u32 mask, u32 action);
@@ -70,19 +72,106 @@ static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self)
 
 static int hw_atl2_hw_reset(struct aq_hw_s *self)
 {
-	return -EOPNOTSUPP;
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	int err;
+
+	err = hw_atl2_utils_soft_reset(self);
+	if (err)
+		return err;
+
+	memset(priv, 0, sizeof(*priv));
+
+	self->aq_fw_ops->set_state(self, MPI_RESET);
+
+	err = aq_hw_err_from_flags(self);
+
+	return err;
 }
 
-static int hw_atl2_hw_rss_hash_set(struct aq_hw_s *self,
-				   struct aq_rss_parameters *rss_params)
+static int hw_atl2_hw_queue_to_tc_map_set(struct aq_hw_s *self)
 {
-	return -EOPNOTSUPP;
+	if (!hw_atl_rpb_rpf_rx_traf_class_mode_get(self)) {
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x11110000);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x33332222);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x55554444);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x77776666);
+	} else {
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x00000000);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x11111111);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x22222222);
+		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x33333333);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	u32 tx_buff_size = HW_ATL2_TXBUF_MAX;
+	u32 rx_buff_size = HW_ATL2_RXBUF_MAX;
+	unsigned int prio = 0U;
+	u32 threshold = 0U;
+	u32 tc = 0U;
+
+	/* TPS Descriptor rate init */
+	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
+	hw_atl_tps_tx_pkt_shed_desc_rate_lim_set(self, 0xA);
+
+	/* TPS VM init */
+	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
+
+	/* TPS TC credits init */
+	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
+
+	tc = 0;
+
+	/* TX Packet Scheduler Data TC0 */
+	hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0, tc);
+	hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
+	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
+	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+
+	/* Tx buf size TC0 */
+	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
+
+	threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
+	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+
+	threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
+	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+
+	/* QoS Rx buf size per TC */
+	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
+
+	threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
+	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+
+	threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
+	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+
+	/* QoS 802.1p priority -> TC mapping */
+	for (prio = 0; prio < 8; ++prio)
+		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
+							cfg->tcs * prio / 8);
+
+	/* ATL2 Apply legacy ring to TC mapping */
+	hw_atl2_hw_queue_to_tc_map_set(self);
+
+	return aq_hw_err_from_flags(self);
 }
 
 static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 			      struct aq_rss_parameters *rss_params)
 {
-	return -EOPNOTSUPP;
+	u8 *indirection_table =	rss_params->indirection_table;
+	int i;
+
+	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;)
+		hw_atl2_new_rpf_rss_redir_set(self, 0, i, indirection_table[i]);
+
+	return hw_atl_b0_hw_rss_set(self, rss_params);
 }
 
 static int hw_atl2_hw_offload_set(struct aq_hw_s *self,
@@ -91,6 +180,80 @@ static int hw_atl2_hw_offload_set(struct aq_hw_s *self,
 	return -EOPNOTSUPP;
 }
 
+static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
+{
+	/* Tx TC/RSS number config */
+	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
+
+	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
+	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
+	hw_atl_thm_lso_tcp_flag_of_last_pkt_set(self, 0x0F7FU);
+
+	/* Tx interrupts */
+	hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
+
+	/* misc */
+	hw_atl_tdm_tx_dca_en_set(self, 0U);
+	hw_atl_tdm_tx_dca_mode_set(self, 0U);
+
+	hw_atl_tpb_tx_path_scp_ins_en_set(self, 1U);
+
+	hw_atl2_tpb_tx_buf_clk_gate_en_set(self, 0U);
+
+	return aq_hw_err_from_flags(self);
+}
+
+static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u8 index;
+
+	hw_atl2_rpf_act_rslvr_section_en_set(self, 0xFFFF);
+	hw_atl2_rpfl2_uc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC,
+				     HW_ATL2_MAC_UC);
+	hw_atl2_rpfl2_bc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC);
+
+	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_OFF_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0,
+				    HW_ATL2_RPF_TAG_UC_MASK |
+					HW_ATL2_RPF_TAG_ALLMC_MASK,
+				    HW_ATL2_ACTION_DROP);
+
+	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_OFF_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0,
+				    HW_ATL2_RPF_TAG_VLAN_MASK |
+					HW_ATL2_RPF_TAG_UNTAG_MASK,
+				    HW_ATL2_ACTION_DROP);
+
+	index = priv->art_base_index + HW_ATL2_RPF_VLAN_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_VLAN,
+				    HW_ATL2_RPF_TAG_VLAN_MASK,
+				    HW_ATL2_ACTION_ASSIGN_TC(0));
+
+	index = priv->art_base_index + HW_ATL2_RPF_MAC_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_UC,
+				    HW_ATL2_RPF_TAG_UC_MASK,
+				    HW_ATL2_ACTION_ASSIGN_TC(0));
+
+	index = priv->art_base_index + HW_ATL2_RPF_ALLMC_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_ALLMC,
+				    HW_ATL2_RPF_TAG_ALLMC_MASK,
+				    HW_ATL2_ACTION_ASSIGN_TC(0));
+
+	index = priv->art_base_index + HW_ATL2_RPF_UNTAG_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_UNTAG_MASK,
+				    HW_ATL2_RPF_TAG_UNTAG_MASK,
+				    HW_ATL2_ACTION_ASSIGN_TC(0));
+
+	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_VLAN_MASK,
+				    HW_ATL2_ACTION_DISABLE);
+
+	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_ON_INDEX;
+	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_UC_MASK,
+				    HW_ATL2_ACTION_DISABLE);
+}
+
 static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
 						  bool promisc)
 {
@@ -145,6 +308,57 @@ static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 	return err;
 }
 
+static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	int i;
+
+	/* Rx TC/RSS number config */
+	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, 1U);
+
+	/* Rx flow control */
+	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
+
+	hw_atl2_rpf_rss_hash_type_set(self, HW_ATL2_RPF_RSS_HASH_TYPE_ALL);
+
+	/* RSS Ring selection */
+	hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ?
+						HW_ATL_RSS_ENABLED_3INDEX_BITS :
+						HW_ATL_RSS_DISABLED);
+
+	/* Multicast filters */
+	for (i = HW_ATL2_MAC_MAX; i--;) {
+		hw_atl_rpfl2_uc_flr_en_set(self, (i == 0U) ? 1U : 0U, i);
+		hw_atl_rpfl2unicast_flr_act_set(self, 1U, i);
+	}
+
+	hw_atl_reg_rx_flr_mcst_flr_msk_set(self, 0x00000000U);
+	hw_atl_reg_rx_flr_mcst_flr_set(self, HW_ATL_MCAST_FLT_ANY_TO_HOST, 0U);
+
+	/* Vlan filters */
+	hw_atl_rpf_vlan_outer_etht_set(self, ETH_P_8021AD);
+	hw_atl_rpf_vlan_inner_etht_set(self, ETH_P_8021Q);
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self, 1);
+
+	/* Always accept untagged packets */
+	hw_atl_rpf_vlan_accept_untagged_packets_set(self, 1U);
+	hw_atl_rpf_vlan_untagged_act_set(self, 1U);
+
+	hw_atl2_hw_init_new_rx_filters(self);
+
+	/* Rx Interrupts */
+	hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
+
+	hw_atl_rpfl2broadcast_flr_act_set(self, 1U);
+	hw_atl_rpfl2broadcast_count_threshold_set(self, 0xFFFFU & (~0U / 256U));
+
+	hw_atl_rdm_rx_dca_en_set(self, 0U);
+	hw_atl_rdm_rx_dca_mode_set(self, 0U);
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl2_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
 {
 	return -EOPNOTSUPP;
@@ -152,7 +366,15 @@ static int hw_atl2_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
 
 static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 {
+	static u32 aq_hw_atl2_igcr_table_[4][2] = {
+		[AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U },
+		[AQ_HW_IRQ_LEGACY]  = { 0x20000080U, 0x20000080U },
+		[AQ_HW_IRQ_MSI]     = { 0x20000021U, 0x20000025U },
+		[AQ_HW_IRQ_MSIX]    = { 0x20000022U, 0x20000026U },
+	};
+
 	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct aq_nic_cfg_s *aq_nic_cfg = self->aq_nic_cfg;
 	u8 base_index, count;
 	int err;
 
@@ -163,7 +385,49 @@ static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 
 	priv->art_base_index = 8 * base_index;
 
-	return -EOPNOTSUPP;
+	hw_atl2_init_launchtime(self);
+
+	hw_atl2_hw_init_tx_path(self);
+	hw_atl2_hw_init_rx_path(self);
+
+	hw_atl2_hw_mac_addr_set(self, mac_addr);
+
+	self->aq_fw_ops->set_link_speed(self, aq_nic_cfg->link_speed_msk);
+	self->aq_fw_ops->set_state(self, MPI_INIT);
+
+	hw_atl2_hw_qos_set(self);
+	hw_atl2_hw_rss_set(self, &aq_nic_cfg->aq_rss);
+	hw_atl_b0_hw_rss_hash_set(self, &aq_nic_cfg->aq_rss);
+
+	hw_atl2_rpf_new_enable_set(self, 1);
+
+	/* Reset link status and read out initial hardware counters */
+	self->aq_link_status.mbps = 0;
+	self->aq_fw_ops->update_stats(self);
+
+	err = aq_hw_err_from_flags(self);
+	if (err < 0)
+		goto err_exit;
+
+	/* Interrupts */
+	hw_atl_reg_irq_glb_ctl_set(self,
+				   aq_hw_atl2_igcr_table_[aq_nic_cfg->irq_type]
+						 [(aq_nic_cfg->vecs > 1U) ?
+						  1 : 0]);
+
+	hw_atl_itr_irq_auto_masklsw_set(self, aq_nic_cfg->aq_hw_caps->irq_mask);
+
+	/* Interrupts */
+	hw_atl_reg_gen_irq_map_set(self,
+				   ((HW_ATL2_ERR_INT << 0x18) |
+				    (1U << 0x1F)) |
+				   ((HW_ATL2_ERR_INT << 0x10) |
+				    (1U << 0x17)), 0U);
+
+	hw_atl2_hw_offload_set(self, aq_nic_cfg);
+
+err_exit:
+	return err;
 }
 
 static int hw_atl2_hw_ring_tx_start(struct aq_hw_s *self,
@@ -178,11 +442,6 @@ static int hw_atl2_hw_ring_rx_start(struct aq_hw_s *self,
 	return -EOPNOTSUPP;
 }
 
-static int hw_atl2_hw_start(struct aq_hw_s *self)
-{
-	return -EOPNOTSUPP;
-}
-
 static int hw_atl2_hw_ring_tx_xmit(struct aq_hw_s *self,
 				   struct aq_ring_s *ring,
 				   unsigned int frags)
@@ -222,58 +481,14 @@ static int hw_atl2_hw_ring_rx_receive(struct aq_hw_s *self,
 	return -EOPNOTSUPP;
 }
 
-static int hw_atl2_hw_irq_enable(struct aq_hw_s *self, u64 mask)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_irq_disable(struct aq_hw_s *self, u64 mask)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_irq_read(struct aq_hw_s *self, u64 *mask)
-{
-	return -EOPNOTSUPP;
-}
-
 #define IS_FILTER_ENABLED(_F_) ((packet_filter & (_F_)) ? 1U : 0U)
 
 static int hw_atl2_hw_packet_filter_set(struct aq_hw_s *self,
 					unsigned int packet_filter)
 {
-	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
-	u32 vlan_promisc;
-	u32 l2_promisc;
-	unsigned int i;
-
-	l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) ||
-		     !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET));
-	vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc;
-
-	hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc);
-
-	hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc);
-
 	hw_atl2_hw_new_rx_filter_promisc(self, IS_FILTER_ENABLED(IFF_PROMISC));
 
-	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
-					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
-
-	hw_atl_rpfl2_accept_all_mc_packets_set(self,
-					      IS_FILTER_ENABLED(IFF_ALLMULTI) &&
-					      IS_FILTER_ENABLED(IFF_MULTICAST));
-
-	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
-
-	for (i = HW_ATL2_MAC_MIN; i < HW_ATL2_MAC_MAX; ++i)
-		hw_atl_rpfl2_uc_flr_en_set(self,
-					   (cfg->is_mc_list_enabled &&
-					    (i <= cfg->mc_list_count)) ?
-				    1U : 0U, i);
-
-	return aq_hw_err_from_flags(self);
+	return hw_atl_b0_hw_packet_filter_set(self, packet_filter);
 }
 
 #undef IS_FILTER_ENABLED
@@ -326,7 +541,9 @@ static int hw_atl2_hw_interrupt_moderation_set(struct aq_hw_s *self)
 
 static int hw_atl2_hw_stop(struct aq_hw_s *self)
 {
-	return -EOPNOTSUPP;
+	hw_atl_b0_hw_irq_disable(self, HW_ATL2_INT_MASK);
+
+	return 0;
 }
 
 static int hw_atl2_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
@@ -400,10 +617,12 @@ static int hw_atl2_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
 }
 
 const struct aq_hw_ops hw_atl2_ops = {
+	.hw_soft_reset        = hw_atl2_utils_soft_reset,
+	.hw_prepare           = hw_atl2_utils_initfw,
 	.hw_set_mac_address   = hw_atl2_hw_mac_addr_set,
 	.hw_init              = hw_atl2_hw_init,
 	.hw_reset             = hw_atl2_hw_reset,
-	.hw_start             = hw_atl2_hw_start,
+	.hw_start             = hw_atl_b0_hw_start,
 	.hw_ring_tx_start     = hw_atl2_hw_ring_tx_start,
 	.hw_ring_tx_stop      = hw_atl2_hw_ring_tx_stop,
 	.hw_ring_rx_start     = hw_atl2_hw_ring_rx_start,
@@ -416,9 +635,9 @@ const struct aq_hw_ops hw_atl2_ops = {
 	.hw_ring_rx_receive      = hw_atl2_hw_ring_rx_receive,
 	.hw_ring_rx_fill         = hw_atl2_hw_ring_rx_fill,
 
-	.hw_irq_enable           = hw_atl2_hw_irq_enable,
-	.hw_irq_disable          = hw_atl2_hw_irq_disable,
-	.hw_irq_read             = hw_atl2_hw_irq_read,
+	.hw_irq_enable           = hw_atl_b0_hw_irq_enable,
+	.hw_irq_disable          = hw_atl_b0_hw_irq_disable,
+	.hw_irq_read             = hw_atl_b0_hw_irq_read,
 
 	.hw_ring_rx_init             = hw_atl2_hw_ring_rx_init,
 	.hw_ring_tx_init             = hw_atl2_hw_ring_tx_init,
@@ -428,7 +647,8 @@ const struct aq_hw_ops hw_atl2_ops = {
 	.hw_multicast_list_set       = hw_atl2_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl2_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl2_hw_rss_set,
-	.hw_rss_hash_set             = hw_atl2_hw_rss_hash_set,
+	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
 	.hw_get_hw_stats             = hw_atl2_utils_get_hw_stats,
+	.hw_get_fw_version           = hw_atl2_utils_get_fw_version,
 	.hw_set_offload              = hw_atl2_hw_offload_set,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index dccc89df2223..eb1243256730 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -22,6 +22,15 @@
 #define HW_ATL2_MAC_MIN  1U
 #define HW_ATL2_MAC_MAX  38U
 
+/* interrupts */
+#define HW_ATL2_ERR_INT 8U
+#define HW_ATL2_INT_MASK  (0xFFFFFFFFU)
+
+#define HW_ATL2_TXBUF_MAX              128U
+#define HW_ATL2_RXBUF_MAX              192U
+
+#define HW_ATL2_RSS_REDIRECTION_MAX 64U
+
 #define HW_ATL2_TC_MAX 1U
 #define HW_ATL2_RSS_MAX 8U
 
@@ -57,6 +66,11 @@
 #define HW_ATL2_RPF_TAG_L4_MASK    (0x00000007 << HW_ATL2_RPF_TAG_L4_OFFSET)
 #define HW_ATL2_RPF_TAG_PCP_MASK   (0x00000007 << HW_ATL2_RPF_TAG_PCP_OFFSET)
 
+#define HW_ATL2_RPF_TAG_BASE_UC    BIT(HW_ATL2_RPF_TAG_UC_OFFSET)
+#define HW_ATL2_RPF_TAG_BASE_ALLMC BIT(HW_ATL2_RPF_TAG_ALLMC_OFFSET)
+#define HW_ATL2_RPF_TAG_BASE_UNTAG BIT(HW_ATL2_RPF_TAG_UNTAG_OFFSET)
+#define HW_ATL2_RPF_TAG_BASE_VLAN  BIT(HW_ATL2_RPF_TAG_VLAN_OFFSET)
+
 enum HW_ATL2_RPF_ART_INDEX {
 	HW_ATL2_RPF_L2_PROMISC_OFF_INDEX,
 	HW_ATL2_RPF_VLAN_PROMISC_OFF_INDEX,
@@ -65,6 +79,13 @@ enum HW_ATL2_RPF_ART_INDEX {
 	HW_ATL2_RPF_VLAN_USER_INDEX	= HW_ATL2_RPF_ET_PCP_USER_INDEX + 16,
 	HW_ATL2_RPF_PCP_TO_TC_INDEX	= HW_ATL2_RPF_VLAN_USER_INDEX +
 					  HW_ATL_VLAN_MAX_FILTERS,
+	HW_ATL2_RPF_VLAN_INDEX		= HW_ATL2_RPF_PCP_TO_TC_INDEX +
+					  AQ_CFG_TCS_MAX,
+	HW_ATL2_RPF_MAC_INDEX,
+	HW_ATL2_RPF_ALLMC_INDEX,
+	HW_ATL2_RPF_UNTAG_INDEX,
+	HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX,
+	HW_ATL2_RPF_L2_PROMISC_ON_INDEX,
 };
 
 #define HW_ATL2_ACTION(ACTION, RSS, INDEX, VALID) \
@@ -78,6 +99,33 @@ enum HW_ATL2_RPF_ART_INDEX {
 #define HW_ATL2_ACTION_ASSIGN_QUEUE(QUEUE) HW_ATL2_ACTION(1, 0, (QUEUE), 1)
 #define HW_ATL2_ACTION_ASSIGN_TC(TC) HW_ATL2_ACTION(1, 1, (TC), 1)
 
+enum HW_ATL2_RPF_RSS_HASH_TYPE {
+	HW_ATL2_RPF_RSS_HASH_TYPE_NONE = 0,
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV4 = BIT(0),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV4_TCP = BIT(1),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV4_UDP = BIT(2),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6 = BIT(3),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_TCP = BIT(4),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_UDP = BIT(5),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX = BIT(6),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_TCP = BIT(7),
+	HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_UDP = BIT(8),
+	HW_ATL2_RPF_RSS_HASH_TYPE_ALL = HW_ATL2_RPF_RSS_HASH_TYPE_IPV4 |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV4_TCP |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV4_UDP |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6 |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_TCP |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_UDP |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_TCP |
+					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_UDP,
+};
+
+#define HW_ATL_RSS_DISABLED 0x00000000U
+#define HW_ATL_RSS_ENABLED_3INDEX_BITS 0xB3333333U
+
+#define HW_ATL_MCAST_FLT_ANY_TO_HOST 0x00010FFFU
+
 struct hw_atl2_priv {
 	struct statistics_s last_stats;
 	unsigned int art_base_index;
-- 
cgit v1.2.3


From 43c670c8e48a1817ae4b64683d7d65cad5bb0502 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 30 Apr 2020 11:04:45 +0300
Subject: net: atlantic: A2 ingress / egress hw configuration

Chip generations are mostly compatible register-wise, but there are still
some differences. Therefore we've made some of first generation (A1) code
non-static to re-use it where possible.

Some pieces are A2 specific, in which case we redefine/extend such APIs.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  54 +++----
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h  |  23 +++
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 176 ++++++++++++---------
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |   3 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |   8 +
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |   5 +
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        |   8 +
 7 files changed, 172 insertions(+), 105 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index c46199f14ec4..cbb7a00d61b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -251,9 +251,10 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
-				    struct aq_nic_cfg_s *aq_nic_cfg)
+int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
+			     struct aq_nic_cfg_s *aq_nic_cfg)
 {
+	u64 rxcsum = !!(aq_nic_cfg->features & NETIF_F_RXCSUM);
 	unsigned int i;
 
 	/* TX checksums offloads*/
@@ -261,10 +262,8 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	hw_atl_tpo_tcp_udp_crc_offload_en_set(self, 1);
 
 	/* RX checksums offloads*/
-	hw_atl_rpo_ipv4header_crc_offload_en_set(self, !!(aq_nic_cfg->features &
-						 NETIF_F_RXCSUM));
-	hw_atl_rpo_tcp_udp_crc_offload_en_set(self, !!(aq_nic_cfg->features &
-					      NETIF_F_RXCSUM));
+	hw_atl_rpo_ipv4header_crc_offload_en_set(self, rxcsum);
+	hw_atl_rpo_tcp_udp_crc_offload_en_set(self, rxcsum);
 
 	/* LSO offloads*/
 	hw_atl_tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
@@ -272,7 +271,7 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	/* Outer VLAN tag offload */
 	hw_atl_rpo_outer_vlan_tag_mode_set(self, 1U);
 
-/* LRO offloads */
+	/* LRO offloads */
 	{
 		unsigned int val = (8U < HW_ATL_B0_LRO_RXD_MAX) ? 0x3U :
 			((4U < HW_ATL_B0_LRO_RXD_MAX) ? 0x2U :
@@ -384,7 +383,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
+int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
 {
 	unsigned int h = 0U;
 	unsigned int l = 0U;
@@ -479,16 +478,14 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_ring_tx_start(struct aq_hw_s *self,
-				      struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_tx_start(struct aq_hw_s *self, struct aq_ring_s *ring)
 {
 	hw_atl_tdm_tx_desc_en_set(self, 1, ring->idx);
 
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_rx_start(struct aq_hw_s *self,
-				      struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_rx_start(struct aq_hw_s *self, struct aq_ring_s *ring)
 {
 	hw_atl_rdm_rx_desc_en_set(self, 1, ring->idx);
 
@@ -511,9 +508,8 @@ static int hw_atl_b0_hw_tx_ring_tail_update(struct aq_hw_s *self,
 	return 0;
 }
 
-static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
-				     struct aq_ring_s *ring,
-				     unsigned int frags)
+int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, struct aq_ring_s *ring,
+			      unsigned int frags)
 {
 	struct aq_ring_buff_s *buff = NULL;
 	struct hw_atl_txd_s *txd = NULL;
@@ -600,9 +596,8 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self,
-				     struct aq_ring_s *aq_ring,
-				     struct aq_ring_param_s *aq_ring_param)
+int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self, struct aq_ring_s *aq_ring,
+			      struct aq_ring_param_s *aq_ring_param)
 {
 	u32 dma_desc_addr_msw = (u32)(((u64)aq_ring->dx_ring_pa) >> 32);
 	u32 vlan_rx_stripping = self->aq_nic_cfg->is_vlan_rx_strip;
@@ -643,9 +638,8 @@ static int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_tx_init(struct aq_hw_s *self,
-				     struct aq_ring_s *aq_ring,
-				     struct aq_ring_param_s *aq_ring_param)
+int hw_atl_b0_hw_ring_tx_init(struct aq_hw_s *self, struct aq_ring_s *aq_ring,
+			      struct aq_ring_param_s *aq_ring_param)
 {
 	u32 dma_desc_msw_addr = (u32)(((u64)aq_ring->dx_ring_pa) >> 32);
 	u32 dma_desc_lsw_addr = (u32)aq_ring->dx_ring_pa;
@@ -673,9 +667,8 @@ static int hw_atl_b0_hw_ring_tx_init(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_rx_fill(struct aq_hw_s *self,
-				     struct aq_ring_s *ring,
-				     unsigned int sw_tail_old)
+int hw_atl_b0_hw_ring_rx_fill(struct aq_hw_s *self, struct aq_ring_s *ring,
+			      unsigned int sw_tail_old)
 {
 	for (; sw_tail_old != ring->sw_tail;
 		sw_tail_old = aq_ring_next_dx(ring, sw_tail_old)) {
@@ -734,8 +727,8 @@ static int hw_atl_b0_hw_ring_hwts_rx_receive(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self,
-					    struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self,
+				     struct aq_ring_s *ring)
 {
 	unsigned int hw_head_;
 	int err = 0;
@@ -753,8 +746,7 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
-					struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, struct aq_ring_s *ring)
 {
 	for (; ring->hw_head != ring->sw_tail;
 		ring->hw_head = aq_ring_next_dx(ring, ring->hw_head)) {
@@ -1071,16 +1063,14 @@ err_exit:
 	return err;
 }
 
-static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self,
-				     struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
 {
 	hw_atl_tdm_tx_desc_en_set(self, 0U, ring->idx);
 
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
-				     struct aq_ring_s *ring)
+int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
 {
 	hw_atl_rdm_rx_desc_en_set(self, 0U, ring->idx);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index ea7136b06b32..f5091d79ab43 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -37,6 +37,29 @@ int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 			      struct aq_rss_parameters *rss_params);
 int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
 			 struct aq_rss_parameters *rss_params);
+int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
+			     struct aq_nic_cfg_s *aq_nic_cfg);
+
+int hw_atl_b0_hw_ring_tx_start(struct aq_hw_s *self, struct aq_ring_s *ring);
+int hw_atl_b0_hw_ring_rx_start(struct aq_hw_s *self, struct aq_ring_s *ring);
+
+int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self, struct aq_ring_s *aq_ring,
+			      struct aq_ring_param_s *aq_ring_param);
+int hw_atl_b0_hw_ring_rx_fill(struct aq_hw_s *self, struct aq_ring_s *ring,
+			      unsigned int sw_tail_old);
+int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, struct aq_ring_s *ring);
+
+int hw_atl_b0_hw_ring_tx_init(struct aq_hw_s *self, struct aq_ring_s *aq_ring,
+			      struct aq_ring_param_s *aq_ring_param);
+int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self, struct aq_ring_s *ring,
+			      unsigned int frags);
+int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self,
+				     struct aq_ring_s *ring);
+
+int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
+int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
+
+int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr);
 
 int hw_atl_b0_hw_start(struct aq_hw_s *self);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index ad0b22b3c01f..04d194f754fa 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -5,6 +5,7 @@
 
 #include "aq_hw.h"
 #include "aq_hw_utils.h"
+#include "aq_ring.h"
 #include "aq_nic.h"
 #include "hw_atl/hw_atl_b0.h"
 #include "hw_atl/hw_atl_utils.h"
@@ -174,12 +175,6 @@ static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 	return hw_atl_b0_hw_rss_set(self, rss_params);
 }
 
-static int hw_atl2_hw_offload_set(struct aq_hw_s *self,
-				  struct aq_nic_cfg_s *aq_nic_cfg)
-{
-	return -EOPNOTSUPP;
-}
-
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 {
 	/* Tx TC/RSS number config */
@@ -359,11 +354,6 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl2_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr)
-{
-	return -EOPNOTSUPP;
-}
-
 static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 {
 	static u32 aq_hw_atl2_igcr_table_[4][2] = {
@@ -390,7 +380,7 @@ static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 	hw_atl2_hw_init_tx_path(self);
 	hw_atl2_hw_init_rx_path(self);
 
-	hw_atl2_hw_mac_addr_set(self, mac_addr);
+	hw_atl_b0_hw_mac_addr_set(self, mac_addr);
 
 	self->aq_fw_ops->set_link_speed(self, aq_nic_cfg->link_speed_msk);
 	self->aq_fw_ops->set_state(self, MPI_INIT);
@@ -424,61 +414,24 @@ static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 				   ((HW_ATL2_ERR_INT << 0x10) |
 				    (1U << 0x17)), 0U);
 
-	hw_atl2_hw_offload_set(self, aq_nic_cfg);
+	hw_atl_b0_hw_offload_set(self, aq_nic_cfg);
 
 err_exit:
 	return err;
 }
 
-static int hw_atl2_hw_ring_tx_start(struct aq_hw_s *self,
-				    struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_rx_start(struct aq_hw_s *self,
-				    struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_tx_xmit(struct aq_hw_s *self,
-				   struct aq_ring_s *ring,
-				   unsigned int frags)
-{
-	return -EOPNOTSUPP;
-}
-
 static int hw_atl2_hw_ring_rx_init(struct aq_hw_s *self,
 				   struct aq_ring_s *aq_ring,
 				   struct aq_ring_param_s *aq_ring_param)
 {
-	return -EOPNOTSUPP;
+	return hw_atl_b0_hw_ring_rx_init(self, aq_ring, aq_ring_param);
 }
 
 static int hw_atl2_hw_ring_tx_init(struct aq_hw_s *self,
 				   struct aq_ring_s *aq_ring,
 				   struct aq_ring_param_s *aq_ring_param)
 {
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_rx_fill(struct aq_hw_s *self, struct aq_ring_s *ring,
-				   unsigned int sw_tail_old)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_tx_head_update(struct aq_hw_s *self,
-					  struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_rx_receive(struct aq_hw_s *self,
-				      struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
+	return hw_atl_b0_hw_ring_tx_init(self, aq_ring, aq_ring_param);
 }
 
 #define IS_FILTER_ENABLED(_F_) ((packet_filter & (_F_)) ? 1U : 0U)
@@ -536,7 +489,94 @@ err_exit:
 
 static int hw_atl2_hw_interrupt_moderation_set(struct aq_hw_s *self)
 {
-	return -EOPNOTSUPP;
+	unsigned int i = 0U;
+	u32 itr_tx = 2U;
+	u32 itr_rx = 2U;
+
+	switch (self->aq_nic_cfg->itr) {
+	case  AQ_CFG_INTERRUPT_MODERATION_ON:
+	case  AQ_CFG_INTERRUPT_MODERATION_AUTO:
+		hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 0U);
+		hw_atl_tdm_tdm_intr_moder_en_set(self, 1U);
+		hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 0U);
+		hw_atl_rdm_rdm_intr_moder_en_set(self, 1U);
+
+		if (self->aq_nic_cfg->itr == AQ_CFG_INTERRUPT_MODERATION_ON) {
+			/* HW timers are in 2us units */
+			int tx_max_timer = self->aq_nic_cfg->tx_itr / 2;
+			int tx_min_timer = tx_max_timer / 2;
+
+			int rx_max_timer = self->aq_nic_cfg->rx_itr / 2;
+			int rx_min_timer = rx_max_timer / 2;
+
+			tx_max_timer = min(HW_ATL2_INTR_MODER_MAX,
+					   tx_max_timer);
+			tx_min_timer = min(HW_ATL2_INTR_MODER_MIN,
+					   tx_min_timer);
+			rx_max_timer = min(HW_ATL2_INTR_MODER_MAX,
+					   rx_max_timer);
+			rx_min_timer = min(HW_ATL2_INTR_MODER_MIN,
+					   rx_min_timer);
+
+			itr_tx |= tx_min_timer << 0x8U;
+			itr_tx |= tx_max_timer << 0x10U;
+			itr_rx |= rx_min_timer << 0x8U;
+			itr_rx |= rx_max_timer << 0x10U;
+		} else {
+			static unsigned int hw_atl2_timers_table_tx_[][2] = {
+				{0xfU, 0xffU}, /* 10Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit */
+				{0xfU, 0x1ffU}, /* 5Gbit 5GS */
+				{0xfU, 0x1ffU}, /* 2.5Gbit */
+				{0xfU, 0x1ffU}, /* 1Gbit */
+				{0xfU, 0x1ffU}, /* 100Mbit */
+			};
+			static unsigned int hw_atl2_timers_table_rx_[][2] = {
+				{0x6U, 0x38U},/* 10Gbit */
+				{0xCU, 0x70U},/* 5Gbit */
+				{0xCU, 0x70U},/* 5Gbit 5GS */
+				{0x18U, 0xE0U},/* 2.5Gbit */
+				{0x30U, 0x80U},/* 1Gbit */
+				{0x4U, 0x50U},/* 100Mbit */
+			};
+			unsigned int mbps = self->aq_link_status.mbps;
+			unsigned int speed_index;
+
+			speed_index = hw_atl_utils_mbps_2_speed_index(mbps);
+
+			/* Update user visible ITR settings */
+			self->aq_nic_cfg->tx_itr = hw_atl2_timers_table_tx_
+							[speed_index][1] * 2;
+			self->aq_nic_cfg->rx_itr = hw_atl2_timers_table_rx_
+							[speed_index][1] * 2;
+
+			itr_tx |= hw_atl2_timers_table_tx_
+						[speed_index][0] << 0x8U;
+			itr_tx |= hw_atl2_timers_table_tx_
+						[speed_index][1] << 0x10U;
+
+			itr_rx |= hw_atl2_timers_table_rx_
+						[speed_index][0] << 0x8U;
+			itr_rx |= hw_atl2_timers_table_rx_
+						[speed_index][1] << 0x10U;
+		}
+		break;
+	case AQ_CFG_INTERRUPT_MODERATION_OFF:
+		hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
+		hw_atl_tdm_tdm_intr_moder_en_set(self, 0U);
+		hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
+		hw_atl_rdm_rdm_intr_moder_en_set(self, 0U);
+		itr_tx = 0U;
+		itr_rx = 0U;
+		break;
+	}
+
+	for (i = HW_ATL2_RINGS_MAX; i--;) {
+		hw_atl2_reg_tx_intr_moder_ctrl_set(self, itr_tx, i);
+		hw_atl_reg_rx_intr_moder_ctrl_set(self, itr_rx, i);
+	}
+
+	return aq_hw_err_from_flags(self);
 }
 
 static int hw_atl2_hw_stop(struct aq_hw_s *self)
@@ -546,16 +586,6 @@ static int hw_atl2_hw_stop(struct aq_hw_s *self)
 	return 0;
 }
 
-static int hw_atl2_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
-}
-
-static int hw_atl2_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
-{
-	return -EOPNOTSUPP;
-}
-
 static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self)
 {
 	return &self->curr_stats;
@@ -619,21 +649,21 @@ static int hw_atl2_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
 const struct aq_hw_ops hw_atl2_ops = {
 	.hw_soft_reset        = hw_atl2_utils_soft_reset,
 	.hw_prepare           = hw_atl2_utils_initfw,
-	.hw_set_mac_address   = hw_atl2_hw_mac_addr_set,
+	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl2_hw_init,
 	.hw_reset             = hw_atl2_hw_reset,
 	.hw_start             = hw_atl_b0_hw_start,
-	.hw_ring_tx_start     = hw_atl2_hw_ring_tx_start,
-	.hw_ring_tx_stop      = hw_atl2_hw_ring_tx_stop,
-	.hw_ring_rx_start     = hw_atl2_hw_ring_rx_start,
-	.hw_ring_rx_stop      = hw_atl2_hw_ring_rx_stop,
+	.hw_ring_tx_start     = hw_atl_b0_hw_ring_tx_start,
+	.hw_ring_tx_stop      = hw_atl_b0_hw_ring_tx_stop,
+	.hw_ring_rx_start     = hw_atl_b0_hw_ring_rx_start,
+	.hw_ring_rx_stop      = hw_atl_b0_hw_ring_rx_stop,
 	.hw_stop              = hw_atl2_hw_stop,
 
-	.hw_ring_tx_xmit         = hw_atl2_hw_ring_tx_xmit,
-	.hw_ring_tx_head_update  = hw_atl2_hw_ring_tx_head_update,
+	.hw_ring_tx_xmit         = hw_atl_b0_hw_ring_tx_xmit,
+	.hw_ring_tx_head_update  = hw_atl_b0_hw_ring_tx_head_update,
 
-	.hw_ring_rx_receive      = hw_atl2_hw_ring_rx_receive,
-	.hw_ring_rx_fill         = hw_atl2_hw_ring_rx_fill,
+	.hw_ring_rx_receive      = hw_atl_b0_hw_ring_rx_receive,
+	.hw_ring_rx_fill         = hw_atl_b0_hw_ring_rx_fill,
 
 	.hw_irq_enable           = hw_atl_b0_hw_irq_enable,
 	.hw_irq_disable          = hw_atl_b0_hw_irq_disable,
@@ -650,5 +680,5 @@ const struct aq_hw_ops hw_atl2_ops = {
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
 	.hw_get_hw_stats             = hw_atl2_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl2_utils_get_fw_version,
-	.hw_set_offload              = hw_atl2_hw_offload_set,
+	.hw_set_offload              = hw_atl_b0_hw_offload_set,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index eb1243256730..e66b3583bfe9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -34,6 +34,9 @@
 #define HW_ATL2_TC_MAX 1U
 #define HW_ATL2_RSS_MAX 8U
 
+#define HW_ATL2_INTR_MODER_MAX  0x1FF
+#define HW_ATL2_INTR_MODER_MIN  0xFF
+
 #define HW_ATL2_MIN_RXD \
 	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
 #define HW_ATL2_MIN_TXD \
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index af176e1e5a18..e779d70fde66 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -68,6 +68,14 @@ void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en)
 			    clk_gate_en);
 }
 
+void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
+					u32 tx_intr_moderation_ctl,
+					u32 queue)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL2_TX_INTR_MODERATION_CTL_ADR(queue),
+			tx_intr_moderation_ctl);
+}
+
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 						    u32 max_credit,
 						    u32 tc)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index 4acbbceb623f..8c6d78a64d42 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -10,6 +10,11 @@
 
 struct aq_hw_s;
 
+/* Set TX Interrupt Moderation Control Register */
+void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
+					u32 tx_intr_moderation_ctl,
+					u32 queue);
+
 /** Set RSS HASH type */
 void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index 14b78e090950..cde9e9d2836d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -178,6 +178,14 @@
 /* default value of bitfield data_tc{t}_weight[8:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_DEFAULT 0x0
 
+/* tx interrupt moderation control register definitions
+ * Preprocessor definitions for TX Interrupt Moderation Control Register
+ * Base Address: 0x00007c28
+ * Parameter: queue {Q} | stride size 0x4 | range [0, 31]
+ */
+
+#define HW_ATL2_TX_INTR_MODERATION_CTL_ADR(queue) (0x00007c28u + (queue) * 0x40)
+
 /* Launch time control register */
 #define HW_ATL2_LT_CTRL_ADR 0x00007a1c
 
-- 
cgit v1.2.3


From eb236c2994b031f805be691fa9ea39cba4690166 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 30 Apr 2020 16:26:51 -0700
Subject: net: bcmgenet: Move wake-up event out of side band ISR

The side band interrupt service routine is not available on chips
like 7211, or rather, it does not permit the signaling of wake-up
events due to the complex interrupt hierarchy.

Move the wake-up event accounting into a .resume_noirq function,
account for possible wake-up events and clear the MPD/HFB interrupts
from there, while leaving the hardware untouched until the resume
function proceeds with doing its usual business.

Because bcmgenet_wol_power_down_cfg() now enables the MPD and HFB
interrupts, it is invoked by a .suspend_noirq function to prevent
the servicing of interrupts after the clocks have been disabled.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 72 ++++++++++++++++++----
 drivers/net/ethernet/broadcom/genet/bcmgenet.h     |  2 +
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c |  6 ++
 3 files changed, 67 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ad614d7201bd..ff31da0ed846 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3270,10 +3270,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 
 static irqreturn_t bcmgenet_wol_isr(int irq, void *dev_id)
 {
-	struct bcmgenet_priv *priv = dev_id;
-
-	pm_wakeup_event(&priv->pdev->dev, 0);
-
+	/* Acknowledge the interrupt */
 	return IRQ_HANDLED;
 }
 
@@ -4174,13 +4171,12 @@ static void bcmgenet_shutdown(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int bcmgenet_resume(struct device *d)
+static int bcmgenet_resume_noirq(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long dma_ctrl;
-	u32 offset, reg;
 	int ret;
+	u32 reg;
 
 	if (!netif_running(dev))
 		return 0;
@@ -4190,6 +4186,34 @@ static int bcmgenet_resume(struct device *d)
 	if (ret)
 		return ret;
 
+	if (device_may_wakeup(d) && priv->wolopts) {
+		/* Account for Wake-on-LAN events and clear those events
+		 * (Some devices need more time between enabling the clocks
+		 *  and the interrupt register reflecting the wake event so
+		 *  read the register twice)
+		 */
+		reg = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT);
+		reg = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT);
+		if (reg & UMAC_IRQ_WAKE_EVENT)
+			pm_wakeup_event(&priv->pdev->dev, 0);
+	}
+
+	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT, INTRL2_CPU_CLEAR);
+
+	return 0;
+}
+
+static int bcmgenet_resume(struct device *d)
+{
+	struct net_device *dev = dev_get_drvdata(d);
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	unsigned long dma_ctrl;
+	u32 offset, reg;
+	int ret;
+
+	if (!netif_running(dev))
+		return 0;
+
 	/* From WOL-enabled suspend, switch to regular clock */
 	if (device_may_wakeup(d) && priv->wolopts)
 		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
@@ -4262,7 +4286,6 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret = 0;
 	u32 offset;
 
 	if (!netif_running(dev))
@@ -4282,23 +4305,46 @@ static int bcmgenet_suspend(struct device *d)
 	priv->hfb_en[2] = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
 	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 
+	return 0;
+}
+
+static int bcmgenet_suspend_noirq(struct device *d)
+{
+	struct net_device *dev = dev_get_drvdata(d);
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	int ret = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts)
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
 	else if (priv->internal_phy)
 		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
 
+	/* Let the framework handle resumption and leave the clocks on */
+	if (ret)
+		return ret;
+
 	/* Turn off the clocks */
 	clk_disable_unprepare(priv->clk);
 
-	if (ret)
-		bcmgenet_resume(d);
-
-	return ret;
+	return 0;
 }
+#else
+#define bcmgenet_suspend	NULL
+#define bcmgenet_suspend_noirq	NULL
+#define bcmgenet_resume		NULL
+#define bcmgenet_resume_noirq	NULL
 #endif /* CONFIG_PM_SLEEP */
 
-static SIMPLE_DEV_PM_OPS(bcmgenet_pm_ops, bcmgenet_suspend, bcmgenet_resume);
+static const struct dev_pm_ops bcmgenet_pm_ops = {
+	.suspend	= bcmgenet_suspend,
+	.suspend_noirq	= bcmgenet_suspend_noirq,
+	.resume		= bcmgenet_resume,
+	.resume_noirq	= bcmgenet_resume_noirq,
+};
 
 static const struct acpi_device_id genet_acpi_match[] = {
 	{ "BCM6E4E", (kernel_ulong_t)&bcm2711_plat_data },
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 031d91f45067..a12cb59298f4 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -312,6 +312,8 @@ struct bcmgenet_mib_counters {
 #define UMAC_IRQ_HFB_SM			(1 << 10)
 #define UMAC_IRQ_HFB_MM			(1 << 11)
 #define UMAC_IRQ_MPD_R			(1 << 12)
+#define UMAC_IRQ_WAKE_EVENT		(UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM | \
+					 UMAC_IRQ_MPD_R)
 #define UMAC_IRQ_RXDMA_MBDONE		(1 << 13)
 #define UMAC_IRQ_RXDMA_PDONE		(1 << 14)
 #define UMAC_IRQ_RXDMA_BDONE		(1 << 15)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 4b9d65f392c2..4ea6a26b04f7 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -193,6 +193,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 	}
 
+	reg = UMAC_IRQ_MPD_R;
+	if (hfb_enable)
+		reg |=  UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
+
+	bcmgenet_intrl2_0_writel(priv, reg, INTRL2_CPU_MASK_CLEAR);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 79e499829f3ff5b8f70c87baf1b03ebb3401a3e4 Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Fri, 1 May 2020 08:53:17 +0800
Subject: net: enetc: add hw tc hw offload features for PSPF capability

This patch is to let ethtool enable/disable the tc flower offload
features. Hardware ENETC has the feature of PSFP which is for per-stream
policing. When enable the tc hw offloading feature, driver would enable
the IEEE 802.1Qci feature. It is only set the register enable bit for
this feature not enable for any entry of per stream filtering and stream
gate or stream identify but get how much capabilities for each feature.

Signed-off-by: Po Liu <Po.Liu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c    | 23 ++++++++++++
 drivers/net/ethernet/freescale/enetc/enetc.h    | 48 +++++++++++++++++++++++++
 drivers/net/ethernet/freescale/enetc/enetc_hw.h | 17 +++++++++
 drivers/net/ethernet/freescale/enetc/enetc_pf.c |  8 +++++
 4 files changed, 96 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index ccf2611f4a20..04aac7cbb506 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -756,6 +756,9 @@ void enetc_get_si_caps(struct enetc_si *si)
 
 	if (val & ENETC_SIPCAPR0_QBV)
 		si->hw_features |= ENETC_SI_F_QBV;
+
+	if (val & ENETC_SIPCAPR0_PSFP)
+		si->hw_features |= ENETC_SI_F_PSFP;
 }
 
 static int enetc_dma_alloc_bdr(struct enetc_bdr *r, size_t bd_size)
@@ -1567,6 +1570,23 @@ static int enetc_set_rss(struct net_device *ndev, int en)
 	return 0;
 }
 
+static int enetc_set_psfp(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (en) {
+		priv->active_offloads |= ENETC_F_QCI;
+		enetc_get_max_cap(priv);
+		enetc_psfp_enable(&priv->si->hw);
+	} else {
+		priv->active_offloads &= ~ENETC_F_QCI;
+		memset(&priv->psfp_cap, 0, sizeof(struct psfp_cap));
+		enetc_psfp_disable(&priv->si->hw);
+	}
+
+	return 0;
+}
+
 int enetc_set_features(struct net_device *ndev,
 		       netdev_features_t features)
 {
@@ -1575,6 +1595,9 @@ int enetc_set_features(struct net_device *ndev,
 	if (changed & NETIF_F_RXHASH)
 		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
 
+	if (changed & NETIF_F_HW_TC)
+		enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 56c43f35b633..2cfe877c3778 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -151,6 +151,7 @@ enum enetc_errata {
 };
 
 #define ENETC_SI_F_QBV BIT(0)
+#define ENETC_SI_F_PSFP BIT(1)
 
 /* PCI IEP device data */
 struct enetc_si {
@@ -203,12 +204,20 @@ struct enetc_cls_rule {
 };
 
 #define ENETC_MAX_BDR_INT	2 /* fixed to max # of available cpus */
+struct psfp_cap {
+	u32 max_streamid;
+	u32 max_psfp_filter;
+	u32 max_psfp_gate;
+	u32 max_psfp_gatelist;
+	u32 max_psfp_meter;
+};
 
 /* TODO: more hardware offloads */
 enum enetc_active_offloads {
 	ENETC_F_RX_TSTAMP	= BIT(0),
 	ENETC_F_TX_TSTAMP	= BIT(1),
 	ENETC_F_QBV             = BIT(2),
+	ENETC_F_QCI		= BIT(3),
 };
 
 struct enetc_ndev_priv {
@@ -231,6 +240,8 @@ struct enetc_ndev_priv {
 
 	struct enetc_cls_rule *cls_rules;
 
+	struct psfp_cap psfp_cap;
+
 	struct device_node *phy_node;
 	phy_interface_t if_mode;
 };
@@ -289,9 +300,46 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data);
 void enetc_sched_speed_set(struct net_device *ndev);
 int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data);
 int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data);
+
+static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv)
+{
+	u32 reg;
+
+	reg = enetc_port_rd(&priv->si->hw, ENETC_PSIDCAPR);
+	priv->psfp_cap.max_streamid = reg & ENETC_PSIDCAPR_MSK;
+	/* Port stream filter capability */
+	reg = enetc_port_rd(&priv->si->hw, ENETC_PSFCAPR);
+	priv->psfp_cap.max_psfp_filter = reg & ENETC_PSFCAPR_MSK;
+	/* Port stream gate capability */
+	reg = enetc_port_rd(&priv->si->hw, ENETC_PSGCAPR);
+	priv->psfp_cap.max_psfp_gate = (reg & ENETC_PSGCAPR_SGIT_MSK);
+	priv->psfp_cap.max_psfp_gatelist = (reg & ENETC_PSGCAPR_GCL_MSK) >> 16;
+	/* Port flow meter capability */
+	reg = enetc_port_rd(&priv->si->hw, ENETC_PFMCAPR);
+	priv->psfp_cap.max_psfp_meter = reg & ENETC_PFMCAPR_MSK;
+}
+
+static inline void enetc_psfp_enable(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC_PPSFPMR, enetc_rd(hw, ENETC_PPSFPMR) |
+		 ENETC_PPSFPMR_PSFPEN | ENETC_PPSFPMR_VS |
+		 ENETC_PPSFPMR_PVC | ENETC_PPSFPMR_PVZC);
+}
+
+static inline void enetc_psfp_disable(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC_PPSFPMR, enetc_rd(hw, ENETC_PPSFPMR) &
+		 ~ENETC_PPSFPMR_PSFPEN & ~ENETC_PPSFPMR_VS &
+		 ~ENETC_PPSFPMR_PVC & ~ENETC_PPSFPMR_PVZC);
+}
 #else
 #define enetc_setup_tc_taprio(ndev, type_data) -EOPNOTSUPP
 #define enetc_sched_speed_set(ndev) (void)0
 #define enetc_setup_tc_cbs(ndev, type_data) -EOPNOTSUPP
 #define enetc_setup_tc_txtime(ndev, type_data) -EOPNOTSUPP
+#define enetc_get_max_cap(p)		\
+	memset(&((p)->psfp_cap), 0, sizeof(struct psfp_cap))
+
+#define enetc_psfp_enable(hw) (void)0
+#define enetc_psfp_disable(hw) (void)0
 #endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 2a6523136947..587974862f48 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -19,6 +19,7 @@
 #define ENETC_SICTR1	0x1c
 #define ENETC_SIPCAPR0	0x20
 #define ENETC_SIPCAPR0_QBV	BIT(4)
+#define ENETC_SIPCAPR0_PSFP	BIT(9)
 #define ENETC_SIPCAPR0_RSS	BIT(8)
 #define ENETC_SIPCAPR1	0x24
 #define ENETC_SITGTGR	0x30
@@ -228,6 +229,15 @@ enum enetc_bdr_type {TX, RX};
 #define ENETC_PM0_IFM_RLP	(BIT(5) | BIT(11))
 #define ENETC_PM0_IFM_RGAUTO	(BIT(15) | ENETC_PMO_IFM_RG | BIT(1))
 #define ENETC_PM0_IFM_XGMII	BIT(12)
+#define ENETC_PSIDCAPR		0x1b08
+#define ENETC_PSIDCAPR_MSK	GENMASK(15, 0)
+#define ENETC_PSFCAPR		0x1b18
+#define ENETC_PSFCAPR_MSK	GENMASK(15, 0)
+#define ENETC_PSGCAPR		0x1b28
+#define ENETC_PSGCAPR_GCL_MSK	GENMASK(18, 16)
+#define ENETC_PSGCAPR_SGIT_MSK	GENMASK(15, 0)
+#define ENETC_PFMCAPR		0x1b38
+#define ENETC_PFMCAPR_MSK	GENMASK(15, 0)
 
 /* MAC counters */
 #define ENETC_PM0_REOCT		0x8100
@@ -621,3 +631,10 @@ struct enetc_cbd {
 /* Port time specific departure */
 #define ENETC_PTCTSDR(n)	(0x1210 + 4 * (n))
 #define ENETC_TSDE		BIT(31)
+
+/* PSFP setting */
+#define ENETC_PPSFPMR 0x11b00
+#define ENETC_PPSFPMR_PSFPEN BIT(0)
+#define ENETC_PPSFPMR_VS BIT(1)
+#define ENETC_PPSFPMR_PVC BIT(2)
+#define ENETC_PPSFPMR_PVZC BIT(3)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index de1ad4975074..cef9fbfdb056 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -727,6 +727,14 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	if (si->hw_features & ENETC_SI_F_QBV)
 		priv->active_offloads |= ENETC_F_QBV;
 
+	if (si->hw_features & ENETC_SI_F_PSFP) {
+		priv->active_offloads |= ENETC_F_QCI;
+		ndev->features |= NETIF_F_HW_TC;
+		ndev->hw_features |= NETIF_F_HW_TC;
+		enetc_get_max_cap(priv);
+		enetc_psfp_enable(&si->hw);
+	}
+
 	/* pick up primary MAC address from SI */
 	enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
 }
-- 
cgit v1.2.3


From 888ae5a3952badf11fdcd210f5da9994462ec2fc Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Fri, 1 May 2020 08:53:18 +0800
Subject: net: enetc: add tc flower psfp offload driver

This patch is to add tc flower offload for the enetc IEEE 802.1Qci(PSFP)
function. There are four main feature parts to implement the flow
policing and filtering for ingress flow with IEEE 802.1Qci features.
They are stream identify(this is defined in the P802.1cb exactly but
needed for 802.1Qci), stream filtering, stream gate and flow metering.
Each function block includes many entries by index to assign parameters.
So for one frame would be filtered by stream identify first, then
flow into stream filter block by the same handle between stream identify
and stream filtering. Then flow into stream gate control which assigned
by the stream filtering entry. And then policing by the gate and limited
by the max sdu in the filter block(optional). At last, policing by the
flow metering block, index choosing at the fitering block.
So you can see that each entry of block may link to many upper entries
since they can be assigned same index means more streams want to share
the same feature in the stream filtering or stream gate or flow
metering.
To implement such features, each stream filtered by source/destination
mac address, some stream maybe also plus the vlan id value would be
treated as one flow chain. This would be identified by the chain_index
which already in the tc filter concept. Driver would maintain this chain
and also with gate modules. The stream filter entry create by the gate
index and flow meter(optional) entry id and also one priority value.
Offloading only transfer the gate action and flow filtering parameters.
Driver would create (or search same gate id and flow meter id and
 priority) one stream filter entry to set to the hardware. So stream
filtering do not need transfer by the action offloading.
This architecture is same with tc filter and actions relationship. tc
filter maintain the list for each flow feature by keys. And actions
maintain by the action list.

Below showing a example commands by tc:
> tc qdisc add dev eth0 ingress
> ip link set eth0 address 10:00:80:00:00:00
> tc filter add dev eth0 parent ffff: protocol ip chain 11 \
	flower skip_sw dst_mac 10:00:80:00:00:00 \
	action gate index 10 \
	sched-entry open 200000000 1 8000000 \
	sched-entry close 100000000 -1 -1

Command means to set the dst_mac 10:00:80:00:00:00 to index 11 of stream
identify module. Then setting the gate index 10 of stream gate module.
Keep the gate open for 200ms and limit the traffic volume to 8MB in this
sched-entry. Then direct the frames to the ingress queue 1.

Signed-off-by: Po Liu <Po.Liu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c     |   25 +-
 drivers/net/ethernet/freescale/enetc/enetc.h     |   46 +-
 drivers/net/ethernet/freescale/enetc/enetc_hw.h  |  142 +++
 drivers/net/ethernet/freescale/enetc/enetc_pf.c  |    4 +-
 drivers/net/ethernet/freescale/enetc/enetc_qos.c | 1098 ++++++++++++++++++++++
 5 files changed, 1300 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 04aac7cbb506..298c55786fd9 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1521,6 +1521,8 @@ int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 		return enetc_setup_tc_cbs(ndev, type_data);
 	case TC_SETUP_QDISC_ETF:
 		return enetc_setup_tc_txtime(ndev, type_data);
+	case TC_SETUP_BLOCK:
+		return enetc_setup_tc_psfp(ndev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1573,17 +1575,23 @@ static int enetc_set_rss(struct net_device *ndev, int en)
 static int enetc_set_psfp(struct net_device *ndev, int en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int err;
 
 	if (en) {
+		err = enetc_psfp_enable(priv);
+		if (err)
+			return err;
+
 		priv->active_offloads |= ENETC_F_QCI;
-		enetc_get_max_cap(priv);
-		enetc_psfp_enable(&priv->si->hw);
-	} else {
-		priv->active_offloads &= ~ENETC_F_QCI;
-		memset(&priv->psfp_cap, 0, sizeof(struct psfp_cap));
-		enetc_psfp_disable(&priv->si->hw);
+		return 0;
 	}
 
+	err = enetc_psfp_disable(priv);
+	if (err)
+		return err;
+
+	priv->active_offloads &= ~ENETC_F_QCI;
+
 	return 0;
 }
 
@@ -1591,14 +1599,15 @@ int enetc_set_features(struct net_device *ndev,
 		       netdev_features_t features)
 {
 	netdev_features_t changed = ndev->features ^ features;
+	int err = 0;
 
 	if (changed & NETIF_F_RXHASH)
 		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
 
 	if (changed & NETIF_F_HW_TC)
-		enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
+		err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
 
-	return 0;
+	return err;
 }
 
 #ifdef CONFIG_FSL_ENETC_PTP_CLOCK
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 2cfe877c3778..b705464f6882 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -300,6 +300,11 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data);
 void enetc_sched_speed_set(struct net_device *ndev);
 int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data);
 int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data);
+int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv);
+int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data);
+int enetc_psfp_init(struct enetc_ndev_priv *priv);
+int enetc_psfp_clean(struct enetc_ndev_priv *priv);
 
 static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv)
 {
@@ -319,27 +324,60 @@ static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv)
 	priv->psfp_cap.max_psfp_meter = reg & ENETC_PFMCAPR_MSK;
 }
 
-static inline void enetc_psfp_enable(struct enetc_hw *hw)
+static inline int enetc_psfp_enable(struct enetc_ndev_priv *priv)
 {
+	struct enetc_hw *hw = &priv->si->hw;
+	int err;
+
+	enetc_get_max_cap(priv);
+
+	err = enetc_psfp_init(priv);
+	if (err)
+		return err;
+
 	enetc_wr(hw, ENETC_PPSFPMR, enetc_rd(hw, ENETC_PPSFPMR) |
 		 ENETC_PPSFPMR_PSFPEN | ENETC_PPSFPMR_VS |
 		 ENETC_PPSFPMR_PVC | ENETC_PPSFPMR_PVZC);
+
+	return 0;
 }
 
-static inline void enetc_psfp_disable(struct enetc_hw *hw)
+static inline int enetc_psfp_disable(struct enetc_ndev_priv *priv)
 {
+	struct enetc_hw *hw = &priv->si->hw;
+	int err;
+
+	err = enetc_psfp_clean(priv);
+	if (err)
+		return err;
+
 	enetc_wr(hw, ENETC_PPSFPMR, enetc_rd(hw, ENETC_PPSFPMR) &
 		 ~ENETC_PPSFPMR_PSFPEN & ~ENETC_PPSFPMR_VS &
 		 ~ENETC_PPSFPMR_PVC & ~ENETC_PPSFPMR_PVZC);
+
+	memset(&priv->psfp_cap, 0, sizeof(struct psfp_cap));
+
+	return 0;
 }
+
 #else
 #define enetc_setup_tc_taprio(ndev, type_data) -EOPNOTSUPP
 #define enetc_sched_speed_set(ndev) (void)0
 #define enetc_setup_tc_cbs(ndev, type_data) -EOPNOTSUPP
 #define enetc_setup_tc_txtime(ndev, type_data) -EOPNOTSUPP
+#define enetc_setup_tc_psfp(ndev, type_data) -EOPNOTSUPP
+#define enetc_setup_tc_block_cb NULL
+
 #define enetc_get_max_cap(p)		\
 	memset(&((p)->psfp_cap), 0, sizeof(struct psfp_cap))
 
-#define enetc_psfp_enable(hw) (void)0
-#define enetc_psfp_disable(hw) (void)0
+static inline int enetc_psfp_enable(struct enetc_ndev_priv *priv)
+{
+	return 0;
+}
+
+static inline int enetc_psfp_disable(struct enetc_ndev_priv *priv)
+{
+	return 0;
+}
 #endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 587974862f48..6314051bc6c1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -567,6 +567,9 @@ enum bdcr_cmd_class {
 	BDCR_CMD_RFS,
 	BDCR_CMD_PORT_GCL,
 	BDCR_CMD_RECV_CLASSIFIER,
+	BDCR_CMD_STREAM_IDENTIFY,
+	BDCR_CMD_STREAM_FILTER,
+	BDCR_CMD_STREAM_GCL,
 	__BDCR_CMD_MAX_LEN,
 	BDCR_CMD_MAX_LEN = __BDCR_CMD_MAX_LEN - 1,
 };
@@ -598,13 +601,152 @@ struct tgs_gcl_data {
 	struct gce	entry[];
 };
 
+/* class 7, command 0, Stream Identity Entry Configuration */
+struct streamid_conf {
+	__le32	stream_handle;	/* init gate value */
+	__le32	iports;
+		u8	id_type;
+		u8	oui[3];
+		u8	res[3];
+		u8	en;
+};
+
+#define ENETC_CBDR_SID_VID_MASK 0xfff
+#define ENETC_CBDR_SID_VIDM BIT(12)
+#define ENETC_CBDR_SID_TG_MASK 0xc000
+/* streamid_conf address point to this data space */
+struct streamid_data {
+	union {
+		u8 dmac[6];
+		u8 smac[6];
+	};
+	u16     vid_vidm_tg;
+};
+
+#define ENETC_CBDR_SFI_PRI_MASK 0x7
+#define ENETC_CBDR_SFI_PRIM		BIT(3)
+#define ENETC_CBDR_SFI_BLOV		BIT(4)
+#define ENETC_CBDR_SFI_BLEN		BIT(5)
+#define ENETC_CBDR_SFI_MSDUEN	BIT(6)
+#define ENETC_CBDR_SFI_FMITEN	BIT(7)
+#define ENETC_CBDR_SFI_ENABLE	BIT(7)
+/* class 8, command 0, Stream Filter Instance, Short Format */
+struct sfi_conf {
+	__le32	stream_handle;
+		u8	multi;
+		u8	res[2];
+		u8	sthm;
+	/* Max Service Data Unit or Flow Meter Instance Table index.
+	 * Depending on the value of FLT this represents either Max
+	 * Service Data Unit (max frame size) allowed by the filter
+	 * entry or is an index into the Flow Meter Instance table
+	 * index identifying the policer which will be used to police
+	 * it.
+	 */
+	__le16	fm_inst_table_index;
+	__le16	msdu;
+	__le16	sg_inst_table_index;
+		u8	res1[2];
+	__le32	input_ports;
+		u8	res2[3];
+		u8	en;
+};
+
+/* class 8, command 2 stream Filter Instance status query short format
+ * command no need structure define
+ * Stream Filter Instance Query Statistics Response data
+ */
+struct sfi_counter_data {
+	u32 matchl;
+	u32 matchh;
+	u32 msdu_dropl;
+	u32 msdu_droph;
+	u32 stream_gate_dropl;
+	u32 stream_gate_droph;
+	u32 flow_meter_dropl;
+	u32 flow_meter_droph;
+};
+
+#define ENETC_CBDR_SGI_OIPV_MASK 0x7
+#define ENETC_CBDR_SGI_OIPV_EN	BIT(3)
+#define ENETC_CBDR_SGI_CGTST	BIT(6)
+#define ENETC_CBDR_SGI_OGTST	BIT(7)
+#define ENETC_CBDR_SGI_CFG_CHG  BIT(1)
+#define ENETC_CBDR_SGI_CFG_PND  BIT(2)
+#define ENETC_CBDR_SGI_OEX		BIT(4)
+#define ENETC_CBDR_SGI_OEXEN	BIT(5)
+#define ENETC_CBDR_SGI_IRX		BIT(6)
+#define ENETC_CBDR_SGI_IRXEN	BIT(7)
+#define ENETC_CBDR_SGI_ACLLEN_MASK 0x3
+#define ENETC_CBDR_SGI_OCLLEN_MASK 0xc
+#define	ENETC_CBDR_SGI_EN		BIT(7)
+/* class 9, command 0, Stream Gate Instance Table, Short Format
+ * class 9, command 2, Stream Gate Instance Table entry query write back
+ * Short Format
+ */
+struct sgi_table {
+	u8	res[8];
+	u8	oipv;
+	u8	res0[2];
+	u8	ocgtst;
+	u8	res1[7];
+	u8	gset;
+	u8	oacl_len;
+	u8	res2[2];
+	u8	en;
+};
+
+#define ENETC_CBDR_SGI_AIPV_MASK 0x7
+#define ENETC_CBDR_SGI_AIPV_EN	BIT(3)
+#define ENETC_CBDR_SGI_AGTST	BIT(7)
+
+/* class 9, command 1, Stream Gate Control List, Long Format */
+struct sgcl_conf {
+	u8	aipv;
+	u8	res[2];
+	u8	agtst;
+	u8	res1[4];
+	union {
+		struct {
+			u8 res2[4];
+			u8 acl_len;
+			u8 res3[3];
+		};
+		u8 cct[8]; /* Config change time */
+	};
+};
+
+#define ENETC_CBDR_SGL_IOMEN	BIT(0)
+#define ENETC_CBDR_SGL_IPVEN	BIT(3)
+#define ENETC_CBDR_SGL_GTST		BIT(4)
+#define ENETC_CBDR_SGL_IPV_MASK 0xe
+/* Stream Gate Control List Entry */
+struct sgce {
+	u32	interval;
+	u8	msdu[3];
+	u8	multi;
+};
+
+/* stream control list class 9 , cmd 1 data buffer */
+struct sgcl_data {
+	u32		btl;
+	u32		bth;
+	u32		ct;
+	u32		cte;
+	struct sgce	sgcl[0];
+};
+
 struct enetc_cbd {
 	union{
+		struct sfi_conf sfi_conf;
+		struct sgi_table sgi_table;
 		struct {
 			__le32	addr[2];
 			union {
 				__le32	opt[4];
 				struct tgs_gcl_conf	gcl_conf;
+				struct streamid_conf	sid_set;
+				struct sgcl_conf	sgcl_conf;
 			};
 		};	/* Long format */
 		__le32 data[6];
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index cef9fbfdb056..824d211ec00f 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -727,12 +727,10 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	if (si->hw_features & ENETC_SI_F_QBV)
 		priv->active_offloads |= ENETC_F_QBV;
 
-	if (si->hw_features & ENETC_SI_F_PSFP) {
+	if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) {
 		priv->active_offloads |= ENETC_F_QCI;
 		ndev->features |= NETIF_F_HW_TC;
 		ndev->hw_features |= NETIF_F_HW_TC;
-		enetc_get_max_cap(priv);
-		enetc_psfp_enable(&si->hw);
 	}
 
 	/* pick up primary MAC address from SI */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 0c6bf3a55a9a..30fca29b2739 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -5,6 +5,9 @@
 
 #include <net/pkt_sched.h>
 #include <linux/math64.h>
+#include <linux/refcount.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gate.h>
 
 static u16 enetc_get_max_gcl_len(struct enetc_hw *hw)
 {
@@ -331,3 +334,1098 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data)
 
 	return 0;
 }
+
+enum streamid_type {
+	STREAMID_TYPE_RESERVED = 0,
+	STREAMID_TYPE_NULL,
+	STREAMID_TYPE_SMAC,
+};
+
+enum streamid_vlan_tagged {
+	STREAMID_VLAN_RESERVED = 0,
+	STREAMID_VLAN_TAGGED,
+	STREAMID_VLAN_UNTAGGED,
+	STREAMID_VLAN_ALL,
+};
+
+#define ENETC_PSFP_WILDCARD -1
+#define HANDLE_OFFSET 100
+
+enum forward_type {
+	FILTER_ACTION_TYPE_PSFP = BIT(0),
+	FILTER_ACTION_TYPE_ACL = BIT(1),
+	FILTER_ACTION_TYPE_BOTH = GENMASK(1, 0),
+};
+
+/* This is for limit output type for input actions */
+struct actions_fwd {
+	u64 actions;
+	u64 keys;	/* include the must needed keys */
+	enum forward_type output;
+};
+
+struct psfp_streamfilter_counters {
+	u64 matching_frames_count;
+	u64 passing_frames_count;
+	u64 not_passing_frames_count;
+	u64 passing_sdu_count;
+	u64 not_passing_sdu_count;
+	u64 red_frames_count;
+};
+
+struct enetc_streamid {
+	u32 index;
+	union {
+		u8 src_mac[6];
+		u8 dst_mac[6];
+	};
+	u8 filtertype;
+	u16 vid;
+	u8 tagged;
+	s32 handle;
+};
+
+struct enetc_psfp_filter {
+	u32 index;
+	s32 handle;
+	s8 prio;
+	u32 gate_id;
+	s32 meter_id;
+	refcount_t refcount;
+	struct hlist_node node;
+};
+
+struct enetc_psfp_gate {
+	u32 index;
+	s8 init_ipv;
+	u64 basetime;
+	u64 cycletime;
+	u64 cycletimext;
+	u32 num_entries;
+	refcount_t refcount;
+	struct hlist_node node;
+	struct action_gate_entry entries[0];
+};
+
+struct enetc_stream_filter {
+	struct enetc_streamid sid;
+	u32 sfi_index;
+	u32 sgi_index;
+	struct flow_stats stats;
+	struct hlist_node node;
+};
+
+struct enetc_psfp {
+	unsigned long dev_bitmap;
+	unsigned long *psfp_sfi_bitmap;
+	struct hlist_head stream_list;
+	struct hlist_head psfp_filter_list;
+	struct hlist_head psfp_gate_list;
+	spinlock_t psfp_lock; /* spinlock for the struct enetc_psfp r/w */
+};
+
+struct actions_fwd enetc_act_fwd[] = {
+	{
+		BIT(FLOW_ACTION_GATE),
+		BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS),
+		FILTER_ACTION_TYPE_PSFP
+	},
+	/* example for ACL actions */
+	{
+		BIT(FLOW_ACTION_DROP),
+		0,
+		FILTER_ACTION_TYPE_ACL
+	}
+};
+
+static struct enetc_psfp epsfp = {
+	.psfp_sfi_bitmap = NULL,
+};
+
+static LIST_HEAD(enetc_block_cb_list);
+
+static inline int enetc_get_port(struct enetc_ndev_priv *priv)
+{
+	return priv->si->pdev->devfn & 0x7;
+}
+
+/* Stream Identity Entry Set Descriptor */
+static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv,
+				 struct enetc_streamid *sid,
+				 u8 enable)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	struct streamid_data *si_data;
+	struct streamid_conf *si_conf;
+	u16 data_size;
+	dma_addr_t dma;
+	int err;
+
+	if (sid->index >= priv->psfp_cap.max_streamid)
+		return -EINVAL;
+
+	if (sid->filtertype != STREAMID_TYPE_NULL &&
+	    sid->filtertype != STREAMID_TYPE_SMAC)
+		return -EOPNOTSUPP;
+
+	/* Disable operation before enable */
+	cbd.index = cpu_to_le16((u16)sid->index);
+	cbd.cls = BDCR_CMD_STREAM_IDENTIFY;
+	cbd.status_flags = 0;
+
+	data_size = sizeof(struct streamid_data);
+	si_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL);
+	cbd.length = cpu_to_le16(data_size);
+
+	dma = dma_map_single(&priv->si->pdev->dev, si_data,
+			     data_size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&priv->si->pdev->dev, dma)) {
+		netdev_err(priv->si->ndev, "DMA mapping failed!\n");
+		kfree(si_data);
+		return -ENOMEM;
+	}
+
+	cbd.addr[0] = lower_32_bits(dma);
+	cbd.addr[1] = upper_32_bits(dma);
+	memset(si_data->dmac, 0xff, ETH_ALEN);
+	si_data->vid_vidm_tg =
+		cpu_to_le16(ENETC_CBDR_SID_VID_MASK
+			    + ((0x3 << 14) | ENETC_CBDR_SID_VIDM));
+
+	si_conf = &cbd.sid_set;
+	/* Only one port supported for one entry, set itself */
+	si_conf->iports = 1 << enetc_get_port(priv);
+	si_conf->id_type = 1;
+	si_conf->oui[2] = 0x0;
+	si_conf->oui[1] = 0x80;
+	si_conf->oui[0] = 0xC2;
+
+	err = enetc_send_cmd(priv->si, &cbd);
+	if (err)
+		return -EINVAL;
+
+	if (!enable) {
+		kfree(si_data);
+		return 0;
+	}
+
+	/* Enable the entry overwrite again incase space flushed by hardware */
+	memset(&cbd, 0, sizeof(cbd));
+
+	cbd.index = cpu_to_le16((u16)sid->index);
+	cbd.cmd = 0;
+	cbd.cls = BDCR_CMD_STREAM_IDENTIFY;
+	cbd.status_flags = 0;
+
+	si_conf->en = 0x80;
+	si_conf->stream_handle = cpu_to_le32(sid->handle);
+	si_conf->iports = 1 << enetc_get_port(priv);
+	si_conf->id_type = sid->filtertype;
+	si_conf->oui[2] = 0x0;
+	si_conf->oui[1] = 0x80;
+	si_conf->oui[0] = 0xC2;
+
+	memset(si_data, 0, data_size);
+
+	cbd.length = cpu_to_le16(data_size);
+
+	cbd.addr[0] = lower_32_bits(dma);
+	cbd.addr[1] = upper_32_bits(dma);
+
+	/* VIDM default to be 1.
+	 * VID Match. If set (b1) then the VID must match, otherwise
+	 * any VID is considered a match. VIDM setting is only used
+	 * when TG is set to b01.
+	 */
+	if (si_conf->id_type == STREAMID_TYPE_NULL) {
+		ether_addr_copy(si_data->dmac, sid->dst_mac);
+		si_data->vid_vidm_tg =
+		cpu_to_le16((sid->vid & ENETC_CBDR_SID_VID_MASK) +
+			    ((((u16)(sid->tagged) & 0x3) << 14)
+			     | ENETC_CBDR_SID_VIDM));
+	} else if (si_conf->id_type == STREAMID_TYPE_SMAC) {
+		ether_addr_copy(si_data->smac, sid->src_mac);
+		si_data->vid_vidm_tg =
+		cpu_to_le16((sid->vid & ENETC_CBDR_SID_VID_MASK) +
+			    ((((u16)(sid->tagged) & 0x3) << 14)
+			     | ENETC_CBDR_SID_VIDM));
+	}
+
+	err = enetc_send_cmd(priv->si, &cbd);
+	kfree(si_data);
+
+	return err;
+}
+
+/* Stream Filter Instance Set Descriptor */
+static int enetc_streamfilter_hw_set(struct enetc_ndev_priv *priv,
+				     struct enetc_psfp_filter *sfi,
+				     u8 enable)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	struct sfi_conf *sfi_config;
+
+	cbd.index = cpu_to_le16(sfi->index);
+	cbd.cls = BDCR_CMD_STREAM_FILTER;
+	cbd.status_flags = 0x80;
+	cbd.length = cpu_to_le16(1);
+
+	sfi_config = &cbd.sfi_conf;
+	if (!enable)
+		goto exit;
+
+	sfi_config->en = 0x80;
+
+	if (sfi->handle >= 0) {
+		sfi_config->stream_handle =
+			cpu_to_le32(sfi->handle);
+		sfi_config->sthm |= 0x80;
+	}
+
+	sfi_config->sg_inst_table_index = cpu_to_le16(sfi->gate_id);
+	sfi_config->input_ports = 1 << enetc_get_port(priv);
+
+	/* The priority value which may be matched against the
+	 * frame’s priority value to determine a match for this entry.
+	 */
+	if (sfi->prio >= 0)
+		sfi_config->multi |= (sfi->prio & 0x7) | 0x8;
+
+	/* Filter Type. Identifies the contents of the MSDU/FM_INST_INDEX
+	 * field as being either an MSDU value or an index into the Flow
+	 * Meter Instance table.
+	 * TODO: no limit max sdu
+	 */
+
+	if (sfi->meter_id >= 0) {
+		sfi_config->fm_inst_table_index = cpu_to_le16(sfi->meter_id);
+		sfi_config->multi |= 0x80;
+	}
+
+exit:
+	return enetc_send_cmd(priv->si, &cbd);
+}
+
+static int enetc_streamcounter_hw_get(struct enetc_ndev_priv *priv,
+				      u32 index,
+				      struct psfp_streamfilter_counters *cnt)
+{
+	struct enetc_cbd cbd = { .cmd = 2 };
+	struct sfi_counter_data *data_buf;
+	dma_addr_t dma;
+	u16 data_size;
+	int err;
+
+	cbd.index = cpu_to_le16((u16)index);
+	cbd.cmd = 2;
+	cbd.cls = BDCR_CMD_STREAM_FILTER;
+	cbd.status_flags = 0;
+
+	data_size = sizeof(struct sfi_counter_data);
+	data_buf = kzalloc(data_size, __GFP_DMA | GFP_KERNEL);
+	if (!data_buf)
+		return -ENOMEM;
+
+	dma = dma_map_single(&priv->si->pdev->dev, data_buf,
+			     data_size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&priv->si->pdev->dev, dma)) {
+		netdev_err(priv->si->ndev, "DMA mapping failed!\n");
+		err = -ENOMEM;
+		goto exit;
+	}
+	cbd.addr[0] = lower_32_bits(dma);
+	cbd.addr[1] = upper_32_bits(dma);
+
+	cbd.length = cpu_to_le16(data_size);
+
+	err = enetc_send_cmd(priv->si, &cbd);
+	if (err)
+		goto exit;
+
+	cnt->matching_frames_count =
+			((u64)le32_to_cpu(data_buf->matchh) << 32)
+			+ data_buf->matchl;
+
+	cnt->not_passing_sdu_count =
+			((u64)le32_to_cpu(data_buf->msdu_droph) << 32)
+			+ data_buf->msdu_dropl;
+
+	cnt->passing_sdu_count = cnt->matching_frames_count
+				- cnt->not_passing_sdu_count;
+
+	cnt->not_passing_frames_count =
+		((u64)le32_to_cpu(data_buf->stream_gate_droph) << 32)
+		+ le32_to_cpu(data_buf->stream_gate_dropl);
+
+	cnt->passing_frames_count = cnt->matching_frames_count
+				- cnt->not_passing_sdu_count
+				- cnt->not_passing_frames_count;
+
+	cnt->red_frames_count =
+		((u64)le32_to_cpu(data_buf->flow_meter_droph) << 32)
+		+ le32_to_cpu(data_buf->flow_meter_dropl);
+
+exit:
+	kfree(data_buf);
+	return err;
+}
+
+static u64 get_ptp_now(struct enetc_hw *hw)
+{
+	u64 now_lo, now_hi, now;
+
+	now_lo = enetc_rd(hw, ENETC_SICTR0);
+	now_hi = enetc_rd(hw, ENETC_SICTR1);
+	now = now_lo | now_hi << 32;
+
+	return now;
+}
+
+static int get_start_ns(u64 now, u64 cycle, u64 *start)
+{
+	u64 n;
+
+	if (!cycle)
+		return -EFAULT;
+
+	n = div64_u64(now, cycle);
+
+	*start = (n + 1) * cycle;
+
+	return 0;
+}
+
+/* Stream Gate Instance Set Descriptor */
+static int enetc_streamgate_hw_set(struct enetc_ndev_priv *priv,
+				   struct enetc_psfp_gate *sgi,
+				   u8 enable)
+{
+	struct enetc_cbd cbd = { .cmd = 0 };
+	struct sgi_table *sgi_config;
+	struct sgcl_conf *sgcl_config;
+	struct sgcl_data *sgcl_data;
+	struct sgce *sgce;
+	dma_addr_t dma;
+	u16 data_size;
+	int err, i;
+	u64 now;
+
+	cbd.index = cpu_to_le16(sgi->index);
+	cbd.cmd = 0;
+	cbd.cls = BDCR_CMD_STREAM_GCL;
+	cbd.status_flags = 0x80;
+
+	/* disable */
+	if (!enable)
+		return enetc_send_cmd(priv->si, &cbd);
+
+	if (!sgi->num_entries)
+		return 0;
+
+	if (sgi->num_entries > priv->psfp_cap.max_psfp_gatelist ||
+	    !sgi->cycletime)
+		return -EINVAL;
+
+	/* enable */
+	sgi_config = &cbd.sgi_table;
+
+	/* Keep open before gate list start */
+	sgi_config->ocgtst = 0x80;
+
+	sgi_config->oipv = (sgi->init_ipv < 0) ?
+				0x0 : ((sgi->init_ipv & 0x7) | 0x8);
+
+	sgi_config->en = 0x80;
+
+	/* Basic config */
+	err = enetc_send_cmd(priv->si, &cbd);
+	if (err)
+		return -EINVAL;
+
+	memset(&cbd, 0, sizeof(cbd));
+
+	cbd.index = cpu_to_le16(sgi->index);
+	cbd.cmd = 1;
+	cbd.cls = BDCR_CMD_STREAM_GCL;
+	cbd.status_flags = 0;
+
+	sgcl_config = &cbd.sgcl_conf;
+
+	sgcl_config->acl_len = (sgi->num_entries - 1) & 0x3;
+
+	data_size = struct_size(sgcl_data, sgcl, sgi->num_entries);
+
+	sgcl_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL);
+	if (!sgcl_data)
+		return -ENOMEM;
+
+	cbd.length = cpu_to_le16(data_size);
+
+	dma = dma_map_single(&priv->si->pdev->dev,
+			     sgcl_data, data_size,
+			     DMA_FROM_DEVICE);
+	if (dma_mapping_error(&priv->si->pdev->dev, dma)) {
+		netdev_err(priv->si->ndev, "DMA mapping failed!\n");
+		kfree(sgcl_data);
+		return -ENOMEM;
+	}
+
+	cbd.addr[0] = lower_32_bits(dma);
+	cbd.addr[1] = upper_32_bits(dma);
+
+	sgce = &sgcl_data->sgcl[0];
+
+	sgcl_config->agtst = 0x80;
+
+	sgcl_data->ct = cpu_to_le32(sgi->cycletime);
+	sgcl_data->cte = cpu_to_le32(sgi->cycletimext);
+
+	if (sgi->init_ipv >= 0)
+		sgcl_config->aipv = (sgi->init_ipv & 0x7) | 0x8;
+
+	for (i = 0; i < sgi->num_entries; i++) {
+		struct action_gate_entry *from = &sgi->entries[i];
+		struct sgce *to = &sgce[i];
+
+		if (from->gate_state)
+			to->multi |= 0x10;
+
+		if (from->ipv >= 0)
+			to->multi |= ((from->ipv & 0x7) << 5) | 0x08;
+
+		if (from->maxoctets >= 0) {
+			to->multi |= 0x01;
+			to->msdu[0] = from->maxoctets & 0xFF;
+			to->msdu[1] = (from->maxoctets >> 8) & 0xFF;
+			to->msdu[2] = (from->maxoctets >> 16) & 0xFF;
+		}
+
+		to->interval = cpu_to_le32(from->interval);
+	}
+
+	/* If basetime is less than now, calculate start time */
+	now = get_ptp_now(&priv->si->hw);
+
+	if (sgi->basetime < now) {
+		u64 start;
+
+		err = get_start_ns(now, sgi->cycletime, &start);
+		if (err)
+			goto exit;
+		sgcl_data->btl = cpu_to_le32(lower_32_bits(start));
+		sgcl_data->bth = cpu_to_le32(upper_32_bits(start));
+	} else {
+		u32 hi, lo;
+
+		hi = upper_32_bits(sgi->basetime);
+		lo = lower_32_bits(sgi->basetime);
+		sgcl_data->bth = cpu_to_le32(hi);
+		sgcl_data->btl = cpu_to_le32(lo);
+	}
+
+	err = enetc_send_cmd(priv->si, &cbd);
+
+exit:
+	kfree(sgcl_data);
+
+	return err;
+}
+
+static struct enetc_stream_filter *enetc_get_stream_by_index(u32 index)
+{
+	struct enetc_stream_filter *f;
+
+	hlist_for_each_entry(f, &epsfp.stream_list, node)
+		if (f->sid.index == index)
+			return f;
+
+	return NULL;
+}
+
+static struct enetc_psfp_gate *enetc_get_gate_by_index(u32 index)
+{
+	struct enetc_psfp_gate *g;
+
+	hlist_for_each_entry(g, &epsfp.psfp_gate_list, node)
+		if (g->index == index)
+			return g;
+
+	return NULL;
+}
+
+static struct enetc_psfp_filter *enetc_get_filter_by_index(u32 index)
+{
+	struct enetc_psfp_filter *s;
+
+	hlist_for_each_entry(s, &epsfp.psfp_filter_list, node)
+		if (s->index == index)
+			return s;
+
+	return NULL;
+}
+
+static struct enetc_psfp_filter
+	*enetc_psfp_check_sfi(struct enetc_psfp_filter *sfi)
+{
+	struct enetc_psfp_filter *s;
+
+	hlist_for_each_entry(s, &epsfp.psfp_filter_list, node)
+		if (s->gate_id == sfi->gate_id &&
+		    s->prio == sfi->prio &&
+		    s->meter_id == sfi->meter_id)
+			return s;
+
+	return NULL;
+}
+
+static int enetc_get_free_index(struct enetc_ndev_priv *priv)
+{
+	u32 max_size = priv->psfp_cap.max_psfp_filter;
+	unsigned long index;
+
+	index = find_first_zero_bit(epsfp.psfp_sfi_bitmap, max_size);
+	if (index == max_size)
+		return -1;
+
+	return index;
+}
+
+static void stream_filter_unref(struct enetc_ndev_priv *priv, u32 index)
+{
+	struct enetc_psfp_filter *sfi;
+	u8 z;
+
+	sfi = enetc_get_filter_by_index(index);
+	WARN_ON(!sfi);
+	z = refcount_dec_and_test(&sfi->refcount);
+
+	if (z) {
+		enetc_streamfilter_hw_set(priv, sfi, false);
+		hlist_del(&sfi->node);
+		kfree(sfi);
+		clear_bit(sfi->index, epsfp.psfp_sfi_bitmap);
+	}
+}
+
+static void stream_gate_unref(struct enetc_ndev_priv *priv, u32 index)
+{
+	struct enetc_psfp_gate *sgi;
+	u8 z;
+
+	sgi = enetc_get_gate_by_index(index);
+	WARN_ON(!sgi);
+	z = refcount_dec_and_test(&sgi->refcount);
+	if (z) {
+		enetc_streamgate_hw_set(priv, sgi, false);
+		hlist_del(&sgi->node);
+		kfree(sgi);
+	}
+}
+
+static void remove_one_chain(struct enetc_ndev_priv *priv,
+			     struct enetc_stream_filter *filter)
+{
+	stream_gate_unref(priv, filter->sgi_index);
+	stream_filter_unref(priv, filter->sfi_index);
+
+	hlist_del(&filter->node);
+	kfree(filter);
+}
+
+static int enetc_psfp_hw_set(struct enetc_ndev_priv *priv,
+			     struct enetc_streamid *sid,
+			     struct enetc_psfp_filter *sfi,
+			     struct enetc_psfp_gate *sgi)
+{
+	int err;
+
+	err = enetc_streamid_hw_set(priv, sid, true);
+	if (err)
+		return err;
+
+	if (sfi) {
+		err = enetc_streamfilter_hw_set(priv, sfi, true);
+		if (err)
+			goto revert_sid;
+	}
+
+	err = enetc_streamgate_hw_set(priv, sgi, true);
+	if (err)
+		goto revert_sfi;
+
+	return 0;
+
+revert_sfi:
+	if (sfi)
+		enetc_streamfilter_hw_set(priv, sfi, false);
+revert_sid:
+	enetc_streamid_hw_set(priv, sid, false);
+	return err;
+}
+
+struct actions_fwd *enetc_check_flow_actions(u64 acts, unsigned int inputkeys)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_act_fwd); i++)
+		if (acts == enetc_act_fwd[i].actions &&
+		    inputkeys & enetc_act_fwd[i].keys)
+			return &enetc_act_fwd[i];
+
+	return NULL;
+}
+
+static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv,
+				      struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct enetc_stream_filter *filter, *old_filter;
+	struct enetc_psfp_filter *sfi, *old_sfi;
+	struct enetc_psfp_gate *sgi, *old_sgi;
+	struct flow_action_entry *entry;
+	struct action_gate_entry *e;
+	u8 sfi_overwrite = 0;
+	int entries_size;
+	int i, err;
+
+	if (f->common.chain_index >= priv->psfp_cap.max_streamid) {
+		NL_SET_ERR_MSG_MOD(extack, "No Stream identify resource!");
+		return -ENOSPC;
+	}
+
+	flow_action_for_each(i, entry, &rule->action)
+		if (entry->id == FLOW_ACTION_GATE)
+			break;
+
+	if (entry->id != FLOW_ACTION_GATE)
+		return -EINVAL;
+
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!filter)
+		return -ENOMEM;
+
+	filter->sid.index = f->common.chain_index;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
+
+		flow_rule_match_eth_addrs(rule, &match);
+
+		if (!is_zero_ether_addr(match.mask->dst) &&
+		    !is_zero_ether_addr(match.mask->src)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot match on both source and destination MAC");
+			goto free_filter;
+		}
+
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (!is_broadcast_ether_addr(match.mask->dst)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Masked matching on destination MAC not supported");
+				goto free_filter;
+			}
+			ether_addr_copy(filter->sid.dst_mac, match.key->dst);
+			filter->sid.filtertype = STREAMID_TYPE_NULL;
+		}
+
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (!is_broadcast_ether_addr(match.mask->src)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Masked matching on source MAC not supported");
+				goto free_filter;
+			}
+			ether_addr_copy(filter->sid.src_mac, match.key->src);
+			filter->sid.filtertype = STREAMID_TYPE_SMAC;
+		}
+	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported, must include ETH_ADDRS");
+		goto free_filter;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_priority) {
+			if (match.mask->vlan_priority !=
+			    (VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT)) {
+				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority");
+				err = -EINVAL;
+				goto free_filter;
+			}
+		}
+
+		if (match.mask->vlan_id) {
+			if (match.mask->vlan_id != VLAN_VID_MASK) {
+				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN id");
+				err = -EINVAL;
+				goto free_filter;
+			}
+
+			filter->sid.vid = match.key->vlan_id;
+			if (!filter->sid.vid)
+				filter->sid.tagged = STREAMID_VLAN_UNTAGGED;
+			else
+				filter->sid.tagged = STREAMID_VLAN_TAGGED;
+		}
+	} else {
+		filter->sid.tagged = STREAMID_VLAN_ALL;
+	}
+
+	/* parsing gate action */
+	if (entry->gate.index >= priv->psfp_cap.max_psfp_gate) {
+		NL_SET_ERR_MSG_MOD(extack, "No Stream Gate resource!");
+		err = -ENOSPC;
+		goto free_filter;
+	}
+
+	if (entry->gate.num_entries >= priv->psfp_cap.max_psfp_gatelist) {
+		NL_SET_ERR_MSG_MOD(extack, "No Stream Gate resource!");
+		err = -ENOSPC;
+		goto free_filter;
+	}
+
+	entries_size = struct_size(sgi, entries, entry->gate.num_entries);
+	sgi = kzalloc(entries_size, GFP_KERNEL);
+	if (!sgi) {
+		err = -ENOMEM;
+		goto free_filter;
+	}
+
+	refcount_set(&sgi->refcount, 1);
+	sgi->index = entry->gate.index;
+	sgi->init_ipv = entry->gate.prio;
+	sgi->basetime = entry->gate.basetime;
+	sgi->cycletime = entry->gate.cycletime;
+	sgi->num_entries = entry->gate.num_entries;
+
+	e = sgi->entries;
+	for (i = 0; i < entry->gate.num_entries; i++) {
+		e[i].gate_state = entry->gate.entries[i].gate_state;
+		e[i].interval = entry->gate.entries[i].interval;
+		e[i].ipv = entry->gate.entries[i].ipv;
+		e[i].maxoctets = entry->gate.entries[i].maxoctets;
+	}
+
+	filter->sgi_index = sgi->index;
+
+	sfi = kzalloc(sizeof(*sfi), GFP_KERNEL);
+	if (!sfi) {
+		err = -ENOMEM;
+		goto free_gate;
+	}
+
+	refcount_set(&sfi->refcount, 1);
+	sfi->gate_id = sgi->index;
+
+	/* flow meter not support yet */
+	sfi->meter_id = ENETC_PSFP_WILDCARD;
+
+	/* prio ref the filter prio */
+	if (f->common.prio && f->common.prio <= BIT(3))
+		sfi->prio = f->common.prio - 1;
+	else
+		sfi->prio = ENETC_PSFP_WILDCARD;
+
+	old_sfi = enetc_psfp_check_sfi(sfi);
+	if (!old_sfi) {
+		int index;
+
+		index = enetc_get_free_index(priv);
+		if (sfi->handle < 0) {
+			NL_SET_ERR_MSG_MOD(extack, "No Stream Filter resource!");
+			err = -ENOSPC;
+			goto free_sfi;
+		}
+
+		sfi->index = index;
+		sfi->handle = index + HANDLE_OFFSET;
+		/* Update the stream filter handle also */
+		filter->sid.handle = sfi->handle;
+		filter->sfi_index = sfi->index;
+		sfi_overwrite = 0;
+	} else {
+		filter->sfi_index = old_sfi->index;
+		filter->sid.handle = old_sfi->handle;
+		sfi_overwrite = 1;
+	}
+
+	err = enetc_psfp_hw_set(priv, &filter->sid,
+				sfi_overwrite ? NULL : sfi, sgi);
+	if (err)
+		goto free_sfi;
+
+	spin_lock(&epsfp.psfp_lock);
+	/* Remove the old node if exist and update with a new node */
+	old_sgi = enetc_get_gate_by_index(filter->sgi_index);
+	if (old_sgi) {
+		refcount_set(&sgi->refcount,
+			     refcount_read(&old_sgi->refcount) + 1);
+		hlist_del(&old_sgi->node);
+		kfree(old_sgi);
+	}
+
+	hlist_add_head(&sgi->node, &epsfp.psfp_gate_list);
+
+	if (!old_sfi) {
+		hlist_add_head(&sfi->node, &epsfp.psfp_filter_list);
+		set_bit(sfi->index, epsfp.psfp_sfi_bitmap);
+	} else {
+		kfree(sfi);
+		refcount_inc(&old_sfi->refcount);
+	}
+
+	old_filter = enetc_get_stream_by_index(filter->sid.index);
+	if (old_filter)
+		remove_one_chain(priv, old_filter);
+
+	filter->stats.lastused = jiffies;
+	hlist_add_head(&filter->node, &epsfp.stream_list);
+
+	spin_unlock(&epsfp.psfp_lock);
+
+	return 0;
+
+free_sfi:
+	kfree(sfi);
+free_gate:
+	kfree(sgi);
+free_filter:
+	kfree(filter);
+
+	return err;
+}
+
+static int enetc_config_clsflower(struct enetc_ndev_priv *priv,
+				  struct flow_cls_offload *cls_flower)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower);
+	struct netlink_ext_ack *extack = cls_flower->common.extack;
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct flow_action *action = &rule->action;
+	struct flow_action_entry *entry;
+	struct actions_fwd *fwd;
+	u64 actions = 0;
+	int i, err;
+
+	if (!flow_action_has_entries(action)) {
+		NL_SET_ERR_MSG_MOD(extack, "At least one action is needed");
+		return -EINVAL;
+	}
+
+	flow_action_for_each(i, entry, action)
+		actions |= BIT(entry->id);
+
+	fwd = enetc_check_flow_actions(actions, dissector->used_keys);
+	if (!fwd) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported filter type!");
+		return -EOPNOTSUPP;
+	}
+
+	if (fwd->output & FILTER_ACTION_TYPE_PSFP) {
+		err = enetc_psfp_parse_clsflower(priv, cls_flower);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid PSFP inputs");
+			return err;
+		}
+	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported actions");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int enetc_psfp_destroy_clsflower(struct enetc_ndev_priv *priv,
+					struct flow_cls_offload *f)
+{
+	struct enetc_stream_filter *filter;
+	struct netlink_ext_ack *extack = f->common.extack;
+	int err;
+
+	if (f->common.chain_index >= priv->psfp_cap.max_streamid) {
+		NL_SET_ERR_MSG_MOD(extack, "No Stream identify resource!");
+		return -ENOSPC;
+	}
+
+	filter = enetc_get_stream_by_index(f->common.chain_index);
+	if (!filter)
+		return -EINVAL;
+
+	err = enetc_streamid_hw_set(priv, &filter->sid, false);
+	if (err)
+		return err;
+
+	remove_one_chain(priv, filter);
+
+	return 0;
+}
+
+static int enetc_destroy_clsflower(struct enetc_ndev_priv *priv,
+				   struct flow_cls_offload *f)
+{
+	return enetc_psfp_destroy_clsflower(priv, f);
+}
+
+static int enetc_psfp_get_stats(struct enetc_ndev_priv *priv,
+				struct flow_cls_offload *f)
+{
+	struct psfp_streamfilter_counters counters = {};
+	struct enetc_stream_filter *filter;
+	struct flow_stats stats = {};
+	int err;
+
+	filter = enetc_get_stream_by_index(f->common.chain_index);
+	if (!filter)
+		return -EINVAL;
+
+	err = enetc_streamcounter_hw_get(priv, filter->sfi_index, &counters);
+	if (err)
+		return -EINVAL;
+
+	spin_lock(&epsfp.psfp_lock);
+	stats.pkts = counters.matching_frames_count - filter->stats.pkts;
+	stats.lastused = filter->stats.lastused;
+	filter->stats.pkts += stats.pkts;
+	spin_unlock(&epsfp.psfp_lock);
+
+	flow_stats_update(&f->stats, 0x0, stats.pkts, stats.lastused,
+			  FLOW_ACTION_HW_STATS_DELAYED);
+
+	return 0;
+}
+
+static int enetc_setup_tc_cls_flower(struct enetc_ndev_priv *priv,
+				     struct flow_cls_offload *cls_flower)
+{
+	switch (cls_flower->command) {
+	case FLOW_CLS_REPLACE:
+		return enetc_config_clsflower(priv, cls_flower);
+	case FLOW_CLS_DESTROY:
+		return enetc_destroy_clsflower(priv, cls_flower);
+	case FLOW_CLS_STATS:
+		return enetc_psfp_get_stats(priv, cls_flower);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static inline void clean_psfp_sfi_bitmap(void)
+{
+	bitmap_free(epsfp.psfp_sfi_bitmap);
+	epsfp.psfp_sfi_bitmap = NULL;
+}
+
+static void clean_stream_list(void)
+{
+	struct enetc_stream_filter *s;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(s, tmp, &epsfp.stream_list, node) {
+		hlist_del(&s->node);
+		kfree(s);
+	}
+}
+
+static void clean_sfi_list(void)
+{
+	struct enetc_psfp_filter *sfi;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(sfi, tmp, &epsfp.psfp_filter_list, node) {
+		hlist_del(&sfi->node);
+		kfree(sfi);
+	}
+}
+
+static void clean_sgi_list(void)
+{
+	struct enetc_psfp_gate *sgi;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(sgi, tmp, &epsfp.psfp_gate_list, node) {
+		hlist_del(&sgi->node);
+		kfree(sgi);
+	}
+}
+
+static void clean_psfp_all(void)
+{
+	/* Disable all list nodes and free all memory */
+	clean_sfi_list();
+	clean_sgi_list();
+	clean_stream_list();
+	epsfp.dev_bitmap = 0;
+	clean_psfp_sfi_bitmap();
+}
+
+int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv)
+{
+	struct net_device *ndev = cb_priv;
+
+	if (!tc_can_offload(ndev))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return enetc_setup_tc_cls_flower(netdev_priv(ndev), type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int enetc_psfp_init(struct enetc_ndev_priv *priv)
+{
+	if (epsfp.psfp_sfi_bitmap)
+		return 0;
+
+	epsfp.psfp_sfi_bitmap = bitmap_zalloc(priv->psfp_cap.max_psfp_filter,
+					      GFP_KERNEL);
+	if (!epsfp.psfp_sfi_bitmap)
+		return -ENOMEM;
+
+	spin_lock_init(&epsfp.psfp_lock);
+
+	if (list_empty(&enetc_block_cb_list))
+		epsfp.dev_bitmap = 0;
+
+	return 0;
+}
+
+int enetc_psfp_clean(struct enetc_ndev_priv *priv)
+{
+	if (!list_empty(&enetc_block_cb_list))
+		return -EBUSY;
+
+	clean_psfp_all();
+
+	return 0;
+}
+
+int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct flow_block_offload *f = type_data;
+	int err;
+
+	err = flow_block_cb_setup_simple(f, &enetc_block_cb_list,
+					 enetc_setup_tc_block_cb,
+					 ndev, ndev, true);
+	if (err)
+		return err;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		set_bit(enetc_get_port(priv), &epsfp.dev_bitmap);
+		break;
+	case FLOW_BLOCK_UNBIND:
+		clear_bit(enetc_get_port(priv), &epsfp.dev_bitmap);
+		if (!epsfp.dev_bitmap)
+			clean_psfp_all();
+		break;
+	}
+
+	return 0;
+}
-- 
cgit v1.2.3


From f166f890c8f026a931e1bb80f51561a1d2f41b27 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 2 May 2020 17:25:04 +0200
Subject: net: ethernet: fec: Replace interrupt driven MDIO with polled IO

Measurements of the MDIO bus have shown that driving the MDIO bus
using interrupts is slow. Back to back MDIO transactions take about
90us, with 25us spent performing the transaction, and the remainder of
the time the bus is idle.

Replacing the completion interrupt with polled IO results in back to
back transactions of 40us. The polling loop waiting for the hardware
to complete the transaction takes around 28us. Which suggests
interrupt handling has an overhead of 50us, and polled IO nearly
halves this overhead, and doubles the MDIO performance.

Care has to be taken when setting the MII_SPEED register, or it can
trigger an MII event> That then upsets the polling, due to an
unexpected pending event.

Suggested-by: Chris Heally <cphealy@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |  4 +-
 drivers/net/ethernet/freescale/fec_main.c | 77 ++++++++++++++++++-------------
 2 files changed, 45 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index e74dd1f86bba..a6cdd5b61921 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -376,8 +376,7 @@ struct bufdesc_ex {
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
 #define FEC_ENET_TS_TIMER       ((uint)0x00008000)
 
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
-#define FEC_NAPI_IMASK	FEC_ENET_MII
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF)
 #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
 
 /* ENET interrupt coalescing macro define */
@@ -543,7 +542,6 @@ struct fec_enet_private {
 	int	link;
 	int	full_duplex;
 	int	speed;
-	struct	completion mdio_done;
 	int	irq[FEC_IRQ_NUM];
 	bool	bufdesc_ex;
 	int	pause_flag;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c7b84bb22f75..2e209142f2d1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -976,8 +976,8 @@ fec_restart(struct net_device *ndev)
 	writel((__force u32)cpu_to_be32(temp_mac[1]),
 	       fep->hwp + FEC_ADDR_HIGH);
 
-	/* Clear any outstanding interrupt. */
-	writel(0xffffffff, fep->hwp + FEC_IEVENT);
+	/* Clear any outstanding interrupt, except MDIO. */
+	writel((0xffffffff & ~FEC_ENET_MII), fep->hwp + FEC_IEVENT);
 
 	fec_enet_bd_init(ndev);
 
@@ -1123,7 +1123,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->link)
 		writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 	else
-		writel(FEC_ENET_MII, fep->hwp + FEC_IMASK);
+		writel(0, fep->hwp + FEC_IMASK);
 
 	/* Init the interrupt coalescing */
 	fec_enet_itr_coal_init(ndev);
@@ -1652,6 +1652,10 @@ fec_enet_interrupt(int irq, void *dev_id)
 	irqreturn_t ret = IRQ_NONE;
 
 	int_events = readl(fep->hwp + FEC_IEVENT);
+
+	/* Don't clear MDIO events, we poll for those */
+	int_events &= ~FEC_ENET_MII;
+
 	writel(int_events, fep->hwp + FEC_IEVENT);
 	fec_enet_collect_events(fep, int_events);
 
@@ -1659,16 +1663,12 @@ fec_enet_interrupt(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 
 		if (napi_schedule_prep(&fep->napi)) {
-			/* Disable the NAPI interrupts */
-			writel(FEC_NAPI_IMASK, fep->hwp + FEC_IMASK);
+			/* Disable interrupts */
+			writel(0, fep->hwp + FEC_IMASK);
 			__napi_schedule(&fep->napi);
 		}
 	}
 
-	if (int_events & FEC_ENET_MII) {
-		ret = IRQ_HANDLED;
-		complete(&fep->mdio_done);
-	}
 	return ret;
 }
 
@@ -1818,11 +1818,24 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 		phy_print_status(phy_dev);
 }
 
+static int fec_enet_mdio_wait(struct fec_enet_private *fep)
+{
+	uint ievent;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(fep->hwp + FEC_IEVENT, ievent,
+					ievent & FEC_ENET_MII, 2, 30000);
+
+	if (!ret)
+		writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
+
+	return ret;
+}
+
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
-	unsigned long time_left;
 	int ret = 0, frame_start, frame_addr, frame_op;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1830,8 +1843,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ret < 0)
 		return ret;
 
-	reinit_completion(&fep->mdio_done);
-
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1843,11 +1854,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		time_left = wait_for_completion_timeout(&fep->mdio_done,
-				usecs_to_jiffies(FEC_MII_TIMEOUT));
-		if (time_left == 0) {
+		ret = fec_enet_mdio_wait(fep);
+		if (ret) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
-			ret = -ETIMEDOUT;
 			goto out;
 		}
 
@@ -1866,11 +1875,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 		FEC_MMFR_TA, fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-	if (time_left == 0) {
+	ret = fec_enet_mdio_wait(fep);
+	if (ret) {
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		ret = -ETIMEDOUT;
 		goto out;
 	}
 
@@ -1888,7 +1895,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 {
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
-	unsigned long time_left;
 	int ret, frame_start, frame_addr;
 	bool is_c45 = !!(regnum & MII_ADDR_C45);
 
@@ -1898,8 +1904,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	else
 		ret = 0;
 
-	reinit_completion(&fep->mdio_done);
-
 	if (is_c45) {
 		frame_start = FEC_MMFR_ST_C45;
 
@@ -1911,11 +1915,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		       fep->hwp + FEC_MII_DATA);
 
 		/* wait for end of transfer */
-		time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-		if (time_left == 0) {
+		ret = fec_enet_mdio_wait(fep);
+		if (ret) {
 			netdev_err(fep->netdev, "MDIO address write timeout\n");
-			ret = -ETIMEDOUT;
 			goto out;
 		}
 	} else {
@@ -1931,12 +1933,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 		fep->hwp + FEC_MII_DATA);
 
 	/* wait for end of transfer */
-	time_left = wait_for_completion_timeout(&fep->mdio_done,
-			usecs_to_jiffies(FEC_MII_TIMEOUT));
-	if (time_left == 0) {
+	ret = fec_enet_mdio_wait(fep);
+	if (ret)
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		ret  = -ETIMEDOUT;
-	}
 
 out:
 	pm_runtime_mark_last_busy(dev);
@@ -2143,8 +2142,21 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	if (suppress_preamble)
 		fep->phy_speed |= BIT(7);
 
+	/* Clear MMFR to avoid to generate MII event by writing MSCR.
+	 * MII event generation condition:
+	 * - writing MSCR:
+	 *	- mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
+	 *	  mscr_reg_data_in[7:0] != 0
+	 * - writing MMFR:
+	 *	- mscr[7:0]_not_zero
+	 */
+	writel(0, fep->hwp + FEC_MII_DATA);
+
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
+	/* Clear any pending transaction complete indication */
+	writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT);
+
 	fep->mii_bus = mdiobus_alloc();
 	if (fep->mii_bus == NULL) {
 		err = -ENOMEM;
@@ -3686,7 +3698,6 @@ fec_probe(struct platform_device *pdev)
 		fep->irq[i] = irq;
 	}
 
-	init_completion(&fep->mdio_done);
 	ret = fec_enet_mii_init(pdev);
 	if (ret)
 		goto failed_mii_init;
-- 
cgit v1.2.3


From 80f8443fcdaa27871a233d08e9142612e6ade77c Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 3 May 2020 09:52:10 +0000
Subject: net: ena: avoid unnecessary admin command when RSS function set fails

Currently when ena_set_hash_function() fails the hash function is
restored to the previous value by calling an admin command to get
the hash function from the device.

In this commit we avoid the admin command, by saving the previous
hash function before calling ena_set_hash_function() and using this
previous value to restore the hash function in case of failure of
ena_set_hash_function().

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index a250046b8e18..424ba08955e9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2286,6 +2286,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 	struct ena_admin_get_feat_resp get_resp;
 	struct ena_admin_feature_rss_flow_hash_control *hash_key =
 		rss->hash_key;
+	enum ena_admin_hash_functions old_func;
 	int rc;
 
 	/* Make sure size is a mult of DWs */
@@ -2325,12 +2326,13 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 		return -EINVAL;
 	}
 
+	old_func = rss->hash_func;
 	rss->hash_func = func;
 	rc = ena_com_set_hash_function(ena_dev);
 
 	/* Restore the old function */
 	if (unlikely(rc))
-		ena_com_get_hash_function(ena_dev, NULL, NULL);
+		rss->hash_func = old_func;
 
 	return rc;
 }
-- 
cgit v1.2.3


From e9a1de378dd46375f9abfd8de1e6f59ee114a793 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 3 May 2020 09:52:11 +0000
Subject: net: ena: fix error returning in ena_com_get_hash_function()

In case the "func" parameter is NULL we now return "-EINVAL".
This shouldn't happen in general, but when it does happen, this is the
proper way to handle it.

We also check func for NULL in the beginning of the function, as there
is no reason to do all the work and realize in the end of the function
it was useless.

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 424ba08955e9..66edc86c41c9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2347,6 +2347,9 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 		rss->hash_key;
 	int rc;
 
+	if (unlikely(!func))
+		return -EINVAL;
+
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_FUNCTION,
 				    rss->hash_key_dma_addr,
@@ -2359,8 +2362,7 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 	if (rss->hash_func)
 		rss->hash_func--;
 
-	if (func)
-		*func = rss->hash_func;
+	*func = rss->hash_func;
 
 	if (key)
 		memcpy(key, hash_key->key, (size_t)(hash_key->keys_num) << 2);
-- 
cgit v1.2.3


From f66c2ea3b18a8cc8e45ff32c636aaefb2ac06315 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:12 +0000
Subject: net: ena: allow setting the hash function without changing the key

Current code does not allow setting the hash function without
changing the key. This commit enables it.

To achieve this we separate ena_com_get_hash_function() to 2 functions:
ena_com_get_hash_function() - which gets only the hash function, and
ena_com_get_hash_key() - which gets only the hash key.

Also return 0 instead of rc at the end of ena_get_rxfh() since all
previous operations succeeded.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c     | 13 +++++++++----
 drivers/net/ethernet/amazon/ena/ena_com.h     | 21 +++++++++++++++------
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 12 ++++++++----
 3 files changed, 32 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 66edc86c41c9..d428d0606166 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2338,13 +2338,10 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 }
 
 int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
-			      enum ena_admin_hash_functions *func,
-			      u8 *key)
+			      enum ena_admin_hash_functions *func)
 {
 	struct ena_rss *rss = &ena_dev->rss;
 	struct ena_admin_get_feat_resp get_resp;
-	struct ena_admin_feature_rss_flow_hash_control *hash_key =
-		rss->hash_key;
 	int rc;
 
 	if (unlikely(!func))
@@ -2364,6 +2361,14 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 
 	*func = rss->hash_func;
 
+	return 0;
+}
+
+int ena_com_get_hash_key(struct ena_com_dev *ena_dev, u8 *key)
+{
+	struct ena_admin_feature_rss_flow_hash_control *hash_key =
+		ena_dev->rss.hash_key;
+
 	if (key)
 		memcpy(key, hash_key->key, (size_t)(hash_key->keys_num) << 2);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 469f298199a7..e2e2fd1dc820 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -695,13 +695,11 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
  */
 int ena_com_set_hash_function(struct ena_com_dev *ena_dev);
 
-/* ena_com_get_hash_function - Retrieve the hash function and the hash key
- * from the device.
+/* ena_com_get_hash_function - Retrieve the hash function from the device.
  * @ena_dev: ENA communication layer struct
  * @func: hash function
- * @key: hash key
  *
- * Retrieve the hash function and the hash key from the device.
+ * Retrieve the hash function from the device.
  *
  * @note: If the caller called ena_com_fill_hash_function but didn't flash
  * it to the device, the new configuration will be lost.
@@ -709,9 +707,20 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev);
  * @return: 0 on Success and negative value otherwise.
  */
 int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
-			      enum ena_admin_hash_functions *func,
-			      u8 *key);
+			      enum ena_admin_hash_functions *func);
 
+/* ena_com_get_hash_key - Retrieve the hash key
+ * @ena_dev: ENA communication layer struct
+ * @key: hash key
+ *
+ * Retrieve the hash key.
+ *
+ * @note: If the caller called ena_com_fill_hash_key but didn't flash
+ * it to the device, the new configuration will be lost.
+ *
+ * @return: 0 on Success and negative value otherwise.
+ */
+int ena_com_get_hash_key(struct ena_com_dev *ena_dev, u8 *key);
 /* ena_com_fill_hash_ctrl - Fill RSS hash control
  * @ena_dev: ENA communication layer struct.
  * @proto: The protocol to configure.
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 9cc28b4b2627..0c3a2f14387e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -672,7 +672,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	/* We call this function in order to check if the device
 	 * supports getting/setting the hash function.
 	 */
-	rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key);
+	rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func);
 	if (rc) {
 		if (rc == -EOPNOTSUPP) {
 			key = NULL;
@@ -683,6 +683,10 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		return rc;
 	}
 
+	rc = ena_com_get_hash_key(adapter->ena_dev, key);
+	if (rc)
+		return rc;
+
 	switch (ena_func) {
 	case ENA_ADMIN_TOEPLITZ:
 		func = ETH_RSS_HASH_TOP;
@@ -699,7 +703,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (hfunc)
 		*hfunc = func;
 
-	return rc;
+	return 0;
 }
 
 static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
@@ -707,7 +711,7 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
-	enum ena_admin_hash_functions func;
+	enum ena_admin_hash_functions func = 0;
 	int rc, i;
 
 	if (indir) {
@@ -746,7 +750,7 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 		return -EOPNOTSUPP;
 	}
 
-	if (key) {
+	if (key || func) {
 		rc = ena_com_fill_hash_function(ena_dev, func, key,
 						ENA_HASH_KEY_SIZE,
 						0xFFFFFFFF);
-- 
cgit v1.2.3


From c1bd17e51c71dc8214fbccc2b5abea4d31ac65e6 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 3 May 2020 09:52:13 +0000
Subject: net: ena: change default RSS hash function to Toeplitz

Currently in the driver we are setting the hash function to be CRC32.
Starting with this commit we want to change the default behaviour so that
we set the hash function to be Toeplitz instead.

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 2cc765df8da3..6baafc3aebea 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3991,7 +3991,7 @@ static int ena_rss_init_default(struct ena_adapter *adapter)
 		}
 	}
 
-	rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_CRC32, NULL,
+	rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_TOEPLITZ, NULL,
 					ENA_HASH_KEY_SIZE, 0xFFFFFFFF);
 	if (unlikely(rc && (rc != -EOPNOTSUPP))) {
 		dev_err(dev, "Cannot fill hash function\n");
-- 
cgit v1.2.3


From 0af3c4e2eab8aa5a904287534e442add36023273 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:14 +0000
Subject: net: ena: changes to RSS hash key allocation

This commit contains 2 cosmetic changes:

1. Use ena_com_check_supported_feature_id() in
   ena_com_hash_key_fill_default_key() instead of rewriting
   its implementation. This also saves us a superfluous admin
   command by using the cached value.

2. Change if conditions in ena_com_rss_init() to be clearer.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index d428d0606166..b51bf62af11b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -1067,16 +1067,10 @@ static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev)
 static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev)
 {
 	struct ena_rss *rss = &ena_dev->rss;
-	struct ena_admin_get_feat_resp get_resp;
-	int rc;
 
-	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
-				    ENA_ADMIN_RSS_HASH_FUNCTION,
-				    ena_dev->rss.hash_key_dma_addr,
-				    sizeof(ena_dev->rss.hash_key), 0);
-	if (unlikely(rc)) {
+	if (!ena_com_check_supported_feature_id(ena_dev,
+						ENA_ADMIN_RSS_HASH_FUNCTION))
 		return -EOPNOTSUPP;
-	}
 
 	rss->hash_key =
 		dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key),
@@ -2650,10 +2644,10 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 indr_tbl_log_size)
 	 * ignore this error and have indirection table support only.
 	 */
 	rc = ena_com_hash_key_allocate(ena_dev);
-	if (unlikely(rc) && rc != -EOPNOTSUPP)
-		goto err_hash_key;
-	else if (rc != -EOPNOTSUPP)
+	if (likely(!rc))
 		ena_com_hash_key_fill_default_key(ena_dev);
+	else if (rc != -EOPNOTSUPP)
+		goto err_hash_key;
 
 	rc = ena_com_hash_ctrl_init(ena_dev);
 	if (unlikely(rc))
-- 
cgit v1.2.3


From cac7172f2d33ae75601d1bc928532d3ef7513db9 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:15 +0000
Subject: net: ena: remove code that does nothing

Both key and func parameters are pointers on the stack.
Setting them to NULL does nothing.
The original intent was to leave the key and func unset in this case,
but for this to happen nothing needs to be done as the calling
function ethtool_get_rxfh() already clears key and func.

This commit removes the above described useless code.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 0c3a2f14387e..c7df25f92dbd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -674,11 +674,8 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	 */
 	rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func);
 	if (rc) {
-		if (rc == -EOPNOTSUPP) {
-			key = NULL;
-			hfunc = NULL;
+		if (rc == -EOPNOTSUPP)
 			rc = 0;
-		}
 
 		return rc;
 	}
-- 
cgit v1.2.3


From d4a8b3bb0bb7e63d391b8e442681b72ab1429471 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:16 +0000
Subject: net: ena: add unmask interrupts statistics to ethtool

Add unmask interrupts statistics to ethtool.

Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 1 +
 drivers/net/ethernet/amazon/ena/ena_netdev.c  | 3 +++
 drivers/net/ethernet/amazon/ena/ena_netdev.h  | 1 +
 3 files changed, 5 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index c7df25f92dbd..74725d606964 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -83,6 +83,7 @@ static const struct ena_stats ena_stats_tx_strings[] = {
 	ENA_STAT_TX_ENTRY(bad_req_id),
 	ENA_STAT_TX_ENTRY(llq_buffer_copy),
 	ENA_STAT_TX_ENTRY(missed_tx),
+	ENA_STAT_TX_ENTRY(unmask_interrupt),
 };
 
 static const struct ena_stats ena_stats_rx_strings[] = {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6baafc3aebea..3cea4c9090c2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1762,6 +1762,9 @@ static void ena_unmask_interrupt(struct ena_ring *tx_ring,
 				tx_ring->smoothed_interval,
 				true);
 
+	u64_stats_update_begin(&tx_ring->syncp);
+	tx_ring->tx_stats.unmask_interrupt++;
+	u64_stats_update_end(&tx_ring->syncp);
 	/* It is a shared MSI-X.
 	 * Tx and Rx CQ have pointer to it.
 	 * So we use one of them to reach the intr reg
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 97dfd0c67e84..ebeb911c0efb 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -248,6 +248,7 @@ struct ena_stats_tx {
 	u64 bad_req_id;
 	u64 llq_buffer_copy;
 	u64 missed_tx;
+	u64 unmask_interrupt;
 };
 
 struct ena_stats_rx {
-- 
cgit v1.2.3


From 5c665f8c596ded2d8b876bac024409856117f40e Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:17 +0000
Subject: net: ena: add support for reporting of packet drops

1. Add support for getting tx drops from the device and saving them
in the driver.
2. Report tx via netdev stats.

Signed-off-by: Igor Chauskin <igorch@amazon.com>
Signed-off-by: Guy Tzalik <gtzalik@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_admin_defs.h | 8 ++++++++
 drivers/net/ethernet/amazon/ena/ena_netdev.c     | 6 ++++++
 drivers/net/ethernet/amazon/ena/ena_netdev.h     | 1 +
 3 files changed, 15 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 8baf847e8622..7be3dcbf3d16 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -404,6 +404,10 @@ struct ena_admin_basic_stats {
 	u32 rx_drops_low;
 
 	u32 rx_drops_high;
+
+	u32 tx_drops_low;
+
+	u32 tx_drops_high;
 };
 
 struct ena_admin_acq_get_stats_resp {
@@ -1017,6 +1021,10 @@ struct ena_admin_aenq_keep_alive_desc {
 	u32 rx_drops_low;
 
 	u32 rx_drops_high;
+
+	u32 tx_drops_low;
+
+	u32 tx_drops_high;
 };
 
 struct ena_admin_ena_mmio_req_read_less_resp {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 3cea4c9090c2..517681319a57 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3172,6 +3172,7 @@ static void ena_get_stats64(struct net_device *netdev,
 	struct ena_ring *rx_ring, *tx_ring;
 	unsigned int start;
 	u64 rx_drops;
+	u64 tx_drops;
 	int i;
 
 	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
@@ -3206,9 +3207,11 @@ static void ena_get_stats64(struct net_device *netdev,
 	do {
 		start = u64_stats_fetch_begin_irq(&adapter->syncp);
 		rx_drops = adapter->dev_stats.rx_drops;
+		tx_drops = adapter->dev_stats.tx_drops;
 	} while (u64_stats_fetch_retry_irq(&adapter->syncp, start));
 
 	stats->rx_dropped = rx_drops;
+	stats->tx_dropped = tx_drops;
 
 	stats->multicast = 0;
 	stats->collisions = 0;
@@ -4517,14 +4520,17 @@ static void ena_keep_alive_wd(void *adapter_data,
 	struct ena_adapter *adapter = (struct ena_adapter *)adapter_data;
 	struct ena_admin_aenq_keep_alive_desc *desc;
 	u64 rx_drops;
+	u64 tx_drops;
 
 	desc = (struct ena_admin_aenq_keep_alive_desc *)aenq_e;
 	adapter->last_keep_alive_jiffies = jiffies;
 
 	rx_drops = ((u64)desc->rx_drops_high << 32) | desc->rx_drops_low;
+	tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low;
 
 	u64_stats_update_begin(&adapter->syncp);
 	adapter->dev_stats.rx_drops = rx_drops;
+	adapter->dev_stats.tx_drops = tx_drops;
 	u64_stats_update_end(&adapter->syncp);
 }
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index ebeb911c0efb..bd278c4721c6 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -334,6 +334,7 @@ struct ena_stats_dev {
 	u64 interface_down;
 	u64 admin_q_pause;
 	u64 rx_drops;
+	u64 tx_drops;
 };
 
 enum ena_flags_t {
-- 
cgit v1.2.3


From f5db045e76fa74bdc95f9736429a565260a5d890 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 3 May 2020 09:52:18 +0000
Subject: net: ena: drop superfluous prototype

Before this commit there was a function prototype named
ena_com_get_ena_admin_polling_mode() that was never implemented.

This patch simply deletes it.

Signed-off-by: Igor Chauskin <igorch@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index e2e2fd1dc820..a55379471f98 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -501,18 +501,6 @@ bool ena_com_get_admin_running_state(struct ena_com_dev *ena_dev);
  */
 void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling);
 
-/* ena_com_set_admin_polling_mode - Get the admin completion queue polling mode
- * @ena_dev: ENA communication layer struct
- *
- * Get the admin completion mode.
- * If polling mode is on, ena_com_execute_admin_command will perform a
- * polling on the admin completion queue for the commands completion,
- * otherwise it will wait on wait event.
- *
- * @return state
- */
-bool ena_com_get_ena_admin_polling_mode(struct ena_com_dev *ena_dev);
-
 /* ena_com_set_admin_auto_polling_mode - Enable autoswitch to polling mode
  * @ena_dev: ENA communication layer struct
  * @polling: Enable/Disable polling mode
-- 
cgit v1.2.3


From c1c0e40b367efc92ad05bb802180817534a32343 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:19 +0000
Subject: net: ena: use SHUTDOWN as reset reason when closing interface

The 'ENA_REGS_RESET_SHUTDOWN' enum indicates a normal driver
shutdown / removal procedure.

Also, a comment is added to one of the reset reason assignments for
code clarity.

Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 517681319a57..2818965427e9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3439,6 +3439,7 @@ static void ena_destroy_device(struct ena_adapter *adapter, bool graceful)
 
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
 
+	/* return reset reason to default value */
 	adapter->reset_reason = ENA_REGS_RESET_NORMAL;
 
 	clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
@@ -4362,6 +4363,7 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
+	adapter->reset_reason = ENA_REGS_RESET_SHUTDOWN;
 	ena_destroy_device(adapter, true);
 	if (shutdown) {
 		netif_device_detach(netdev);
-- 
cgit v1.2.3


From dcc2789a11f9bbe27dc79f85f426c22def3e921c Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Sun, 3 May 2020 09:52:20 +0000
Subject: net: ena: cosmetic: remove unnecessary spaces and tabs in ena_com.h
 macros

The macros in ena_com.h have inconsistent spaces between
the macro name and it's value.

This commit sets all the macros to have a single space between
the name and value.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index a55379471f98..13a1b7812c46 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -54,9 +54,9 @@
 #undef pr_fmt
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#define ENA_MAX_NUM_IO_QUEUES		128U
+#define ENA_MAX_NUM_IO_QUEUES 128U
 /* We need to queues for each IO (on for Tx and one for Rx) */
-#define ENA_TOTAL_NUM_QUEUES		(2 * (ENA_MAX_NUM_IO_QUEUES))
+#define ENA_TOTAL_NUM_QUEUES (2 * (ENA_MAX_NUM_IO_QUEUES))
 
 #define ENA_MAX_HANDLERS 256
 
@@ -73,13 +73,13 @@
 /*****************************************************************************/
 /* ENA adaptive interrupt moderation settings */
 
-#define ENA_INTR_INITIAL_TX_INTERVAL_USECS		64
-#define ENA_INTR_INITIAL_RX_INTERVAL_USECS		0
-#define ENA_DEFAULT_INTR_DELAY_RESOLUTION		1
+#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 64
+#define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0
+#define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1
 
-#define ENA_HW_HINTS_NO_TIMEOUT				0xFFFF
+#define ENA_HW_HINTS_NO_TIMEOUT	0xFFFF
 
-#define ENA_FEATURE_MAX_QUEUE_EXT_VER	1
+#define ENA_FEATURE_MAX_QUEUE_EXT_VER 1
 
 struct ena_llq_configurations {
 	enum ena_admin_llq_header_location llq_header_location;
-- 
cgit v1.2.3


From 77a651f5647da15b215e3523acce852dad453b6c Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 3 May 2020 09:52:21 +0000
Subject: net: ena: cosmetic: extract code to ena_indirection_table_set()

Extract code to ena_indirection_table_set() to make
the code cleaner.

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 48 +++++++++++++++++----------
 1 file changed, 30 insertions(+), 18 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 74725d606964..830d3711d6ee 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -636,6 +636,32 @@ static u32 ena_get_rxfh_key_size(struct net_device *netdev)
 	return ENA_HASH_KEY_SIZE;
 }
 
+static int ena_indirection_table_set(struct ena_adapter *adapter,
+				     const u32 *indir)
+{
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
+	int i, rc;
+
+	for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) {
+		rc = ena_com_indirect_table_fill_entry(ena_dev,
+						       i,
+						       ENA_IO_RXQ_IDX(indir[i]));
+		if (unlikely(rc)) {
+			netif_err(adapter, drv, adapter->netdev,
+				  "Cannot fill indirect table (index is too large)\n");
+			return rc;
+		}
+	}
+
+	rc = ena_com_indirect_table_set(ena_dev);
+	if (rc) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Cannot set indirect table\n");
+		return rc == -EPERM ? -EOPNOTSUPP : rc;
+	}
+	return rc;
+}
+
 static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir)
 {
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
@@ -710,26 +736,12 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	enum ena_admin_hash_functions func = 0;
-	int rc, i;
+	int rc;
 
 	if (indir) {
-		for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) {
-			rc = ena_com_indirect_table_fill_entry(ena_dev,
-							       i,
-							       ENA_IO_RXQ_IDX(indir[i]));
-			if (unlikely(rc)) {
-				netif_err(adapter, drv, netdev,
-					  "Cannot fill indirect table (index is too large)\n");
-				return rc;
-			}
-		}
-
-		rc = ena_com_indirect_table_set(ena_dev);
-		if (rc) {
-			netif_err(adapter, drv, netdev,
-				  "Cannot set indirect table\n");
-			return rc == -EPERM ? -EOPNOTSUPP : rc;
-		}
+		rc = ena_indirection_table_set(adapter, indir);
+		if (rc)
+			return rc;
 	}
 
 	switch (hfunc) {
-- 
cgit v1.2.3


From 460c2577aaf349f4e49eaf2b9ec3d8c52a619ef5 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:27 -0400
Subject: bnxt_en: Update firmware spec. to 1.10.1.33.

Changes include additional statistics, ECN support, context memory
interface change for better TQM context memory sizing, firmware
health status definitions, etc.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 216 ++++++++++++++++++++++----
 1 file changed, 184 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 7cf27dffadb5..7e9235c8d21e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -2,7 +2,7 @@
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
  * Copyright (c) 2014-2018 Broadcom Limited
- * Copyright (c) 2018-2019 Broadcom Inc.
+ * Copyright (c) 2018-2020 Broadcom Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -207,6 +207,8 @@ struct cmd_nums {
 	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
 	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
 	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
+	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
+	#define HWRM_PORT_ECN_QSTATS                      0xbaUL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
 	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
@@ -220,6 +222,8 @@ struct cmd_nums {
 	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
 	#define HWRM_FW_GET_STRUCTURED_DATA               0xcbUL
 	#define HWRM_FW_IPC_MAILBOX                       0xccUL
+	#define HWRM_FW_ECN_CFG                           0xcdUL
+	#define HWRM_FW_ECN_QCFG                          0xceUL
 	#define HWRM_EXEC_FWD_RESP                        0xd0UL
 	#define HWRM_REJECT_FWD_RESP                      0xd1UL
 	#define HWRM_FWD_RESP                             0xd2UL
@@ -233,6 +237,7 @@ struct cmd_nums {
 	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
 	#define HWRM_REG_POWER_QUERY                      0xe1UL
 	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
+	#define HWRM_REG_POWER_HISTOGRAM                  0xe3UL
 	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
 	#define HWRM_WOL_FILTER_FREE                      0xf1UL
 	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
@@ -331,6 +336,7 @@ struct cmd_nums {
 	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
 	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
 	#define HWRM_FUNC_HOST_PF_IDS_QUERY               0x197UL
+	#define HWRM_FUNC_QSTATS_EXT                      0x198UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -341,6 +347,31 @@ struct cmd_nums {
 	#define HWRM_MFG_OTP_CFG                          0x207UL
 	#define HWRM_MFG_OTP_QCFG                         0x208UL
 	#define HWRM_MFG_HDMA_TEST                        0x209UL
+	#define HWRM_MFG_FRU_EEPROM_WRITE                 0x20aUL
+	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
+	#define HWRM_TF                                   0x2bcUL
+	#define HWRM_TF_VERSION_GET                       0x2bdUL
+	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
+	#define HWRM_TF_SESSION_ATTACH                    0x2c7UL
+	#define HWRM_TF_SESSION_CLOSE                     0x2c8UL
+	#define HWRM_TF_SESSION_QCFG                      0x2c9UL
+	#define HWRM_TF_SESSION_RESC_QCAPS                0x2caUL
+	#define HWRM_TF_SESSION_RESC_ALLOC                0x2cbUL
+	#define HWRM_TF_SESSION_RESC_FREE                 0x2ccUL
+	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cdUL
+	#define HWRM_TF_TBL_TYPE_GET                      0x2d0UL
+	#define HWRM_TF_TBL_TYPE_SET                      0x2d1UL
+	#define HWRM_TF_CTXT_MEM_RGTR                     0x2daUL
+	#define HWRM_TF_CTXT_MEM_UNRGTR                   0x2dbUL
+	#define HWRM_TF_EXT_EM_QCAPS                      0x2dcUL
+	#define HWRM_TF_EXT_EM_OP                         0x2ddUL
+	#define HWRM_TF_EXT_EM_CFG                        0x2deUL
+	#define HWRM_TF_EXT_EM_QCFG                       0x2dfUL
+	#define HWRM_TF_TCAM_SET                          0x2eeUL
+	#define HWRM_TF_TCAM_GET                          0x2efUL
+	#define HWRM_TF_TCAM_MOVE                         0x2f0UL
+	#define HWRM_TF_TCAM_FREE                         0x2f1UL
+	#define HWRM_SV                                   0x400UL
 	#define HWRM_DBG_READ_DIRECT                      0xff10UL
 	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
 	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
@@ -356,6 +387,10 @@ struct cmd_nums {
 	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
 	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
 	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
+	#define HWRM_DBG_DRV_TRACE                        0xff1fUL
+	#define HWRM_DBG_QCAPS                            0xff20UL
+	#define HWRM_DBG_QCFG                             0xff21UL
+	#define HWRM_DBG_CRASHDUMP_MEDIUM_CFG             0xff22UL
 	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
 	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
 	#define HWRM_NVM_FLUSH                            0xfff0UL
@@ -429,8 +464,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 1
-#define HWRM_VERSION_RSVD 12
-#define HWRM_VERSION_STR "1.10.1.12"
+#define HWRM_VERSION_RSVD 33
+#define HWRM_VERSION_STR "1.10.1.33"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -482,6 +517,7 @@ struct hwrm_ver_get_output {
 	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED                    0x4000UL
 	u8	roce_fw_maj_8b;
 	u8	roce_fw_min_8b;
 	u8	roce_fw_bld_8b;
@@ -647,6 +683,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE   0x3eUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_QUIESCE_DONE               0x3fUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE          0x40UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE    0x41UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG               0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
@@ -1089,7 +1126,7 @@ struct hwrm_func_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcaps_output (size:640b/80B) */
+/* hwrm_func_qcaps_output (size:704b/88B) */
 struct hwrm_func_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1126,6 +1163,10 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD                    0x2000000UL
 	#define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED     0x4000000UL
 	#define FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED         0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_COREDUMP_CMD_SUPPORTED                0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_CRASHDUMP_CMD_SUPPORTED               0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PFC_WD_STATS_SUPPORTED                0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED               0x80000000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -1146,7 +1187,12 @@ struct hwrm_func_qcaps_output {
 	__le32	max_flow_id;
 	__le32	max_hw_ring_grps;
 	__le16	max_sp_tx_rings;
-	u8	unused_0;
+	u8	unused_0[2];
+	__le32	flags_ext;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED         0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED        0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED     0x4UL
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -1161,7 +1207,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:704b/88B) */
+/* hwrm_func_qcfg_output (size:768b/96B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1267,7 +1313,11 @@ struct hwrm_func_qcfg_output {
 	u8	always_1;
 	__le32	reset_addr_poll;
 	__le16	legacy_l2_db_size_kb;
-	u8	unused_2[1];
+	__le16	svif_info;
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
+	u8	unused_2[7];
 	u8	valid;
 };
 
@@ -1420,9 +1470,10 @@ struct hwrm_func_qstats_input {
 	__le64	resp_addr;
 	__le16	fid;
 	u8	flags;
-	#define FUNC_QSTATS_REQ_FLAGS_UNUSED    0x0UL
-	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY 0x1UL
-	#define FUNC_QSTATS_REQ_FLAGS_LAST     FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY
+	#define FUNC_QSTATS_REQ_FLAGS_UNUSED       0x0UL
+	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY    0x1UL
+	#define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK 0x2UL
+	#define FUNC_QSTATS_REQ_FLAGS_LAST        FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK
 	u8	unused_0[5];
 };
 
@@ -1456,6 +1507,53 @@ struct hwrm_func_qstats_output {
 	u8	valid;
 };
 
+/* hwrm_func_qstats_ext_input (size:192b/24B) */
+struct hwrm_func_qstats_ext_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	flags;
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_UNUSED       0x0UL
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY    0x1UL
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x2UL
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_LAST        FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK
+	u8	unused_0[5];
+};
+
+/* hwrm_func_qstats_ext_output (size:1472b/184B) */
+struct hwrm_func_qstats_ext_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_drop_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_drop_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_func_clr_stats_input (size:192b/24B) */
 struct hwrm_func_clr_stats_input {
 	__le16	req_type;
@@ -1808,7 +1906,7 @@ struct hwrm_func_backing_store_qcaps_output {
 	u8	ctx_kind_initializer;
 	__le32	rsvd;
 	__le16	rsvd1;
-	u8	rsvd2;
+	u8	tqm_fp_rings_count;
 	u8	valid;
 };
 
@@ -2231,7 +2329,17 @@ struct hwrm_error_recovery_qcfg_output {
 	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
 	__le32	reset_reg_val[16];
 	u8	delay_after_reset[16];
-	u8	unused_1[7];
+	__le32	err_recovery_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SFT           2
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -2934,7 +3042,11 @@ struct hwrm_port_qstats_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	port_id;
-	u8	unused_0[6];
+	u8	flags;
+	#define PORT_QSTATS_REQ_FLAGS_UNUSED       0x0UL
+	#define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL
+	#define PORT_QSTATS_REQ_FLAGS_LAST        PORT_QSTATS_REQ_FLAGS_COUNTER_MASK
+	u8	unused_0[5];
 	__le64	tx_stat_host_addr;
 	__le64	rx_stat_host_addr;
 };
@@ -3058,7 +3170,11 @@ struct hwrm_port_qstats_ext_input {
 	__le16	port_id;
 	__le16	tx_stat_size;
 	__le16	rx_stat_size;
-	u8	unused_0[2];
+	u8	flags;
+	#define PORT_QSTATS_EXT_REQ_FLAGS_UNUSED       0x0UL
+	#define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK 0x1UL
+	#define PORT_QSTATS_EXT_REQ_FLAGS_LAST        PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK
+	u8	unused_0;
 	__le64	tx_stat_host_addr;
 	__le64	rx_stat_host_addr;
 };
@@ -3840,14 +3956,22 @@ struct hwrm_queue_pfcenable_qcfg_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le32	flags;
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED     0x1UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED     0x2UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED     0x4UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED     0x8UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED     0x10UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED     0x20UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED     0x40UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED     0x80UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -3860,14 +3984,22 @@ struct hwrm_queue_pfcenable_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	flags;
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED     0x1UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED     0x2UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED     0x4UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED     0x8UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED     0x10UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED     0x20UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED     0x40UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED     0x80UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
 	__le16	port_id;
 	u8	unused_0[2];
 };
@@ -5287,7 +5419,11 @@ struct hwrm_ring_cmpl_ring_qaggint_params_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	ring_id;
-	u8	unused_0[6];
+	__le16	flags;
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_MASK 0x3UL
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_SFT 0
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_IS_NQ        0x4UL
+	u8	unused_0[4];
 };
 
 /* hwrm_ring_cmpl_ring_qaggint_params_output (size:256b/32B) */
@@ -7618,7 +7754,9 @@ struct hwrm_nvm_modify_input {
 	__le64	resp_addr;
 	__le64	host_src_addr;
 	__le16	dir_idx;
-	u8	unused_0[2];
+	__le16	flags;
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_MODE     0x1UL
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_LAST     0x2UL
 	__le32	offset;
 	__le32	len;
 	u8	unused_1[4];
@@ -8027,4 +8165,18 @@ struct hwrm_selftest_irq_output {
 	u8	valid;
 };
 
+/* fw_status_reg (size:32b/4B) */
+struct fw_status_reg {
+	u32	fw_status;
+	#define FW_STATUS_REG_CODE_MASK              0xffffUL
+	#define FW_STATUS_REG_CODE_SFT               0
+	#define FW_STATUS_REG_CODE_READY               0x8000UL
+	#define FW_STATUS_REG_CODE_LAST               FW_STATUS_REG_CODE_READY
+	#define FW_STATUS_REG_IMAGE_DEGRADED         0x10000UL
+	#define FW_STATUS_REG_RECOVERABLE            0x20000UL
+	#define FW_STATUS_REG_CRASHDUMP_ONGOING      0x40000UL
+	#define FW_STATUS_REG_CRASHDUMP_COMPLETE     0x80000UL
+	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
+};
+
 #endif /* _BNXT_HSI_H_ */
-- 
cgit v1.2.3


From ac3158cb01084aa654222f1ad970b6c1af3cef98 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:28 -0400
Subject: bnxt_en: Allocate TQM ring context memory according to fw
 specification.

Newer firmware spec. will specify the number of TQM rings to allocate
context memory for.  Use the firmware specified value and fall back
to the old value derived from bp->max_q if it is not available.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 30 +++++++++++++++++-------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fead64f1ad90..32a208397b68 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6434,23 +6434,13 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 	if (!rc) {
 		struct bnxt_ctx_pg_info *ctx_pg;
 		struct bnxt_ctx_mem_info *ctx;
-		int i;
+		int i, tqm_rings;
 
 		ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 		if (!ctx) {
 			rc = -ENOMEM;
 			goto ctx_err;
 		}
-		ctx_pg = kzalloc(sizeof(*ctx_pg) * (bp->max_q + 1), GFP_KERNEL);
-		if (!ctx_pg) {
-			kfree(ctx);
-			rc = -ENOMEM;
-			goto ctx_err;
-		}
-		for (i = 0; i < bp->max_q + 1; i++, ctx_pg++)
-			ctx->tqm_mem[i] = ctx_pg;
-
-		bp->ctx = ctx;
 		ctx->qp_max_entries = le32_to_cpu(resp->qp_max_entries);
 		ctx->qp_min_qp1_entries = le16_to_cpu(resp->qp_min_qp1_entries);
 		ctx->qp_max_l2_entries = le16_to_cpu(resp->qp_max_l2_entries);
@@ -6483,6 +6473,20 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 		ctx->tim_entry_size = le16_to_cpu(resp->tim_entry_size);
 		ctx->tim_max_entries = le32_to_cpu(resp->tim_max_entries);
 		ctx->ctx_kind_initializer = resp->ctx_kind_initializer;
+		ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count;
+		if (!ctx->tqm_fp_rings_count)
+			ctx->tqm_fp_rings_count = bp->max_q;
+
+		tqm_rings = ctx->tqm_fp_rings_count + 1;
+		ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL);
+		if (!ctx_pg) {
+			kfree(ctx);
+			rc = -ENOMEM;
+			goto ctx_err;
+		}
+		for (i = 0; i < tqm_rings; i++, ctx_pg++)
+			ctx->tqm_mem[i] = ctx_pg;
+		bp->ctx = ctx;
 	} else {
 		rc = 0;
 	}
@@ -6735,7 +6739,7 @@ static void bnxt_free_ctx_mem(struct bnxt *bp)
 		return;
 
 	if (ctx->tqm_mem[0]) {
-		for (i = 0; i < bp->max_q + 1; i++)
+		for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++)
 			bnxt_free_ctx_pg_tbls(bp, ctx->tqm_mem[i]);
 		kfree(ctx->tqm_mem[0]);
 		ctx->tqm_mem[0] = NULL;
@@ -6849,7 +6853,7 @@ skip_rdma:
 	entries = roundup(entries, ctx->tqm_entries_multiple);
 	entries = clamp_t(u32, entries, ctx->tqm_min_entries_per_ring,
 			  ctx->tqm_max_entries_per_ring);
-	for (i = 0; i < bp->max_q + 1; i++) {
+	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
 		ctx_pg = ctx->tqm_mem[i];
 		ctx_pg->entries = entries;
 		mem_size = ctx->tqm_entry_size * entries;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f2caa2756f5b..1dbc3aece7a6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1357,6 +1357,7 @@ struct bnxt_ctx_mem_info {
 	u16	mrav_num_entries_units;
 	u8	tqm_entries_multiple;
 	u8	ctx_kind_initializer;
+	u8	tqm_fp_rings_count;
 
 	u32	flags;
 	#define BNXT_CTX_FLAG_INITED	0x01
-- 
cgit v1.2.3


From c7dd7ab4b204ac0142e0d05e71e05e71ae6cb270 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:29 -0400
Subject: bnxt_en: Improve TQM ring context memory sizing formulas.

The current formulas to calculate the TQM slow path and fast path ring
context memory sizes are not quite correct.  TQM slow path entry is
array index 0 of ctx->tqm_mem[].  The other array entries are for fast
path.  Fix these sizes according to latest firmware spec. for 57500 and
newer chips.

Fixes: 3be8136ce14e ("bnxt_en: Initialize context memory to the value specified by firmware.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 32a208397b68..0cf41a167204 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6760,6 +6760,7 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	struct bnxt_ctx_pg_info *ctx_pg;
 	struct bnxt_ctx_mem_info *ctx;
 	u32 mem_size, ena, entries;
+	u32 entries_sp, min;
 	u32 num_mr, num_ah;
 	u32 extra_srqs = 0;
 	u32 extra_qps = 0;
@@ -6849,14 +6850,17 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
 
 skip_rdma:
-	entries = ctx->qp_max_l2_entries + extra_qps;
+	min = ctx->tqm_min_entries_per_ring;
+	entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries +
+		     2 * (extra_qps + ctx->qp_min_qp1_entries) + min;
+	entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple);
+	entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries;
 	entries = roundup(entries, ctx->tqm_entries_multiple);
-	entries = clamp_t(u32, entries, ctx->tqm_min_entries_per_ring,
-			  ctx->tqm_max_entries_per_ring);
+	entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring);
 	for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) {
 		ctx_pg = ctx->tqm_mem[i];
-		ctx_pg->entries = entries;
-		mem_size = ctx->tqm_entry_size * entries;
+		ctx_pg->entries = i ? entries : entries_sp;
+		mem_size = ctx->tqm_entry_size * ctx_pg->entries;
 		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1, false);
 		if (rc)
 			return rc;
-- 
cgit v1.2.3


From d0b82c5461c9b9bfcb572fe0b50d8e2662e281f1 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Mon, 4 May 2020 04:50:30 -0400
Subject: bnxt_en: Do not include ETH_FCS_LEN in the max packet length sent to
 fw.

The firmware does not expect the CRC to be included in the length
passed from the driver.  The firmware always configures the chip
to strip out the CRC.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 3 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0cf41a167204..5919f729e8a2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5045,8 +5045,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	req.dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
 	req.lb_rule = cpu_to_le16(0xffff);
 vnic_mru:
-	req.mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + ETH_FCS_LEN +
-			      VLAN_HLEN);
+	req.mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN);
 
 	req.vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 #ifdef CONFIG_BNXT_SRIOV
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 6ea3df6da18c..c883e8884faf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -651,7 +651,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 				  FUNC_CFG_REQ_ENABLES_NUM_VNICS |
 				  FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS);
 
-	mtu = bp->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	mtu = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 	req.mru = cpu_to_le16(mtu);
 	req.mtu = cpu_to_le16(mtu);
 
-- 
cgit v1.2.3


From 95fec034fd440b4882701df3e84d2b76af4e627d Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Mon, 4 May 2020 04:50:31 -0400
Subject: bnxt_en: prepare to refactor ethtool reset types

Extract bnxt_hwrm_firmware_reset() for performing firmware reset
operations. This new helper function will be used in a subsequent
patch to separate unrelated reset types out of bnxt_firmware_reset().

Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 46 ++++++++++++++---------
 1 file changed, 29 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 34046a6286e8..ed6a32299bec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1749,8 +1749,8 @@ static int bnxt_flash_nvram(struct net_device *dev,
 	return rc;
 }
 
-static int bnxt_firmware_reset(struct net_device *dev,
-			       u16 dir_type)
+static int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type,
+				    u8 self_reset, u8 flags)
 {
 	struct hwrm_fw_reset_input req = {0};
 	struct bnxt *bp = netdev_priv(dev);
@@ -1758,48 +1758,60 @@ static int bnxt_firmware_reset(struct net_device *dev,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
+	req.embedded_proc_type = proc_type;
+	req.selfrst_status = self_reset;
+	req.flags = flags;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == -EACCES)
+		bnxt_print_admin_err(bp);
+	return rc;
+}
+
+static int bnxt_firmware_reset(struct net_device *dev, u16 dir_type)
+{
+	u8 self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE;
+	struct bnxt *bp = netdev_priv(dev);
+	u8 proc_type, flags = 0;
+
 	/* TODO: Address self-reset of APE/KONG/BONO/TANG or ungraceful reset */
 	/*       (e.g. when firmware isn't already running) */
 	switch (dir_type) {
 	case BNX_DIR_TYPE_CHIMP_PATCH:
 	case BNX_DIR_TYPE_BOOTCODE:
 	case BNX_DIR_TYPE_BOOTCODE_2:
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT;
 		/* Self-reset ChiMP upon next PCIe reset: */
-		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST;
+		self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST;
 		break;
 	case BNX_DIR_TYPE_APE_FW:
 	case BNX_DIR_TYPE_APE_PATCH:
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT;
 		/* Self-reset APE upon next PCIe reset: */
-		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST;
+		self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST;
 		break;
 	case BNX_DIR_TYPE_KONG_FW:
 	case BNX_DIR_TYPE_KONG_PATCH:
-		req.embedded_proc_type =
-			FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL;
 		break;
 	case BNX_DIR_TYPE_BONO_FW:
 	case BNX_DIR_TYPE_BONO_PATCH:
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE;
 		break;
 	case BNXT_FW_RESET_CHIP:
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
-		req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
+		self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
 		if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
-			req.flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
+			flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
 		break;
 	case BNXT_FW_RESET_AP:
-		req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP;
+		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc == -EACCES)
-		bnxt_print_admin_err(bp);
-	return rc;
+	return bnxt_hwrm_firmware_reset(dev, proc_type, self_reset, flags);
 }
 
 static int bnxt_flash_firmware(struct net_device *dev,
-- 
cgit v1.2.3


From 94f17e89c956553606d5c7cf4f40ce6012529d48 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Mon, 4 May 2020 04:50:32 -0400
Subject: bnxt_en: refactor ethtool firmware reset types

The case statement in bnxt_firmware_reset() dangerously mixes types.
This patch separates the application processor and whole chip resets
from the rest such that the selection is performed on a pure type.

Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 38 +++++++++++++++--------
 1 file changed, 25 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ed6a32299bec..d99da82b6eff 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1768,10 +1768,10 @@ static int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type,
 	return rc;
 }
 
-static int bnxt_firmware_reset(struct net_device *dev, u16 dir_type)
+static int bnxt_firmware_reset(struct net_device *dev,
+			       enum bnxt_nvm_directory_type dir_type)
 {
 	u8 self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE;
-	struct bnxt *bp = netdev_priv(dev);
 	u8 proc_type, flags = 0;
 
 	/* TODO: Address self-reset of APE/KONG/BONO/TANG or ungraceful reset */
@@ -1798,15 +1798,6 @@ static int bnxt_firmware_reset(struct net_device *dev, u16 dir_type)
 	case BNX_DIR_TYPE_BONO_PATCH:
 		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE;
 		break;
-	case BNXT_FW_RESET_CHIP:
-		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP;
-		self_reset = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP;
-		if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
-			flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
-		break;
-	case BNXT_FW_RESET_AP:
-		proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP;
-		break;
 	default:
 		return -EINVAL;
 	}
@@ -1814,6 +1805,27 @@ static int bnxt_firmware_reset(struct net_device *dev, u16 dir_type)
 	return bnxt_hwrm_firmware_reset(dev, proc_type, self_reset, flags);
 }
 
+static int bnxt_firmware_reset_chip(struct net_device *dev)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	u8 flags = 0;
+
+	if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
+		flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL;
+
+	return bnxt_hwrm_firmware_reset(dev,
+					FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP,
+					FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP,
+					flags);
+}
+
+static int bnxt_firmware_reset_ap(struct net_device *dev)
+{
+	return bnxt_hwrm_firmware_reset(dev, FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP,
+					FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE,
+					0);
+}
+
 static int bnxt_flash_firmware(struct net_device *dev,
 			       u16 dir_type,
 			       const u8 *fw_data,
@@ -3006,7 +3018,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 		if (bp->hwrm_spec_code < 0x10803)
 			return -EOPNOTSUPP;
 
-		rc = bnxt_firmware_reset(dev, BNXT_FW_RESET_CHIP);
+		rc = bnxt_firmware_reset_chip(dev);
 		if (!rc) {
 			netdev_info(dev, "Reset request successful.\n");
 			if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET))
@@ -3018,7 +3030,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 		if (bp->hwrm_spec_code < 0x10803)
 			return -EOPNOTSUPP;
 
-		rc = bnxt_firmware_reset(dev, BNXT_FW_RESET_AP);
+		rc = bnxt_firmware_reset_ap(dev);
 		if (!rc) {
 			netdev_info(dev, "Reset Application Processor request successful.\n");
 			*flags = 0;
-- 
cgit v1.2.3


From 7a13240e371891d90cd51e3ea55ea04f4b2065dc Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Mon, 4 May 2020 04:50:33 -0400
Subject: bnxt_en: fix ethtool_reset_flags ABI violations

The ethtool ABI specifies that the reset operation should only clear
the flags that were actually reset. Setting the flags to zero after
a chip reset violates this because it does not include resetting the
application processor complex. Similarly, components that are not yet
defined are also not necessarily being reset.

The fact that chip reset does not cover the AP also means that it is
inappropriate to treat these two components exclusively of one another.
The ABI provides a mechanism to report a failure to reset independent
components via the returned bitmask, so it is also wrong to fail hard
if one of a set of independent resets is not possible.

It is incorrect to rely on the passed by reference flags in bnxt_reset(),
which are being updated as components are reset. The initially requested
value should be used instead so that hard errors do not propagate if any
earlier components could have been reset successfully.

Note, AP and chip resets are global in nature. Dedicated resets are
thus not currently supported.

Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 47 ++++++++++++-----------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h |  8 +++-
 2 files changed, 31 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index d99da82b6eff..9937c216aa48 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2999,7 +2999,10 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 static int bnxt_reset(struct net_device *dev, u32 *flags)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int rc = 0;
+	u32 req = *flags;
+
+	if (!req)
+		return -EINVAL;
 
 	if (!BNXT_PF(bp)) {
 		netdev_err(dev, "Reset is not supported from a VF\n");
@@ -3013,33 +3016,33 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 		return -EBUSY;
 	}
 
-	if (*flags == ETH_RESET_ALL) {
+	if ((req & BNXT_FW_RESET_CHIP) == BNXT_FW_RESET_CHIP) {
 		/* This feature is not supported in older firmware versions */
-		if (bp->hwrm_spec_code < 0x10803)
-			return -EOPNOTSUPP;
-
-		rc = bnxt_firmware_reset_chip(dev);
-		if (!rc) {
-			netdev_info(dev, "Reset request successful.\n");
-			if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET))
-				netdev_info(dev, "Reload driver to complete reset\n");
-			*flags = 0;
+		if (bp->hwrm_spec_code >= 0x10803) {
+			if (!bnxt_firmware_reset_chip(dev)) {
+				netdev_info(dev, "Firmware reset request successful.\n");
+				if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET))
+					netdev_info(dev, "Reload driver to complete reset\n");
+				*flags &= ~BNXT_FW_RESET_CHIP;
+			}
+		} else if (req == BNXT_FW_RESET_CHIP) {
+			return -EOPNOTSUPP; /* only request, fail hard */
 		}
-	} else if (*flags == ETH_RESET_AP) {
-		/* This feature is not supported in older firmware versions */
-		if (bp->hwrm_spec_code < 0x10803)
-			return -EOPNOTSUPP;
+	}
 
-		rc = bnxt_firmware_reset_ap(dev);
-		if (!rc) {
-			netdev_info(dev, "Reset Application Processor request successful.\n");
-			*flags = 0;
+	if (req & BNXT_FW_RESET_AP) {
+		/* This feature is not supported in older firmware versions */
+		if (bp->hwrm_spec_code >= 0x10803) {
+			if (!bnxt_firmware_reset_ap(dev)) {
+				netdev_info(dev, "Reset application processor successful.\n");
+				*flags &= ~BNXT_FW_RESET_AP;
+			}
+		} else if (req == BNXT_FW_RESET_AP) {
+			return -EOPNOTSUPP; /* only request, fail hard */
 		}
-	} else {
-		rc = -EINVAL;
 	}
 
-	return rc;
+	return 0;
 }
 
 static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index 3576d951727b..ce7585ff9e4d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -77,8 +77,12 @@ struct hwrm_dbg_cmn_output {
 #define BNXT_LED_DFLT_ENABLES(x)			\
 	cpu_to_le32(BNXT_LED_DFLT_ENA << (BNXT_LED_DFLT_ENA_SHIFT * (x)))
 
-#define BNXT_FW_RESET_AP	0xfffe
-#define BNXT_FW_RESET_CHIP	0xffff
+#define BNXT_FW_RESET_AP	(ETH_RESET_AP << ETH_RESET_SHARED_SHIFT)
+#define BNXT_FW_RESET_CHIP	((ETH_RESET_MGMT | ETH_RESET_IRQ |	\
+				  ETH_RESET_DMA | ETH_RESET_FILTER |	\
+				  ETH_RESET_OFFLOAD | ETH_RESET_MAC |	\
+				  ETH_RESET_PHY | ETH_RESET_RAM)	\
+				 << ETH_RESET_SHARED_SHIFT)
 
 extern const struct ethtool_ops bnxt_ethtool_ops;
 
-- 
cgit v1.2.3


From 8cec0940803c255f501d4b9f4764cd47fc206ad4 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Mon, 4 May 2020 04:50:34 -0400
Subject: bnxt_en: Improve kernel log messages related to ethtool reset.

Kernel log messages for failed AP reset commands should be suppressed.
These are expected to fail on devices that do not have an AP.  Add
missing driver reload message after AP reset and log it in a common
way without duplication.

Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9937c216aa48..ad68bc393cc7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1762,9 +1762,14 @@ static int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type,
 	req.selfrst_status = self_reset;
 	req.flags = flags;
 
-	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (rc == -EACCES)
-		bnxt_print_admin_err(bp);
+	if (proc_type == FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP) {
+		rc = hwrm_send_message_silent(bp, &req, sizeof(req),
+					      HWRM_CMD_TIMEOUT);
+	} else {
+		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+		if (rc == -EACCES)
+			bnxt_print_admin_err(bp);
+	}
 	return rc;
 }
 
@@ -2999,6 +3004,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 static int bnxt_reset(struct net_device *dev, u32 *flags)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	bool reload = false;
 	u32 req = *flags;
 
 	if (!req)
@@ -3022,7 +3028,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 			if (!bnxt_firmware_reset_chip(dev)) {
 				netdev_info(dev, "Firmware reset request successful.\n");
 				if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET))
-					netdev_info(dev, "Reload driver to complete reset\n");
+					reload = true;
 				*flags &= ~BNXT_FW_RESET_CHIP;
 			}
 		} else if (req == BNXT_FW_RESET_CHIP) {
@@ -3035,6 +3041,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 		if (bp->hwrm_spec_code >= 0x10803) {
 			if (!bnxt_firmware_reset_ap(dev)) {
 				netdev_info(dev, "Reset application processor successful.\n");
+				reload = true;
 				*flags &= ~BNXT_FW_RESET_AP;
 			}
 		} else if (req == BNXT_FW_RESET_AP) {
@@ -3042,6 +3049,9 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 		}
 	}
 
+	if (reload)
+		netdev_info(dev, "Reload driver to complete reset\n");
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From ebdf73dc595b6711dbfaf3007d513909bd814940 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:35 -0400
Subject: bnxt_en: Define the doorbell offsets on 57500 chips.

Define the 57500 chip doorbell offsets instead of using the magic
values in the C file.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5919f729e8a2..2e564026fe96 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5355,9 +5355,9 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 {
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		if (BNXT_PF(bp))
-			db->doorbell = bp->bar1 + 0x10000;
+			db->doorbell = bp->bar1 + DB_PF_OFFSET_P5;
 		else
-			db->doorbell = bp->bar1 + 0x4000;
+			db->doorbell = bp->bar1 + DB_VF_OFFSET_P5;
 		switch (ring_type) {
 		case HWRM_RING_ALLOC_TX:
 			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 1dbc3aece7a6..a3b80409c25e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -537,6 +537,9 @@ struct nqe_cn {
 #define DBR_TYPE_NQ_ARM					(0xbULL << 60)
 #define DBR_TYPE_NULL					(0xfULL << 60)
 
+#define DB_PF_OFFSET_P5					0x10000
+#define DB_VF_OFFSET_P5					0x4000
+
 #define INVALID_HW_RING_ID	((u16)-1)
 
 /* The hardware supports certain page sizes.  Use the supported page sizes
-- 
cgit v1.2.3


From e93b30d56fc0670e508456afc59f16d70fe1f83f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:36 -0400
Subject: bnxt_en: Set the db_offset on 57500 chips for the RDMA MSIX entries.

The driver provides completion ring or NQ doorbell offset for each
MSIX entry requested by the RDMA driver.  The NQ offset on 57500
chips is different than legacy chips.  Set it correctly based on
chip type for correctness.  The RDMA driver is ignoring this field
for the 57500 chips so it is not causing any problem.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 4a316c4b3fa8..4b40778ac8dd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -104,7 +104,13 @@ static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent)
 	for (i = 0; i < num_msix; i++) {
 		ent[i].vector = bp->irq_tbl[idx + i].vector;
 		ent[i].ring_idx = idx + i;
-		ent[i].db_offset = (idx + i) * 0x80;
+		if (bp->flags & BNXT_FLAG_CHIP_P5) {
+			ent[i].db_offset = DB_PF_OFFSET_P5;
+			if (BNXT_VF(bp))
+				ent[i].db_offset = DB_VF_OFFSET_P5;
+		} else {
+			ent[i].db_offset = (idx + i) * 0x80;
+		}
 	}
 }
 
-- 
cgit v1.2.3


From 8ae2473842bdbb95bfb451b130dad6a650b3ad1b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:37 -0400
Subject: bnxt_en: Add support for L2 doorbell size.

Read the L2 doorbell size from the firmware and only map the portion
of the doorbell BAR for L2 use.  This will leave the remaining doorbell
BAR available for the RoCE driver to use.  The RoCE driver can map
the remaining portion as write-combining to support the push feature.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 43 ++++++++++++++++++++++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 37 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2e564026fe96..8f11344b8055 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6364,6 +6364,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 {
 	struct hwrm_func_qcfg_input req = {0};
 	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	u32 min_db_offset = 0;
 	u16 flags;
 	int rc;
 
@@ -6412,6 +6413,21 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	if (!bp->max_mtu)
 		bp->max_mtu = BNXT_MAX_MTU;
 
+	if (bp->db_size)
+		goto func_qcfg_exit;
+
+	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (BNXT_PF(bp))
+			min_db_offset = DB_PF_OFFSET_P5;
+		else
+			min_db_offset = DB_VF_OFFSET_P5;
+	}
+	bp->db_size = PAGE_ALIGN(le16_to_cpu(resp->l2_doorbell_bar_size_kb) *
+				 1024);
+	if (!bp->db_size || bp->db_size > pci_resource_len(bp->pdev, 2) ||
+	    bp->db_size <= min_db_offset)
+		bp->db_size = pci_resource_len(bp->pdev, 2);
+
 func_qcfg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -10898,6 +10914,9 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	bp->dev = dev;
 	bp->pdev = pdev;
 
+	/* Doorbell BAR bp->bar1 is mapped after bnxt_fw_init_one_p2()
+	 * determines the BAR size.
+	 */
 	bp->bar0 = pci_ioremap_bar(pdev, 0);
 	if (!bp->bar0) {
 		dev_err(&pdev->dev, "Cannot map device registers, aborting\n");
@@ -10905,13 +10924,6 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 		goto init_err_release;
 	}
 
-	bp->bar1 = pci_ioremap_bar(pdev, 2);
-	if (!bp->bar1) {
-		dev_err(&pdev->dev, "Cannot map doorbell registers, aborting\n");
-		rc = -ENOMEM;
-		goto init_err_release;
-	}
-
 	bp->bar2 = pci_ioremap_bar(pdev, 4);
 	if (!bp->bar2) {
 		dev_err(&pdev->dev, "Cannot map bar4 registers, aborting\n");
@@ -11833,6 +11845,16 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
 	return 0;
 }
 
+static int bnxt_map_db_bar(struct bnxt *bp)
+{
+	if (!bp->db_size)
+		return -ENODEV;
+	bp->bar1 = pci_iomap(bp->pdev, 2, bp->db_size);
+	if (!bp->bar1)
+		return -ENOMEM;
+	return 0;
+}
+
 static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *dev;
@@ -11893,6 +11915,13 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	rc = bnxt_map_db_bar(bp);
+	if (rc) {
+		dev_err(&pdev->dev, "Cannot map doorbell BAR rc = %d, aborting\n",
+			rc);
+		goto init_err_pci_clean;
+	}
+
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
 			   NETIF_F_TSO | NETIF_F_TSO6 |
 			   NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a3b80409c25e..6114b0a576ff 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1820,6 +1820,7 @@ struct bnxt {
 	/* ensure atomic 64-bit doorbell writes on 32-bit systems. */
 	spinlock_t		db_lock;
 #endif
+	int			db_size;
 
 #define BNXT_NTP_FLTR_MAX_FLTR	4096
 #define BNXT_NTP_FLTR_HASH_SIZE	512
-- 
cgit v1.2.3


From 098286ff930ca752e4c9295ea65840dd55f5f290 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:38 -0400
Subject: bnxt_en: Add doorbell information to bnxt_en_dev struct.

The purpose of this is to inform the RDMA driver the size of the doorbell
BAR that the L2 driver has mapped and the portion that is mapped
uncacheable.  The unchaeable portion is shared with the RoCE driver.
Any remaining unmapped doorbell BAR can be used by the RDMA driver for
its own purpose.  Currently, the entire L2 portion is mapped uncacheable.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h | 8 ++++++++
 2 files changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 4b40778ac8dd..8c8368c2f335 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -481,6 +481,8 @@ struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
 			edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
 		edev->net = dev;
 		edev->pdev = bp->pdev;
+		edev->l2_db_size = bp->db_size;
+		edev->l2_db_size_nc = bp->db_size;
 		bp->edev = edev;
 	}
 	return bp->edev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 9895406b9830..6b4d2556a6df 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -67,6 +67,14 @@ struct bnxt_en_dev {
 	#define BNXT_EN_FLAG_ULP_STOPPED	0x8
 	const struct bnxt_en_ops	*en_ops;
 	struct bnxt_ulp			ulp_tbl[BNXT_MAX_ULP];
+	int				l2_db_size;	/* Doorbell BAR size in
+							 * bytes mapped by L2
+							 * driver.
+							 */
+	int				l2_db_size_nc;	/* Doorbell BAR size in
+							 * bytes mapped as non-
+							 * cacheable.
+							 */
 };
 
 struct bnxt_en_ops {
-- 
cgit v1.2.3


From 9d8b5f05529c619b63d68b0dd26a1dfe35a4fab2 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:39 -0400
Subject: bnxt_en: Refactor the software ring counters.

We currently have 3 software ring counters, rx_l4_csum_errors,
rx_buf_errors, and missed_irqs.  The 1st two are RX counters and the
last one is a common counter.  Organize them into 2 structures
bnxt_rx_sw_stats and bnxt_cmn_sw_stats.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         |  6 ++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         | 19 +++++++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 30 +++++++++++++++++------
 3 files changed, 42 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8f11344b8055..4bbfea147d98 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1766,7 +1766,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 		rc = -EIO;
 		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
-			bnapi->cp_ring.rx_buf_errors++;
+			bnapi->cp_ring.sw_stats.rx.rx_buf_errors++;
 			if (!(bp->flags & BNXT_FLAG_CHIP_P5)) {
 				netdev_warn(bp->dev, "RX buffer error %x\n",
 					    rx_err);
@@ -1849,7 +1849,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	} else {
 		if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L4_CS_ERR_BITS) {
 			if (dev->features & NETIF_F_RXCSUM)
-				bnapi->cp_ring.rx_l4_csum_errors++;
+				bnapi->cp_ring.sw_stats.rx.rx_l4_csum_errors++;
 		}
 	}
 
@@ -10285,7 +10285,7 @@ static void bnxt_chk_missed_irq(struct bnxt *bp)
 			bnxt_dbg_hwrm_ring_info_get(bp,
 				DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL,
 				fw_ring_id, &val[0], &val[1]);
-			cpr->missed_irqs++;
+			cpr->sw_stats.cmn.missed_irqs++;
 		}
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6114b0a576ff..c15517ff7ff6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -910,6 +910,20 @@ struct bnxt_rx_ring_info {
 	struct page_pool	*page_pool;
 };
 
+struct bnxt_rx_sw_stats {
+	u64			rx_l4_csum_errors;
+	u64			rx_buf_errors;
+};
+
+struct bnxt_cmn_sw_stats {
+	u64			missed_irqs;
+};
+
+struct bnxt_sw_stats {
+	struct bnxt_rx_sw_stats rx;
+	struct bnxt_cmn_sw_stats cmn;
+};
+
 struct bnxt_cp_ring_info {
 	struct bnxt_napi	*bnapi;
 	u32			cp_raw_cons;
@@ -937,9 +951,8 @@ struct bnxt_cp_ring_info {
 	struct ctx_hw_stats	*hw_stats;
 	dma_addr_t		hw_stats_map;
 	u32			hw_stats_ctx_id;
-	u64			rx_l4_csum_errors;
-	u64			rx_buf_errors;
-	u64			missed_irqs;
+
+	struct bnxt_sw_stats	sw_stats;
 
 	struct bnxt_ring_struct	cp_ring_struct;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ad68bc393cc7..b2b43a7a9abb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -171,9 +171,12 @@ static const char * const bnxt_ring_tpa2_stats_str[] = {
 	"rx_tpa_errors",
 };
 
-static const char * const bnxt_ring_sw_stats_str[] = {
+static const char * const bnxt_rx_sw_stats_str[] = {
 	"rx_l4_csum_errors",
 	"rx_buf_errors",
+};
+
+static const char * const bnxt_cmn_sw_stats_str[] = {
 	"missed_irqs",
 };
 
@@ -485,7 +488,8 @@ static int bnxt_get_num_ring_stats(struct bnxt *bp)
 	int num_stats;
 
 	num_stats = ARRAY_SIZE(bnxt_ring_stats_str) +
-		    ARRAY_SIZE(bnxt_ring_sw_stats_str) +
+		    ARRAY_SIZE(bnxt_rx_sw_stats_str) +
+		    ARRAY_SIZE(bnxt_cmn_sw_stats_str) +
 		    bnxt_get_num_tpa_ring_stats(bp);
 	return num_stats * bp->cp_nr_rings;
 }
@@ -548,13 +552,19 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 		__le64 *hw_stats = (__le64 *)cpr->hw_stats;
+		u64 *sw;
 		int k;
 
 		for (k = 0; k < stat_fields; j++, k++)
 			buf[j] = le64_to_cpu(hw_stats[k]);
-		buf[j++] = cpr->rx_l4_csum_errors;
-		buf[j++] = cpr->rx_buf_errors;
-		buf[j++] = cpr->missed_irqs;
+
+		sw = (u64 *)&cpr->sw_stats.rx;
+		for (k = 0; k < ARRAY_SIZE(bnxt_rx_sw_stats_str); j++, k++)
+			buf[j] = sw[k];
+
+		sw = (u64 *)&cpr->sw_stats.cmn;
+		for (k = 0; k < ARRAY_SIZE(bnxt_cmn_sw_stats_str); j++, k++)
+			buf[j] = sw[k];
 
 		bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter +=
 			le64_to_cpu(cpr->hw_stats->rx_discard_pkts);
@@ -653,10 +663,16 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				buf += ETH_GSTRING_LEN;
 			}
 skip_tpa_stats:
-			num_str = ARRAY_SIZE(bnxt_ring_sw_stats_str);
+			num_str = ARRAY_SIZE(bnxt_rx_sw_stats_str);
+			for (j = 0; j < num_str; j++) {
+				sprintf(buf, "[%d]: %s", i,
+					bnxt_rx_sw_stats_str[j]);
+				buf += ETH_GSTRING_LEN;
+			}
+			num_str = ARRAY_SIZE(bnxt_cmn_sw_stats_str);
 			for (j = 0; j < num_str; j++) {
 				sprintf(buf, "[%d]: %s", i,
-					bnxt_ring_sw_stats_str[j]);
+					bnxt_cmn_sw_stats_str[j]);
 				buf += ETH_GSTRING_LEN;
 			}
 		}
-- 
cgit v1.2.3


From 3316d50905f0e551d4786767d827589960a8cb83 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 4 May 2020 04:50:40 -0400
Subject: bnxt_en: Split HW ring statistics strings into RX and TX parts.

This will allow the RX and TX ring statistics to be separated if needed.
In the next patch, we'll be able to only display RX or TX statistcis if
the channel is RX only or TX only.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 53 ++++++++++++++---------
 1 file changed, 33 insertions(+), 20 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index b2b43a7a9abb..85080f50bce5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -137,7 +137,7 @@ reset_coalesce:
 	return rc;
 }
 
-static const char * const bnxt_ring_stats_str[] = {
+static const char * const bnxt_ring_rx_stats_str[] = {
 	"rx_ucast_packets",
 	"rx_mcast_packets",
 	"rx_bcast_packets",
@@ -146,6 +146,9 @@ static const char * const bnxt_ring_stats_str[] = {
 	"rx_ucast_bytes",
 	"rx_mcast_bytes",
 	"rx_bcast_bytes",
+};
+
+static const char * const bnxt_ring_tx_stats_str[] = {
 	"tx_ucast_packets",
 	"tx_mcast_packets",
 	"tx_bcast_packets",
@@ -306,6 +309,11 @@ static struct {
 	{0, "tx_total_discard_pkts"},
 };
 
+#define NUM_RING_RX_SW_STATS		ARRAY_SIZE(bnxt_rx_sw_stats_str)
+#define NUM_RING_CMN_SW_STATS		ARRAY_SIZE(bnxt_cmn_sw_stats_str)
+#define NUM_RING_RX_HW_STATS		ARRAY_SIZE(bnxt_ring_rx_stats_str)
+#define NUM_RING_TX_HW_STATS		ARRAY_SIZE(bnxt_ring_tx_stats_str)
+
 static const struct {
 	long offset;
 	char string[ETH_GSTRING_LEN];
@@ -485,13 +493,13 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 
 static int bnxt_get_num_ring_stats(struct bnxt *bp)
 {
-	int num_stats;
+	int rx, tx, cmn;
 
-	num_stats = ARRAY_SIZE(bnxt_ring_stats_str) +
-		    ARRAY_SIZE(bnxt_rx_sw_stats_str) +
-		    ARRAY_SIZE(bnxt_cmn_sw_stats_str) +
-		    bnxt_get_num_tpa_ring_stats(bp);
-	return num_stats * bp->cp_nr_rings;
+	rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS +
+	     bnxt_get_num_tpa_ring_stats(bp);
+	tx = NUM_RING_TX_HW_STATS;
+	cmn = NUM_RING_CMN_SW_STATS;
+	return (rx + tx + cmn) * bp->cp_nr_rings;
 }
 
 static int bnxt_get_num_stats(struct bnxt *bp)
@@ -537,7 +545,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 {
 	u32 i, j = 0;
 	struct bnxt *bp = netdev_priv(dev);
-	u32 stat_fields = ARRAY_SIZE(bnxt_ring_stats_str) +
+	u32 stat_fields = NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS +
 			  bnxt_get_num_tpa_ring_stats(bp);
 
 	if (!bp->bnapi) {
@@ -559,11 +567,11 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 			buf[j] = le64_to_cpu(hw_stats[k]);
 
 		sw = (u64 *)&cpr->sw_stats.rx;
-		for (k = 0; k < ARRAY_SIZE(bnxt_rx_sw_stats_str); j++, k++)
+		for (k = 0; k < NUM_RING_RX_SW_STATS; j++, k++)
 			buf[j] = sw[k];
 
 		sw = (u64 *)&cpr->sw_stats.cmn;
-		for (k = 0; k < ARRAY_SIZE(bnxt_cmn_sw_stats_str); j++, k++)
+		for (k = 0; k < NUM_RING_CMN_SW_STATS; j++, k++)
 			buf[j] = sw[k];
 
 		bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter +=
@@ -642,34 +650,39 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < bp->cp_nr_rings; i++) {
-			num_str = ARRAY_SIZE(bnxt_ring_stats_str);
+			num_str = NUM_RING_RX_HW_STATS;
 			for (j = 0; j < num_str; j++) {
 				sprintf(buf, "[%d]: %s", i,
-					bnxt_ring_stats_str[j]);
+					bnxt_ring_rx_stats_str[j]);
 				buf += ETH_GSTRING_LEN;
 			}
-			if (!BNXT_SUPPORTS_TPA(bp))
+			num_str = NUM_RING_TX_HW_STATS;
+			for (j = 0; j < num_str; j++) {
+				sprintf(buf, "[%d]: %s", i,
+					bnxt_ring_tx_stats_str[j]);
+				buf += ETH_GSTRING_LEN;
+			}
+			num_str = bnxt_get_num_tpa_ring_stats(bp);
+			if (!num_str)
 				goto skip_tpa_stats;
 
-			if (bp->max_tpa_v2) {
-				num_str = ARRAY_SIZE(bnxt_ring_tpa2_stats_str);
+			if (bp->max_tpa_v2)
 				str = bnxt_ring_tpa2_stats_str;
-			} else {
-				num_str = ARRAY_SIZE(bnxt_ring_tpa_stats_str);
+			else
 				str = bnxt_ring_tpa_stats_str;
-			}
+
 			for (j = 0; j < num_str; j++) {
 				sprintf(buf, "[%d]: %s", i, str[j]);
 				buf += ETH_GSTRING_LEN;
 			}
 skip_tpa_stats:
-			num_str = ARRAY_SIZE(bnxt_rx_sw_stats_str);
+			num_str = NUM_RING_RX_SW_STATS;
 			for (j = 0; j < num_str; j++) {
 				sprintf(buf, "[%d]: %s", i,
 					bnxt_rx_sw_stats_str[j]);
 				buf += ETH_GSTRING_LEN;
 			}
-			num_str = ARRAY_SIZE(bnxt_cmn_sw_stats_str);
+			num_str = NUM_RING_CMN_SW_STATS;
 			for (j = 0; j < num_str; j++) {
 				sprintf(buf, "[%d]: %s", i,
 					bnxt_cmn_sw_stats_str[j]);
-- 
cgit v1.2.3


From 125592fbf467d1a70312006bbaf29724d0ba5897 Mon Sep 17 00:00:00 2001
From: Rajesh Ravi <rajesh.ravi@broadcom.com>
Date: Mon, 4 May 2020 04:50:41 -0400
Subject: bnxt_en: show only relevant ethtool stats for a TX or RX ring

Currently, ethtool -S shows all TX/RX ring counters whether the
channel is combined, RX, or TX.  The unused counters will always be
zero.  Improve it by showing only the relevant counters if the channel
is RX or TX.  If the channel is combined, the counters will be shown
exactly the same as before.

[ MChan: Lots of cleanups and simplifications on Rajesh's original
code]

Signed-off-by: Rajesh Ravi <rajesh.ravi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 93 +++++++++++++++++------
 1 file changed, 71 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 85080f50bce5..07526868f7be 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -494,12 +494,20 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 static int bnxt_get_num_ring_stats(struct bnxt *bp)
 {
 	int rx, tx, cmn;
+	bool sh = false;
+
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+		sh = true;
 
 	rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS +
 	     bnxt_get_num_tpa_ring_stats(bp);
 	tx = NUM_RING_TX_HW_STATS;
 	cmn = NUM_RING_CMN_SW_STATS;
-	return (rx + tx + cmn) * bp->cp_nr_rings;
+	if (sh)
+		return (rx + tx + cmn) * bp->cp_nr_rings;
+	else
+		return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings +
+		       cmn * bp->cp_nr_rings;
 }
 
 static int bnxt_get_num_stats(struct bnxt *bp)
@@ -540,13 +548,29 @@ static int bnxt_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
+static bool is_rx_ring(struct bnxt *bp, int ring_num)
+{
+	return ring_num < bp->rx_nr_rings;
+}
+
+static bool is_tx_ring(struct bnxt *bp, int ring_num)
+{
+	int tx_base = 0;
+
+	if (!(bp->flags & BNXT_FLAG_SHARED_RINGS))
+		tx_base = bp->rx_nr_rings;
+
+	if (ring_num >= tx_base && ring_num < (tx_base + bp->tx_nr_rings))
+		return true;
+	return false;
+}
+
 static void bnxt_get_ethtool_stats(struct net_device *dev,
 				   struct ethtool_stats *stats, u64 *buf)
 {
 	u32 i, j = 0;
 	struct bnxt *bp = netdev_priv(dev);
-	u32 stat_fields = NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS +
-			  bnxt_get_num_tpa_ring_stats(bp);
+	u32 tpa_stats;
 
 	if (!bp->bnapi) {
 		j += bnxt_get_num_ring_stats(bp) + BNXT_NUM_SW_FUNC_STATS;
@@ -556,6 +580,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
 		bnxt_sw_func_stats[i].counter = 0;
 
+	tpa_stats = bnxt_get_num_tpa_ring_stats(bp);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -563,12 +588,30 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 		u64 *sw;
 		int k;
 
-		for (k = 0; k < stat_fields; j++, k++)
+		if (is_rx_ring(bp, i)) {
+			for (k = 0; k < NUM_RING_RX_HW_STATS; j++, k++)
+				buf[j] = le64_to_cpu(hw_stats[k]);
+		}
+		if (is_tx_ring(bp, i)) {
+			k = NUM_RING_RX_HW_STATS;
+			for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS;
+			       j++, k++)
+				buf[j] = le64_to_cpu(hw_stats[k]);
+		}
+		if (!tpa_stats || !is_rx_ring(bp, i))
+			goto skip_tpa_ring_stats;
+
+		k = NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS;
+		for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS +
+			   tpa_stats; j++, k++)
 			buf[j] = le64_to_cpu(hw_stats[k]);
 
+skip_tpa_ring_stats:
 		sw = (u64 *)&cpr->sw_stats.rx;
-		for (k = 0; k < NUM_RING_RX_SW_STATS; j++, k++)
-			buf[j] = sw[k];
+		if (is_rx_ring(bp, i)) {
+			for (k = 0; k < NUM_RING_RX_SW_STATS; j++, k++)
+				buf[j] = sw[k];
+		}
 
 		sw = (u64 *)&cpr->sw_stats.cmn;
 		for (k = 0; k < NUM_RING_CMN_SW_STATS; j++, k++)
@@ -650,20 +693,24 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 	switch (stringset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < bp->cp_nr_rings; i++) {
-			num_str = NUM_RING_RX_HW_STATS;
-			for (j = 0; j < num_str; j++) {
-				sprintf(buf, "[%d]: %s", i,
-					bnxt_ring_rx_stats_str[j]);
-				buf += ETH_GSTRING_LEN;
+			if (is_rx_ring(bp, i)) {
+				num_str = NUM_RING_RX_HW_STATS;
+				for (j = 0; j < num_str; j++) {
+					sprintf(buf, "[%d]: %s", i,
+						bnxt_ring_rx_stats_str[j]);
+					buf += ETH_GSTRING_LEN;
+				}
 			}
-			num_str = NUM_RING_TX_HW_STATS;
-			for (j = 0; j < num_str; j++) {
-				sprintf(buf, "[%d]: %s", i,
-					bnxt_ring_tx_stats_str[j]);
-				buf += ETH_GSTRING_LEN;
+			if (is_tx_ring(bp, i)) {
+				num_str = NUM_RING_TX_HW_STATS;
+				for (j = 0; j < num_str; j++) {
+					sprintf(buf, "[%d]: %s", i,
+						bnxt_ring_tx_stats_str[j]);
+					buf += ETH_GSTRING_LEN;
+				}
 			}
 			num_str = bnxt_get_num_tpa_ring_stats(bp);
-			if (!num_str)
+			if (!num_str || !is_rx_ring(bp, i))
 				goto skip_tpa_stats;
 
 			if (bp->max_tpa_v2)
@@ -676,11 +723,13 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				buf += ETH_GSTRING_LEN;
 			}
 skip_tpa_stats:
-			num_str = NUM_RING_RX_SW_STATS;
-			for (j = 0; j < num_str; j++) {
-				sprintf(buf, "[%d]: %s", i,
-					bnxt_rx_sw_stats_str[j]);
-				buf += ETH_GSTRING_LEN;
+			if (is_rx_ring(bp, i)) {
+				num_str = NUM_RING_RX_SW_STATS;
+				for (j = 0; j < num_str; j++) {
+					sprintf(buf, "[%d]: %s", i,
+						bnxt_rx_sw_stats_str[j]);
+					buf += ETH_GSTRING_LEN;
+				}
 			}
 			num_str = NUM_RING_CMN_SW_STATS;
 			for (j = 0; j < num_str; j++) {
-- 
cgit v1.2.3


From bc54ac3609aa0361dfeb15758b7bacf3637f6d4a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 4 May 2020 19:28:21 +0200
Subject: r8169: use new helper eth_hw_addr_crc

Use new helper eth_hw_addr_crc to simplify the code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 8b665f2ec21f..2f6512ed0a78 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -19,7 +19,6 @@
 #include <linux/ethtool.h>
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
-#include <linux/crc32.h>
 #include <linux/in.h>
 #include <linux/io.h>
 #include <linux/ip.h>
@@ -2610,7 +2609,7 @@ static void rtl_set_rx_mode(struct net_device *dev)
 
 		mc_filter[1] = mc_filter[0] = 0;
 		netdev_for_each_mc_addr(ha, dev) {
-			u32 bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26;
+			u32 bit_nr = eth_hw_addr_crc(ha) >> 26;
 			mc_filter[bit_nr >> 5] |= BIT(bit_nr & 31);
 		}
 
-- 
cgit v1.2.3


From f6bd59526ca527e203e3c6c2e62cda5a0fd5c1a2 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 1 May 2020 23:50:06 +0300
Subject: net: ethernet: ti: introduce am654 common platform time sync driver

The CPTS module is used to facilitate host control of time sync operations.
Main features of CPTS module are:
- selection of multiple external clock sources
- control of time sync events via interrupt or polling
- 64-bit timestamp mode in ns with HW PPM and nudge adjustment.
- hardware timestamp ext. inputs (HWx_TS_PUSH)
- timestamp Generator function outputs (TS_GENFx)
Depending on integration it enables compliance with the IEEE 1588-2008
standard for a precision clock synchronization protocol, Ethernet Enhanced
Scheduled Traffic Operations (CPTS_ESTFn) and PCIe Subsystem Precision Time
Measurement (PTM).

Introduced driver provides Linux PTP hardware clock for each CPTS device
and network packets timestamping where applicable. CPTS PTP hardware clock
supports following operations:
    - Set time
    - Get time
    - Shift the clock by a given offset atomically
    - Adjust clock frequency
    - Time stamp external events
    - Periodic output signals

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig     |   14 +
 drivers/net/ethernet/ti/Makefile    |    1 +
 drivers/net/ethernet/ti/am65-cpts.c | 1041 +++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/am65-cpts.h |   50 ++
 4 files changed, 1106 insertions(+)
 create mode 100644 drivers/net/ethernet/ti/am65-cpts.c
 create mode 100644 drivers/net/ethernet/ti/am65-cpts.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 7b0ad777828d..2b7590cece39 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -110,6 +110,20 @@ config TI_K3_AM65_CPSW_NUSS
 	  To compile this driver as a module, choose M here: the module
 	  will be called ti-am65-cpsw-nuss.
 
+config TI_K3_AM65_CPTS
+	tristate "TI K3 AM65x CPTS"
+	depends on ARCH_K3 && OF && PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK
+	select NET_PTP_CLASSIFY
+	help
+	  Say y here to support the TI K3 AM65x CPTS with 1588 features such as
+	  PTP hardware clock for each CPTS device and network packets
+	  timestamping where applicable.
+	  Depending on integration CPTS blocks enable compliance with
+	  the IEEE 1588-2008 standard for a precision clock synchronization
+	  protocol, Ethernet Enhanced Scheduled Traffic Operations (CPTS_ESTFn)
+	  and PCIe Subsystem Precision Time Measurement (PTM).
+
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
 	select TI_DAVINCI_MDIO
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 53792190e9c2..bf86067f9b4c 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -26,3 +26,4 @@ keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.
 
 obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
 ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o
+obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
new file mode 100644
index 000000000000..370162c86e7f
--- /dev/null
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -0,0 +1,1041 @@
+// SPDX-License-Identifier: GPL-2.0
+/* TI K3 AM65x Common Platform Time Sync
+ *
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/ptp_classify.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "am65-cpts.h"
+
+struct am65_genf_regs {
+	u32 comp_lo;	/* Comparison Low Value 0:31 */
+	u32 comp_hi;	/* Comparison High Value 32:63 */
+	u32 control;	/* control */
+	u32 length;	/* Length */
+	u32 ppm_low;	/* PPM Load Low Value 0:31 */
+	u32 ppm_hi;	/* PPM Load High Value 32:63 */
+	u32 ts_nudge;	/* Nudge value */
+} __aligned(32) __packed;
+
+#define AM65_CPTS_GENF_MAX_NUM 9
+#define AM65_CPTS_ESTF_MAX_NUM 8
+
+struct am65_cpts_regs {
+	u32 idver;		/* Identification and version */
+	u32 control;		/* Time sync control */
+	u32 rftclk_sel;		/* Reference Clock Select Register */
+	u32 ts_push;		/* Time stamp event push */
+	u32 ts_load_val_lo;	/* Time Stamp Load Low Value 0:31 */
+	u32 ts_load_en;		/* Time stamp load enable */
+	u32 ts_comp_lo;		/* Time Stamp Comparison Low Value 0:31 */
+	u32 ts_comp_length;	/* Time Stamp Comparison Length */
+	u32 intstat_raw;	/* Time sync interrupt status raw */
+	u32 intstat_masked;	/* Time sync interrupt status masked */
+	u32 int_enable;		/* Time sync interrupt enable */
+	u32 ts_comp_nudge;	/* Time Stamp Comparison Nudge Value */
+	u32 event_pop;		/* Event interrupt pop */
+	u32 event_0;		/* Event Time Stamp lo 0:31 */
+	u32 event_1;		/* Event Type Fields */
+	u32 event_2;		/* Event Type Fields domain */
+	u32 event_3;		/* Event Time Stamp hi 32:63 */
+	u32 ts_load_val_hi;	/* Time Stamp Load High Value 32:63 */
+	u32 ts_comp_hi;		/* Time Stamp Comparison High Value 32:63 */
+	u32 ts_add_val;		/* Time Stamp Add value */
+	u32 ts_ppm_low;		/* Time Stamp PPM Load Low Value 0:31 */
+	u32 ts_ppm_hi;		/* Time Stamp PPM Load High Value 32:63 */
+	u32 ts_nudge;		/* Time Stamp Nudge value */
+	u32 reserv[33];
+	struct am65_genf_regs genf[AM65_CPTS_GENF_MAX_NUM];
+	struct am65_genf_regs estf[AM65_CPTS_ESTF_MAX_NUM];
+};
+
+/* CONTROL_REG */
+#define AM65_CPTS_CONTROL_EN			BIT(0)
+#define AM65_CPTS_CONTROL_INT_TEST		BIT(1)
+#define AM65_CPTS_CONTROL_TS_COMP_POLARITY	BIT(2)
+#define AM65_CPTS_CONTROL_TSTAMP_EN		BIT(3)
+#define AM65_CPTS_CONTROL_SEQUENCE_EN		BIT(4)
+#define AM65_CPTS_CONTROL_64MODE		BIT(5)
+#define AM65_CPTS_CONTROL_TS_COMP_TOG		BIT(6)
+#define AM65_CPTS_CONTROL_TS_PPM_DIR		BIT(7)
+#define AM65_CPTS_CONTROL_HW1_TS_PUSH_EN	BIT(8)
+#define AM65_CPTS_CONTROL_HW2_TS_PUSH_EN	BIT(9)
+#define AM65_CPTS_CONTROL_HW3_TS_PUSH_EN	BIT(10)
+#define AM65_CPTS_CONTROL_HW4_TS_PUSH_EN	BIT(11)
+#define AM65_CPTS_CONTROL_HW5_TS_PUSH_EN	BIT(12)
+#define AM65_CPTS_CONTROL_HW6_TS_PUSH_EN	BIT(13)
+#define AM65_CPTS_CONTROL_HW7_TS_PUSH_EN	BIT(14)
+#define AM65_CPTS_CONTROL_HW8_TS_PUSH_EN	BIT(15)
+#define AM65_CPTS_CONTROL_HW1_TS_PUSH_OFFSET	(8)
+
+#define AM65_CPTS_CONTROL_TS_SYNC_SEL_MASK	(0xF)
+#define AM65_CPTS_CONTROL_TS_SYNC_SEL_SHIFT	(28)
+
+/* RFTCLK_SEL_REG */
+#define AM65_CPTS_RFTCLK_SEL_MASK		(0x1F)
+
+/* TS_PUSH_REG */
+#define AM65_CPTS_TS_PUSH			BIT(0)
+
+/* TS_LOAD_EN_REG */
+#define AM65_CPTS_TS_LOAD_EN			BIT(0)
+
+/* INTSTAT_RAW_REG */
+#define AM65_CPTS_INTSTAT_RAW_TS_PEND		BIT(0)
+
+/* INTSTAT_MASKED_REG */
+#define AM65_CPTS_INTSTAT_MASKED_TS_PEND	BIT(0)
+
+/* INT_ENABLE_REG */
+#define AM65_CPTS_INT_ENABLE_TS_PEND_EN		BIT(0)
+
+/* TS_COMP_NUDGE_REG */
+#define AM65_CPTS_TS_COMP_NUDGE_MASK		(0xFF)
+
+/* EVENT_POP_REG */
+#define AM65_CPTS_EVENT_POP			BIT(0)
+
+/* EVENT_1_REG */
+#define AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK	GENMASK(15, 0)
+
+#define AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK	GENMASK(19, 16)
+#define AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT	(16)
+
+#define AM65_CPTS_EVENT_1_EVENT_TYPE_MASK	GENMASK(23, 20)
+#define AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT	(20)
+
+#define AM65_CPTS_EVENT_1_PORT_NUMBER_MASK	GENMASK(28, 24)
+#define AM65_CPTS_EVENT_1_PORT_NUMBER_SHIFT	(24)
+
+/* EVENT_2_REG */
+#define AM65_CPTS_EVENT_2_REG_DOMAIN_MASK	(0xFF)
+#define AM65_CPTS_EVENT_2_REG_DOMAIN_SHIFT	(0)
+
+enum {
+	AM65_CPTS_EV_PUSH,	/* Time Stamp Push Event */
+	AM65_CPTS_EV_ROLL,	/* Time Stamp Rollover Event */
+	AM65_CPTS_EV_HALF,	/* Time Stamp Half Rollover Event */
+	AM65_CPTS_EV_HW,		/* Hardware Time Stamp Push Event */
+	AM65_CPTS_EV_RX,		/* Ethernet Receive Event */
+	AM65_CPTS_EV_TX,		/* Ethernet Transmit Event */
+	AM65_CPTS_EV_TS_COMP,	/* Time Stamp Compare Event */
+	AM65_CPTS_EV_HOST,	/* Host Transmit Event */
+};
+
+struct am65_cpts_event {
+	struct list_head list;
+	unsigned long tmo;
+	u32 event1;
+	u32 event2;
+	u64 timestamp;
+};
+
+#define AM65_CPTS_FIFO_DEPTH		(16)
+#define AM65_CPTS_MAX_EVENTS		(32)
+#define AM65_CPTS_EVENT_RX_TX_TIMEOUT	(20) /* ms */
+#define AM65_CPTS_SKB_TX_WORK_TIMEOUT	1 /* jiffies */
+#define AM65_CPTS_MIN_PPM		0x400
+
+struct am65_cpts {
+	struct device *dev;
+	struct am65_cpts_regs __iomem *reg;
+	struct ptp_clock_info ptp_info;
+	struct ptp_clock *ptp_clock;
+	int phc_index;
+	struct clk_hw *clk_mux_hw;
+	struct device_node *clk_mux_np;
+	struct clk *refclk;
+	u32 refclk_freq;
+	struct list_head events;
+	struct list_head pool;
+	struct am65_cpts_event pool_data[AM65_CPTS_MAX_EVENTS];
+	spinlock_t lock; /* protects events lists*/
+	u32 ext_ts_inputs;
+	u32 genf_num;
+	u32 ts_add_val;
+	int irq;
+	struct mutex ptp_clk_lock; /* PHC access sync */
+	u64 timestamp;
+	u32 genf_enable;
+	u32 hw_ts_enable;
+	struct sk_buff_head txq;
+};
+
+struct am65_cpts_skb_cb_data {
+	unsigned long tmo;
+	u32 skb_mtype_seqid;
+};
+
+#define am65_cpts_write32(c, v, r) writel(v, &(c)->reg->r)
+#define am65_cpts_read32(c, r) readl(&(c)->reg->r)
+
+static void am65_cpts_settime(struct am65_cpts *cpts, u64 start_tstamp)
+{
+	u32 val;
+
+	val = upper_32_bits(start_tstamp);
+	am65_cpts_write32(cpts, val, ts_load_val_hi);
+	val = lower_32_bits(start_tstamp);
+	am65_cpts_write32(cpts, val, ts_load_val_lo);
+
+	am65_cpts_write32(cpts, AM65_CPTS_TS_LOAD_EN, ts_load_en);
+}
+
+static void am65_cpts_set_add_val(struct am65_cpts *cpts)
+{
+	/* select coefficient according to the rate */
+	cpts->ts_add_val = (NSEC_PER_SEC / cpts->refclk_freq - 1) & 0x7;
+
+	am65_cpts_write32(cpts, cpts->ts_add_val, ts_add_val);
+}
+
+static void am65_cpts_disable(struct am65_cpts *cpts)
+{
+	am65_cpts_write32(cpts, 0, control);
+	am65_cpts_write32(cpts, 0, int_enable);
+}
+
+static int am65_cpts_event_get_port(struct am65_cpts_event *event)
+{
+	return (event->event1 & AM65_CPTS_EVENT_1_PORT_NUMBER_MASK) >>
+		AM65_CPTS_EVENT_1_PORT_NUMBER_SHIFT;
+}
+
+static int am65_cpts_event_get_type(struct am65_cpts_event *event)
+{
+	return (event->event1 & AM65_CPTS_EVENT_1_EVENT_TYPE_MASK) >>
+		AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT;
+}
+
+static int am65_cpts_cpts_purge_events(struct am65_cpts *cpts)
+{
+	struct list_head *this, *next;
+	struct am65_cpts_event *event;
+	int removed = 0;
+
+	list_for_each_safe(this, next, &cpts->events) {
+		event = list_entry(this, struct am65_cpts_event, list);
+		if (time_after(jiffies, event->tmo)) {
+			list_del_init(&event->list);
+			list_add(&event->list, &cpts->pool);
+			++removed;
+		}
+	}
+
+	if (removed)
+		dev_dbg(cpts->dev, "event pool cleaned up %d\n", removed);
+	return removed ? 0 : -1;
+}
+
+static bool am65_cpts_fifo_pop_event(struct am65_cpts *cpts,
+				     struct am65_cpts_event *event)
+{
+	u32 r = am65_cpts_read32(cpts, intstat_raw);
+
+	if (r & AM65_CPTS_INTSTAT_RAW_TS_PEND) {
+		event->timestamp = am65_cpts_read32(cpts, event_0);
+		event->event1 = am65_cpts_read32(cpts, event_1);
+		event->event2 = am65_cpts_read32(cpts, event_2);
+		event->timestamp |= (u64)am65_cpts_read32(cpts, event_3) << 32;
+		am65_cpts_write32(cpts, AM65_CPTS_EVENT_POP, event_pop);
+		return false;
+	}
+	return true;
+}
+
+static int am65_cpts_fifo_read(struct am65_cpts *cpts)
+{
+	struct ptp_clock_event pevent;
+	struct am65_cpts_event *event;
+	bool schedule = false;
+	int i, type, ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	for (i = 0; i < AM65_CPTS_FIFO_DEPTH; i++) {
+		event = list_first_entry_or_null(&cpts->pool,
+						 struct am65_cpts_event, list);
+
+		if (!event) {
+			if (am65_cpts_cpts_purge_events(cpts)) {
+				dev_err(cpts->dev, "cpts: event pool empty\n");
+				ret = -1;
+				goto out;
+			}
+			continue;
+		}
+
+		if (am65_cpts_fifo_pop_event(cpts, event))
+			break;
+
+		type = am65_cpts_event_get_type(event);
+		switch (type) {
+		case AM65_CPTS_EV_PUSH:
+			cpts->timestamp = event->timestamp;
+			dev_dbg(cpts->dev, "AM65_CPTS_EV_PUSH t:%llu\n",
+				cpts->timestamp);
+			break;
+		case AM65_CPTS_EV_RX:
+		case AM65_CPTS_EV_TX:
+			event->tmo = jiffies +
+				msecs_to_jiffies(AM65_CPTS_EVENT_RX_TX_TIMEOUT);
+
+			list_del_init(&event->list);
+			list_add_tail(&event->list, &cpts->events);
+
+			dev_dbg(cpts->dev,
+				"AM65_CPTS_EV_TX e1:%08x e2:%08x t:%lld\n",
+				event->event1, event->event2,
+				event->timestamp);
+			schedule = true;
+			break;
+		case AM65_CPTS_EV_HW:
+			pevent.index = am65_cpts_event_get_port(event) - 1;
+			pevent.timestamp = event->timestamp;
+			pevent.type = PTP_CLOCK_EXTTS;
+			dev_dbg(cpts->dev, "AM65_CPTS_EV_HW p:%d t:%llu\n",
+				pevent.index, event->timestamp);
+
+			ptp_clock_event(cpts->ptp_clock, &pevent);
+			break;
+		case AM65_CPTS_EV_HOST:
+			break;
+		case AM65_CPTS_EV_ROLL:
+		case AM65_CPTS_EV_HALF:
+		case AM65_CPTS_EV_TS_COMP:
+			dev_dbg(cpts->dev,
+				"AM65_CPTS_EVT: %d e1:%08x e2:%08x t:%lld\n",
+				type,
+				event->event1, event->event2,
+				event->timestamp);
+			break;
+		default:
+			dev_err(cpts->dev, "cpts: unknown event type\n");
+			ret = -1;
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	if (schedule)
+		ptp_schedule_worker(cpts->ptp_clock, 0);
+
+	return ret;
+}
+
+static u64 am65_cpts_gettime(struct am65_cpts *cpts,
+			     struct ptp_system_timestamp *sts)
+{
+	unsigned long flags;
+	u64 val = 0;
+
+	/* temporarily disable cpts interrupt to avoid intentional
+	 * doubled read. Interrupt can be in-flight - it's Ok.
+	 */
+	am65_cpts_write32(cpts, 0, int_enable);
+
+	/* use spin_lock_irqsave() here as it has to run very fast */
+	spin_lock_irqsave(&cpts->lock, flags);
+	ptp_read_system_prets(sts);
+	am65_cpts_write32(cpts, AM65_CPTS_TS_PUSH, ts_push);
+	am65_cpts_read32(cpts, ts_push);
+	ptp_read_system_postts(sts);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	am65_cpts_fifo_read(cpts);
+
+	am65_cpts_write32(cpts, AM65_CPTS_INT_ENABLE_TS_PEND_EN, int_enable);
+
+	val = cpts->timestamp;
+
+	return val;
+}
+
+static irqreturn_t am65_cpts_interrupt(int irq, void *dev_id)
+{
+	struct am65_cpts *cpts = dev_id;
+
+	if (am65_cpts_fifo_read(cpts))
+		dev_dbg(cpts->dev, "cpts: unable to obtain a time stamp\n");
+
+	return IRQ_HANDLED;
+}
+
+/* PTP clock operations */
+static int am65_cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+	int neg_adj = 0;
+	u64 adj_period;
+	u32 val;
+
+	if (ppb < 0) {
+		neg_adj = 1;
+		ppb = -ppb;
+	}
+
+	/* base freq = 1GHz = 1 000 000 000
+	 * ppb_norm = ppb * base_freq / clock_freq;
+	 * ppm_norm = ppb_norm / 1000
+	 * adj_period = 1 000 000 / ppm_norm
+	 * adj_period = 1 000 000 000 / ppb_norm
+	 * adj_period = 1 000 000 000 / (ppb * base_freq / clock_freq)
+	 * adj_period = (1 000 000 000 * clock_freq) / (ppb * base_freq)
+	 * adj_period = clock_freq / ppb
+	 */
+	adj_period = div_u64(cpts->refclk_freq, ppb);
+
+	mutex_lock(&cpts->ptp_clk_lock);
+
+	val = am65_cpts_read32(cpts, control);
+	if (neg_adj)
+		val |= AM65_CPTS_CONTROL_TS_PPM_DIR;
+	else
+		val &= ~AM65_CPTS_CONTROL_TS_PPM_DIR;
+	am65_cpts_write32(cpts, val, control);
+
+	val = upper_32_bits(adj_period) & 0x3FF;
+	am65_cpts_write32(cpts, val, ts_ppm_hi);
+	val = lower_32_bits(adj_period);
+	am65_cpts_write32(cpts, val, ts_ppm_low);
+
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	return 0;
+}
+
+static int am65_cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+	s64 ns;
+
+	mutex_lock(&cpts->ptp_clk_lock);
+	ns = am65_cpts_gettime(cpts, NULL);
+	ns += delta;
+	am65_cpts_settime(cpts, ns);
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	return 0;
+}
+
+static int am65_cpts_ptp_gettimex(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+	u64 ns;
+
+	mutex_lock(&cpts->ptp_clk_lock);
+	ns = am65_cpts_gettime(cpts, sts);
+	mutex_unlock(&cpts->ptp_clk_lock);
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int am65_cpts_ptp_settime(struct ptp_clock_info *ptp,
+				 const struct timespec64 *ts)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+	u64 ns;
+
+	ns = timespec64_to_ns(ts);
+	mutex_lock(&cpts->ptp_clk_lock);
+	am65_cpts_settime(cpts, ns);
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	return 0;
+}
+
+static void am65_cpts_extts_enable_hw(struct am65_cpts *cpts, u32 index, int on)
+{
+	u32 v;
+
+	v = am65_cpts_read32(cpts, control);
+	if (on) {
+		v |= BIT(AM65_CPTS_CONTROL_HW1_TS_PUSH_OFFSET + index);
+		cpts->hw_ts_enable |= BIT(index);
+	} else {
+		v &= ~BIT(AM65_CPTS_CONTROL_HW1_TS_PUSH_OFFSET + index);
+		cpts->hw_ts_enable &= ~BIT(index);
+	}
+	am65_cpts_write32(cpts, v, control);
+}
+
+static int am65_cpts_extts_enable(struct am65_cpts *cpts, u32 index, int on)
+{
+	if (!!(cpts->hw_ts_enable & BIT(index)) == !!on)
+		return 0;
+
+	mutex_lock(&cpts->ptp_clk_lock);
+	am65_cpts_extts_enable_hw(cpts, index, on);
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	dev_dbg(cpts->dev, "%s: ExtTS:%u %s\n",
+		__func__, index, on ? "enabled" : "disabled");
+
+	return 0;
+}
+
+static void am65_cpts_perout_enable_hw(struct am65_cpts *cpts,
+				       struct ptp_perout_request *req, int on)
+{
+	u64 ns_period, ns_start, cycles;
+	struct timespec64 ts;
+	u32 val;
+
+	if (on) {
+		ts.tv_sec = req->period.sec;
+		ts.tv_nsec = req->period.nsec;
+		ns_period = timespec64_to_ns(&ts);
+
+		cycles = (ns_period * cpts->refclk_freq) / NSEC_PER_SEC;
+
+		ts.tv_sec = req->start.sec;
+		ts.tv_nsec = req->start.nsec;
+		ns_start = timespec64_to_ns(&ts);
+
+		val = upper_32_bits(ns_start);
+		am65_cpts_write32(cpts, val, genf[req->index].comp_hi);
+		val = lower_32_bits(ns_start);
+		am65_cpts_write32(cpts, val, genf[req->index].comp_lo);
+		val = lower_32_bits(cycles);
+		am65_cpts_write32(cpts, val, genf[req->index].length);
+
+		cpts->genf_enable |= BIT(req->index);
+	} else {
+		am65_cpts_write32(cpts, 0, genf[req->index].length);
+
+		cpts->genf_enable &= ~BIT(req->index);
+	}
+}
+
+static int am65_cpts_perout_enable(struct am65_cpts *cpts,
+				   struct ptp_perout_request *req, int on)
+{
+	if (!!(cpts->genf_enable & BIT(req->index)) == !!on)
+		return 0;
+
+	mutex_lock(&cpts->ptp_clk_lock);
+	am65_cpts_perout_enable_hw(cpts, req, on);
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	dev_dbg(cpts->dev, "%s: GenF:%u %s\n",
+		__func__, req->index, on ? "enabled" : "disabled");
+
+	return 0;
+}
+
+static int am65_cpts_ptp_enable(struct ptp_clock_info *ptp,
+				struct ptp_clock_request *rq, int on)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+
+	switch (rq->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return am65_cpts_extts_enable(cpts, rq->extts.index, on);
+	case PTP_CLK_REQ_PEROUT:
+		return am65_cpts_perout_enable(cpts, &rq->perout, on);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static long am65_cpts_ts_work(struct ptp_clock_info *ptp);
+
+static struct ptp_clock_info am65_ptp_info = {
+	.owner		= THIS_MODULE,
+	.name		= "CTPS timer",
+	.adjfreq	= am65_cpts_ptp_adjfreq,
+	.adjtime	= am65_cpts_ptp_adjtime,
+	.gettimex64	= am65_cpts_ptp_gettimex,
+	.settime64	= am65_cpts_ptp_settime,
+	.enable		= am65_cpts_ptp_enable,
+	.do_aux_work	= am65_cpts_ts_work,
+};
+
+static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts,
+				  struct am65_cpts_event *event)
+{
+	struct sk_buff_head txq_list;
+	struct sk_buff *skb, *tmp;
+	unsigned long flags;
+	bool found = false;
+	u32 mtype_seqid;
+
+	mtype_seqid = event->event1 &
+		      (AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK |
+		       AM65_CPTS_EVENT_1_EVENT_TYPE_MASK |
+		       AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK);
+
+	__skb_queue_head_init(&txq_list);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice_init(&cpts->txq, &txq_list);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	/* no need to grab txq.lock as access is always done under cpts->lock */
+	skb_queue_walk_safe(&txq_list, skb, tmp) {
+		struct skb_shared_hwtstamps ssh;
+		struct am65_cpts_skb_cb_data *skb_cb =
+					(struct am65_cpts_skb_cb_data *)skb->cb;
+
+		if (mtype_seqid == skb_cb->skb_mtype_seqid) {
+			u64 ns = event->timestamp;
+
+			memset(&ssh, 0, sizeof(ssh));
+			ssh.hwtstamp = ns_to_ktime(ns);
+			skb_tstamp_tx(skb, &ssh);
+			found = true;
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+			dev_dbg(cpts->dev,
+				"match tx timestamp mtype_seqid %08x\n",
+				mtype_seqid);
+			break;
+		}
+
+		if (time_after(jiffies, skb_cb->tmo)) {
+			/* timeout any expired skbs over 100 ms */
+			dev_dbg(cpts->dev,
+				"expiring tx timestamp mtype_seqid %08x\n",
+				mtype_seqid);
+			__skb_unlink(skb, &txq_list);
+			dev_consume_skb_any(skb);
+		}
+	}
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	skb_queue_splice(&txq_list, &cpts->txq);
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	return found;
+}
+
+static void am65_cpts_find_ts(struct am65_cpts *cpts)
+{
+	struct am65_cpts_event *event;
+	struct list_head *this, *next;
+	LIST_HEAD(events_free);
+	unsigned long flags;
+	LIST_HEAD(events);
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_init(&cpts->events, &events);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	list_for_each_safe(this, next, &events) {
+		event = list_entry(this, struct am65_cpts_event, list);
+		if (am65_cpts_match_tx_ts(cpts, event) ||
+		    time_after(jiffies, event->tmo)) {
+			list_del_init(&event->list);
+			list_add(&event->list, &events_free);
+		}
+	}
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	list_splice_tail(&events, &cpts->events);
+	list_splice_tail(&events_free, &cpts->pool);
+	spin_unlock_irqrestore(&cpts->lock, flags);
+}
+
+static long am65_cpts_ts_work(struct ptp_clock_info *ptp)
+{
+	struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info);
+	unsigned long flags;
+	long delay = -1;
+
+	am65_cpts_find_ts(cpts);
+
+	spin_lock_irqsave(&cpts->txq.lock, flags);
+	if (!skb_queue_empty(&cpts->txq))
+		delay = AM65_CPTS_SKB_TX_WORK_TIMEOUT;
+	spin_unlock_irqrestore(&cpts->txq.lock, flags);
+
+	return delay;
+}
+
+/**
+ * am65_cpts_rx_enable - enable rx timestamping
+ * @cpts: cpts handle
+ * @skb: packet
+ *
+ * This functions enables rx packets timestamping. The CPTS can timestamp all
+ * rx packets.
+ */
+void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
+{
+	u32 val;
+
+	mutex_lock(&cpts->ptp_clk_lock);
+	val = am65_cpts_read32(cpts, control);
+	if (en)
+		val |= AM65_CPTS_CONTROL_TSTAMP_EN;
+	else
+		val &= ~AM65_CPTS_CONTROL_TSTAMP_EN;
+	am65_cpts_write32(cpts, val, control);
+	mutex_unlock(&cpts->ptp_clk_lock);
+}
+EXPORT_SYMBOL_GPL(am65_cpts_rx_enable);
+
+static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid)
+{
+	unsigned int ptp_class = ptp_classify_raw(skb);
+	u8 *msgtype, *data = skb->data;
+	unsigned int offset = 0;
+	__be16 *seqid;
+
+	if (ptp_class == PTP_CLASS_NONE)
+		return 0;
+
+	if (ptp_class & PTP_CLASS_VLAN)
+		offset += VLAN_HLEN;
+
+	switch (ptp_class & PTP_CLASS_PMASK) {
+	case PTP_CLASS_IPV4:
+		offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN;
+		break;
+	case PTP_CLASS_IPV6:
+		offset += ETH_HLEN + IP6_HLEN + UDP_HLEN;
+		break;
+	case PTP_CLASS_L2:
+		offset += ETH_HLEN;
+		break;
+	default:
+		return 0;
+	}
+
+	if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid))
+		return 0;
+
+	if (unlikely(ptp_class & PTP_CLASS_V1))
+		msgtype = data + offset + OFF_PTP_CONTROL;
+	else
+		msgtype = data + offset;
+
+	seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+	*mtype_seqid = (*msgtype << AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT) &
+			AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK;
+	*mtype_seqid |= (ntohs(*seqid) & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK);
+
+	return 1;
+}
+
+/**
+ * am65_cpts_tx_timestamp - save tx packet for timestamping
+ * @cpts: cpts handle
+ * @skb: packet
+ *
+ * This functions saves tx packet for timestamping if packet can be timestamped.
+ * The future processing is done in from PTP auxiliary worker.
+ */
+void am65_cpts_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb)
+{
+	struct am65_cpts_skb_cb_data *skb_cb = (void *)skb->cb;
+
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
+		return;
+
+	/* add frame to queue for processing later.
+	 * The periodic FIFO check will handle this.
+	 */
+	skb_get(skb);
+	/* get the timestamp for timeouts */
+	skb_cb->tmo = jiffies + msecs_to_jiffies(100);
+	skb_queue_tail(&cpts->txq, skb);
+	ptp_schedule_worker(cpts->ptp_clock, 0);
+}
+EXPORT_SYMBOL_GPL(am65_cpts_tx_timestamp);
+
+/**
+ * am65_cpts_prep_tx_timestamp - check and prepare tx packet for timestamping
+ * @cpts: cpts handle
+ * @skb: packet
+ *
+ * This functions should be called from .xmit().
+ * It checks if packet can be timestamped, fills internal cpts data
+ * in skb-cb and marks packet as SKBTX_IN_PROGRESS.
+ */
+void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb)
+{
+	struct am65_cpts_skb_cb_data *skb_cb = (void *)skb->cb;
+	int ret;
+
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		return;
+
+	ret = am65_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid);
+	if (!ret)
+		return;
+	skb_cb->skb_mtype_seqid |= (AM65_CPTS_EV_TX <<
+				   AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT);
+
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
+EXPORT_SYMBOL_GPL(am65_cpts_prep_tx_timestamp);
+
+int am65_cpts_phc_index(struct am65_cpts *cpts)
+{
+	return cpts->phc_index;
+}
+EXPORT_SYMBOL_GPL(am65_cpts_phc_index);
+
+static void cpts_free_clk_mux(void *data)
+{
+	struct am65_cpts *cpts = data;
+
+	of_clk_del_provider(cpts->clk_mux_np);
+	clk_hw_unregister_mux(cpts->clk_mux_hw);
+	of_node_put(cpts->clk_mux_np);
+}
+
+static int cpts_of_mux_clk_setup(struct am65_cpts *cpts,
+				 struct device_node *node)
+{
+	unsigned int num_parents;
+	const char **parent_names;
+	char *clk_mux_name;
+	void __iomem *reg;
+	int ret = -EINVAL;
+
+	cpts->clk_mux_np = of_get_child_by_name(node, "refclk-mux");
+	if (!cpts->clk_mux_np)
+		return 0;
+
+	num_parents = of_clk_get_parent_count(cpts->clk_mux_np);
+	if (num_parents < 1) {
+		dev_err(cpts->dev, "mux-clock %pOF must have parents\n",
+			cpts->clk_mux_np);
+		goto mux_fail;
+	}
+
+	parent_names = devm_kcalloc(cpts->dev, sizeof(char *), num_parents,
+				    GFP_KERNEL);
+	if (!parent_names) {
+		ret = -ENOMEM;
+		goto mux_fail;
+	}
+
+	of_clk_parent_fill(cpts->clk_mux_np, parent_names, num_parents);
+
+	clk_mux_name = devm_kasprintf(cpts->dev, GFP_KERNEL, "%s.%pOFn",
+				      dev_name(cpts->dev), cpts->clk_mux_np);
+	if (!clk_mux_name) {
+		ret = -ENOMEM;
+		goto mux_fail;
+	}
+
+	reg = &cpts->reg->rftclk_sel;
+	/* dev must be NULL to avoid recursive incrementing
+	 * of module refcnt
+	 */
+	cpts->clk_mux_hw = clk_hw_register_mux(NULL, clk_mux_name,
+					       parent_names, num_parents,
+					       0, reg, 0, 5, 0, NULL);
+	if (IS_ERR(cpts->clk_mux_hw)) {
+		ret = PTR_ERR(cpts->clk_mux_hw);
+		goto mux_fail;
+	}
+
+	ret = of_clk_add_hw_provider(cpts->clk_mux_np, of_clk_hw_simple_get,
+				     cpts->clk_mux_hw);
+	if (ret)
+		goto clk_hw_register;
+
+	ret = devm_add_action_or_reset(cpts->dev, cpts_free_clk_mux, cpts);
+	if (ret)
+		dev_err(cpts->dev, "failed to add clkmux reset action %d", ret);
+
+	return ret;
+
+clk_hw_register:
+	clk_hw_unregister_mux(cpts->clk_mux_hw);
+mux_fail:
+	of_node_put(cpts->clk_mux_np);
+	return ret;
+}
+
+static int am65_cpts_of_parse(struct am65_cpts *cpts, struct device_node *node)
+{
+	u32 prop[2];
+
+	if (!of_property_read_u32(node, "ti,cpts-ext-ts-inputs", &prop[0]))
+		cpts->ext_ts_inputs = prop[0];
+
+	if (!of_property_read_u32(node, "ti,cpts-periodic-outputs", &prop[0]))
+		cpts->genf_num = prop[0];
+
+	return cpts_of_mux_clk_setup(cpts, node);
+}
+
+static void am65_cpts_release(void *data)
+{
+	struct am65_cpts *cpts = data;
+
+	ptp_clock_unregister(cpts->ptp_clock);
+	am65_cpts_disable(cpts);
+	clk_disable_unprepare(cpts->refclk);
+}
+
+struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs,
+				   struct device_node *node)
+{
+	struct am65_cpts *cpts;
+	int ret, i;
+
+	cpts = devm_kzalloc(dev, sizeof(*cpts), GFP_KERNEL);
+	if (!cpts)
+		return ERR_PTR(-ENOMEM);
+
+	cpts->dev = dev;
+	cpts->reg = (struct am65_cpts_regs __iomem *)regs;
+
+	cpts->irq = of_irq_get_byname(node, "cpts");
+	if (cpts->irq <= 0) {
+		ret = cpts->irq ?: -ENXIO;
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get IRQ number (err = %d)\n",
+				ret);
+		return ERR_PTR(ret);
+	}
+
+	ret = am65_cpts_of_parse(cpts, node);
+	if (ret)
+		return ERR_PTR(ret);
+
+	mutex_init(&cpts->ptp_clk_lock);
+	INIT_LIST_HEAD(&cpts->events);
+	INIT_LIST_HEAD(&cpts->pool);
+	spin_lock_init(&cpts->lock);
+	skb_queue_head_init(&cpts->txq);
+
+	for (i = 0; i < AM65_CPTS_MAX_EVENTS; i++)
+		list_add(&cpts->pool_data[i].list, &cpts->pool);
+
+	cpts->refclk = devm_get_clk_from_child(dev, node, "cpts");
+	if (IS_ERR(cpts->refclk)) {
+		ret = PTR_ERR(cpts->refclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get refclk %d\n", ret);
+		return ERR_PTR(ret);
+	}
+
+	ret = clk_prepare_enable(cpts->refclk);
+	if (ret) {
+		dev_err(dev, "Failed to enable refclk %d\n", ret);
+		return ERR_PTR(ret);
+	}
+
+	cpts->refclk_freq = clk_get_rate(cpts->refclk);
+
+	am65_ptp_info.max_adj = cpts->refclk_freq / AM65_CPTS_MIN_PPM;
+	cpts->ptp_info = am65_ptp_info;
+
+	if (cpts->ext_ts_inputs)
+		cpts->ptp_info.n_ext_ts = cpts->ext_ts_inputs;
+	if (cpts->genf_num)
+		cpts->ptp_info.n_per_out = cpts->genf_num;
+
+	am65_cpts_set_add_val(cpts);
+
+	am65_cpts_write32(cpts, AM65_CPTS_CONTROL_EN | AM65_CPTS_CONTROL_64MODE,
+			  control);
+	am65_cpts_write32(cpts, AM65_CPTS_INT_ENABLE_TS_PEND_EN, int_enable);
+
+	/* set time to the current system time */
+	am65_cpts_settime(cpts, ktime_to_ns(ktime_get_real()));
+
+	cpts->ptp_clock = ptp_clock_register(&cpts->ptp_info, cpts->dev);
+	if (IS_ERR_OR_NULL(cpts->ptp_clock)) {
+		dev_err(dev, "Failed to register ptp clk %ld\n",
+			PTR_ERR(cpts->ptp_clock));
+		if (!cpts->ptp_clock)
+			ret = -ENODEV;
+		goto refclk_disable;
+	}
+	cpts->phc_index = ptp_clock_index(cpts->ptp_clock);
+
+	ret = devm_add_action_or_reset(dev, am65_cpts_release, cpts);
+	if (ret) {
+		dev_err(dev, "failed to add ptpclk reset action %d", ret);
+		return ERR_PTR(ret);
+	}
+
+	ret = devm_request_threaded_irq(dev, cpts->irq, NULL,
+					am65_cpts_interrupt,
+					IRQF_ONESHOT, dev_name(dev), cpts);
+	if (ret < 0) {
+		dev_err(cpts->dev, "error attaching irq %d\n", ret);
+		return ERR_PTR(ret);
+	}
+
+	dev_info(dev, "CPTS ver 0x%08x, freq:%u, add_val:%u\n",
+		 am65_cpts_read32(cpts, idver),
+		 cpts->refclk_freq, cpts->ts_add_val);
+
+	return cpts;
+
+refclk_disable:
+	clk_disable_unprepare(cpts->refclk);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(am65_cpts_create);
+
+static int am65_cpts_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct am65_cpts *cpts;
+	struct resource *res;
+	void __iomem *base;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cpts");
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	cpts = am65_cpts_create(dev, base, node);
+	if (IS_ERR(cpts))
+		return PTR_ERR(cpts);
+
+	return 0;
+}
+
+static const struct of_device_id am65_cpts_of_match[] = {
+	{ .compatible = "ti,am65-cpts", },
+	{ .compatible = "ti,j721e-cpts", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, am65_cpts_of_match);
+
+static struct platform_driver am65_cpts_driver = {
+	.probe		= am65_cpts_probe,
+	.driver		= {
+		.name	= "am65-cpts",
+		.of_match_table = am65_cpts_of_match,
+	},
+};
+module_platform_driver(am65_cpts_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Grygorii Strashko <grygorii.strashko@ti.com>");
+MODULE_DESCRIPTION("TI K3 AM65 CPTS driver");
diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h
new file mode 100644
index 000000000000..0b55dc12ba48
--- /dev/null
+++ b/drivers/net/ethernet/ti/am65-cpts.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* TI K3 AM65 CPTS driver interface
+ *
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
+ */
+
+#ifndef K3_CPTS_H_
+#define K3_CPTS_H_
+
+#include <linux/device.h>
+#include <linux/of.h>
+
+struct am65_cpts;
+
+#if IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)
+struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs,
+				   struct device_node *node);
+int am65_cpts_phc_index(struct am65_cpts *cpts);
+void am65_cpts_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
+void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
+void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en);
+#else
+static inline struct am65_cpts *am65_cpts_create(struct device *dev,
+						 void __iomem *regs,
+						 struct device_node *node)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int am65_cpts_phc_index(struct am65_cpts *cpts)
+{
+	return -1;
+}
+
+static inline void am65_cpts_tx_timestamp(struct am65_cpts *cpts,
+					  struct sk_buff *skb)
+{
+}
+
+static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts,
+					       struct sk_buff *skb)
+{
+}
+
+static inline void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
+{
+}
+#endif
+
+#endif /* K3_CPTS_H_ */
-- 
cgit v1.2.3


From b1f66a5bee07adaab218fb98800928185e5f0f18 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 1 May 2020 23:50:07 +0300
Subject: net: ethernet: ti: am65-cpsw-nuss: enable packet timestamping support

The MCU CPSW Common Platform Time Sync (CPTS) provides possibility to
timestamp TX PTP packets and all RX packets.

This enables corresponding support in TI AM65x/J721E MCU CPSW driver.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig             |   1 +
 drivers/net/ethernet/ti/am65-cpsw-ethtool.c |  24 +++-
 drivers/net/ethernet/ti/am65-cpsw-nuss.c    | 172 ++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/am65-cpsw-nuss.h    |   6 +-
 4 files changed, 201 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 2b7590cece39..69b64620a454 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -100,6 +100,7 @@ config TI_K3_AM65_CPSW_NUSS
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
 	select TI_DAVINCI_MDIO
 	imply PHY_TI_GMII_SEL
+	imply TI_AM65_CPTS
 	help
 	  This driver supports TI K3 AM654/J721E CPSW2G Ethernet SubSystem.
 	  The two-port Gigabit Ethernet MAC (MCU_CPSW0) subsystem provides
diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index c3502aa15ea0..23661a6ed426 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -12,6 +12,7 @@
 
 #include "am65-cpsw-nuss.h"
 #include "cpsw_ale.h"
+#include "am65-cpts.h"
 
 #define AM65_CPSW_REGDUMP_VER 0x1
 
@@ -694,6 +695,27 @@ static void am65_cpsw_get_ethtool_stats(struct net_device *ndev,
 					hw_stats[i].offset);
 }
 
+static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev,
+					 struct ethtool_ts_info *info)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+
+	if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS))
+		return ethtool_op_get_ts_info(ndev, info);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->phc_index = am65_cpts_phc_index(common->cpts);
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+	return 0;
+}
+
 static u32 am65_cpsw_get_ethtool_priv_flags(struct net_device *ndev)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
@@ -730,7 +752,7 @@ const struct ethtool_ops am65_cpsw_ethtool_ops_slave = {
 	.get_sset_count		= am65_cpsw_get_sset_count,
 	.get_strings		= am65_cpsw_get_strings,
 	.get_ethtool_stats	= am65_cpsw_get_ethtool_stats,
-	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_ts_info		= am65_cpsw_get_ethtool_ts_info,
 	.get_priv_flags		= am65_cpsw_get_ethtool_priv_flags,
 	.set_priv_flags		= am65_cpsw_set_ethtool_priv_flags,
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 2bf56733ba94..bb391286d89e 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -30,6 +30,7 @@
 #include "cpsw_sl.h"
 #include "am65-cpsw-nuss.h"
 #include "k3-cppi-desc-pool.h"
+#include "am65-cpts.h"
 
 #define AM65_CPSW_SS_BASE	0x0
 #define AM65_CPSW_SGMII_BASE	0x100
@@ -668,6 +669,18 @@ static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 	dev_kfree_skb_any(skb);
 }
 
+static void am65_cpsw_nuss_rx_ts(struct sk_buff *skb, u32 *psdata)
+{
+	struct skb_shared_hwtstamps *ssh;
+	u64 ns;
+
+	ns = ((u64)psdata[1] << 32) | psdata[0];
+
+	ssh = skb_hwtstamps(skb);
+	memset(ssh, 0, sizeof(*ssh));
+	ssh->hwtstamp = ns_to_ktime(ns);
+}
+
 /* RX psdata[2] word format - checksum information */
 #define AM65_CPSW_RX_PSD_CSUM_ADD	GENMASK(15, 0)
 #define AM65_CPSW_RX_PSD_CSUM_ERR	BIT(16)
@@ -745,6 +758,9 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	skb->dev = ndev;
 
 	psdata = cppi5_hdesc_get_psdata(desc_rx);
+	/* add RX timestamp */
+	if (port->rx_ts_enabled)
+		am65_cpsw_nuss_rx_ts(skb, psdata);
 	csum_info = psdata[2];
 	dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info);
 
@@ -904,6 +920,8 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 
 		ndev = skb->dev;
 
+		am65_cpts_tx_timestamp(common->cpts, skb);
+
 		ndev_priv = netdev_priv(ndev);
 		stats = this_cpu_ptr(ndev_priv->stats);
 		u64_stats_update_begin(&stats->syncp);
@@ -995,6 +1013,10 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	/* padding enabled in hw */
 	pkt_len = skb_headlen(skb);
 
+	/* SKB TX timestamp */
+	if (port->tx_ts_enabled)
+		am65_cpts_prep_tx_timestamp(common->cpts, skb);
+
 	q_idx = skb_get_queue_mapping(skb);
 	dev_dbg(dev, "%s skb_queue:%d\n", __func__, q_idx);
 
@@ -1158,6 +1180,111 @@ static int am65_cpsw_nuss_ndo_slave_set_mac_address(struct net_device *ndev,
 	return 0;
 }
 
+static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
+				       struct ifreq *ifr)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	u32 ts_ctrl, seq_id, ts_ctrl_ltype2, ts_vlan_ltype;
+	struct hwtstamp_config cfg;
+
+	if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS))
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+		return -EFAULT;
+
+	/* TX HW timestamp */
+	switch (cfg.tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (cfg.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		port->rx_ts_enabled = false;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		port->rx_ts_enabled = true;
+		cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	port->tx_ts_enabled = (cfg.tx_type == HWTSTAMP_TX_ON);
+
+	/* cfg TX timestamp */
+	seq_id = (AM65_CPSW_TS_SEQ_ID_OFFSET <<
+		  AM65_CPSW_PN_TS_SEQ_ID_OFFSET_SHIFT) | ETH_P_1588;
+
+	ts_vlan_ltype = ETH_P_8021Q;
+
+	ts_ctrl_ltype2 = ETH_P_1588 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_107 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_129 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_130 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_131 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_132 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_319 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_320 |
+			 AM65_CPSW_PN_TS_CTL_LTYPE2_TS_TTL_NONZERO;
+
+	ts_ctrl = AM65_CPSW_TS_EVENT_MSG_TYPE_BITS <<
+		  AM65_CPSW_PN_TS_CTL_MSG_TYPE_EN_SHIFT;
+
+	if (port->tx_ts_enabled)
+		ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN |
+			   AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN;
+
+	writel(seq_id, port->port_base + AM65_CPSW_PORTN_REG_TS_SEQ_LTYPE_REG);
+	writel(ts_vlan_ltype, port->port_base +
+	       AM65_CPSW_PORTN_REG_TS_VLAN_LTYPE_REG);
+	writel(ts_ctrl_ltype2, port->port_base +
+	       AM65_CPSW_PORTN_REG_TS_CTL_LTYPE2);
+	writel(ts_ctrl, port->port_base + AM65_CPSW_PORTN_REG_TS_CTL);
+
+	/* en/dis RX timestamp */
+	am65_cpts_rx_enable(common->cpts, port->rx_ts_enabled);
+
+	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev,
+				       struct ifreq *ifr)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct hwtstamp_config cfg;
+
+	if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS))
+		return -EOPNOTSUPP;
+
+	cfg.flags = 0;
+	cfg.tx_type = port->tx_ts_enabled ?
+		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg.rx_filter = port->rx_ts_enabled ?
+			HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+
+	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
 static int am65_cpsw_nuss_ndo_slave_ioctl(struct net_device *ndev,
 					  struct ifreq *req, int cmd)
 {
@@ -1166,6 +1293,13 @@ static int am65_cpsw_nuss_ndo_slave_ioctl(struct net_device *ndev,
 	if (!netif_running(ndev))
 		return -EINVAL;
 
+	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		return am65_cpsw_nuss_hwtstamp_set(ndev, req);
+	case SIOCGHWTSTAMP:
+		return am65_cpsw_nuss_hwtstamp_get(ndev, req);
+	}
+
 	if (!port->slave.phy)
 		return -EOPNOTSUPP;
 
@@ -1531,6 +1665,40 @@ static int am65_cpsw_am654_get_efuse_macid(struct device_node *of_node,
 	return 0;
 }
 
+static int am65_cpsw_init_cpts(struct am65_cpsw_common *common)
+{
+	struct device *dev = common->dev;
+	struct device_node *node;
+	struct am65_cpts *cpts;
+	void __iomem *reg_base;
+
+	if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS))
+		return 0;
+
+	node = of_get_child_by_name(dev->of_node, "cpts");
+	if (!node) {
+		dev_err(dev, "%s cpts not found\n", __func__);
+		return -ENOENT;
+	}
+
+	reg_base = common->cpsw_base + AM65_CPSW_NU_CPTS_BASE;
+	cpts = am65_cpts_create(dev, reg_base, node);
+	if (IS_ERR(cpts)) {
+		int ret = PTR_ERR(cpts);
+
+		if (ret == -EOPNOTSUPP) {
+			dev_info(dev, "cpts disabled\n");
+			return 0;
+		}
+
+		dev_err(dev, "cpts create err %d\n", ret);
+		return ret;
+	}
+	common->cpts = cpts;
+
+	return 0;
+}
+
 static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 {
 	struct device_node *node, *port_np;
@@ -1899,6 +2067,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		goto err_of_clear;
 	}
 
+	ret = am65_cpsw_init_cpts(common);
+	if (ret)
+		goto err_of_clear;
+
 	/* init ports */
 	for (i = 0; i < common->port_num; i++)
 		am65_cpsw_nuss_slave_disable_unused(&common->ports[i]);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 41ae5b4c7931..b1cddfd05a45 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -10,6 +10,8 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 
+struct am65_cpts;
+
 #define HOST_PORT_NUM		0
 
 #define AM65_CPSW_MAX_TX_QUEUES	8
@@ -37,6 +39,8 @@ struct am65_cpsw_port {
 	void __iomem			*stat_base;
 	bool				disabled;
 	struct am65_cpsw_slave_data	slave;
+	bool				tx_ts_enabled;
+	bool				rx_ts_enabled;
 };
 
 struct am65_cpsw_host {
@@ -96,8 +100,8 @@ struct am65_cpsw_common {
 
 	u32			nuss_ver;
 	u32			cpsw_ver;
-
 	bool			pf_p0_rx_ptype_rrobin;
+	struct am65_cpts	*cpts;
 };
 
 struct am65_cpsw_ndev_stats {
-- 
cgit v1.2.3


From 1a33e10e4a95cb109ff1145098175df3113313ef Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 2 May 2020 22:22:19 -0700
Subject: net: partially revert dynamic lockdep key changes

This patch reverts the folowing commits:

commit 064ff66e2bef84f1153087612032b5b9eab005bd
"bonding: add missing netdev_update_lockdep_key()"

commit 53d374979ef147ab51f5d632dfe20b14aebeccd0
"net: avoid updating qdisc_xmit_lock_key in netdev_update_lockdep_key()"

commit 1f26c0d3d24125992ab0026b0dab16c08df947c7
"net: fix kernel-doc warning in <linux/netdevice.h>"

commit ab92d68fc22f9afab480153bd82a20f6e2533769
"net: core: add generic lockdep keys"

but keeps the addr_list_lock_key because we still lock
addr_list_lock nestedly on stack devices, unlikely xmit_lock
this is safe because we don't take addr_list_lock on any fast
path.

Reported-and-tested-by: syzbot+aaa6fa4949cc5d9b7b25@syzkaller.appspotmail.com
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c                   |  1 +
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 16 ++++
 drivers/net/hamradio/bpqether.c                   | 20 +++++
 drivers/net/hyperv/netvsc_drv.c                   |  2 +
 drivers/net/ipvlan/ipvlan_main.c                  |  2 +
 drivers/net/macsec.c                              |  2 +
 drivers/net/macvlan.c                             |  2 +
 drivers/net/ppp/ppp_generic.c                     |  2 +
 drivers/net/team/team.c                           |  1 +
 drivers/net/vrf.c                                 |  1 +
 drivers/net/wireless/intersil/hostap/hostap_hw.c  | 22 ++++++
 include/linux/netdevice.h                         | 27 +++++--
 net/8021q/vlan_dev.c                              | 21 ++++++
 net/batman-adv/soft-interface.c                   | 30 ++++++++
 net/bluetooth/6lowpan.c                           |  8 ++
 net/core/dev.c                                    | 90 ++++++++++++++++++-----
 net/dsa/slave.c                                   | 12 +++
 net/ieee802154/6lowpan/core.c                     |  8 ++
 net/l2tp/l2tp_eth.c                               |  1 +
 net/netrom/af_netrom.c                            | 21 ++++++
 net/rose/af_rose.c                                | 21 ++++++
 net/sched/sch_generic.c                           | 17 +++--
 22 files changed, 294 insertions(+), 33 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2e70e43c5df5..d01871321d22 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4898,6 +4898,7 @@ static int bond_init(struct net_device *bond_dev)
 	spin_lock_init(&bond->stats_lock);
 	lockdep_register_key(&bond->stats_lock_key);
 	lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key);
+	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 79d72c88bbef..b3cabc274121 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -299,6 +299,20 @@ static void nfp_repr_clean(struct nfp_repr *repr)
 	nfp_port_free(repr->port);
 }
 
+static struct lock_class_key nfp_repr_netdev_xmit_lock_key;
+
+static void nfp_repr_set_lockdep_class_one(struct net_device *dev,
+					   struct netdev_queue *txq,
+					   void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &nfp_repr_netdev_xmit_lock_key);
+}
+
+static void nfp_repr_set_lockdep_class(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, nfp_repr_set_lockdep_class_one, NULL);
+}
+
 int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  u32 cmsg_port_id, struct nfp_port *port,
 		  struct net_device *pf_netdev)
@@ -308,6 +322,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	u32 repr_cap = nn->tlv_caps.repr_cap;
 	int err;
 
+	nfp_repr_set_lockdep_class(netdev);
+
 	repr->port = port;
 	repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL);
 	if (!repr->dst)
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index fbea6f232819..206688154fdf 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -107,6 +107,25 @@ struct bpqdev {
 
 static LIST_HEAD(bpq_devices);
 
+/*
+ * bpqether network devices are paired with ethernet devices below them, so
+ * form a special "super class" of normal ethernet devices; split their locks
+ * off into a separate class since they always nest.
+ */
+static struct lock_class_key bpq_netdev_xmit_lock_key;
+
+static void bpq_set_lockdep_class_one(struct net_device *dev,
+				      struct netdev_queue *txq,
+				      void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key);
+}
+
+static void bpq_set_lockdep_class(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL);
+}
+
 /* ------------------------------------------------------------------------ */
 
 
@@ -477,6 +496,7 @@ static int bpq_new_device(struct net_device *edev)
 	err = register_netdevice(ndev);
 	if (err)
 		goto error;
+	bpq_set_lockdep_class(ndev);
 
 	/* List protected by RTNL */
 	list_add_rcu(&bpq->bpq_list, &bpq_devices);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d8e86bdbfba1..c0b647a4c893 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2456,6 +2456,8 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
+	netdev_lockdep_set_classes(net);
+
 	/* MTU range: 68 - 1500 or 65521 */
 	net->min_mtu = NETVSC_MTU_MIN;
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index f195f278a83a..15e87c097b0b 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -131,6 +131,8 @@ static int ipvlan_init(struct net_device *dev)
 	dev->gso_max_segs = phy_dev->gso_max_segs;
 	dev->hard_header_len = phy_dev->hard_header_len;
 
+	netdev_lockdep_set_classes(dev);
+
 	ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats);
 	if (!ipvlan->pcpu_stats)
 		return -ENOMEM;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 758baf7cb8a1..ea3f25cc79ef 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4047,6 +4047,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
+	netdev_lockdep_set_classes(dev);
+
 	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
 		goto unregister;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d45600e0a38c..34eb073cdd74 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -890,6 +890,8 @@ static int macvlan_init(struct net_device *dev)
 	dev->gso_max_segs	= lowerdev->gso_max_segs;
 	dev->hard_header_len	= lowerdev->hard_header_len;
 
+	netdev_lockdep_set_classes(dev);
+
 	vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->pcpu_stats)
 		return -ENOMEM;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 22cc2cb9d878..7d005896a0f9 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1410,6 +1410,8 @@ static int ppp_dev_init(struct net_device *dev)
 {
 	struct ppp *ppp;
 
+	netdev_lockdep_set_classes(dev);
+
 	ppp = netdev_priv(dev);
 	/* Let the netdevice take a reference on the ppp file. This ensures
 	 * that ppp_destroy_interface() won't run before the device gets
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 04845a4017f9..8c1e02752ff6 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,6 +1647,7 @@ static int team_init(struct net_device *dev)
 
 	lockdep_register_key(&team->team_lock_key);
 	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 56f8aab46f89..43928a1c2f2a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -867,6 +867,7 @@ static int vrf_dev_init(struct net_device *dev)
 
 	/* similarly, oper state is irrelevant; set to up to avoid confusion */
 	dev->operstate = IF_OPER_UP;
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 out_rth:
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 58212c532c90..aadf3dec5bf3 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -3041,6 +3041,27 @@ static void prism2_clear_set_tim_queue(local_info_t *local)
 	}
 }
 
+
+/*
+ * HostAP uses two layers of net devices, where the inner
+ * layer gets called all the time from the outer layer.
+ * This is a natural nesting, which needs a split lock type.
+ */
+static struct lock_class_key hostap_netdev_xmit_lock_key;
+
+static void prism2_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &hostap_netdev_xmit_lock_key);
+}
+
+static void prism2_set_lockdep_class(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL);
+}
+
 static struct net_device *
 prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx,
 		       struct device *sdev)
@@ -3199,6 +3220,7 @@ while (0)
 	if (ret >= 0)
 		ret = register_netdevice(dev);
 
+	prism2_set_lockdep_class(dev);
 	rtnl_unlock();
 	if (ret < 0) {
 		printk(KERN_WARNING "%s: register netdevice failed!\n",
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5a8d40f1ffe2..7725efd6e48a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1805,13 +1805,11 @@ enum netdev_priv_flags {
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
- *	@qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock
- *				spinlock
- *	@qdisc_running_key:	lockdep class annotating Qdisc->running seqcount
- *	@qdisc_xmit_lock_key:	lockdep class annotating
- *				netdev_queue->_xmit_lock spinlock
+ *
  *	@addr_list_lock_key:	lockdep class annotating
  *				net_device->addr_list_lock spinlock
+ *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
+ *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -2112,10 +2110,9 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
-	struct lock_class_key	qdisc_tx_busylock_key;
-	struct lock_class_key	qdisc_running_key;
-	struct lock_class_key	qdisc_xmit_lock_key;
 	struct lock_class_key	addr_list_lock_key;
+	struct lock_class_key	*qdisc_tx_busylock;
+	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
 	unsigned		wol_enabled:1;
 
@@ -2200,6 +2197,20 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_running_key;		\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	(dev)->qdisc_running_key = &qdisc_running_key;		\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 990b9fde28c6..319220b2341d 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -489,6 +489,25 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
+/*
+ * vlan network devices have devices nesting below it, and are a special
+ * "super class" of normal network devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key vlan_netdev_xmit_lock_key;
+
+static void vlan_dev_set_lockdep_one(struct net_device *dev,
+				     struct netdev_queue *txq,
+				     void *unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key);
+}
+
+static void vlan_dev_set_lockdep_class(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL);
+}
+
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.parse	 = eth_header_parse,
@@ -579,6 +598,8 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
+	vlan_dev_set_lockdep_class(dev);
+
 	vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->vlan_pcpu_stats)
 		return -ENOMEM;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5f05a728f347..822af540b854 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -739,6 +739,34 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
 	return 0;
 }
 
+/* batman-adv network devices have devices nesting below it and are a special
+ * "super class" of normal network devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key batadv_netdev_xmit_lock_key;
+
+/**
+ * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue
+ * @dev: device which owns the tx queue
+ * @txq: tx queue to modify
+ * @_unused: always NULL
+ */
+static void batadv_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key);
+}
+
+/**
+ * batadv_set_lockdep_class() - Set txq and addr_list lockdep class
+ * @dev: network device to modify
+ */
+static void batadv_set_lockdep_class(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL);
+}
+
 /**
  * batadv_softif_init_late() - late stage initialization of soft interface
  * @dev: registered network device to modify
@@ -752,6 +780,8 @@ static int batadv_softif_init_late(struct net_device *dev)
 	int ret;
 	size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM;
 
+	batadv_set_lockdep_class(dev);
+
 	bat_priv = netdev_priv(dev);
 	bat_priv->soft_iface = dev;
 
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 4febc82a7c76..bb55d92691b0 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -571,7 +571,15 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return err < 0 ? NET_XMIT_DROP : err;
 }
 
+static int bt_dev_init(struct net_device *dev)
+{
+	netdev_lockdep_set_classes(dev);
+
+	return 0;
+}
+
 static const struct net_device_ops netdev_ops = {
+	.ndo_init		= bt_dev_init,
 	.ndo_start_xmit		= bt_xmit,
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index afff16849c26..f8d83922a6af 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -398,6 +398,74 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
 DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
+#ifdef CONFIG_LOCKDEP
+/*
+ * register_netdevice() inits txq->_xmit_lock and sets lockdep class
+ * according to dev->type
+ */
+static const unsigned short netdev_lock_type[] = {
+	 ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
+	 ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
+	 ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
+	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
+	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
+	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
+	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
+	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
+	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
+	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
+	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
+	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
+	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
+	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
+	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
+
+static const char *const netdev_lock_name[] = {
+	"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
+	"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
+	"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
+	"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
+	"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
+	"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
+	"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
+	"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
+	"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
+	"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
+	"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
+	"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
+	"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
+	"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
+	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
+
+static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
+
+static inline unsigned short netdev_lock_pos(unsigned short dev_type)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
+		if (netdev_lock_type[i] == dev_type)
+			return i;
+	/* the last key is used by default */
+	return ARRAY_SIZE(netdev_lock_type) - 1;
+}
+
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+						 unsigned short dev_type)
+{
+	int i;
+
+	i = netdev_lock_pos(dev_type);
+	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
+				   netdev_lock_name[i]);
+}
+#else
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+						 unsigned short dev_type)
+{
+}
+#endif
+
 /*******************************************************************************
  *
  *		Protocol management and registration routines
@@ -9208,7 +9276,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 {
 	/* Initialize queue lock */
 	spin_lock_init(&queue->_xmit_lock);
-	lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
+	netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
 	queue->xmit_lock_owner = -1;
 	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
 	queue->dev = dev;
@@ -9255,22 +9323,6 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
-static void netdev_register_lockdep_key(struct net_device *dev)
-{
-	lockdep_register_key(&dev->qdisc_tx_busylock_key);
-	lockdep_register_key(&dev->qdisc_running_key);
-	lockdep_register_key(&dev->qdisc_xmit_lock_key);
-	lockdep_register_key(&dev->addr_list_lock_key);
-}
-
-static void netdev_unregister_lockdep_key(struct net_device *dev)
-{
-	lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
-	lockdep_unregister_key(&dev->qdisc_running_key);
-	lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-}
-
 void netdev_update_lockdep_key(struct net_device *dev)
 {
 	lockdep_unregister_key(&dev->addr_list_lock_key);
@@ -9837,7 +9889,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	netdev_register_lockdep_key(dev);
+	lockdep_register_key(&dev->addr_list_lock_key);
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
@@ -9926,7 +9978,7 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->xdp_bulkq);
 	dev->xdp_bulkq = NULL;
 
-	netdev_unregister_lockdep_key(dev);
+	lockdep_unregister_key(&dev->addr_list_lock_key);
 
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ba8bf90dc0cc..fa2634043751 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1671,6 +1671,15 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
 	return ret;
 }
 
+static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
+static void dsa_slave_set_lockdep_class_one(struct net_device *dev,
+					    struct netdev_queue *txq,
+					    void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &dsa_slave_netdev_xmit_lock_key);
+}
+
 int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
@@ -1754,6 +1763,9 @@ int dsa_slave_create(struct dsa_port *port)
 		slave_dev->max_mtu = ETH_MAX_MTU;
 	SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
 
+	netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
+				 NULL);
+
 	SET_NETDEV_DEV(slave_dev, port->ds->dev);
 	slave_dev->dev.of_node = port->dn;
 	slave_dev->vlan_features = master->vlan_features;
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index c0b107cdd715..3297e7fa9945 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -58,6 +58,13 @@ static const struct header_ops lowpan_header_ops = {
 	.create	= lowpan_header_create,
 };
 
+static int lowpan_dev_init(struct net_device *ldev)
+{
+	netdev_lockdep_set_classes(ldev);
+
+	return 0;
+}
+
 static int lowpan_open(struct net_device *dev)
 {
 	if (!open_count)
@@ -89,6 +96,7 @@ static int lowpan_get_iflink(const struct net_device *dev)
 }
 
 static const struct net_device_ops lowpan_netdev_ops = {
+	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_open		= lowpan_open,
 	.ndo_stop		= lowpan_stop,
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index d3b520b9b2c9..fd5ac2788e45 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -56,6 +56,7 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 {
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 }
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 7b1a74f74aad..eccc7d366e17 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -63,6 +63,26 @@ static DEFINE_SPINLOCK(nr_list_lock);
 
 static const struct proto_ops nr_proto_ops;
 
+/*
+ * NETROM network devices are virtual network devices encapsulating NETROM
+ * frames into AX.25 which will be sent through an AX.25 device, so form a
+ * special "super class" of normal net devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key nr_netdev_xmit_lock_key;
+
+static void nr_set_lockdep_one(struct net_device *dev,
+			       struct netdev_queue *txq,
+			       void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key);
+}
+
+static void nr_set_lockdep_key(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL);
+}
+
 /*
  *	Socket removal during an interrupt is now safe.
  */
@@ -1394,6 +1414,7 @@ static int __init nr_proto_init(void)
 			free_netdev(dev);
 			goto fail;
 		}
+		nr_set_lockdep_key(dev);
 		dev_nr[i] = dev;
 	}
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 1e8eeb044b07..e7a872207b46 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -64,6 +64,26 @@ static const struct proto_ops rose_proto_ops;
 
 ax25_address rose_callsign;
 
+/*
+ * ROSE network devices are virtual network devices encapsulating ROSE
+ * frames into AX.25 which will be sent through an AX.25 device, so form a
+ * special "super class" of normal net devices; split their locks off into a
+ * separate class since they always nest.
+ */
+static struct lock_class_key rose_netdev_xmit_lock_key;
+
+static void rose_set_lockdep_one(struct net_device *dev,
+				 struct netdev_queue *txq,
+				 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock, &rose_netdev_xmit_lock_key);
+}
+
+static void rose_set_lockdep_key(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL);
+}
+
 /*
  *	Convert a ROSE address into text.
  */
@@ -1511,6 +1531,7 @@ static int __init rose_proto_init(void)
 			free_netdev(dev);
 			goto fail;
 		}
+		rose_set_lockdep_key(dev);
 		dev_rose[i] = dev;
 	}
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index ad24fa1a51e6..ebc55d884247 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -794,6 +794,9 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 };
 EXPORT_SYMBOL(pfifo_fast_ops);
 
+static struct lock_class_key qdisc_tx_busylock;
+static struct lock_class_key qdisc_running_key;
+
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack)
@@ -846,9 +849,17 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	}
 
 	spin_lock_init(&sch->busylock);
+	lockdep_set_class(&sch->busylock,
+			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
 	/* seqlock has the same scope of busylock, for NOLOCK qdisc */
 	spin_lock_init(&sch->seqlock);
+	lockdep_set_class(&sch->busylock,
+			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
 	seqcount_init(&sch->running);
+	lockdep_set_class(&sch->running,
+			  dev->qdisc_running_key ?: &qdisc_running_key);
 
 	sch->ops = ops;
 	sch->flags = ops->static_flags;
@@ -859,12 +870,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	dev_hold(dev);
 	refcount_set(&sch->refcnt, 1);
 
-	if (sch != &noop_qdisc) {
-		lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key);
-		lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key);
-		lockdep_set_class(&sch->running, &dev->qdisc_running_key);
-	}
-
 	return sch;
 errout1:
 	kfree(p);
-- 
cgit v1.2.3


From 09f6c44aaae0f1bdb8b983d7762676d5018c53bc Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 5 May 2020 10:49:20 +0800
Subject: net: allwinner: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type. And emac_start_xmit() can
leak one skb if 'channel' == 3.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/allwinner/sun4i-emac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 18d3b4340bd4..b3b8a8010142 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -417,7 +417,7 @@ static void emac_timeout(struct net_device *dev, unsigned int txqueue)
 /* Hardware start transmission.
  * Send a packet to media from the upper layer.
  */
-static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
 	unsigned long channel;
@@ -425,7 +425,7 @@ static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	channel = db->tx_fifo_stat & 3;
 	if (channel == 3)
-		return 1;
+		return NETDEV_TX_BUSY;
 
 	channel = (channel == 1 ? 1 : 0);
 
-- 
cgit v1.2.3


From ab99b7d2ae6e33077045e92b5ca173635c7eceef Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 5 May 2020 11:06:45 +0800
Subject: net: altera: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/altera/altera_tse_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 1671c1f36691..907125abef2c 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -554,7 +554,7 @@ static irqreturn_t altera_isr(int irq, void *dev_id)
  * physically contiguous fragment starting at
  * skb->data, for length of skb_headlen(skb).
  */
-static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
 	unsigned int txsize = priv->tx_ring_size;
@@ -562,7 +562,7 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct tse_buffer *buffer = NULL;
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	unsigned int nopaged_len = skb_headlen(skb);
-	enum netdev_tx ret = NETDEV_TX_OK;
+	netdev_tx_t ret = NETDEV_TX_OK;
 	dma_addr_t dma_addr;
 
 	spin_lock_bh(&priv->tx_lock);
-- 
cgit v1.2.3


From 58618ef85546726cf27c38ddc1b022c703b7a6ad Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 5 May 2020 11:22:20 +0800
Subject: net: nxp: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/nxp/lpc_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 311454d9b0bc..d3cbb4215f5c 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1030,7 +1030,8 @@ static int lpc_eth_close(struct net_device *ndev)
 	return 0;
 }
 
-static int lpc_eth_hard_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t lpc_eth_hard_start_xmit(struct sk_buff *skb,
+					   struct net_device *ndev)
 {
 	struct netdata_local *pldat = netdev_priv(ndev);
 	u32 len, txidx;
-- 
cgit v1.2.3


From 3e1853e4e1137ba0a4d314521d153852dbf4aff5 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 5 May 2020 13:57:49 +0800
Subject: net: emac: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/emac/emac-mac.c | 5 +++--
 drivers/net/ethernet/qualcomm/emac/emac-mac.h | 5 +++--
 drivers/net/ethernet/qualcomm/emac/emac.c     | 3 ++-
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 251d4ac4af02..117188e3c7de 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -1431,8 +1431,9 @@ error:
 }
 
 /* Transmit the packet using specified transmit queue */
-int emac_mac_tx_buf_send(struct emac_adapter *adpt, struct emac_tx_queue *tx_q,
-			 struct sk_buff *skb)
+netdev_tx_t emac_mac_tx_buf_send(struct emac_adapter *adpt,
+				 struct emac_tx_queue *tx_q,
+				 struct sk_buff *skb)
 {
 	struct emac_tpd tpd;
 	u32 prod_idx;
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.h b/drivers/net/ethernet/qualcomm/emac/emac-mac.h
index ae08bdd9046c..920123eb8ace 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.h
@@ -227,8 +227,9 @@ void emac_mac_stop(struct emac_adapter *adpt);
 void emac_mac_mode_config(struct emac_adapter *adpt);
 void emac_mac_rx_process(struct emac_adapter *adpt, struct emac_rx_queue *rx_q,
 			 int *num_pkts, int max_pkts);
-int emac_mac_tx_buf_send(struct emac_adapter *adpt, struct emac_tx_queue *tx_q,
-			 struct sk_buff *skb);
+netdev_tx_t emac_mac_tx_buf_send(struct emac_adapter *adpt,
+				 struct emac_tx_queue *tx_q,
+				 struct sk_buff *skb);
 void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q);
 void emac_mac_rx_tx_ring_init_all(struct platform_device *pdev,
 				  struct emac_adapter *adpt);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 18b0c7a2d6dc..20b1b43a0e39 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -115,7 +115,8 @@ static int emac_napi_rtx(struct napi_struct *napi, int budget)
 }
 
 /* Transmit the packet */
-static int emac_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t emac_start_xmit(struct sk_buff *skb,
+				   struct net_device *netdev)
 {
 	struct emac_adapter *adpt = netdev_priv(netdev);
 
-- 
cgit v1.2.3


From d9a1c584a93a90ecd24fca775a68d113fda05576 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:43:49 +0800
Subject: qlcnic: use true,false for bool variable in qlcnic_sriov_common.c

Fix the following coccicheck warning:

drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c:1585:3-25:
WARNING: Assignment of 0/1 to bool variable
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c:1588:3-25:
WARNING: Assignment of 0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index f7c2f32237cb..7adbb03cb931 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -1582,10 +1582,10 @@ void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
 		if (mode == VPORT_MISS_MODE_ACCEPT_ALL &&
 		    !adapter->fdb_mac_learn) {
 			qlcnic_alloc_lb_filters_mem(adapter);
-			adapter->drv_mac_learn = 1;
+			adapter->drv_mac_learn = true;
 			adapter->rx_mac_learn = true;
 		} else {
-			adapter->drv_mac_learn = 0;
+			adapter->drv_mac_learn = false;
 			adapter->rx_mac_learn = false;
 		}
 	}
-- 
cgit v1.2.3


From 66b63a60d7ea9f589a9cdc404057d8072930962d Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:44:00 +0800
Subject: bnx2x: Remove Comparison to bool in bnx2x_dcb.c

Fix the following coccicheck warning:

drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c:1548:17-31: WARNING:
Comparison to bool
drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c:1148:16-24: WARNING:
Comparison to bool
drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c:1158:30-38: WARNING:
Comparison to bool

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 2c6ba046d2a8..17ae6df90723 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -1145,7 +1145,7 @@ static void bnx2x_dcbx_get_num_pg_traf_type(struct bnx2x *bp,
 					break;
 				}
 			}
-			if (false == pg_found) {
+			if (!pg_found) {
 				data[help_data->num_of_pg].pg = add_pg;
 				data[help_data->num_of_pg].pg_priority =
 						(1 << ttp[add_traf_type]);
@@ -1155,7 +1155,7 @@ static void bnx2x_dcbx_get_num_pg_traf_type(struct bnx2x *bp,
 		}
 		DP(BNX2X_MSG_DCB,
 		   "add_traf_type %d pg_found %s num_of_pg %d\n",
-		   add_traf_type, (false == pg_found) ? "NO" : "YES",
+		   add_traf_type, !pg_found ? "NO" : "YES",
 		   help_data->num_of_pg);
 	}
 }
@@ -1544,8 +1544,7 @@ static void bnx2x_dcbx_2cos_limit_cee_three_pg_to_cos_params(
 			if (pg_entry < DCBX_MAX_NUM_PG_BW_ENTRIES) {
 				entry = 0;
 
-				if (i == (num_of_pri-1) &&
-				    false == b_found_strict)
+				if (i == (num_of_pri-1) && !b_found_strict)
 					/* last entry will be handled separately
 					 * If no priority is strict than last
 					 * entry goes to last queue.
-- 
cgit v1.2.3


From 93e6044bd1cb635c3a07dc1b8471bc965feb9b04 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:45:39 +0800
Subject: net: qede: Use true for bool variable in qede_init_fp()

Fix the following coccicheck warning:

drivers/net/ethernet/qlogic/qede/qede_main.c:1717:5-19: WARNING:
Assignment of 0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 9b456198cb50..256506024b88 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1714,7 +1714,7 @@ static void qede_init_fp(struct qede_dev *edev)
 				txq->ndev_txq_id = ndev_tx_id;
 
 				if (edev->dev_info.is_legacy)
-					txq->is_legacy = 1;
+					txq->is_legacy = true;
 				txq->dev = &edev->pdev->dev;
 			}
 
-- 
cgit v1.2.3


From e8cc063d83106bc6855c07db0001e8d01cbd8b3e Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:45:46 +0800
Subject: net: atheros: remove conversion to bool in atl1c_start_mac()

No need to convert '==' expression to bool. This fixes the following
coccicheck warning:

drivers/net/ethernet/atheros/atl1c/atl1c_main.c:1189:63-68: WARNING:
conversion to bool not needed here

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 00bd7bd55794..04bc53af12d9 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1186,7 +1186,7 @@ static void atl1c_start_mac(struct atl1c_adapter *adapter)
 	struct atl1c_hw *hw = &adapter->hw;
 	u32 mac, txq, rxq;
 
-	hw->mac_duplex = adapter->link_duplex == FULL_DUPLEX ? true : false;
+	hw->mac_duplex = adapter->link_duplex == FULL_DUPLEX;
 	hw->mac_speed = adapter->link_speed == SPEED_1000 ?
 		atl1c_mac_speed_1000 : atl1c_mac_speed_10_100;
 
-- 
cgit v1.2.3


From ec161116ad554fec2e87215da93db48b5767f323 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:45:56 +0800
Subject: net: agere: use true,false for bool variable

Fix the following coccicheck warning:

drivers/net/ethernet/agere/et131x.c:717:3-22: WARNING: Assignment of
0/1 to bool variable
drivers/net/ethernet/agere/et131x.c:721:1-20: WARNING: Assignment of
0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Acked-by: Mark Einon <mark.einon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/agere/et131x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 1b19385ad8a9..865892c1f23f 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -714,11 +714,11 @@ static int et131x_init_eeprom(struct et131x_adapter *adapter)
 			 * gather additional information that normally would
 			 * come from the eeprom, like MAC Address
 			 */
-			adapter->has_eeprom = 0;
+			adapter->has_eeprom = false;
 			return -EIO;
 		}
 	}
-	adapter->has_eeprom = 1;
+	adapter->has_eeprom = true;
 
 	/* Read the EEPROM for information regarding LED behavior. Refer to
 	 * et131x_xcvr_init() for its use.
-- 
cgit v1.2.3


From ba42580019560ed9c54f87c3c4e852ce26869c5d Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:46:08 +0800
Subject: net: bnxt: Remove Comparison to bool in bnxt_ethtool.c

Fix the following coccicheck warning:

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:1991:5-46: WARNING:
Comparison to bool
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:1993:10-54: WARNING:
Comparison to bool
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2380:5-38: WARNING:
Comparison to bool

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 07526868f7be..dd0c3f227009 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2095,9 +2095,9 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev,
 			   rc, filename);
 		return rc;
 	}
-	if (bnxt_dir_type_is_ape_bin_format(dir_type) == true)
+	if (bnxt_dir_type_is_ape_bin_format(dir_type))
 		rc = bnxt_flash_firmware(dev, dir_type, fw->data, fw->size);
-	else if (bnxt_dir_type_is_other_exec_format(dir_type) == true)
+	else if (bnxt_dir_type_is_other_exec_format(dir_type))
 		rc = bnxt_flash_microcode(dev, dir_type, fw->data, fw->size);
 	else
 		rc = bnxt_flash_nvram(dev, dir_type, BNX_DIR_ORDINAL_FIRST,
@@ -2484,7 +2484,7 @@ static int bnxt_set_eeprom(struct net_device *dev,
 	}
 
 	/* Create or re-write an NVM item: */
-	if (bnxt_dir_type_is_executable(type) == true)
+	if (bnxt_dir_type_is_executable(type))
 		return -EOPNOTSUPP;
 	ext = eeprom->magic & 0xffff;
 	ordinal = eeprom->offset >> 16;
-- 
cgit v1.2.3


From d192ae55382dceb5f782b5a2d70ebc887a410305 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:46:23 +0800
Subject: net: ethernet: ti: use true, false for bool variables in cpsw_new.c

Fix the following coccicheck warning:

drivers/net/ethernet/ti/cpsw_new.c:1924:2-17: WARNING: Assignment of
0/1 to bool variable
drivers/net/ethernet/ti/cpsw_new.c:1231:1-16: WARNING: Assignment of
0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_new.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 33c8dd686206..dce49311d3d3 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1228,7 +1228,7 @@ static int cpsw_probe_dt(struct cpsw_common *cpsw)
 	data->active_slave = 0;
 	data->channels = CPSW_MAX_QUEUES;
 	data->ale_entries = CPSW_ALE_NUM_ENTRIES;
-	data->dual_emac = 1;
+	data->dual_emac = true;
 	data->bd_ram_size = CPSW_BD_RAM_SIZE;
 	data->mac_control = 0;
 
@@ -1921,7 +1921,7 @@ static int cpsw_probe(struct platform_device *pdev)
 
 	soc = soc_device_match(cpsw_soc_devices);
 	if (soc)
-		cpsw->quirk_irq = 1;
+		cpsw->quirk_irq = true;
 
 	cpsw->rx_packet_max = rx_packet_max;
 	cpsw->descs_pool_size = descs_pool_size;
-- 
cgit v1.2.3


From 015cba7e369e91656ed31afbadce044a10fa0fab Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 5 May 2020 15:59:26 +0800
Subject: net: ni: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ni/nixge.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 2fdd0753b3af..d2708a57f2ff 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -502,7 +502,8 @@ static int nixge_check_tx_bd_space(struct nixge_priv *priv,
 	return 0;
 }
 
-static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t nixge_start_xmit(struct sk_buff *skb,
+				    struct net_device *ndev)
 {
 	struct nixge_priv *priv = netdev_priv(ndev);
 	struct nixge_hw_dma_bd *cur_p;
-- 
cgit v1.2.3


From e94caac1bc0b628b14dd6d81a94315cd880d6150 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:31:56 +0800
Subject: net: tehuti: remove unused inline function bdx_tx_db_size

There's no callers in-tree anymore.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/tehuti/tehuti.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 40a2ce0ca808..e28727297563 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1362,18 +1362,6 @@ static void print_rxfd(struct rxf_desc *rxfd)
  * As our benchmarks shows, it adds 1.5 Gbit/sec to NIS's throuput.
  */
 
-/*************************************************************************
- *     Tx DB                                                             *
- *************************************************************************/
-static inline int bdx_tx_db_size(struct txdb *db)
-{
-	int taken = db->wptr - db->rptr;
-	if (taken < 0)
-		taken = db->size + 1 + taken;	/* (size + 1) equals memsz */
-
-	return db->size - taken;
-}
-
 /**
  * __bdx_tx_db_ptr_next - helper function, increment read/write pointer + wrap
  * @db: tx data base
-- 
cgit v1.2.3


From 7a4d40ddf1fa2d78e0a144a6bde9bf783682fba7 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:33:12 +0800
Subject: net: sun: cassini: Remove unused inline functions

There's no callers in-tree anymore.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/cassini.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 3ee6ab104cb9..e6e25960da4f 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -237,12 +237,6 @@ static inline void cas_lock_tx(struct cas *cp)
 		spin_lock_nested(&cp->tx_lock[i], i);
 }
 
-static inline void cas_lock_all(struct cas *cp)
-{
-	spin_lock_irq(&cp->lock);
-	cas_lock_tx(cp);
-}
-
 /* WTZ: QA was finding deadlock problems with the previous
  * versions after long test runs with multiple cards per machine.
  * See if replacing cas_lock_all with safer versions helps. The
@@ -266,12 +260,6 @@ static inline void cas_unlock_tx(struct cas *cp)
 		spin_unlock(&cp->tx_lock[i - 1]);
 }
 
-static inline void cas_unlock_all(struct cas *cp)
-{
-	cas_unlock_tx(cp);
-	spin_unlock_irq(&cp->lock);
-}
-
 #define cas_unlock_all_restore(cp, flags) \
 do { \
 	struct cas *xxxcp = (cp); \
-- 
cgit v1.2.3


From 12dcceb39aabcc199461f2fdc3ff81be0cd7003e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:40:37 +0800
Subject: net: mv643xx_eth: Remove unused inline function sum16_as_be

commit 84411f73b884 ("net: mv643xx_eth: Avoid setting the initial TCP checksum")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mv643xx_eth.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 81d24481b22c..4d4b6243318a 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -666,11 +666,6 @@ static inline unsigned int has_tiny_unaligned_frags(struct sk_buff *skb)
 	return 0;
 }
 
-static inline __be16 sum16_as_be(__sum16 sum)
-{
-	return (__force __be16)sum;
-}
-
 static int skb_tx_csum(struct mv643xx_eth_private *mp, struct sk_buff *skb,
 		       u16 *l4i_chk, u32 *command, int length)
 {
-- 
cgit v1.2.3


From d66e67bd4cc76626253bd51ee034bbbaede4e9ba Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:42:56 +0800
Subject: net: stmmac: Remove unused inline function stmmac_rx_threshold_count

There's no caller in-tree since
commit 2af6106ae949 ("net: stmmac: Introducing support for Page Pool")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ff22f274aa43..90bddca1ddd8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3543,15 +3543,6 @@ static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb)
 	}
 }
 
-
-static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q)
-{
-	if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH)
-		return 0;
-
-	return 1;
-}
-
 /**
  * stmmac_rx_refill - refill used skb preallocated buffers
  * @priv: driver private structure
-- 
cgit v1.2.3


From 9f410c2cb7371c2645f6a8cd39cea0e62e391570 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:43:39 +0800
Subject: myri10ge: Remove unused inline function myri10ge_vlan_ip_csum

commit 4ca3221fe4b6 ("myri10ge: Convert from LRO to GRO")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 2616fd735aab..e1e1f4e3639e 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1174,18 +1174,6 @@ myri10ge_submit_8rx(struct mcp_kreq_ether_recv __iomem * dst,
 	mb();
 }
 
-static inline void myri10ge_vlan_ip_csum(struct sk_buff *skb, __wsum hw_csum)
-{
-	struct vlan_hdr *vh = (struct vlan_hdr *)(skb->data);
-
-	if ((skb->protocol == htons(ETH_P_8021Q)) &&
-	    (vh->h_vlan_encapsulated_proto == htons(ETH_P_IP) ||
-	     vh->h_vlan_encapsulated_proto == htons(ETH_P_IPV6))) {
-		skb->csum = hw_csum;
-		skb->ip_summed = CHECKSUM_COMPLETE;
-	}
-}
-
 static void
 myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 			int bytes, int watchdog)
-- 
cgit v1.2.3


From b16751f7adae1d1b6beae0a44cd45d65715ddbf2 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:44:21 +0800
Subject: net: microchip: Remove unused inline function is_bits_set

There's no callers in-tree.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/encx24j600-regmap.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c
index 1f496fac7033..5bd7fb917b7a 100644
--- a/drivers/net/ethernet/microchip/encx24j600-regmap.c
+++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c
@@ -17,11 +17,6 @@
 
 #include "encx24j600_hw.h"
 
-static inline bool is_bits_set(int value, int mask)
-{
-	return (value & mask) == mask;
-}
-
 static int encx24j600_switch_bank(struct encx24j600_context *ctx,
 				  int bank)
 {
-- 
cgit v1.2.3


From e36cac0c056404c7c595c91773a93dd01aacc367 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:50:09 +0800
Subject: bnx2x: Remove unused inline function bnx2x_vf_vlan_credit

commit 05cc5a39ddb7 ("bnx2x: add vlan filtering offload")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 21 ---------------------
 1 file changed, 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 5097a44686b3..b4476f44e386 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -331,27 +331,6 @@ bnx2x_vf_set_igu_info(struct bnx2x *bp, u8 igu_sb_id, u8 abs_vfid)
 	BP_VFDB(bp)->vf_sbs_pool++;
 }
 
-static inline void bnx2x_vf_vlan_credit(struct bnx2x *bp,
-					struct bnx2x_vlan_mac_obj *obj,
-					atomic_t *counter)
-{
-	struct list_head *pos;
-	int read_lock;
-	int cnt = 0;
-
-	read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj);
-	if (read_lock)
-		DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n");
-
-	list_for_each(pos, &obj->head)
-		cnt++;
-
-	if (!read_lock)
-		bnx2x_vlan_mac_h_read_unlock(bp, obj);
-
-	atomic_set(counter, cnt);
-}
-
 static int bnx2x_vf_vlan_mac_clear(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				   int qid, bool drv_only, int type)
 {
-- 
cgit v1.2.3


From 730f135104f3afe320d0df4c53c28d6ad9d17d6b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 5 May 2020 15:34:00 +0200
Subject: cxgb4/cxgb4vf: Remove superfluous void * cast in
 debugfs_create_file() call

There is no need to cast a typed pointer to a void pointer when calling
a function that accepts the latter.  Remove it, as the cast prevents
further compiler checks.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 9cc3541a7e1c..cec865a97464 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2480,7 +2480,7 @@ static int setup_debugfs(struct adapter *adapter)
 	for (i = 0; i < ARRAY_SIZE(debugfs_files); i++)
 		debugfs_create_file(debugfs_files[i].name,
 				    debugfs_files[i].mode,
-				    adapter->debugfs_root, (void *)adapter,
+				    adapter->debugfs_root, adapter,
 				    debugfs_files[i].fops);
 
 	return 0;
-- 
cgit v1.2.3


From 01241aa000ab0a685062a448b0d7d97f470f446f Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 5 May 2020 19:21:23 +0300
Subject: net: ethernet: ti: am65-cpts: fix build

It's possible to have build configuration which will force PTP_1588_CLOCK=m
and so TI_K3_AM65_CPTS=m while still have TI_K3_AM65_CPSW_NUSS=y. This will
cause build failures:

aarch64-linux-gnu-ld: ../drivers/net/ethernet/ti/am65-cpsw-nuss.o: in function `am65_cpsw_init_cpts':
../drivers/net/ethernet/ti/am65-cpsw-nuss.c:1685: undefined reference to `am65_cpts_create'
aarch64-linux-gnu-ld: ../drivers/net/ethernet/ti/am65-cpsw-nuss.c:1685:(.text+0x2e20):
relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `am65_cpts_create'

Fix it by adding dependencies from CPTS in TI_K3_AM65_CPSW_NUSS as below:
   config TI_K3_AM65_CPSW_NUSS
   ...
     depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS

Note. This will create below dependencies and for NFS boot + CPTS all of them
have to be built-in.
  PTP_1588_CLOCK -> TI_K3_AM65_CPTS -> TI_K3_AM65_CPSW_NUSS

While here, clean up TI_K3_AM65_CPTS definition.

Fixes: b1f66a5bee07 ("net: ethernet: ti: am65-cpsw-nuss: enable packet timestamping support")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 69b64620a454..519f5a8c5810 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -100,7 +100,7 @@ config TI_K3_AM65_CPSW_NUSS
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
 	select TI_DAVINCI_MDIO
 	imply PHY_TI_GMII_SEL
-	imply TI_AM65_CPTS
+	depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS
 	help
 	  This driver supports TI K3 AM654/J721E CPSW2G Ethernet SubSystem.
 	  The two-port Gigabit Ethernet MAC (MCU_CPSW0) subsystem provides
@@ -113,9 +113,8 @@ config TI_K3_AM65_CPSW_NUSS
 
 config TI_K3_AM65_CPTS
 	tristate "TI K3 AM65x CPTS"
-	depends on ARCH_K3 && OF && PTP_1588_CLOCK
+	depends on ARCH_K3 && OF
 	depends on PTP_1588_CLOCK
-	select NET_PTP_CLASSIFY
 	help
 	  Say y here to support the TI K3 AM65x CPTS with 1588 features such as
 	  PTP hardware clock for each CPTS device and network packets
-- 
cgit v1.2.3


From bbae62e32ee9ef3995cb72e565dd8790a6858de2 Mon Sep 17 00:00:00 2001
From: Samuel Zou <zou_wei@huawei.com>
Date: Wed, 6 May 2020 10:54:58 +0800
Subject: net: ethernet: ti: Use PTR_ERR_OR_ZERO() to simplify code

Fixes coccicheck warning:

drivers/net/ethernet/ti/am65-cpts.c:1017:1-3: WARNING: PTR_ERR_OR_ZERO can be used

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Samuel Zou <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpts.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index 370162c86e7f..51c94b2a77b1 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -1014,10 +1014,7 @@ static int am65_cpts_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	cpts = am65_cpts_create(dev, base, node);
-	if (IS_ERR(cpts))
-		return PTR_ERR(cpts);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(cpts);
 }
 
 static const struct of_device_id am65_cpts_of_match[] = {
-- 
cgit v1.2.3


From cadb5c4e394da0fc13e4d46ad7c1445d60dc175f Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 14:10:41 +0800
Subject: net: cortina: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 5bff5c2be88b..8d13ea370db1 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1224,7 +1224,8 @@ map_error:
 	return -ENOMEM;
 }
 
-static int gmac_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t gmac_start_xmit(struct sk_buff *skb,
+				   struct net_device *netdev)
 {
 	struct gemini_ethernet_port *port = netdev_priv(netdev);
 	unsigned short m = (1 << port->txq_order) - 1;
-- 
cgit v1.2.3


From f9cbf19c7f5d92e3e91727b6dff6e43b1d6a62a3 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Wed, 6 May 2020 14:16:30 +0800
Subject: net: mlx4: remove unneeded variable "err" in mlx4_en_get_rxfh()

Fix the following coccicheck warning:

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c:1238:5-8: Unneeded
variable: "err". Return "0" on line 1252

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 8a5ea2543670..216e6b2e9eed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1235,7 +1235,6 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u32 n = mlx4_en_get_rxfh_indir_size(dev);
 	u32 i, rss_rings;
-	int err = 0;
 
 	rss_rings = priv->prof->rss_rings ?: n;
 	rss_rings = rounddown_pow_of_two(rss_rings);
@@ -1249,7 +1248,7 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
 	if (hfunc)
 		*hfunc = priv->rss_hash_fn;
-	return err;
+	return 0;
 }
 
 static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
-- 
cgit v1.2.3


From 2f8649900b7d0dced6aff0765ea15e874a91b73c Mon Sep 17 00:00:00 2001
From: Samuel Zou <zou_wei@huawei.com>
Date: Wed, 6 May 2020 14:27:30 +0800
Subject: net: ethernet: mediatek: Make mtk_m32 static

Fix the following sparse warning:

drivers/net/ethernet/mediatek/mtk_eth_soc.c:68:5: warning:
symbol 'mtk_m32' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Samuel Zou <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 09047109d0da..2822268220f7 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -65,7 +65,7 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg)
 	return __raw_readl(eth->base + reg);
 }
 
-u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
+static u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
 {
 	u32 val;
 
-- 
cgit v1.2.3


From 1f3e915e316c4393ce940ab184c176b7202f3ff7 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 17:25:14 +0800
Subject: net: renesas: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 8ed73f44405d..f45331ed90b0 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2472,7 +2472,8 @@ static void sh_eth_tx_timeout(struct net_device *ndev, unsigned int txqueue)
 }
 
 /* Packet transmit function */
-static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t sh_eth_start_xmit(struct sk_buff *skb,
+				     struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	struct sh_eth_txdesc *txdesc;
-- 
cgit v1.2.3


From d54fc481bd828afee199e4853020c5ecd9d79778 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 19:04:59 +0800
Subject: net: socionext: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/sni_ave.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 67ddf782d98a..f2638446b62e 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1394,7 +1394,7 @@ static int ave_stop(struct net_device *ndev)
 	return 0;
 }
 
-static int ave_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t ave_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct ave_private *priv = netdev_priv(ndev);
 	u32 proc_idx, done_idx, ndesc, cmdsts;
-- 
cgit v1.2.3


From e910a3993818ab69fcb9d791cbbe07bb153c0660 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 19:13:08 +0800
Subject: net: mediatek: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 2822268220f7..f6a1f8666f95 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1122,7 +1122,7 @@ static void mtk_stop_queue(struct mtk_eth *eth)
 	}
 }
 
-static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
-- 
cgit v1.2.3


From df1577cbaa87d8a29bf18f41d2ba82668d59d106 Mon Sep 17 00:00:00 2001
From: ChenTao <chentao107@huawei.com>
Date: Wed, 6 May 2020 19:22:17 +0800
Subject: net: enetc: Make some symbols static

Fix the following warning:

drivers/net/ethernet/freescale/enetc/enetc_qos.c:427:20: warning:
symbol 'enetc_act_fwd' was not declared. Should it be static?
drivers/net/ethernet/freescale/enetc/enetc_qos.c:966:20: warning:
symbol 'enetc_check_flow_actions' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: ChenTao <chentao107@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_qos.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 48e589e9d0f7..172acb602ccb 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -424,7 +424,7 @@ struct enetc_psfp {
 	spinlock_t psfp_lock; /* spinlock for the struct enetc_psfp r/w */
 };
 
-struct actions_fwd enetc_act_fwd[] = {
+static struct actions_fwd enetc_act_fwd[] = {
 	{
 		BIT(FLOW_ACTION_GATE),
 		BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS),
@@ -963,7 +963,8 @@ revert_sid:
 	return err;
 }
 
-struct actions_fwd *enetc_check_flow_actions(u64 acts, unsigned int inputkeys)
+static struct actions_fwd *enetc_check_flow_actions(u64 acts,
+						    unsigned int inputkeys)
 {
 	int i;
 
-- 
cgit v1.2.3


From 1cfecc2353c24b37eea69d9b9a606ca9f473f9bc Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 19:38:46 +0800
Subject: net: lantiq: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 900affbdcc0e..1645e4e7ebdb 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -276,7 +276,8 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 	return pkts;
 }
 
-static int xrx200_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
+static netdev_tx_t xrx200_start_xmit(struct sk_buff *skb,
+				     struct net_device *net_dev)
 {
 	struct xrx200_priv *priv = netdev_priv(net_dev);
 	struct xrx200_chan *ch = &priv->chan_tx;
-- 
cgit v1.2.3


From 10786531cf996d0d1a0f901d9d559eb947013ac3 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 20:10:28 +0800
Subject: net: moxa: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/moxa/moxart_ether.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index e1651756bf9d..1b25cc42f442 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -331,14 +331,15 @@ static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
+					 struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
 	void *desc;
 	unsigned int len;
 	unsigned int tx_head;
 	u32 txdes1;
-	int ret = NETDEV_TX_BUSY;
+	netdev_tx_t ret = NETDEV_TX_BUSY;
 
 	spin_lock_irq(&priv->txlock);
 
-- 
cgit v1.2.3


From 787e4a79cd5ffc46fe5fa1ce9464e79143423ac0 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 20:21:45 +0800
Subject: net: cpmac: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index a530afe3ce12..c20715107075 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -532,7 +532,7 @@ fatal_error:
 
 }
 
-static int cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	int queue;
 	unsigned int len;
-- 
cgit v1.2.3


From 9532131f6995002e88390b8b6572a44531c1fae0 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Wed, 6 May 2020 20:55:52 +0800
Subject: net: 7990: Fix use correct return type for ndo_start_xmit()

The method ndo_start_xmit() returns a value of type netdev_tx_t. Fix
the ndo function to use the correct type.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/7990.c | 2 +-
 drivers/net/ethernet/amd/7990.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c
index cf3562e82ca9..50fb66369415 100644
--- a/drivers/net/ethernet/amd/7990.c
+++ b/drivers/net/ethernet/amd/7990.c
@@ -536,7 +536,7 @@ void lance_tx_timeout(struct net_device *dev, unsigned int txqueue)
 }
 EXPORT_SYMBOL_GPL(lance_tx_timeout);
 
-int lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
+netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct lance_private *lp = netdev_priv(dev);
 	volatile struct lance_init_block *ib = lp->init_block;
diff --git a/drivers/net/ethernet/amd/7990.h b/drivers/net/ethernet/amd/7990.h
index 8266b3c1fefc..e53551daeea1 100644
--- a/drivers/net/ethernet/amd/7990.h
+++ b/drivers/net/ethernet/amd/7990.h
@@ -241,7 +241,7 @@ struct lance_private {
 /* Now the prototypes we export */
 int lance_open(struct net_device *dev);
 int lance_close(struct net_device *dev);
-int lance_start_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev);
 void lance_set_multicast(struct net_device *dev);
 void lance_tx_timeout(struct net_device *dev, unsigned int txqueue);
 #ifdef CONFIG_NET_POLL_CONTROLLER
-- 
cgit v1.2.3


From d6836ef02c1726c4c5f1cb712a9abdcd5f8fcd14 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 May 2020 23:29:12 +0200
Subject: r8169: use fsleep in polling functions

Use new flexible sleep function fsleep() to merge the udelay and msleep
polling functions. We can safely do this because no polling function
is used in atomic context in this driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 108 ++++++++++++------------------
 1 file changed, 44 insertions(+), 64 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2f6512ed0a78..f06dbc9a046d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -724,55 +724,35 @@ struct rtl_cond {
 	const char *msg;
 };
 
-static void rtl_udelay(unsigned int d)
-{
-	udelay(d);
-}
-
 static bool rtl_loop_wait(struct rtl8169_private *tp, const struct rtl_cond *c,
-			  void (*delay)(unsigned int), unsigned int d, int n,
-			  bool high)
+			  unsigned long usecs, int n, bool high)
 {
 	int i;
 
 	for (i = 0; i < n; i++) {
 		if (c->check(tp) == high)
 			return true;
-		delay(d);
+		fsleep(usecs);
 	}
 
 	if (net_ratelimit())
-		netdev_err(tp->dev, "%s == %d (loop: %d, delay: %d).\n",
-			   c->msg, !high, n, d);
+		netdev_err(tp->dev, "%s == %d (loop: %d, delay: %lu).\n",
+			   c->msg, !high, n, usecs);
 	return false;
 }
 
-static bool rtl_udelay_loop_wait_high(struct rtl8169_private *tp,
-				      const struct rtl_cond *c,
-				      unsigned int d, int n)
-{
-	return rtl_loop_wait(tp, c, rtl_udelay, d, n, true);
-}
-
-static bool rtl_udelay_loop_wait_low(struct rtl8169_private *tp,
-				     const struct rtl_cond *c,
-				     unsigned int d, int n)
-{
-	return rtl_loop_wait(tp, c, rtl_udelay, d, n, false);
-}
-
-static bool rtl_msleep_loop_wait_high(struct rtl8169_private *tp,
-				      const struct rtl_cond *c,
-				      unsigned int d, int n)
+static bool rtl_loop_wait_high(struct rtl8169_private *tp,
+			       const struct rtl_cond *c,
+			       unsigned long d, int n)
 {
-	return rtl_loop_wait(tp, c, msleep, d, n, true);
+	return rtl_loop_wait(tp, c, d, n, true);
 }
 
-static bool rtl_msleep_loop_wait_low(struct rtl8169_private *tp,
-				     const struct rtl_cond *c,
-				     unsigned int d, int n)
+static bool rtl_loop_wait_low(struct rtl8169_private *tp,
+			      const struct rtl_cond *c,
+			      unsigned long d, int n)
 {
-	return rtl_loop_wait(tp, c, msleep, d, n, false);
+	return rtl_loop_wait(tp, c, d, n, false);
 }
 
 #define DECLARE_RTL_COND(name)				\
@@ -807,7 +787,7 @@ static void r8168_phy_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
 
 	RTL_W32(tp, GPHY_OCP, OCPAR_FLAG | (reg << 15) | data);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_ocp_gphy_cond, 25, 10);
+	rtl_loop_wait_low(tp, &rtl_ocp_gphy_cond, 25, 10);
 }
 
 static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
@@ -817,7 +797,7 @@ static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
 
 	RTL_W32(tp, GPHY_OCP, reg << 15);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_ocp_gphy_cond, 25, 10) ?
+	return rtl_loop_wait_high(tp, &rtl_ocp_gphy_cond, 25, 10) ?
 		(RTL_R32(tp, GPHY_OCP) & 0xffff) : -ETIMEDOUT;
 }
 
@@ -895,7 +875,7 @@ static void r8169_mdio_write(struct rtl8169_private *tp, int reg, int value)
 {
 	RTL_W32(tp, PHYAR, 0x80000000 | (reg & 0x1f) << 16 | (value & 0xffff));
 
-	rtl_udelay_loop_wait_low(tp, &rtl_phyar_cond, 25, 20);
+	rtl_loop_wait_low(tp, &rtl_phyar_cond, 25, 20);
 	/*
 	 * According to hardware specs a 20us delay is required after write
 	 * complete indication, but before sending next command.
@@ -909,7 +889,7 @@ static int r8169_mdio_read(struct rtl8169_private *tp, int reg)
 
 	RTL_W32(tp, PHYAR, 0x0 | (reg & 0x1f) << 16);
 
-	value = rtl_udelay_loop_wait_high(tp, &rtl_phyar_cond, 25, 20) ?
+	value = rtl_loop_wait_high(tp, &rtl_phyar_cond, 25, 20) ?
 		RTL_R32(tp, PHYAR) & 0xffff : -ETIMEDOUT;
 
 	/*
@@ -932,7 +912,7 @@ static void r8168dp_1_mdio_access(struct rtl8169_private *tp, int reg, u32 data)
 	RTL_W32(tp, OCPAR, OCPAR_GPHY_WRITE_CMD);
 	RTL_W32(tp, EPHY_RXER_NUM, 0);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_ocpar_cond, 1000, 100);
+	rtl_loop_wait_low(tp, &rtl_ocpar_cond, 1000, 100);
 }
 
 static void r8168dp_1_mdio_write(struct rtl8169_private *tp, int reg, int value)
@@ -949,7 +929,7 @@ static int r8168dp_1_mdio_read(struct rtl8169_private *tp, int reg)
 	RTL_W32(tp, OCPAR, OCPAR_GPHY_READ_CMD);
 	RTL_W32(tp, EPHY_RXER_NUM, 0);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_ocpar_cond, 1000, 100) ?
+	return rtl_loop_wait_high(tp, &rtl_ocpar_cond, 1000, 100) ?
 		RTL_R32(tp, OCPDR) & OCPDR_DATA_MASK : -ETIMEDOUT;
 }
 
@@ -1035,7 +1015,7 @@ static void rtl_ephy_write(struct rtl8169_private *tp, int reg_addr, int value)
 	RTL_W32(tp, EPHYAR, EPHYAR_WRITE_CMD | (value & EPHYAR_DATA_MASK) |
 		(reg_addr & EPHYAR_REG_MASK) << EPHYAR_REG_SHIFT);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_ephyar_cond, 10, 100);
+	rtl_loop_wait_low(tp, &rtl_ephyar_cond, 10, 100);
 
 	udelay(10);
 }
@@ -1044,7 +1024,7 @@ static u16 rtl_ephy_read(struct rtl8169_private *tp, int reg_addr)
 {
 	RTL_W32(tp, EPHYAR, (reg_addr & EPHYAR_REG_MASK) << EPHYAR_REG_SHIFT);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_ephyar_cond, 10, 100) ?
+	return rtl_loop_wait_high(tp, &rtl_ephyar_cond, 10, 100) ?
 		RTL_R32(tp, EPHYAR) & EPHYAR_DATA_MASK : ~0;
 }
 
@@ -1060,7 +1040,7 @@ static void _rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 	RTL_W32(tp, ERIDR, val);
 	RTL_W32(tp, ERIAR, ERIAR_WRITE_CMD | type | mask | addr);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_eriar_cond, 100, 100);
+	rtl_loop_wait_low(tp, &rtl_eriar_cond, 100, 100);
 }
 
 static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
@@ -1073,7 +1053,7 @@ static u32 _rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
 {
 	RTL_W32(tp, ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_eriar_cond, 100, 100) ?
+	return rtl_loop_wait_high(tp, &rtl_eriar_cond, 100, 100) ?
 		RTL_R32(tp, ERIDR) : ~0;
 }
 
@@ -1106,7 +1086,7 @@ static void rtl_eri_clear_bits(struct rtl8169_private *tp, int addr, u32 mask,
 static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
 {
 	RTL_W32(tp, OCPAR, ((u32)mask & 0x0f) << 12 | (reg & 0x0fff));
-	return rtl_udelay_loop_wait_high(tp, &rtl_ocpar_cond, 100, 20) ?
+	return rtl_loop_wait_high(tp, &rtl_ocpar_cond, 100, 20) ?
 		RTL_R32(tp, OCPDR) : ~0;
 }
 
@@ -1120,7 +1100,7 @@ static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 {
 	RTL_W32(tp, OCPDR, data);
 	RTL_W32(tp, OCPAR, OCPAR_FLAG | ((u32)mask & 0x0f) << 12 | (reg & 0x0fff));
-	rtl_udelay_loop_wait_low(tp, &rtl_ocpar_cond, 100, 20);
+	rtl_loop_wait_low(tp, &rtl_ocpar_cond, 100, 20);
 }
 
 static void r8168ep_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
@@ -1168,7 +1148,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond)
 static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, IBCR2, RTL_R8(tp, IBCR2) & ~0x01);
-	rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000);
+	rtl_loop_wait_high(tp, &rtl_ocp_tx_cond, 50000, 2000);
 	RTL_W8(tp, IBISR0, RTL_R8(tp, IBISR0) | 0x20);
 	RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01);
 }
@@ -1176,7 +1156,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 static void rtl8168dp_driver_start(struct rtl8169_private *tp)
 {
 	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START);
-	rtl_msleep_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10, 10);
+	rtl_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10);
 }
 
 static void rtl8168ep_driver_start(struct rtl8169_private *tp)
@@ -1184,7 +1164,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
 	r8168ep_ocp_write(tp, 0x01, 0x30,
 			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
-	rtl_msleep_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10, 10);
+	rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10);
 }
 
 static void rtl8168_driver_start(struct rtl8169_private *tp)
@@ -1207,7 +1187,7 @@ static void rtl8168_driver_start(struct rtl8169_private *tp)
 static void rtl8168dp_driver_stop(struct rtl8169_private *tp)
 {
 	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP);
-	rtl_msleep_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10, 10);
+	rtl_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10);
 }
 
 static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
@@ -1216,7 +1196,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
 	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
 	r8168ep_ocp_write(tp, 0x01, 0x30,
 			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
-	rtl_msleep_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10, 10);
+	rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10);
 }
 
 static void rtl8168_driver_stop(struct rtl8169_private *tp)
@@ -1277,7 +1257,7 @@ u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr)
 {
 	RTL_W32(tp, EFUSEAR, (reg_addr & EFUSEAR_REG_MASK) << EFUSEAR_REG_SHIFT);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_efusear_cond, 100, 300) ?
+	return rtl_loop_wait_high(tp, &rtl_efusear_cond, 100, 300) ?
 		RTL_R32(tp, EFUSEAR) & EFUSEAR_DATA_MASK : ~0;
 }
 
@@ -1614,7 +1594,7 @@ static void rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd)
 	RTL_W32(tp, CounterAddrLow, cmd);
 	RTL_W32(tp, CounterAddrLow, cmd | counter_cmd);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
+	rtl_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
 }
 
 static void rtl8169_reset_counters(struct rtl8169_private *tp)
@@ -2471,7 +2451,7 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, ChipCmd, CmdReset);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
+	rtl_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
 }
 
 static void rtl_request_firmware(struct rtl8169_private *tp)
@@ -2525,12 +2505,12 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_27:
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
-		rtl_udelay_loop_wait_low(tp, &rtl_npq_cond, 20, 42*42);
+		rtl_loop_wait_low(tp, &rtl_npq_cond, 20, 2000);
 		break;
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
-		rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
+		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
 	default:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
@@ -2640,7 +2620,7 @@ static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value)
 	RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
 		CSIAR_BYTE_ENABLE | func << 16);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100);
+	rtl_loop_wait_low(tp, &rtl_csiar_cond, 10, 100);
 }
 
 static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
@@ -2650,7 +2630,7 @@ static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
 	RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | func << 16 |
 		CSIAR_BYTE_ENABLE);
 
-	return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ?
+	return rtl_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ?
 		RTL_R32(tp, CSIDR) : ~0;
 }
 
@@ -3605,7 +3585,7 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 
 	r8168_mac_ocp_write(tp, 0xe098, 0xc302);
 
-	rtl_udelay_loop_wait_low(tp, &rtl_mac_ocp_e00e_cond, 1000, 10);
+	rtl_loop_wait_low(tp, &rtl_mac_ocp_e00e_cond, 1000, 10);
 
 	rtl8125_config_eee_mac(tp);
 
@@ -5148,10 +5128,10 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42))
+	if (!rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42))
 		return;
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
+	if (!rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
 		return;
 
 	RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb));
@@ -5160,19 +5140,19 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 
 	r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0);
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
+	if (!rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
 		return;
 
 	r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15));
 
-	rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
+	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
 }
 
 static void rtl_hw_init_8125(struct rtl8169_private *tp)
 {
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
+	if (!rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
 		return;
 
 	RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb));
@@ -5181,14 +5161,14 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp)
 
 	r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0);
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
+	if (!rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
 		return;
 
 	r8168_mac_ocp_write(tp, 0xc0aa, 0x07d0);
 	r8168_mac_ocp_write(tp, 0xc0a6, 0x0150);
 	r8168_mac_ocp_write(tp, 0xc01e, 0x5555);
 
-	rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
+	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
 }
 
 static void rtl_hw_initialize(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From f9a98f901e19eb0fbd61c29cf38b75d210d276bc Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 7 May 2020 19:08:36 +0800
Subject: net: atheros: remove dead code in atl1c_resume()

This code has been marked dead for nearly 10 years. Remove it.

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 04bc53af12d9..decab9a8e4a8 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2449,12 +2449,6 @@ static int atl1c_resume(struct device *dev)
 	atl1c_reset_mac(&adapter->hw);
 	atl1c_phy_init(&adapter->hw);
 
-#if 0
-	AT_READ_REG(&adapter->hw, REG_PM_CTRLSTAT, &pm_data);
-	pm_data &= ~PM_CTRLSTAT_PME_EN;
-	AT_WRITE_REG(&adapter->hw, REG_PM_CTRLSTAT, pm_data);
-#endif
-
 	netif_device_attach(netdev);
 	if (netif_running(netdev))
 		atl1c_up(adapter);
-- 
cgit v1.2.3


From 27ad2cd2000298e5822a12012edda47d72fdb27e Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 7 May 2020 19:08:47 +0800
Subject: net: tulip: de4x5: make PCI_signature() return void

This function always return 0 now, we can make it return void to
simplify the code. This fixes the following coccicheck warning:

drivers/net/ethernet/dec/tulip/de4x5.c:3908:11-17: Unneeded variable:
"status". Return "0" on line 3912

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index f16853c3c851..0ccd9994ad45 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -951,7 +951,7 @@ static void    reset_init_sia(struct net_device *dev, s32 sicr, s32 strr, s32 si
 static int     test_ans(struct net_device *dev, s32 irqs, s32 irq_mask, s32 msec);
 static int     test_tp(struct net_device *dev, s32 msec);
 static int     EISA_signature(char *name, struct device *device);
-static int     PCI_signature(char *name, struct de4x5_private *lp);
+static void    PCI_signature(char *name, struct de4x5_private *lp);
 static void    DevicePresent(struct net_device *dev, u_long iobase);
 static void    enet_addr_rst(u_long aprom_addr);
 static int     de4x5_bad_srom(struct de4x5_private *lp);
@@ -3902,14 +3902,14 @@ EISA_signature(char *name, struct device *device)
 /*
 ** Look for a particular board name in the PCI configuration space
 */
-static int
+static void
 PCI_signature(char *name, struct de4x5_private *lp)
 {
-    int i, status = 0, siglen = ARRAY_SIZE(de4x5_signatures);
+    int i, siglen = ARRAY_SIZE(de4x5_signatures);
 
     if (lp->chipset == DC21040) {
 	strcpy(name, "DE434/5");
-	return status;
+	return;
     } else {                           /* Search for a DEC name in the SROM */
 	int tmp = *((char *)&lp->srom + 19) * 3;
 	strncpy(name, (char *)&lp->srom + 26 + tmp, 8);
@@ -3935,8 +3935,6 @@ PCI_signature(char *name, struct de4x5_private *lp)
     } else if ((lp->chipset & ~0x00ff) == DC2114x) {
 	lp->useSROM = true;
     }
-
-    return status;
 }
 
 /*
-- 
cgit v1.2.3


From 5a7c45097c3f63ac10def7206292b88023205a3e Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 7 May 2020 19:08:57 +0800
Subject: net: mlx4: remove unneeded variable "err" in
 mlx4_en_ethtool_add_mac_rule()

Fix the following coccicheck warning:

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c:1396:5-8: Unneeded
variable: "err". Return "0" on line 1411

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 216e6b2e9eed..b816154bc79a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1392,7 +1392,6 @@ static int mlx4_en_ethtool_add_mac_rule(struct ethtool_rxnfc *cmd,
 					struct mlx4_spec_list *spec_l2,
 					unsigned char *mac)
 {
-	int err = 0;
 	__be64 mac_msk = cpu_to_be64(MLX4_MAC_MASK << 16);
 
 	spec_l2->id = MLX4_NET_TRANS_RULE_ID_ETH;
@@ -1407,7 +1406,7 @@ static int mlx4_en_ethtool_add_mac_rule(struct ethtool_rxnfc *cmd,
 
 	list_add_tail(&spec_l2->list, rule_list_h);
 
-	return err;
+	return 0;
 }
 
 static int mlx4_en_ethtool_add_mac_rule_by_ipv4(struct mlx4_en_priv *priv,
-- 
cgit v1.2.3


From 7f960633a458136d168f2049508d39cba8be55bd Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 7 May 2020 19:09:05 +0800
Subject: net: encx24j600: make encx24j600_hw_init() return void

This function always return 0 now, we can make it return void to
simplify the code. This fixes the following coccicheck warning:

drivers/net/ethernet/microchip/encx24j600.c:609:5-8: Unneeded variable:
"ret". Return "0" on line 653

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/encx24j600.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index 39925e4bf2ec..fccc4805247f 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -604,9 +604,8 @@ static void encx24j600_set_rxfilter_mode(struct encx24j600_priv *priv)
 	}
 }
 
-static int encx24j600_hw_init(struct encx24j600_priv *priv)
+static void encx24j600_hw_init(struct encx24j600_priv *priv)
 {
-	int ret = 0;
 	u16 macon2;
 
 	priv->hw_enabled = false;
@@ -649,8 +648,6 @@ static int encx24j600_hw_init(struct encx24j600_priv *priv)
 
 	if (netif_msg_hw(priv))
 		encx24j600_dump_config(priv, "Hw is initialized");
-
-	return ret;
 }
 
 static void encx24j600_hw_enable(struct encx24j600_priv *priv)
@@ -1042,12 +1039,7 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 	}
 
 	/* Initialize the device HW to the consistent state */
-	if (encx24j600_hw_init(priv)) {
-		netif_err(priv, probe, ndev,
-			  DRV_NAME ": HW initialization error\n");
-		ret = -EIO;
-		goto out_free;
-	}
+	encx24j600_hw_init(priv);
 
 	kthread_init_worker(&priv->kworker);
 	kthread_init_work(&priv->tx_work, encx24j600_tx_proc);
-- 
cgit v1.2.3


From 571cf29644542b9e410ed102cb35ecb27b4fdfa3 Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Thu, 7 May 2020 18:57:38 +0800
Subject: net:enetc: bug fix for qos sfi operate space after freed

'Dan Carpenter' reported:
This code frees "sfi" and then dereferences it on the next line:
>                 kfree(sfi);
>                 clear_bit(sfi->index, epsfp.psfp_sfi_bitmap);

This "sfi->index" should be "index".

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Po Liu <Po.Liu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_qos.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 172acb602ccb..fd3df19eaa32 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -903,7 +903,7 @@ static void stream_filter_unref(struct enetc_ndev_priv *priv, u32 index)
 		enetc_streamfilter_hw_set(priv, sfi, false);
 		hlist_del(&sfi->node);
 		kfree(sfi);
-		clear_bit(sfi->index, epsfp.psfp_sfi_bitmap);
+		clear_bit(index, epsfp.psfp_sfi_bitmap);
 	}
 }
 
-- 
cgit v1.2.3


From 0932969e0b1b6ba54028b35b80148302e8fe7db8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 7 May 2020 13:42:05 +0200
Subject: via-rhine: Add platform dependencies

The VIA Rhine Ethernet interface is only present on PCI devices or
VIA/WonderMedia VT8500/WM85xx SoCs.  Add platform dependencies to the
VIA_RHINE config symbol, to avoid asking the user about it when
configuring a kernel without PCI or VT8500/WM85xx support.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/via/Kconfig | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index a962097b58c6..6cff5f7d57c4 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -19,6 +19,7 @@ if NET_VENDOR_VIA
 config VIA_RHINE
 	tristate "VIA Rhine support"
 	depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP)
+	depends on PCI || ARCH_VT8500 || COMPILE_TEST
 	depends on HAS_DMA
 	select CRC32
 	select MII
-- 
cgit v1.2.3


From bb206a0869b7f1e7c853d7b94e91510c321402c7 Mon Sep 17 00:00:00 2001
From: Chen Zhou <chenzhou10@huawei.com>
Date: Thu, 7 May 2020 21:26:39 +0800
Subject: cxgb4: remove duplicate headers

Remove duplicate headers which are included twice.

Signed-off-by: Chen Zhou <chenzhou10@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index e46a14f44a6f..30d25a37fc3b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -466,8 +466,6 @@ static inline struct mbox_cmd *mbox_cmd_log_entry(struct mbox_cmd_log *log,
 	return &((struct mbox_cmd *)&(log)[1])[entry_idx];
 }
 
-#include "t4fw_api.h"
-
 #define FW_VERSION(chip) ( \
 		FW_HDR_FW_VER_MAJOR_G(chip##FW_VERSION_MAJOR) | \
 		FW_HDR_FW_VER_MINOR_G(chip##FW_VERSION_MINOR) | \
-- 
cgit v1.2.3


From 38c440b24052cad3fa6dcbc32bf8e132da3fe55d Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 6 May 2020 20:47:17 +0300
Subject: dpaa2-eth: create a function to flush the XDP fds

Create an independent function that takes a particular frame queue and
an array of frame descriptors and tries to enqueue them until it hits
the maximum number fo retries. The same function will be used in the
next patch also on the XDP_TX path.

Also, create the dpaa2_eth_xdp_fds structure to incorporate the array of
FDs as well as the number of FDs already populated.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 61 ++++++++++++++++--------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  7 ++-
 2 files changed, 46 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 11accab81ea1..0f3e842a4fd6 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -244,6 +244,35 @@ static void xdp_release_buf(struct dpaa2_eth_priv *priv,
 	ch->xdp.drop_cnt = 0;
 }
 
+static int dpaa2_eth_xdp_flush(struct dpaa2_eth_priv *priv,
+			       struct dpaa2_eth_fq *fq,
+			       struct dpaa2_eth_xdp_fds *xdp_fds)
+{
+	int total_enqueued = 0, retries = 0, enqueued;
+	struct dpaa2_eth_drv_stats *percpu_extras;
+	int num_fds, err, max_retries;
+	struct dpaa2_fd *fds;
+
+	percpu_extras = this_cpu_ptr(priv->percpu_extras);
+
+	/* try to enqueue all the FDs until the max number of retries is hit */
+	fds = xdp_fds->fds;
+	num_fds = xdp_fds->num;
+	max_retries = num_fds * DPAA2_ETH_ENQUEUE_RETRIES;
+	while (total_enqueued < num_fds && retries < max_retries) {
+		err = priv->enqueue(priv, fq, &fds[total_enqueued],
+				    0, num_fds - total_enqueued, &enqueued);
+		if (err == -EBUSY) {
+			percpu_extras->tx_portal_busy += ++retries;
+			continue;
+		}
+		total_enqueued += enqueued;
+	}
+	xdp_fds->num = 0;
+
+	return total_enqueued;
+}
+
 static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 		       void *buf_start, u16 queue_id)
 {
@@ -1934,12 +1963,11 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 			      struct xdp_frame **frames, u32 flags)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
-	int total_enqueued = 0, retries = 0, enqueued;
-	struct dpaa2_eth_drv_stats *percpu_extras;
+	struct dpaa2_eth_xdp_fds *xdp_redirect_fds;
 	struct rtnl_link_stats64 *percpu_stats;
-	int num_fds, i, err, max_retries;
 	struct dpaa2_eth_fq *fq;
 	struct dpaa2_fd *fds;
+	int enqueued, i, err;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
@@ -1948,10 +1976,10 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 		return -ENETDOWN;
 
 	fq = &priv->fq[smp_processor_id()];
-	fds = fq->xdp_fds;
+	xdp_redirect_fds = &fq->xdp_redirect_fds;
+	fds = xdp_redirect_fds->fds;
 
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
-	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 
 	/* create a FD for each xdp_frame in the list received */
 	for (i = 0; i < n; i++) {
@@ -1959,28 +1987,19 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
 		if (err)
 			break;
 	}
-	num_fds = i;
+	xdp_redirect_fds->num = i;
 
-	/* try to enqueue all the FDs until the max number of retries is hit */
-	max_retries = num_fds * DPAA2_ETH_ENQUEUE_RETRIES;
-	while (total_enqueued < num_fds && retries < max_retries) {
-		err = priv->enqueue(priv, fq, &fds[total_enqueued],
-				    0, num_fds - total_enqueued, &enqueued);
-		if (err == -EBUSY) {
-			percpu_extras->tx_portal_busy += ++retries;
-			continue;
-		}
-		total_enqueued += enqueued;
-	}
+	/* enqueue all the frame descriptors */
+	enqueued = dpaa2_eth_xdp_flush(priv, fq, xdp_redirect_fds);
 
 	/* update statistics */
-	percpu_stats->tx_packets += total_enqueued;
-	for (i = 0; i < total_enqueued; i++)
+	percpu_stats->tx_packets += enqueued;
+	for (i = 0; i < enqueued; i++)
 		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]);
-	for (i = total_enqueued; i < n; i++)
+	for (i = enqueued; i < n; i++)
 		xdp_return_frame_rx_napi(frames[i]);
 
-	return total_enqueued;
+	return enqueued;
 }
 
 static int update_xps(struct dpaa2_eth_priv *priv)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 43cd8409f2e9..b5f7dbbc2a02 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -310,6 +310,11 @@ enum dpaa2_eth_fq_type {
 
 struct dpaa2_eth_priv;
 
+struct dpaa2_eth_xdp_fds {
+	struct dpaa2_fd fds[DEV_MAP_BULK_SIZE];
+	ssize_t num;
+};
+
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
@@ -328,7 +333,7 @@ struct dpaa2_eth_fq {
 			struct dpaa2_eth_fq *fq);
 	struct dpaa2_eth_fq_stats stats;
 
-	struct dpaa2_fd xdp_fds[DEV_MAP_BULK_SIZE];
+	struct dpaa2_eth_xdp_fds xdp_redirect_fds;
 };
 
 struct dpaa2_eth_ch_xdp {
-- 
cgit v1.2.3


From a45cfcc69a2519463db0e18db5b7f9c7739f559d Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Wed, 6 May 2020 21:13:59 +0300
Subject: net: ethernet: ti: am65-cpsw-nuss: use of_platform_device_create()
 for mdio

The MCU CPSW expected to populate only MDIO device, but follow up patches
will add "compatible" property to the MCU CPSW CPTS node which will cause
creation of CPTS device and MCU CPSW init failure. Hence, switch to use
of_platform_device_create() instead of of_platform_populate() for MDIO
device population.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 24 ++++++++++++++++++------
 drivers/net/ethernet/ti/am65-cpsw-nuss.h |  2 ++
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index f8c589929308..8cdbb2b9b13a 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2031,10 +2031,21 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
-	/* We do not want to force this, as in some cases may not have child */
-	if (ret)
-		dev_warn(dev, "populating child nodes err:%d\n", ret);
+	node = of_get_child_by_name(dev->of_node, "mdio");
+	if (!node) {
+		dev_warn(dev, "MDIO node not found\n");
+	} else if (of_device_is_available(node)) {
+		struct platform_device *mdio_pdev;
+
+		mdio_pdev = of_platform_device_create(node, NULL, dev);
+		if (!mdio_pdev) {
+			ret = -ENODEV;
+			goto err_pm_clear;
+		}
+
+		common->mdio_dev =  &mdio_pdev->dev;
+	}
+	of_node_put(node);
 
 	am65_cpsw_nuss_get_ver(common);
 
@@ -2090,7 +2101,8 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	return 0;
 
 err_of_clear:
-	of_platform_depopulate(dev);
+	of_platform_device_destroy(common->mdio_dev, NULL);
+err_pm_clear:
 	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 	return ret;
@@ -2115,7 +2127,7 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev)
 	 */
 	am65_cpsw_nuss_cleanup_ndev(common);
 
-	of_platform_depopulate(dev);
+	of_platform_device_destroy(common->mdio_dev, NULL);
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index b1cddfd05a45..8a6382188cb5 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 
 struct am65_cpts;
 
@@ -76,6 +77,7 @@ struct am65_cpsw_pdata {
 
 struct am65_cpsw_common {
 	struct device		*dev;
+	struct device		*mdio_dev;
 	const struct am65_cpsw_pdata *pdata;
 
 	void __iomem		*ss_base;
-- 
cgit v1.2.3


From c75a33c84b83ffbb8b8b58a6bf4dea69dba21326 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 May 2020 17:58:27 -0700
Subject: net: remove newlines in NL_SET_ERR_MSG_MOD

The NL_SET_ERR_MSG_MOD macro is used to report a string describing an
error message to userspace via the netlink extended ACK structure. It
should not have a trailing newline.

Add a cocci script which catches cases where the newline marker is
present. Using this script, fix the handful of cases which accidentally
included a trailing new line.

I couldn't figure out a way to get a patch mode working, so this script
only implements context, report, and org.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |  2 +-
 drivers/net/ethernet/mscc/ocelot_tc.c           |  6 +-
 net/bridge/br_mrp_netlink.c                     |  2 +-
 net/bridge/br_stp_if.c                          |  2 +-
 net/dsa/slave.c                                 |  6 +-
 scripts/coccinelle/misc/newline_in_nl_msg.cocci | 75 +++++++++++++++++++++++++
 6 files changed, 84 insertions(+), 9 deletions(-)
 create mode 100644 scripts/coccinelle/misc/newline_in_nl_msg.cocci

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 77397aa66810..a050808f2128 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1097,7 +1097,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		if (IS_ERR(priv->fs.tc.t)) {
 			mutex_unlock(&priv->fs.tc.t_lock);
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Failed to create tc offload table\n");
+					   "Failed to create tc offload table");
 			netdev_err(priv->netdev,
 				   "Failed to create tc offload table\n");
 			return PTR_ERR(priv->fs.tc.t);
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c
index d326e231f0ad..b7baf7624e18 100644
--- a/drivers/net/ethernet/mscc/ocelot_tc.c
+++ b/drivers/net/ethernet/mscc/ocelot_tc.c
@@ -48,7 +48,7 @@ static int ocelot_setup_tc_cls_matchall(struct ocelot_port_private *priv,
 
 		if (priv->tc.police_id && priv->tc.police_id != f->cookie) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Only one policer per port is supported\n");
+					   "Only one policer per port is supported");
 			return -EEXIST;
 		}
 
@@ -59,7 +59,7 @@ static int ocelot_setup_tc_cls_matchall(struct ocelot_port_private *priv,
 
 		err = ocelot_port_policer_add(ocelot, port, &pol);
 		if (err) {
-			NL_SET_ERR_MSG_MOD(extack, "Could not add policer\n");
+			NL_SET_ERR_MSG_MOD(extack, "Could not add policer");
 			return err;
 		}
 
@@ -73,7 +73,7 @@ static int ocelot_setup_tc_cls_matchall(struct ocelot_port_private *priv,
 		err = ocelot_port_policer_del(ocelot, port);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Could not delete policer\n");
+					   "Could not delete policer");
 			return err;
 		}
 		priv->tc.police_id = 0;
diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c
index 503896638be0..397e7f710772 100644
--- a/net/bridge/br_mrp_netlink.c
+++ b/net/bridge/br_mrp_netlink.c
@@ -28,7 +28,7 @@ int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
 	int err;
 
 	if (br->stp_enabled != BR_NO_STP) {
-		NL_SET_ERR_MSG_MOD(extack, "MRP can't be enabled if STP is already enabled\n");
+		NL_SET_ERR_MSG_MOD(extack, "MRP can't be enabled if STP is already enabled");
 		return -EINVAL;
 	}
 
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index a42850b7eb9a..ba55851fe132 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -203,7 +203,7 @@ int br_stp_set_enabled(struct net_bridge *br, unsigned long val,
 
 	if (br_mrp_enabled(br)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "STP can't be enabled if MRP is already enabled\n");
+				   "STP can't be enabled if MRP is already enabled");
 		return -EINVAL;
 	}
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ea0fcf7bf786..dfb4282fc339 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -911,13 +911,13 @@ dsa_slave_add_cls_matchall_police(struct net_device *dev,
 
 	if (!ds->ops->port_policer_add) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Policing offload not implemented\n");
+				   "Policing offload not implemented");
 		return -EOPNOTSUPP;
 	}
 
 	if (!ingress) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Only supported on ingress qdisc\n");
+				   "Only supported on ingress qdisc");
 		return -EOPNOTSUPP;
 	}
 
@@ -928,7 +928,7 @@ dsa_slave_add_cls_matchall_police(struct net_device *dev,
 	list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) {
 		if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Only one port policer allowed\n");
+					   "Only one port policer allowed");
 			return -EEXIST;
 		}
 	}
diff --git a/scripts/coccinelle/misc/newline_in_nl_msg.cocci b/scripts/coccinelle/misc/newline_in_nl_msg.cocci
new file mode 100644
index 000000000000..c175886e4015
--- /dev/null
+++ b/scripts/coccinelle/misc/newline_in_nl_msg.cocci
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+///
+/// Catch strings ending in newline with GENL_SET_ERR_MSG, NL_SET_ERR_MSG,
+/// NL_SET_ERR_MSG_MOD.
+///
+// Confidence: Very High
+// Copyright: (C) 2020 Intel Corporation
+// URL: http://coccinelle.lip6.fr/
+// Options: --no-includes --include-headers
+
+virtual context
+virtual org
+virtual report
+
+@r depends on context || org || report@
+expression e;
+constant m;
+position p;
+@@
+  \(GENL_SET_ERR_MSG\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\)(e,m@p)
+
+@script:python@
+m << r.m;
+@@
+
+if not m.endswith("\\n\""):
+	cocci.include_match(False)
+
+@r1 depends on r@
+identifier fname;
+expression r.e;
+constant r.m;
+position r.p;
+@@
+  fname(e,m@p)
+
+//----------------------------------------------------------
+//  For context mode
+//----------------------------------------------------------
+
+@depends on context && r@
+identifier r1.fname;
+expression r.e;
+constant r.m;
+@@
+* fname(e,m)
+
+//----------------------------------------------------------
+//  For org mode
+//----------------------------------------------------------
+
+@script:python depends on org@
+fname << r1.fname;
+m << r.m;
+p << r.p;
+@@
+
+if m.endswith("\\n\""):
+	msg="WARNING avoid newline at end of message in %s" % (fname)
+	msg_safe=msg.replace("[","@(").replace("]",")")
+	coccilib.org.print_todo(p[0], msg_safe)
+
+//----------------------------------------------------------
+//  For report mode
+//----------------------------------------------------------
+
+@script:python depends on report@
+fname << r1.fname;
+m << r.m;
+p << r.p;
+@@
+
+if m.endswith("\\n\""):
+	msg="WARNING avoid newline at end of message in %s" % (fname)
+	coccilib.report.print_report(p[0], msg)
-- 
cgit v1.2.3


From e031ce80d9f9867ab7c27b9acaadd75c62d6007a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 23:30:02 +0200
Subject: r8169: add helper r8168g_wait_ll_share_fifo_ready

Create a helper for this waiting function, name of the helper is
borrowed from the vendor driver. In addition don't return in the two
hw_init functions if the first wait runs into a timeout, there's no
benefit in doing so.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index f06dbc9a046d..ba67864c04c1 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5055,6 +5055,11 @@ DECLARE_RTL_COND(rtl_link_list_ready_cond)
 	return RTL_R8(tp, MCU) & LINK_LIST_RDY;
 }
 
+static void r8168g_wait_ll_share_fifo_ready(struct rtl8169_private *tp)
+{
+	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
+}
+
 DECLARE_RTL_COND(rtl_rxtx_empty_cond)
 {
 	return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
@@ -5139,13 +5144,10 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
 
 	r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0);
-
-	if (!rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
-		return;
+	r8168g_wait_ll_share_fifo_ready(tp);
 
 	r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15));
-
-	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
+	r8168g_wait_ll_share_fifo_ready(tp);
 }
 
 static void rtl_hw_init_8125(struct rtl8169_private *tp)
@@ -5160,15 +5162,12 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
 
 	r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0);
-
-	if (!rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
-		return;
+	r8168g_wait_ll_share_fifo_ready(tp);
 
 	r8168_mac_ocp_write(tp, 0xc0aa, 0x07d0);
 	r8168_mac_ocp_write(tp, 0xc0a6, 0x0150);
 	r8168_mac_ocp_write(tp, 0xc01e, 0x5555);
-
-	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
+	r8168g_wait_ll_share_fifo_ready(tp);
 }
 
 static void rtl_hw_initialize(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 9617886fa65d3264c5aac5f1305e8e5a6ca865f4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 23:30:43 +0200
Subject: r8169: add helper rtl_enable_rxdvgate

Add a helper for setting RXDV_GATED_EN, the 2ms delay is copied from
the vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index ba67864c04c1..5b389d3e7c9a 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2494,6 +2494,12 @@ DECLARE_RTL_COND(rtl_txcfg_empty_cond)
 	return RTL_R32(tp, TxConfig) & TXCFG_EMPTY;
 }
 
+static void rtl_enable_rxdvgate(struct rtl8169_private *tp)
+{
+	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
+	fsleep(2000);
+}
+
 static void rtl8169_hw_reset(struct rtl8169_private *tp)
 {
 	/* Disable interrupts */
@@ -5131,7 +5137,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 
 static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
-	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
+	rtl_enable_rxdvgate(tp);
 
 	if (!rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42))
 		return;
@@ -5152,7 +5158,7 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 
 static void rtl_hw_init_8125(struct rtl8169_private *tp)
 {
-	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
+	rtl_enable_rxdvgate(tp);
 
 	if (!rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
 		return;
-- 
cgit v1.2.3


From 6f9395c69e62e0ffefaaddf97f32d7690e00f791 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 23:31:46 +0200
Subject: r8169: add helper rtl_wait_txrx_fifo_empty

Add a helper for waiting for FIFO's to be empty, again the name is
borrowed from the vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 35 ++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5b389d3e7c9a..47ff514aec39 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2494,10 +2494,31 @@ DECLARE_RTL_COND(rtl_txcfg_empty_cond)
 	return RTL_R32(tp, TxConfig) & TXCFG_EMPTY;
 }
 
+DECLARE_RTL_COND(rtl_rxtx_empty_cond)
+{
+	return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
+}
+
+static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp)
+{
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
+		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42);
+		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
+		break;
+	case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_61:
+		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
+		break;
+	default:
+		break;
+	}
+}
+
 static void rtl_enable_rxdvgate(struct rtl8169_private *tp)
 {
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 	fsleep(2000);
+	rtl_wait_txrx_fifo_empty(tp);
 }
 
 static void rtl8169_hw_reset(struct rtl8169_private *tp)
@@ -5066,11 +5087,6 @@ static void r8168g_wait_ll_share_fifo_ready(struct rtl8169_private *tp)
 	rtl_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
 }
 
-DECLARE_RTL_COND(rtl_rxtx_empty_cond)
-{
-	return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
-}
-
 static int r8169_mdio_read_reg(struct mii_bus *mii_bus, int phyaddr, int phyreg)
 {
 	struct rtl8169_private *tp = mii_bus->priv;
@@ -5139,12 +5155,6 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
 	rtl_enable_rxdvgate(tp);
 
-	if (!rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42))
-		return;
-
-	if (!rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
-		return;
-
 	RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb));
 	msleep(1);
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
@@ -5160,9 +5170,6 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp)
 {
 	rtl_enable_rxdvgate(tp);
 
-	if (!rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42))
-		return;
-
 	RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb));
 	msleep(1);
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
-- 
cgit v1.2.3


From ce740c5f6f7a2142ca7acee7799996c0beac2980 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 23:32:49 +0200
Subject: r8169: improve reset handling for chips from RTL8168g

Sync the reset preparation for chips from RTL8168g with the r8168 and
r8125 vendor drivers.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 47ff514aec39..b4e49c446bd0 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2535,10 +2535,13 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 		rtl_loop_wait_low(tp, &rtl_npq_cond, 20, 2000);
 		break;
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_61:
+		rtl_enable_rxdvgate(tp);
+		fsleep(2000);
+		break;
 	default:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		udelay(100);
-- 
cgit v1.2.3


From 4d2c99940825637d007da150ad03a6f4442de0f0 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 9 May 2020 00:14:47 +0100
Subject: net: tg3: tidy up loop, remove need to compute off with a multiply

Currently the value for 'off' is computed using a multiplication and
a couple of statements later off is being incremented by len and
this value is never read.  Clean up the code by removing the
multiplication and just increment off by len on each iteration.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/tg3.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ff98a82b7bc4..7a3b22b35238 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -10797,17 +10797,15 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy)
 #ifdef CONFIG_TIGON3_HWMON
 static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir)
 {
+	u32 off, len = TG3_OCIR_LEN;
 	int i;
 
-	for (i = 0; i < TG3_SD_NUM_RECS; i++, ocir++) {
-		u32 off = i * TG3_OCIR_LEN, len = TG3_OCIR_LEN;
-
+	for (i = 0, off = 0; i < TG3_SD_NUM_RECS; i++, ocir++, off += len) {
 		tg3_ape_scratchpad_read(tp, (u32 *) ocir, off, len);
-		off += len;
 
 		if (ocir->signature != TG3_OCIR_SIG_MAGIC ||
 		    !(ocir->version_flags & TG3_OCIR_FLAG_ACTIVE))
-			memset(ocir, 0, TG3_OCIR_LEN);
+			memset(ocir, 0, len);
 	}
 }
 
-- 
cgit v1.2.3


From d8f05e9891fd4e80863f09a17c6d594ac6870a33 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 8 May 2020 23:40:26 +0100
Subject: cnic: remove redundant assignment to variable ret

The variable ret is being assigned with a value that is never read,
the assignment is redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/cnic.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 61ab7d21f6bd..c5cca63b8571 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1918,7 +1918,6 @@ static int cnic_bnx2x_iscsi_ofld1(struct cnic_dev *dev, struct kwqe *wqes[],
 	ret = cnic_alloc_bnx2x_conn_resc(dev, l5_cid);
 	if (ret) {
 		atomic_dec(&cp->iscsi_conn);
-		ret = 0;
 		goto done;
 	}
 	ret = cnic_setup_bnx2x_ctx(dev, wqes, num);
-- 
cgit v1.2.3


From 6a9c9548ee204882d196fdbc95f689e1d0fd00aa Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 8 May 2020 23:33:21 +0100
Subject: net/atheros: remove redundant assignment to variable size

The variable size is being assigned with a value that is never read,
the assignment is redundant and cab be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/atlx/atl1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 271e7034fa70..b35fcfcd692d 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1042,7 +1042,7 @@ static s32 atl1_setup_ring_resources(struct atl1_adapter *adapter)
 	 * each ring/block may need up to 8 bytes for alignment, hence the
 	 * additional 40 bytes tacked onto the end.
 	 */
-	ring_header->size = size =
+	ring_header->size =
 		sizeof(struct tx_packet_desc) * tpd_ring->count
 		+ sizeof(struct rx_free_desc) * rfd_ring->count
 		+ sizeof(struct rx_return_desc) * rrd_ring->count
-- 
cgit v1.2.3


From 5eb2bcf247de02b92749fe6a6b342f6393ca3f86 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 8 May 2020 23:58:10 +0100
Subject: net: lio_core: remove redundant assignment to variable tx_done

The variable tx_done is being assigned with a value that is never read
as the function returns a few statements later.  The assignment is
redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/liquidio/lio_core.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index d7e805749a5b..e40c64b79f66 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -782,7 +782,6 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 	if ((work_done < budget && tx_done) ||
 	    (iq && iq->pkt_in_done >= MAX_REG_CNT) ||
 	    (droq->pkt_count >= MAX_REG_CNT)) {
-		tx_done = 1;
 		napi_complete_done(napi, work_done);
 
 		octeon_enable_irq(droq->oct_dev, droq->q_no);
-- 
cgit v1.2.3


From f02bac9ad6415e40bf32bf84ce5832698ebe5d15 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 5 Dec 2019 18:07:25 +0200
Subject: net/mlx5e: Return bool from TLS and IPSEC offloads

TLS and IPSEC offloads currently return struct sk_buff *, but the value
is either NULL or the same skb that was passed as a parameter. Return
bool instead to provide stronger guarantees to the calling code (it
won't need to support handling a different SKB that could be potentially
returned before this change) and to simplify restructuring this code in
the following commits.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en_accel/en_accel.h         | 23 +++++------
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c       | 12 +++---
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h       |  6 +--
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.h    |  7 ++--
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 11 +++--
 .../mellanox/mlx5/core/en_accel/tls_rxtx.c         | 48 +++++++++-------------
 .../mellanox/mlx5/core/en_accel/tls_rxtx.h         |  8 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    |  3 +-
 8 files changed, 50 insertions(+), 68 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index a6f65d4b2f36..6249998444c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -102,33 +102,30 @@ mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
 	udp_hdr(skb)->len = htons(payload_len);
 }
 
-static inline struct sk_buff *
-mlx5e_accel_handle_tx(struct sk_buff *skb,
-		      struct mlx5e_txqsq *sq,
-		      struct net_device *dev,
-		      struct mlx5e_tx_wqe **wqe,
-		      u16 *pi)
+static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
+					 struct mlx5e_txqsq *sq,
+					 struct net_device *dev,
+					 struct mlx5e_tx_wqe **wqe,
+					 u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
-		skb = mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi);
-		if (unlikely(!skb))
-			return NULL;
+		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi)))
+			return false;
 	}
 #endif
 
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) {
-		skb = mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb);
-		if (unlikely(!skb))
-			return NULL;
+		if (unlikely(!mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb)))
+			return false;
 	}
 #endif
 
 	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
 		mlx5e_udp_gso_handle_tx_skb(skb);
 
-	return skb;
+	return true;
 }
 
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 0dd17514caae..f60eb6a4b57c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -233,9 +233,9 @@ static void mlx5e_ipsec_set_metadata(struct sk_buff *skb,
 		   ntohs(mdata->content.tx.seq));
 }
 
-struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
-					  struct mlx5e_tx_wqe *wqe,
-					  struct sk_buff *skb)
+bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
+			       struct mlx5e_tx_wqe *wqe,
+			       struct sk_buff *skb)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct xfrm_offload *xo = xfrm_offload(skb);
@@ -245,7 +245,7 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 	struct sec_path *sp;
 
 	if (!xo)
-		return skb;
+		return true;
 
 	sp = skb_sec_path(skb);
 	if (unlikely(sp->len != 1)) {
@@ -281,11 +281,11 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 	sa_entry->set_iv_op(skb, x, xo);
 	mlx5e_ipsec_set_metadata(skb, mdata, xo);
 
-	return skb;
+	return true;
 
 drop:
 	kfree_skb(skb);
-	return NULL;
+	return false;
 }
 
 static inline struct xfrm_state *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index db84500b024f..64e948cc3dc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -52,9 +52,9 @@ void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
 			    struct xfrm_offload *xo);
 void mlx5e_ipsec_set_iv(struct sk_buff *skb, struct xfrm_state *x,
 			struct xfrm_offload *xo);
-struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
-					  struct mlx5e_tx_wqe *wqe,
-					  struct sk_buff *skb);
+bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
+			       struct mlx5e_tx_wqe *wqe,
+			       struct sk_buff *skb);
 
 #endif /* CONFIG_MLX5_EN_IPSEC */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 9daaec244385..742aca8782d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -95,10 +95,9 @@ mlx5e_get_ktls_tx_priv_ctx(struct tls_context *tls_ctx)
 void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv);
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx);
 
-struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
-					 struct mlx5e_txqsq *sq,
-					 struct sk_buff *skb,
-					 struct mlx5e_tx_wqe **wqe, u16 *pi);
+bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
+			      u16 *pi);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index ba973937f0b5..8fcd14803558 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -413,10 +413,9 @@ err_out:
 	return MLX5E_KTLS_SYNC_FAIL;
 }
 
-struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
-					 struct mlx5e_txqsq *sq,
-					 struct sk_buff *skb,
-					 struct mlx5e_tx_wqe **wqe, u16 *pi)
+bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
+			      u16 *pi)
 {
 	struct mlx5e_ktls_offload_context_tx *priv_tx;
 	struct mlx5e_sq_stats *stats = sq->stats;
@@ -474,9 +473,9 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 	stats->tls_encrypted_bytes   += datalen;
 
 out:
-	return skb;
+	return true;
 
 err_out:
 	dev_kfree_skb_any(skb);
-	return NULL;
+	return false;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 1d7ddeb7a46b..e8f2c214a8de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -184,12 +184,10 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 	nskb->queue_mapping = skb->queue_mapping;
 }
 
-static struct sk_buff *
-mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
-		     struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		     struct mlx5e_tx_wqe **wqe,
-		     u16 *pi,
-		     struct mlx5e_tls *tls)
+static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
+				 struct mlx5e_txqsq *sq, struct sk_buff *skb,
+				 struct mlx5e_tx_wqe **wqe, u16 *pi,
+				 struct mlx5e_tls *tls)
 {
 	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
 	struct sync_info info;
@@ -217,7 +215,7 @@ mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 		if (likely(payload <= -info.sync_len))
 			/* SKB payload doesn't require offload
 			 */
-			return skb;
+			return true;
 
 		atomic64_inc(&tls->sw_stats.tx_tls_drop_bypass_required);
 		goto err_out;
@@ -250,18 +248,16 @@ mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	mlx5e_sq_xmit(sq, nskb, *wqe, *pi, true);
 	*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
 	*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
-	return skb;
+	return true;
 
 err_out:
 	dev_kfree_skb_any(skb);
-	return NULL;
+	return false;
 }
 
-struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
-					struct mlx5e_txqsq *sq,
-					struct sk_buff *skb,
-					struct mlx5e_tx_wqe **wqe,
-					u16 *pi)
+bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+			     struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
+			     u16 *pi)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_tls_offload_context_tx *context;
@@ -270,41 +266,35 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) {
-		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
-		goto out;
-	}
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx))
+		return mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
 
 	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
-		goto out;
+		return true;
 
 	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
 	if (!datalen)
-		goto out;
+		return true;
 
 	tls_ctx = tls_get_ctx(skb->sk);
 	if (unlikely(tls_ctx->netdev != netdev))
-		goto out;
+		return true;
 
 	skb_seq = ntohl(tcp_hdr(skb)->seq);
 	context = mlx5e_get_tls_tx_context(tls_ctx);
 	expected_seq = context->expected_seq;
 
-	if (unlikely(expected_seq != skb_seq)) {
-		skb = mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls);
-		goto out;
-	}
+	if (unlikely(expected_seq != skb_seq))
+		return mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls);
 
 	if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
 		atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata);
 		dev_kfree_skb_any(skb);
-		skb = NULL;
-		goto out;
+		return false;
 	}
 
 	context->expected_seq = skb_seq + datalen;
-out:
-	return skb;
+	return true;
 }
 
 static int tls_update_resync_sn(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 90bc1f2384c8..890d452bf1ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -40,11 +40,9 @@
 #include "en.h"
 #include "en/txrx.h"
 
-struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
-					struct mlx5e_txqsq *sq,
-					struct sk_buff *skb,
-					struct mlx5e_tx_wqe **wqe,
-					u16 *pi);
+bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+			     struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
+			     u16 *pi);
 
 void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 			     u32 *cqe_bcnt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 583e1b201b75..7a6ed72ae00a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -394,8 +394,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	/* might send skbs and update wqe and pi */
-	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
-	if (unlikely(!skb))
+	if (unlikely(!mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi)))
 		return NETDEV_TX_OK;
 
 	return mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
-- 
cgit v1.2.3


From 7f8546f3f041d6b1cce270581517217867764077 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 3 Jan 2020 16:17:30 +0200
Subject: net/mlx5e: Unify checks of TLS offloads

Both INNOVA and ConnectX TLS offloads perform the same checks in the
beginning. Unify them to reduce repeating code. Do WARN_ON_ONCE on
netdev mismatch and finish with an error in both offloads, not only in
the ConnectX one.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c  | 17 ++---------------
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c | 14 +++++++++-----
 3 files changed, 13 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 742aca8782d6..81f8b7467569 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -95,9 +95,9 @@ mlx5e_get_ktls_tx_priv_ctx(struct tls_context *tls_ctx)
 void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv);
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx);
 
-bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
 			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			      u16 *pi);
+			      u16 *pi, int datalen);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 8fcd14803558..c61604f3722c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -413,28 +413,15 @@ err_out:
 	return MLX5E_KTLS_SYNC_FAIL;
 }
 
-bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
+bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
 			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			      u16 *pi)
+			      u16 *pi, int datalen)
 {
 	struct mlx5e_ktls_offload_context_tx *priv_tx;
 	struct mlx5e_sq_stats *stats = sq->stats;
 	struct mlx5_wqe_ctrl_seg *cseg;
-	struct tls_context *tls_ctx;
-	int datalen;
 	u32 seq;
 
-	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
-		goto out;
-
-	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
-	if (!datalen)
-		goto out;
-
-	tls_ctx = tls_get_ctx(skb->sk);
-	if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
-		goto err_out;
-
 	priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
 
 	if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index e8f2c214a8de..26c59cfbec9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -266,9 +266,6 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx))
-		return mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
-
 	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
 		return true;
 
@@ -277,8 +274,11 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 		return true;
 
 	tls_ctx = tls_get_ctx(skb->sk);
-	if (unlikely(tls_ctx->netdev != netdev))
-		return true;
+	if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
+		goto err_out;
+
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx))
+		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, wqe, pi, datalen);
 
 	skb_seq = ntohl(tcp_hdr(skb)->seq);
 	context = mlx5e_get_tls_tx_context(tls_ctx);
@@ -295,6 +295,10 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 
 	context->expected_seq = skb_seq + datalen;
 	return true;
+
+err_out:
+	dev_kfree_skb_any(skb);
+	return false;
 }
 
 static int tls_update_resync_sn(struct net_device *netdev,
-- 
cgit v1.2.3


From 3df711db05b545f3c9b610bee62d33f4e67f64b7 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 5 Dec 2019 18:11:16 +0200
Subject: net/mlx5e: Return void from mlx5e_sq_xmit and mlx5i_sq_xmit

mlx5e_sq_xmit and mlx5i_sq_xmit always return NETDEV_TX_OK. Drop the
return value to simplify the code.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    | 24 ++++++++++------------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  4 +++-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h  |  5 ++---
 4 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0864b76ca2c0..da7fe6aafeed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -919,8 +919,8 @@ void mlx5e_build_ptys2ethtool_map(void);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
-netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
+void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
 void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 7a6ed72ae00a..bb6d3774eafb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -265,8 +265,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 }
 
-netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
+void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5_wqe_ctrl_seg *cseg;
@@ -373,13 +373,11 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
 			     num_dma, wi, cseg, xmit_more);
 
-	return NETDEV_TX_OK;
+	return;
 
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
-
-	return NETDEV_TX_OK;
 }
 
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -395,9 +393,12 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* might send skbs and update wqe and pi */
 	if (unlikely(!mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi)))
-		return NETDEV_TX_OK;
+		goto out;
+
+	mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
 
-	return mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
+out:
+	return NETDEV_TX_OK;
 }
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
@@ -567,9 +568,8 @@ mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey,
 	dseg->av.key.qkey.qkey = cpu_to_be32(dqkey);
 }
 
-netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
-			  bool xmit_more)
+void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		   struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more)
 {
 	struct mlx5i_tx_wqe *wqe;
 
@@ -647,12 +647,10 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
 			     num_dma, wi, cseg, xmit_more);
 
-	return NETDEV_TX_OK;
+	return;
 
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
-
-	return NETDEV_TX_OK;
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 068578be00f1..035bd21e5d4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -663,7 +663,9 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
 	struct mlx5_ib_ah *mah   = to_mah(address);
 	struct mlx5i_priv *ipriv = epriv->ppriv;
 
-	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey, netdev_xmit_more());
+	mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey, netdev_xmit_more());
+
+	return NETDEV_TX_OK;
 }
 
 static void mlx5i_set_pkey_index(struct net_device *netdev, int id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 7844ab5d0ce7..c4aa47018c0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -113,9 +113,8 @@ struct mlx5i_tx_wqe {
 #define MLX5I_SQ_FETCH_WQE(sq, pi) \
 	((struct mlx5i_tx_wqe *)mlx5e_fetch_wqe(&(sq)->wq, pi, sizeof(struct mlx5i_tx_wqe)))
 
-netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
-			  bool xmit_more);
+void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		   struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more);
 void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 
-- 
cgit v1.2.3


From 0bdb078c74854c48bffa323899f2e0c5ca924e72 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 6 Dec 2019 16:14:57 +0200
Subject: net/mlx5e: Pass only eseg to IPSEC offload

IPSEC offload needs to modify the eseg of the WQE that is being filled,
but it receives a pointer to the whole WQE. To make the contract
stricter, pass only the pointer to the eseg of that WQE. This commit is
preparation for the following refactoring of offloads in the TX path and
for the MPWQE support.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h   | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 6249998444c0..c658c8556863 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -117,7 +117,7 @@ static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
 
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) {
-		if (unlikely(!mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb)))
+		if (unlikely(!mlx5e_ipsec_handle_tx_skb(dev, &(*wqe)->eth, skb)))
 			return false;
 	}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index f60eb6a4b57c..0e1ac3e68c72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -234,7 +234,7 @@ static void mlx5e_ipsec_set_metadata(struct sk_buff *skb,
 }
 
 bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
-			       struct mlx5e_tx_wqe *wqe,
+			       struct mlx5_wqe_eth_seg *eseg,
 			       struct sk_buff *skb)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -276,7 +276,7 @@ bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_metadata);
 		goto drop;
 	}
-	mlx5e_ipsec_set_swp(skb, &wqe->eth, x->props.mode, xo);
+	mlx5e_ipsec_set_swp(skb, eseg, x->props.mode, xo);
 	sa_entry = (struct mlx5e_ipsec_sa_entry *)x->xso.offload_handle;
 	sa_entry->set_iv_op(skb, x, xo);
 	mlx5e_ipsec_set_metadata(skb, mdata, xo);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 64e948cc3dc5..bd6f32aee8d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -53,7 +53,7 @@ void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
 void mlx5e_ipsec_set_iv(struct sk_buff *skb, struct xfrm_state *x,
 			struct xfrm_offload *xo);
 bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
-			       struct mlx5e_tx_wqe *wqe,
+			       struct mlx5_wqe_eth_seg *eseg,
 			       struct sk_buff *skb);
 
 #endif /* CONFIG_MLX5_EN_IPSEC */
-- 
cgit v1.2.3


From 2eeb6e384102e1124d0a5633803dda0cdbcac471 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 6 Dec 2019 16:42:09 +0200
Subject: net/mlx5e: Make TLS offload independent of wqe and pi

TLS offload may write a 32-bit field (tisn) to the cseg of the WQE. To
do that, it receives pi and wqe pointers. As TLS offload may also send
additional WQEs, it has to update pi and wqe, and in many cases it even
doesn't use pi calculated before and wqe zeroed before and does it
itself. Also, mlx5e_sq_xmit has to copy the whole cseg if it goes to the
mlx5e_fill_sq_frag_edge flow. This all is not efficient.

It's more efficient to do the following:

1. Just return tisn from TLS offload and make the caller fill it in a
more appropriate place.

2. Calculate pi and clear wqe after calling TLS offload.

3. If TLS offload has to send WQEs, calculate pi and clear wqe just
before that. It's already done in all places anyway, so this commit
allows to remove some redundant memsets and calls.

Copying of cseg will be eliminated in one of the following commits, and
all other stuff is done here.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h | 10 +++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h |  3 +--
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c  | 13 +++----------
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c | 17 +++++++++--------
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h |  3 +--
 5 files changed, 23 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index c658c8556863..66bfab021d6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -109,10 +109,18 @@ static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
 					 u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
+	u32 tls_tisn = 0;
+
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
-		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi)))
+		/* May send SKBs and WQEs. */
+		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, &tls_tisn)))
 			return false;
 	}
+
+	*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
+
+	(*wqe)->ctrl.tisn = cpu_to_be32(tls_tisn << 8);
 #endif
 
 #ifdef CONFIG_MLX5_EN_IPSEC
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 81f8b7467569..7d9d9420f19d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -96,8 +96,7 @@ void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv);
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx);
 
 bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
-			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			      u16 *pi, int datalen);
+			      struct sk_buff *skb, u32 *tisn, int datalen);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index c61604f3722c..b49d7c1e49dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -414,20 +414,16 @@ err_out:
 }
 
 bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
-			      struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			      u16 *pi, int datalen)
+			      struct sk_buff *skb, u32 *tisn, int datalen)
 {
 	struct mlx5e_ktls_offload_context_tx *priv_tx;
 	struct mlx5e_sq_stats *stats = sq->stats;
-	struct mlx5_wqe_ctrl_seg *cseg;
 	u32 seq;
 
 	priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
 
 	if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
 		mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false);
-		*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-		*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
 		stats->tls_ctx++;
 	}
 
@@ -438,23 +434,20 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s
 
 		switch (ret) {
 		case MLX5E_KTLS_SYNC_DONE:
-			*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-			*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
 			break;
 		case MLX5E_KTLS_SYNC_SKIP_NO_DATA:
 			if (likely(!skb->decrypted))
 				goto out;
 			WARN_ON_ONCE(1);
 			/* fall-through */
-		default: /* MLX5E_KTLS_SYNC_FAIL */
+		case MLX5E_KTLS_SYNC_FAIL:
 			goto err_out;
 		}
 	}
 
 	priv_tx->expected_seq = seq + datalen;
 
-	cseg = &(*wqe)->ctrl;
-	cseg->tisn = cpu_to_be32(priv_tx->tisn << 8);
+	*tisn = priv_tx->tisn;
 
 	stats->tls_encrypted_packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 	stats->tls_encrypted_bytes   += datalen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 26c59cfbec9b..8e6b0b0ce2e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -186,14 +186,15 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 
 static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 				 struct mlx5e_txqsq *sq, struct sk_buff *skb,
-				 struct mlx5e_tx_wqe **wqe, u16 *pi,
 				 struct mlx5e_tls *tls)
 {
 	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	struct mlx5e_tx_wqe *wqe;
 	struct sync_info info;
 	struct sk_buff *nskb;
 	int linear_len = 0;
 	int headln;
+	u16 pi;
 	int i;
 
 	sq->stats->tls_ooo++;
@@ -245,9 +246,10 @@ static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	sq->stats->tls_resync_bytes += nskb->len;
 	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
 				    cpu_to_be64(info.rcd_sn));
-	mlx5e_sq_xmit(sq, nskb, *wqe, *pi, true);
-	*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-	*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
+	mlx5e_sq_xmit(sq, nskb, wqe, pi, true);
+
 	return true;
 
 err_out:
@@ -256,8 +258,7 @@ err_out:
 }
 
 bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
-			     struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			     u16 *pi)
+			     struct sk_buff *skb, u32 *tisn)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_tls_offload_context_tx *context;
@@ -278,14 +279,14 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 		goto err_out;
 
 	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx))
-		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, wqe, pi, datalen);
+		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, tisn, datalen);
 
 	skb_seq = ntohl(tcp_hdr(skb)->seq);
 	context = mlx5e_get_tls_tx_context(tls_ctx);
 	expected_seq = context->expected_seq;
 
 	if (unlikely(expected_seq != skb_seq))
-		return mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls);
+		return mlx5e_tls_handle_ooo(context, sq, skb, priv->tls);
 
 	if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
 		atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 890d452bf1ae..3630ed8b1206 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -41,8 +41,7 @@
 #include "en/txrx.h"
 
 bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
-			     struct sk_buff *skb, struct mlx5e_tx_wqe **wqe,
-			     u16 *pi);
+			     struct sk_buff *skb, u32 *tisn);
 
 void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 			     u32 *cqe_bcnt);
-- 
cgit v1.2.3


From 5546100038eeff96fd0361f9b820405c016f8578 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 9 Dec 2019 12:30:42 +0200
Subject: net/mlx5e: Update UDP fields of the SKB for GSO first

mlx5e_udp_gso_handle_tx_skb updates the length field in the UDP header
in case of GSO. It doesn't interfere with other offloads, so do it first
to simplify further restructuring of the code. This way we'll make all
independent modifications to the SKB before starting to work with WQEs.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 66bfab021d6b..d286fb09955c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -110,7 +110,12 @@ static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	u32 tls_tisn = 0;
+#endif
+
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+		mlx5e_udp_gso_handle_tx_skb(skb);
 
+#ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
 		/* May send SKBs and WQEs. */
 		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, &tls_tisn)))
@@ -130,9 +135,6 @@ static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
-	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-		mlx5e_udp_gso_handle_tx_skb(skb);
-
 	return true;
 }
 
-- 
cgit v1.2.3


From 714c88a38bce3477392944d6c0d0bc724abaff09 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Wed, 29 Jan 2020 14:35:09 +0200
Subject: net/mlx5e: Split TX acceleration offloads into two phases

After previous modifications, the offloads are no longer called one by
one, the pi is calculated and the wqe is cleared on between of TLS and
IPSEC offloads, which doesn't quite fit mlx5e_accel_handle_tx's purpose.

This patch splits mlx5e_accel_handle_tx into two functions that
correspond to two logical phases of running offloads:

1. Before fetching a WQE. Here runs the code that can post WQEs on its
own, before the main WQE is fetched. It's the main part of TLS offload.

2. After fetching a WQE. Here runs the code that updates the WQE's
fields, but can't post other WQEs any more. It's a minor part of TLS
offload that sets the tisn field in the cseg, and eseg-based offloads
(currently IPSEC, and later patches will move GENEVE and checksum
offloads there, too).

It allows to make mlx5e_xmit take care of all actions needed to transmit
a packet in the right order, improve the structure of the code and
reduce unnecessary operations. The structure will be further improved in
the following patches (all eseg-based offloads will be moved to a single
place, and reserving space for the main WQE will happen between phase 1
and phase 2 of offloads to eliminate unneeded data movements).

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en_accel/en_accel.h         | 33 ++++++++++++++--------
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c       |  3 +-
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h       |  2 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.h    |  4 ++-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c |  5 ++--
 .../mellanox/mlx5/core/en_accel/tls_rxtx.c         | 10 +++++--
 .../mellanox/mlx5/core/en_accel/tls_rxtx.h         |  8 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    | 10 +++++--
 8 files changed, 52 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index d286fb09955c..fac145dcf2ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -102,35 +102,44 @@ mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
 	udp_hdr(skb)->len = htons(payload_len);
 }
 
-static inline bool mlx5e_accel_handle_tx(struct sk_buff *skb,
-					 struct mlx5e_txqsq *sq,
-					 struct net_device *dev,
-					 struct mlx5e_tx_wqe **wqe,
-					 u16 *pi)
-{
+struct mlx5e_accel_tx_state {
 #ifdef CONFIG_MLX5_EN_TLS
-	u32 tls_tisn = 0;
+	struct mlx5e_accel_tx_tls_state tls;
 #endif
+};
 
+static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
+					struct mlx5e_txqsq *sq,
+					struct sk_buff *skb,
+					struct mlx5e_accel_tx_state *state)
+{
 	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
 		mlx5e_udp_gso_handle_tx_skb(skb);
 
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
 		/* May send SKBs and WQEs. */
-		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, &tls_tisn)))
+		if (unlikely(!mlx5e_tls_handle_tx_skb(dev, sq, skb, &state->tls)))
 			return false;
 	}
+#endif
 
-	*pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-	*wqe = MLX5E_TX_FETCH_WQE(sq, *pi);
+	return true;
+}
 
-	(*wqe)->ctrl.tisn = cpu_to_be32(tls_tisn << 8);
+static inline bool mlx5e_accel_tx_finish(struct mlx5e_priv *priv,
+					 struct mlx5e_txqsq *sq,
+					 struct sk_buff *skb,
+					 struct mlx5e_tx_wqe *wqe,
+					 struct mlx5e_accel_tx_state *state)
+{
+#ifdef CONFIG_MLX5_EN_TLS
+	mlx5e_tls_handle_tx_wqe(sq, &wqe->ctrl, &state->tls);
 #endif
 
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) {
-		if (unlikely(!mlx5e_ipsec_handle_tx_skb(dev, &(*wqe)->eth, skb)))
+		if (unlikely(!mlx5e_ipsec_handle_tx_skb(priv, &wqe->eth, skb)))
 			return false;
 	}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 0e1ac3e68c72..824b87ac8f9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -233,11 +233,10 @@ static void mlx5e_ipsec_set_metadata(struct sk_buff *skb,
 		   ntohs(mdata->content.tx.seq));
 }
 
-bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
+bool mlx5e_ipsec_handle_tx_skb(struct mlx5e_priv *priv,
 			       struct mlx5_wqe_eth_seg *eseg,
 			       struct sk_buff *skb)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct mlx5e_ipsec_metadata *mdata;
 	struct mlx5e_ipsec_sa_entry *sa_entry;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index bd6f32aee8d6..ba02643586a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -52,7 +52,7 @@ void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
 			    struct xfrm_offload *xo);
 void mlx5e_ipsec_set_iv(struct sk_buff *skb, struct xfrm_state *x,
 			struct xfrm_offload *xo);
-bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
+bool mlx5e_ipsec_handle_tx_skb(struct mlx5e_priv *priv,
 			       struct mlx5_wqe_eth_seg *eseg,
 			       struct sk_buff *skb);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 7d9d9420f19d..dabbc5f226ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -9,6 +9,7 @@
 #ifdef CONFIG_MLX5_EN_TLS
 #include <net/tls.h>
 #include "accel/tls.h"
+#include "en_accel/tls_rxtx.h"
 
 #define MLX5E_KTLS_STATIC_UMR_WQE_SZ \
 	(offsetof(struct mlx5e_umr_wqe, tls_static_params_ctx) + \
@@ -96,7 +97,8 @@ void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv);
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx);
 
 bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
-			      struct sk_buff *skb, u32 *tisn, int datalen);
+			      struct sk_buff *skb, int datalen,
+			      struct mlx5e_accel_tx_tls_state *state);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index b49d7c1e49dc..352b0a3ef0ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -414,7 +414,8 @@ err_out:
 }
 
 bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq,
-			      struct sk_buff *skb, u32 *tisn, int datalen)
+			      struct sk_buff *skb, int datalen,
+			      struct mlx5e_accel_tx_tls_state *state)
 {
 	struct mlx5e_ktls_offload_context_tx *priv_tx;
 	struct mlx5e_sq_stats *stats = sq->stats;
@@ -447,7 +448,7 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s
 
 	priv_tx->expected_seq = seq + datalen;
 
-	*tisn = priv_tx->tisn;
+	state->tls_tisn = priv_tx->tisn;
 
 	stats->tls_encrypted_packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 	stats->tls_encrypted_bytes   += datalen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 8e6b0b0ce2e4..05454a843b28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -258,7 +258,7 @@ err_out:
 }
 
 bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
-			     struct sk_buff *skb, u32 *tisn)
+			     struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_tls_offload_context_tx *context;
@@ -279,7 +279,7 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 		goto err_out;
 
 	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx))
-		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, tisn, datalen);
+		return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state);
 
 	skb_seq = ntohl(tcp_hdr(skb)->seq);
 	context = mlx5e_get_tls_tx_context(tls_ctx);
@@ -302,6 +302,12 @@ err_out:
 	return false;
 }
 
+void mlx5e_tls_handle_tx_wqe(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+			     struct mlx5e_accel_tx_tls_state *state)
+{
+	cseg->tisn = cpu_to_be32(state->tls_tisn << 8);
+}
+
 static int tls_update_resync_sn(struct net_device *netdev,
 				struct sk_buff *skb,
 				struct mlx5e_tls_metadata *mdata)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 3630ed8b1206..a50d0394df0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -40,8 +40,14 @@
 #include "en.h"
 #include "en/txrx.h"
 
+struct mlx5e_accel_tx_tls_state {
+	u32 tls_tisn;
+};
+
 bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
-			     struct sk_buff *skb, u32 *tisn);
+			     struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state);
+void mlx5e_tls_handle_tx_wqe(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+			     struct mlx5e_accel_tx_tls_state *state);
 
 void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 			     u32 *cqe_bcnt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index bb6d3774eafb..f79454746d0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -383,16 +383,22 @@ err_drop:
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_accel_tx_state accel = {};
 	struct mlx5e_tx_wqe *wqe;
 	struct mlx5e_txqsq *sq;
 	u16 pi;
 
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
+
+	/* May send SKBs and WQEs. */
+	if (unlikely(!mlx5e_accel_tx_begin(dev, sq, skb, &accel)))
+		goto out;
+
 	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
-	/* might send skbs and update wqe and pi */
-	if (unlikely(!mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi)))
+	/* May update the WQE, but may not post other WQEs. */
+	if (unlikely(!mlx5e_accel_tx_finish(priv, sq, skb, wqe, &accel)))
 		goto out;
 
 	mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
-- 
cgit v1.2.3


From ab1e0ce99d3dabc57e5a383b3ffc60fb97aafe9e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 9 Apr 2020 14:02:04 +0300
Subject: net/mlx5e: kTLS, Fill work queue edge separately in TX flow

For the static and progress context params WQEs, do the edge
filling separately.
This improves the WQ utilization, code readability, and reduces
the chance of future bugs.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 352b0a3ef0ad..efc271e24b03 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -134,14 +134,14 @@ post_static_params(struct mlx5e_txqsq *sq,
 		   struct mlx5e_ktls_offload_context_tx *priv_tx,
 		   bool fence)
 {
+	u16 pi, num_wqebbs = MLX5E_KTLS_STATIC_WQEBBS;
 	struct mlx5e_umr_wqe *umr_wqe;
-	u16 pi;
 
-	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	pi = mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
 	umr_wqe = MLX5E_TLS_FETCH_UMR_WQE(sq, pi);
 	build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, 0, NULL);
-	sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
+	tx_fill_wi(sq, pi, num_wqebbs, 0, NULL);
+	sq->pc += num_wqebbs;
 }
 
 static void
@@ -149,14 +149,14 @@ post_progress_params(struct mlx5e_txqsq *sq,
 		     struct mlx5e_ktls_offload_context_tx *priv_tx,
 		     bool fence)
 {
+	u16 pi, num_wqebbs = MLX5E_KTLS_PROGRESS_WQEBBS;
 	struct mlx5e_tx_wqe *wqe;
-	u16 pi;
 
-	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	pi = mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
 	wqe = MLX5E_TLS_FETCH_PROGRESS_WQE(sq, pi);
 	build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, 0, NULL);
-	sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
+	tx_fill_wi(sq, pi, num_wqebbs, 0, NULL);
+	sq->pc += num_wqebbs;
 }
 
 static void
@@ -166,8 +166,6 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 {
 	bool progress_fence = skip_static_post || !fence_first_post;
 
-	mlx5e_txqsq_get_next_pi(sq, MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS);
-
 	if (!skip_static_post)
 		post_static_params(sq, priv_tx, fence_first_post);
 
-- 
cgit v1.2.3


From f713ce1de8970f52ebaec7aa516b125b5c75dad9 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 9 Apr 2020 12:53:31 +0300
Subject: net/mlx5e: kTLS, Do not fill edge for the DUMP WQEs in TX flow

Every single DUMP WQE resides in a single WQEBB.
As the pi is calculated per each one separately, there is
no real need for a contiguous room for them, allow them to populate
different WQ fragments.
This reduces WQ waste and improves its utilization.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index efc271e24b03..1c9d0174676d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -272,6 +272,7 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	int fsz;
 	u16 pi;
 
+	BUILD_BUG_ON(MLX5E_KTLS_DUMP_WQEBBS != 1);
 	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
 	wqe = MLX5E_TLS_FETCH_DUMP_WQE(sq, pi);
 
@@ -340,7 +341,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	struct mlx5e_sq_stats *stats = sq->stats;
 	enum mlx5e_ktls_sync_retval ret;
 	struct tx_sync_info info = {};
-	u8 num_wqebbs;
 	int i = 0;
 
 	ret = tx_sync_info_get(priv_tx, seq, datalen, &info);
@@ -369,9 +369,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 		return MLX5E_KTLS_SYNC_DONE;
 	}
 
-	num_wqebbs = mlx5e_ktls_dumps_num_wqebbs(sq, info.nr_frags, info.sync_len);
-	mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
-
 	for (; i < info.nr_frags; i++) {
 		unsigned int orig_fsz, frag_offset = 0, n = 0;
 		skb_frag_t *f = &info.frags[i];
-- 
cgit v1.2.3


From 05dfd570826f1ae408e1a3faeddb753ff06fed14 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 9 Apr 2020 13:43:43 +0300
Subject: net/mlx5e: Take TX WQE info structures out of general EN header

Into the txrx header file.
The mlx5e_sq_wqe_info structure describes WQE info for the ICOSQ,
rename it to better reflect this.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 27 -----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 22 ++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  |  5 +++++
 3 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index da7fe6aafeed..3bd64c63865b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -339,16 +339,6 @@ struct mlx5e_cq_decomp {
 	u16                        wqe_counter;
 } ____cacheline_aligned_in_smp;
 
-struct mlx5e_tx_wqe_info {
-	struct sk_buff *skb;
-	u32 num_bytes;
-	u8  num_wqebbs;
-	u8  num_dma;
-#ifdef CONFIG_MLX5_EN_TLS
-	struct page *resync_dump_frag_page;
-#endif
-};
-
 enum mlx5e_dma_map_type {
 	MLX5E_DMA_MAP_SINGLE,
 	MLX5E_DMA_MAP_PAGE
@@ -370,18 +360,6 @@ enum {
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 };
 
-struct mlx5e_icosq_wqe_info {
-	u8  opcode;
-	u8 num_wqebbs;
-
-	/* Auxiliary data for different opcodes. */
-	union {
-		struct {
-			struct mlx5e_rq *rq;
-		} umr;
-	};
-};
-
 struct mlx5e_txqsq {
 	/* data path */
 
@@ -484,11 +462,6 @@ struct mlx5e_xdp_info_fifo {
 	u32 mask;
 };
 
-struct mlx5e_xdp_wqe_info {
-	u8 num_wqebbs;
-	u8 num_pkts;
-};
-
 struct mlx5e_xdp_mpwqe {
 	/* Current MPWQE session */
 	struct mlx5e_tx_wqe *wqe;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 89fe65593c16..9e150d160cde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -81,6 +81,16 @@ mlx5e_post_nop_fence(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
 	return wqe;
 }
 
+struct mlx5e_tx_wqe_info {
+	struct sk_buff *skb;
+	u32 num_bytes;
+	u8 num_wqebbs;
+	u8 num_dma;
+#ifdef CONFIG_MLX5_EN_TLS
+	struct page *resync_dump_frag_page;
+#endif
+};
+
 static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
@@ -109,6 +119,18 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+struct mlx5e_icosq_wqe_info {
+	u8 opcode;
+	u8 num_wqebbs;
+
+	/* Auxiliary data for different opcodes. */
+	union {
+		struct {
+			struct mlx5e_rq *rq;
+		} umr;
+	};
+};
+
 static inline u16 mlx5e_icosq_get_next_pi(struct mlx5e_icosq *sq, u16 size)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ed6f045febeb..e2e01f064c1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -137,6 +137,11 @@ mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
 	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
 }
 
+struct mlx5e_xdp_wqe_info {
+	u8 num_wqebbs;
+	u8 num_pkts;
+};
+
 static inline void
 mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 			 struct mlx5e_xdp_xmit_data *xdptxd,
-- 
cgit v1.2.3


From 41a8e4ebb4727912c54504125e134723df8cf3cf Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 19 Mar 2020 16:50:14 +0200
Subject: net/mlx5e: Use struct assignment for WQE info updates

Struct assignment looks more clean, and implies resetting
the not assigned fields to zero, instead of holding values
from older ring cycles.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c   |  9 +++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c        | 16 ++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c          |  9 ++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c        |  7 +++++--
 4 files changed, 24 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 1c9d0174676d..3cd78d9503c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -108,10 +108,11 @@ static void tx_fill_wi(struct mlx5e_txqsq *sq,
 {
 	struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
 
-	memset(wi, 0, sizeof(*wi));
-	wi->num_wqebbs = num_wqebbs;
-	wi->num_bytes  = num_bytes;
-	wi->resync_dump_frag_page = page;
+	*wi = (struct mlx5e_tx_wqe_info) {
+		.num_wqebbs = num_wqebbs,
+		.num_bytes  = num_bytes,
+		.resync_dump_frag_page = page,
+	};
 }
 
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 048a4f8601a8..0a9dfc31de3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1364,13 +1364,12 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
 		u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-		struct mlx5e_tx_wqe_info *wi;
 		struct mlx5e_tx_wqe *nop;
 
-		wi = &sq->db.wqe_info[pi];
+		sq->db.wqe_info[pi] = (struct mlx5e_tx_wqe_info) {
+			.num_wqebbs = 1,
+		};
 
-		memset(wi, 0, sizeof(*wi));
-		wi->num_wqebbs = 1;
 		nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
@@ -1482,20 +1481,21 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 
 		/* Pre initialize fixed WQE fields */
 		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-			struct mlx5e_xdp_wqe_info *wi  = &sq->db.wqe_info[i];
 			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
 			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
 			struct mlx5_wqe_data_seg *dseg;
 
+			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
+				.num_wqebbs = 1,
+				.num_pkts   = 1,
+			};
+
 			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
 			dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
 			dseg->lkey = sq->mkey_be;
-
-			wi->num_wqebbs = 1;
-			wi->num_pkts   = 1;
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d9a5a669b84d..8142b6e70857 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -505,9 +505,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 			    MLX5_OPCODE_UMR);
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
-	sq->db.wqe_info[pi].opcode = MLX5_OPCODE_UMR;
-	sq->db.wqe_info[pi].num_wqebbs = MLX5E_UMR_WQEBBS;
-	sq->db.wqe_info[pi].umr.rq = rq;
+	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
+		.opcode     = MLX5_OPCODE_UMR,
+		.num_wqebbs = MLX5E_UMR_WQEBBS,
+		.umr.rq     = rq,
+	};
+
 	sq->pc += MLX5E_UMR_WQEBBS;
 
 	sq->doorbell_cseg = &umr_wqe->ctrl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 869fd58a6775..73293f9c3f63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -78,8 +78,11 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 	struct mlx5e_tx_wqe *nopwqe;
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
-	sq->db.wqe_info[pi].opcode = MLX5_OPCODE_NOP;
-	sq->db.wqe_info[pi].num_wqebbs = 1;
+	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
+		.opcode     = MLX5_OPCODE_NOP,
+		.num_wqebbs = 1,
+	};
+
 	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
-- 
cgit v1.2.3


From 6b74f60ef5a97ec3988a41e4bb745660029209a2 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 30 Mar 2020 15:42:02 +0300
Subject: net/mlx5: Accel, Remove unnecessary header include

The include of Ethernet driver header in core is not needed
and actually wrong.
Remove it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
index c13260467750..82b185121edb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
@@ -5,7 +5,6 @@
 
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
-#include "en.h"
 
 static inline bool is_metadata_hdr_valid(struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From 28bff09518e9ef942173e41e7521b93ea7be0cf0 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 16 Dec 2019 14:05:07 +0200
Subject: net/mlx5e: Enhance ICOSQ WQE info fields

The same WQE opcode might be used in different ICOSQ flows
and WQE types.
To have a better distinguishability, replace it with an enum that
better indicates the WQE type and flow it is used for.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 11 ++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 17 ++++++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |  2 +-
 3 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 9e150d160cde..dce2bbbf9109 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -27,6 +27,11 @@
 
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
 
+enum mlx5e_icosq_wqe_type {
+	MLX5E_ICOSQ_WQE_NOP,
+	MLX5E_ICOSQ_WQE_UMR_RX,
+};
+
 static inline bool
 mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 {
@@ -120,10 +125,10 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 }
 
 struct mlx5e_icosq_wqe_info {
-	u8 opcode;
+	u8 wqe_type;
 	u8 num_wqebbs;
 
-	/* Auxiliary data for different opcodes. */
+	/* Auxiliary data for different wqe types. */
 	union {
 		struct {
 			struct mlx5e_rq *rq;
@@ -147,7 +152,7 @@ static inline u16 mlx5e_icosq_get_next_pi(struct mlx5e_icosq *sq, u16 size)
 		/* Fill SQ frag edge with NOPs to avoid WQE wrapping two pages. */
 		for (; wi < edge_wi; wi++) {
 			*wi = (struct mlx5e_icosq_wqe_info) {
-				.opcode = MLX5_OPCODE_NOP,
+				.wqe_type   = MLX5E_ICOSQ_WQE_NOP,
 				.num_wqebbs = 1,
 			};
 			mlx5e_post_nop(wq, sq->sqn, &sq->pc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8142b6e70857..779600bebcca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -506,7 +506,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
-		.opcode     = MLX5_OPCODE_UMR,
+		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,
 		.num_wqebbs = MLX5E_UMR_WQEBBS,
 		.umr.rq     = rq,
 	};
@@ -619,15 +619,18 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 				break;
 			}
 
-			if (likely(wi->opcode == MLX5_OPCODE_UMR))
+			switch (wi->wqe_type) {
+			case MLX5E_ICOSQ_WQE_UMR_RX:
 				wi->umr.rq->mpwqe.umr_completed++;
-			else if (unlikely(wi->opcode != MLX5_OPCODE_NOP))
+				break;
+			case MLX5E_ICOSQ_WQE_NOP:
+				break;
+			default:
 				netdev_WARN_ONCE(cq->channel->netdev,
-						 "Bad OPCODE in ICOSQ WQE info: 0x%x\n",
-						 wi->opcode);
-
+						 "Bad WQE type in ICOSQ WQE info: 0x%x\n",
+						 wi->wqe_type);
+			}
 		} while (!last_wqe);
-
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	sq->cc = sqcc;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 73293f9c3f63..8480278f2ee2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -79,7 +79,7 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
-		.opcode     = MLX5_OPCODE_NOP,
+		.wqe_type   = MLX5E_ICOSQ_WQE_NOP,
 		.num_wqebbs = 1,
 	};
 
-- 
cgit v1.2.3


From 38e86bfcf7f565639d89ce99ecf41a598f652cdc Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:54 +0300
Subject: net: atlantic: use __packed instead of the full expansion.

This patches fixes the review comment made by Jakub Kicinski
in the "net: atlantic: A2 support" patch series.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
index 2317dd8459d0..b66fa346581c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -103,7 +103,7 @@ struct sleep_proxy_s {
 		u32 crc32;
 	} wake_up_pattern[8];
 
-	struct __attribute__ ((__packed__)) {
+	struct __packed {
 		u8 arp_responder:1;
 		u8 echo_responder:1;
 		u8 igmp_client:1;
@@ -119,7 +119,7 @@ struct sleep_proxy_s {
 	u32 ipv4_offload_addr[8];
 	u32 reserved[8];
 
-	struct __attribute__ ((__packed__)) {
+	struct __packed {
 		u8 ns_responder:1;
 		u8 echo_responder:1;
 		u8 mld_client:1;
-- 
cgit v1.2.3


From 7bb377107c72a40ab7505341f8626c8eb79a0cb7 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:55 +0300
Subject: net: atlantic: minor MACSec code cleanup

This patch fixes a couple of minor merge issues found in macsec_api.c
after corresponding patch series has been applied.

These are not real bugs, so pushing to net-next.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c
index fbe9d88b13c7..36c7cf05630a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c
+++ b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c
@@ -846,8 +846,7 @@ static int get_ingress_sakey_record(struct aq_hw_s *hw,
 	rec->key[7] = packed_record[14];
 	rec->key[7] |= packed_record[15] << 16;
 
-	rec->key_len = (rec->key_len & 0xFFFFFFFC) |
-		       (packed_record[16] & 0x3);
+	rec->key_len = packed_record[16] & 0x3;
 
 	return 0;
 }
@@ -1158,6 +1157,7 @@ static int set_egress_ctlf_record(struct aq_hw_s *hw,
 
 	packed_record[0] = rec->sa_da[0] & 0xFFFF;
 	packed_record[1] = (rec->sa_da[0] >> 16) & 0xFFFF;
+
 	packed_record[2] = rec->sa_da[1] & 0xFFFF;
 
 	packed_record[3] = rec->eth_type & 0xFFFF;
@@ -1552,7 +1552,7 @@ static int set_egress_sc_record(struct aq_hw_s *hw,
 
 	packed_record[5] |= (rec->sak_len & 0x3) << 4;
 
-	packed_record[7] |= (rec->valid & 0x1) << 15;
+	packed_record[7] = (rec->valid & 0x1) << 15;
 
 	return set_raw_egress_record(hw, packed_record, 8, 2,
 				     ROWOFFSET_EGRESSSCRECORD + table_index);
-- 
cgit v1.2.3


From 843e1396f62ed7ff57feaea9ceb3374ad42f445f Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:56 +0300
Subject: net: atlantic: rename AQ_NIC_RATE_2GS to AQ_NIC_RATE_2G5

This patch changes the constant name to a more logical "2G5"
(for 2.5G speeds).

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_common.h        | 11 ++++++-----
 drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c       |  2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c           | 13 +++++++------
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c | 15 ++++++++-------
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 15 ++++++++-------
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c  |  9 +++++----
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h  |  9 +++++----
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c | 13 +++++++------
 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c  |  2 +-
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c |  2 +-
 10 files changed, 49 insertions(+), 42 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index 53620ba6d7a6..52ad9433cabc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File aq_common.h: Basic includes for all files in project. */
@@ -53,14 +54,14 @@
 #define AQ_NIC_RATE_10G		BIT(0)
 #define AQ_NIC_RATE_5G		BIT(1)
 #define AQ_NIC_RATE_5GSR	BIT(2)
-#define AQ_NIC_RATE_2GS		BIT(3)
+#define AQ_NIC_RATE_2G5		BIT(3)
 #define AQ_NIC_RATE_1G		BIT(4)
 #define AQ_NIC_RATE_100M	BIT(5)
 #define AQ_NIC_RATE_10M		BIT(6)
 
 #define AQ_NIC_RATE_EEE_10G	BIT(7)
 #define AQ_NIC_RATE_EEE_5G	BIT(8)
-#define AQ_NIC_RATE_EEE_2GS	BIT(9)
+#define AQ_NIC_RATE_EEE_2G5	BIT(9)
 #define AQ_NIC_RATE_EEE_1G	BIT(10)
 #define AQ_NIC_RATE_EEE_100M	BIT(11)
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 0c9dd8edc062..86fc77d85fda 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -605,7 +605,7 @@ static enum hw_atl_fw2x_rate eee_mask_to_ethtool_mask(u32 speed)
 	if (speed & AQ_NIC_RATE_EEE_10G)
 		rate |= SUPPORTED_10000baseT_Full;
 
-	if (speed & AQ_NIC_RATE_EEE_2GS)
+	if (speed & AQ_NIC_RATE_EEE_2G5)
 		rate |= SUPPORTED_2500baseX_Full;
 
 	if (speed & AQ_NIC_RATE_EEE_1G)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index f97b073efd8e..18cad06f2ea7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2019 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File aq_nic.c: Definition of common code for NIC. */
@@ -894,7 +895,7 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     5000baseT_Full);
 
-	if (self->aq_nic_cfg.aq_hw_caps->link_speed_msk & AQ_NIC_RATE_2GS)
+	if (self->aq_nic_cfg.aq_hw_caps->link_speed_msk & AQ_NIC_RATE_2G5)
 		ethtool_link_ksettings_add_link_mode(cmd, supported,
 						     2500baseT_Full);
 
@@ -937,7 +938,7 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     5000baseT_Full);
 
-	if (self->aq_nic_cfg.link_speed_msk  & AQ_NIC_RATE_2GS)
+	if (self->aq_nic_cfg.link_speed_msk  & AQ_NIC_RATE_2G5)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     2500baseT_Full);
 
@@ -996,7 +997,7 @@ int aq_nic_set_link_ksettings(struct aq_nic_s *self,
 			break;
 
 		case SPEED_2500:
-			rate = AQ_NIC_RATE_2GS;
+			rate = AQ_NIC_RATE_2G5;
 			break;
 
 		case SPEED_5000:
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index eee265b4415a..70f06c40bdf2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_a0.c: Definition of Atlantic hardware specific functions. */
@@ -47,7 +48,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = {
 	DEFAULT_A0_BOARD_BASIC_CAPABILITIES,
 	.media_type = AQ_HW_MEDIA_TYPE_FIBRE,
 	.link_speed_msk = AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -57,7 +58,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc107 = {
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
 	.link_speed_msk = AQ_NIC_RATE_10G |
 			  AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -66,7 +67,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc108 = {
 	DEFAULT_A0_BOARD_BASIC_CAPABILITIES,
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
 	.link_speed_msk = AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -74,7 +75,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc108 = {
 const struct aq_hw_caps_s hw_atl_a0_caps_aqc109 = {
 	DEFAULT_A0_BOARD_BASIC_CAPABILITIES,
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
-	.link_speed_msk = AQ_NIC_RATE_2GS |
+	.link_speed_msk = AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index cbb7a00d61b4..1d872547a87c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2019 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_b0.c: Definition of Atlantic hardware specific functions. */
@@ -59,7 +60,7 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = {
 	.media_type = AQ_HW_MEDIA_TYPE_FIBRE,
 	.link_speed_msk = AQ_NIC_RATE_10G |
 			  AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -69,7 +70,7 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc107 = {
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
 	.link_speed_msk = AQ_NIC_RATE_10G |
 			  AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -78,7 +79,7 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc108 = {
 	DEFAULT_B0_BOARD_BASIC_CAPABILITIES,
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
 	.link_speed_msk = AQ_NIC_RATE_5G |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
@@ -86,7 +87,7 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc108 = {
 const struct aq_hw_caps_s hw_atl_b0_caps_aqc109 = {
 	DEFAULT_B0_BOARD_BASIC_CAPABILITIES,
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
-	.link_speed_msk = AQ_NIC_RATE_2GS |
+	.link_speed_msk = AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G |
 			  AQ_NIC_RATE_100M,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 1100d40a0302..73c0f41df8d8 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2019 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_utils.c: Definition of common functions for Atlantic hardware
@@ -687,7 +688,7 @@ int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
 			link_status->mbps = 5000U;
 			break;
 
-		case HAL_ATLANTIC_RATE_2GS:
+		case HAL_ATLANTIC_RATE_2G5:
 			link_status->mbps = 2500U;
 			break;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 99c1b6644ec3..0b4b54fc1de0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2019 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_utils.h: Declaration of common functions for Atlantic hardware
@@ -418,7 +419,7 @@ enum hal_atl_utils_fw_state_e {
 #define HAL_ATLANTIC_RATE_10G        BIT(0)
 #define HAL_ATLANTIC_RATE_5G         BIT(1)
 #define HAL_ATLANTIC_RATE_5GSR       BIT(2)
-#define HAL_ATLANTIC_RATE_2GS        BIT(3)
+#define HAL_ATLANTIC_RATE_2G5        BIT(3)
 #define HAL_ATLANTIC_RATE_1G         BIT(4)
 #define HAL_ATLANTIC_RATE_100M       BIT(5)
 #define HAL_ATLANTIC_RATE_INVALID    BIT(6)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 1ad10cc14918..017364486703 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2019 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_utils_fw2x.c: Definition of firmware 2.x functions for
@@ -134,7 +135,7 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
 	if (speed & AQ_NIC_RATE_5GSR)
 		rate |= FW2X_RATE_5G;
 
-	if (speed & AQ_NIC_RATE_2GS)
+	if (speed & AQ_NIC_RATE_2G5)
 		rate |= FW2X_RATE_2G5;
 
 	if (speed & AQ_NIC_RATE_1G)
@@ -155,7 +156,7 @@ static u32 fw2x_to_eee_mask(u32 speed)
 	if (speed & HW_ATL_FW2X_CAP_EEE_5G_MASK)
 		rate |= AQ_NIC_RATE_EEE_5G;
 	if (speed & HW_ATL_FW2X_CAP_EEE_2G5_MASK)
-		rate |= AQ_NIC_RATE_EEE_2GS;
+		rate |= AQ_NIC_RATE_EEE_2G5;
 	if (speed & HW_ATL_FW2X_CAP_EEE_1G_MASK)
 		rate |= AQ_NIC_RATE_EEE_1G;
 
@@ -170,7 +171,7 @@ static u32 eee_mask_to_fw2x(u32 speed)
 		rate |= HW_ATL_FW2X_CAP_EEE_10G_MASK;
 	if (speed & AQ_NIC_RATE_EEE_5G)
 		rate |= HW_ATL_FW2X_CAP_EEE_5G_MASK;
-	if (speed & AQ_NIC_RATE_EEE_2GS)
+	if (speed & AQ_NIC_RATE_EEE_2G5)
 		rate |= HW_ATL_FW2X_CAP_EEE_2G5_MASK;
 	if (speed & AQ_NIC_RATE_EEE_1G)
 		rate |= HW_ATL_FW2X_CAP_EEE_1G_MASK;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 04d194f754fa..84d9b828dc4e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -60,7 +60,7 @@ const struct aq_hw_caps_s hw_atl2_caps_aqc113 = {
 	.media_type = AQ_HW_MEDIA_TYPE_TP,
 	.link_speed_msk = AQ_NIC_RATE_10G |
 			  AQ_NIC_RATE_5G  |
-			  AQ_NIC_RATE_2GS |
+			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G  |
 			  AQ_NIC_RATE_100M      |
 			  AQ_NIC_RATE_10M,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index f5fb4b11f51a..e8f4aad8c1e5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -129,7 +129,7 @@ static void a2_link_speed_mask2fw(u32 speed,
 	link_options->rate_10G = !!(speed & AQ_NIC_RATE_10G);
 	link_options->rate_5G = !!(speed & AQ_NIC_RATE_5G);
 	link_options->rate_N5G = !!(speed & AQ_NIC_RATE_5GSR);
-	link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2GS);
+	link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2G5);
 	link_options->rate_N2P5G = link_options->rate_2P5G;
 	link_options->rate_1G = !!(speed & AQ_NIC_RATE_1G);
 	link_options->rate_100M = !!(speed & AQ_NIC_RATE_100M);
-- 
cgit v1.2.3


From c64d7b23f51161ceb6e92f8e5b8077e8e04ddbef Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:57 +0300
Subject: net: atlantic: remove TPO2 check from A0 code

TPO2 was introduced in B0 only, no reason to check for it in A0 code.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 70f06c40bdf2..1b0670a8ae33 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -268,8 +268,7 @@ static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self)
 	hw_atl_tdm_tx_desc_wr_wb_irq_en_set(self, 1U);
 
 	/* misc */
-	aq_hw_write_reg(self, 0x00007040U, ATL_HW_IS_CHIP_FEATURE(self, TPO2) ?
-			0x00010000U : 0x00000000U);
+	aq_hw_write_reg(self, 0x00007040U, 0x00000000U);
 	hw_atl_tdm_tx_dca_en_set(self, 0U);
 	hw_atl_tdm_tx_dca_mode_set(self, 0U);
 
-- 
cgit v1.2.3


From ad46bd5ec357ebb18c42398d8760bad4d611b53e Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:58 +0300
Subject: net: atlantic: remove hw_atl_b0_hw_rss_set call from A2 code

No need to call hw_atl_b0_hw_rss_set from hw_atl2_hw_rss_set

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 4 ++--
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h | 9 ++++-----
 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c  | 2 +-
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 1d872547a87c..fa3cd7e9954b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -216,8 +216,8 @@ err_exit:
 	return err;
 }
 
-int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
-			 struct aq_rss_parameters *rss_params)
+static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
+				struct aq_rss_parameters *rss_params)
 {
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	u8 *indirection_table =	rss_params->indirection_table;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index f5091d79ab43..b855459272ca 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * aQuantia Corporation Network Driver
- * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
+/* Atlantic Network Driver
+ *
+ * Copyright (C) 2014-2019 aQuantia Corporation
+ * Copyright (C) 2019-2020 Marvell International Ltd.
  */
 
 /* File hw_atl_b0.h: Declaration of abstract interface for Atlantic hardware
@@ -35,8 +36,6 @@ extern const struct aq_hw_ops hw_atl_ops_b0;
 
 int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 			      struct aq_rss_parameters *rss_params);
-int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
-			 struct aq_rss_parameters *rss_params);
 int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 			     struct aq_nic_cfg_s *aq_nic_cfg);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 84d9b828dc4e..6f2b33ae3d06 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -172,7 +172,7 @@ static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;)
 		hw_atl2_new_rpf_rss_redir_set(self, 0, i, indirection_table[i]);
 
-	return hw_atl_b0_hw_rss_set(self, rss_params);
+	return aq_hw_err_from_flags(self);
 }
 
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
-- 
cgit v1.2.3


From 097d638cf4e19be208d26c6bbbca7f8da348294a Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:46:59 +0300
Subject: net: atlantic: remove check for boot code survivability before reset
 request

This patch removes unnecessary check for boot code survivability before
reset request.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c
index 85ccc9a011a0..f3766780e975 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.c
@@ -75,14 +75,6 @@ int hw_atl2_utils_soft_reset(struct aq_hw_s *self)
 	u32 rbl_request;
 	int err;
 
-	err = readx_poll_timeout_atomic(hw_atl2_mif_mcp_boot_reg_get, self,
-				rbl_status,
-				((rbl_status & AQ_A2_BOOT_STARTED) &&
-				 (rbl_status != 0xFFFFFFFFu)),
-				10, 500000);
-	if (err)
-		aq_pr_trace("Boot code probably hanged, reboot anyway");
-
 	hw_atl2_mif_host_req_int_clr(self, 0x01);
 	rbl_request = AQ_A2_FW_BOOT_REQ_REBOOT;
 #ifdef AQ_CFG_FAST_START
-- 
cgit v1.2.3


From b4de6c49e569c7ca91bf0d4c25cdb6eeca9c9529 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Sat, 9 May 2020 09:47:00 +0300
Subject: net: atlantic: unify MAC generation

This patch unifies invalid MAC address handling with other drivers.

Basically we've switched to using standard APIs (is_valid_ether_addr /
eth_hw_addr_random) where possible.
It's worth noting that some of engineering Aquantia NICs might be
provisioned with a partially zeroed out MAC, which is still invalid,
but not caught by is_valid_ether_addr(), so we've added a special
handling for this case.

Also adding a warning in case of fallback to random MAC, because
this shouldn't be needed on production NICs, they should all be
provisioned with unique MAC.

NB! Default systemd/udevd configuration is 'MACAddressPolicy=persistent'.
    This causes MAC address to be persisted across driver reloads and
    reboots. We had to change it to 'none' for verification purposes.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 14 +++++++++++++
 .../aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   | 22 ---------------------
 .../aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c   | 23 +---------------------
 3 files changed, 15 insertions(+), 44 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 18cad06f2ea7..1c6d12deb47a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -272,6 +272,14 @@ exit:
 	return err;
 }
 
+static bool aq_nic_is_valid_ether_addr(const u8 *addr)
+{
+	/* Some engineering samples of Aquantia NICs are provisioned with a
+	 * partially populated MAC, which is still invalid.
+	 */
+	return !(addr[0] == 0 && addr[1] == 0 && addr[2] == 0);
+}
+
 int aq_nic_ndev_register(struct aq_nic_s *self)
 {
 	int err = 0;
@@ -296,6 +304,12 @@ int aq_nic_ndev_register(struct aq_nic_s *self)
 	if (err)
 		goto err_exit;
 
+	if (!is_valid_ether_addr(self->ndev->dev_addr) ||
+	    !aq_nic_is_valid_ether_addr(self->ndev->dev_addr)) {
+		netdev_warn(self->ndev, "MAC is invalid, will use random.");
+		eth_hw_addr_random(self->ndev);
+	}
+
 #if defined(AQ_CFG_MAC_ADDR_PERMANENT)
 	{
 		static u8 mac_addr_permanent[] = AQ_CFG_MAC_ADDR_PERMANENT;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 017364486703..eeedd8c90067 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -283,8 +283,6 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
 	u32 efuse_addr = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_EFUSE_ADDR);
 	u32 mac_addr[2] = { 0 };
 	int err = 0;
-	u32 h = 0U;
-	u32 l = 0U;
 
 	if (efuse_addr != 0) {
 		err = hw_atl_utils_fw_downld_dwords(self,
@@ -299,26 +297,6 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
 
 	ether_addr_copy(mac, (u8 *)mac_addr);
 
-	if ((mac[0] & 0x01U) || ((mac[0] | mac[1] | mac[2]) == 0x00U)) {
-		unsigned int rnd = 0;
-
-		get_random_bytes(&rnd, sizeof(unsigned int));
-
-		l = 0xE3000000U | (0xFFFFU & rnd) | (0x00 << 16);
-		h = 0x8001300EU;
-
-		mac[5] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[4] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[3] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[2] = (u8)(0xFFU & l);
-		mac[1] = (u8)(0xFFU & h);
-		h >>= 8;
-		mac[0] = (u8)(0xFFU & h);
-	}
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index e8f4aad8c1e5..0ffc33bd67d0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -6,6 +6,7 @@
 #include <linux/iopoll.h>
 
 #include "aq_hw.h"
+#include "aq_hw_utils.h"
 #include "hw_atl/hw_atl_llh.h"
 #include "hw_atl2_utils.h"
 #include "hw_atl2_llh.h"
@@ -212,28 +213,6 @@ static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
 	hw_atl2_shared_buffer_get(self, mac_address, mac_address);
 	ether_addr_copy(mac, (u8 *)mac_address.aligned.mac_address);
 
-	if ((mac[0] & 0x01U) || ((mac[0] | mac[1] | mac[2]) == 0x00U)) {
-		unsigned int rnd = 0;
-		u32 h;
-		u32 l;
-
-		get_random_bytes(&rnd, sizeof(unsigned int));
-
-		l = 0xE3000000U | (0xFFFFU & rnd) | (0x00 << 16);
-		h = 0x8001300EU;
-
-		mac[5] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[4] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[3] = (u8)(0xFFU & l);
-		l >>= 8;
-		mac[2] = (u8)(0xFFU & l);
-		mac[1] = (u8)(0xFFU & h);
-		h >>= 8;
-		mac[0] = (u8)(0xFFU & h);
-	}
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 72ef908bb3ff9261dc38d079ef332c91418f8693 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Fri, 8 May 2020 20:18:50 +0000
Subject: hinic: add three net_device_ops of vf

adds ndo_set_vf_rate/ndo_set_vf_spoofchk/ndo_set_vf_link_state
to configure netdev of virtual function

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c |  29 +++
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c  |  35 ++-
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h  |  21 ++
 drivers/net/ethernet/huawei/hinic/hinic_hw_if.c   |  32 ++-
 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h   |   6 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c |   4 +-
 drivers/net/ethernet/huawei/hinic/hinic_main.c    |  17 +-
 drivers/net/ethernet/huawei/hinic/hinic_port.c    |   8 +-
 drivers/net/ethernet/huawei/hinic/hinic_port.h    |  43 ++++
 drivers/net/ethernet/huawei/hinic/hinic_sriov.c   | 275 ++++++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_sriov.h   |   7 +
 11 files changed, 453 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index 33c5333657c1..cb5b6e5f787f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -849,6 +849,25 @@ err_init_cmdq:
 	return err;
 }
 
+static int hinic_set_cmdq_depth(struct hinic_hwdev *hwdev, u16 cmdq_depth)
+{
+	struct hinic_cmd_hw_ioctxt hw_ioctxt = { 0 };
+	struct hinic_pfhwdev *pfhwdev;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+	hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwdev->hwif);
+
+	hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_ENABLE;
+	hw_ioctxt.cmdq_depth = (u8)ilog2(cmdq_depth);
+
+	return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
+				 HINIC_COMM_CMD_HWCTXT_SET,
+				 &hw_ioctxt, sizeof(hw_ioctxt), NULL,
+				 NULL, HINIC_MGMT_MSG_SYNC);
+}
+
 /**
  * hinic_init_cmdqs - init all cmdqs
  * @cmdqs: cmdqs to init
@@ -899,8 +918,18 @@ int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif,
 
 	hinic_ceq_register_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ, cmdqs,
 			      cmdq_ceq_handler);
+
+	err = hinic_set_cmdq_depth(hwdev, CMDQ_DEPTH);
+	if (err) {
+		dev_err(&hwif->pdev->dev, "Failed to set cmdq depth\n");
+		goto err_set_cmdq_depth;
+	}
+
 	return 0;
 
+err_set_cmdq_depth:
+	hinic_ceq_unregister_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ);
+
 err_cmdq_ctxt:
 	hinic_wqs_cmdq_free(&cmdqs->cmdq_pages, cmdqs->saved_wqs,
 			    HINIC_MAX_CMDQ_TYPES);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index e5cab58e4ddd..1ce8b8d572cf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -44,10 +44,6 @@ enum io_status {
 	IO_RUNNING = 1,
 };
 
-enum hw_ioctxt_set_cmdq_depth {
-	HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT,
-};
-
 /**
  * get_capability - convert device capabilities to NIC capabilities
  * @hwdev: the HW device to set and convert device capabilities for
@@ -667,6 +663,32 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev)
 	hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt);
 }
 
+static int hinic_l2nic_reset(struct hinic_hwdev *hwdev)
+{
+	struct hinic_cmd_l2nic_reset l2nic_reset = {0};
+	u16 out_size = sizeof(l2nic_reset);
+	struct hinic_pfhwdev *pfhwdev;
+	int err;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	l2nic_reset.func_id = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+	/* 0 represents standard l2nic reset flow */
+	l2nic_reset.reset_flag = 0;
+
+	err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
+				HINIC_COMM_CMD_L2NIC_RESET, &l2nic_reset,
+				sizeof(l2nic_reset), &l2nic_reset,
+				&out_size, HINIC_MGMT_MSG_SYNC);
+	if (err || !out_size || l2nic_reset.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to reset L2NIC resources, err: %d, status: 0x%x, out_size: 0x%x\n",
+			err, l2nic_reset.status, out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /**
  * hinic_init_hwdev - Initialize the NIC HW
  * @pdev: the NIC pci device
@@ -729,6 +751,10 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev)
 		goto err_init_pfhwdev;
 	}
 
+	err = hinic_l2nic_reset(hwdev);
+	if (err)
+		goto err_l2nic_reset;
+
 	err = get_dev_cap(hwdev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to get device capabilities\n");
@@ -759,6 +785,7 @@ err_resources_state:
 err_init_fw_ctxt:
 	hinic_vf_func_free(hwdev);
 err_vf_func_init:
+err_l2nic_reset:
 err_dev_cap:
 	free_pfhwdev(pfhwdev);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 531d1072e0df..c8f62a024a58 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -25,6 +25,7 @@
 
 #define HINIC_PF_SET_VF_ALREADY				0x4
 #define HINIC_MGMT_STATUS_EXIST				0x6
+#define HINIC_MGMT_CMD_UNSUPPORTED			0xFF
 
 struct hinic_cap {
 	u16     max_qps;
@@ -33,6 +34,11 @@ struct hinic_cap {
 	u16     max_vf_qps;
 };
 
+enum hw_ioctxt_set_cmdq_depth {
+	HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT,
+	HW_IOCTXT_SET_CMDQ_DEPTH_ENABLE,
+};
+
 enum hinic_port_cmd {
 	HINIC_PORT_CMD_VF_REGISTER = 0x0,
 	HINIC_PORT_CMD_VF_UNREGISTER = 0x1,
@@ -86,12 +92,16 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_FWCTXT_INIT      = 69,
 
+	HINIC_PORT_CMD_ENABLE_SPOOFCHK = 78,
+
 	HINIC_PORT_CMD_GET_MGMT_VERSION = 88,
 
 	HINIC_PORT_CMD_SET_FUNC_STATE   = 93,
 
 	HINIC_PORT_CMD_GET_GLOBAL_QPN   = 102,
 
+	HINIC_PORT_CMD_SET_VF_RATE = 105,
+
 	HINIC_PORT_CMD_SET_VF_VLAN	= 106,
 
 	HINIC_PORT_CMD_CLR_VF_VLAN,
@@ -107,6 +117,8 @@ enum hinic_port_cmd {
 	HINIC_PORT_CMD_GET_CAP          = 170,
 
 	HINIC_PORT_CMD_SET_LRO_TIMER	= 244,
+
+	HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 249,
 };
 
 enum hinic_ucode_cmd {
@@ -247,6 +259,15 @@ struct hinic_cmd_hw_ci {
 	u64     ci_addr;
 };
 
+struct hinic_cmd_l2nic_reset {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	reset_flag;
+};
+
 struct hinic_hwdev {
 	struct hinic_hwif               *hwif;
 	struct msix_entry               *msix_entries;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index 3fbd2eb80582..cf127d896ba6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -10,6 +10,7 @@
 #include <linux/io.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
+#include <linux/delay.h>
 
 #include "hinic_hw_csr.h"
 #include "hinic_hw_if.h"
@@ -18,6 +19,8 @@
 
 #define VALID_MSIX_IDX(attr, msix_index) ((msix_index) < (attr)->num_irqs)
 
+#define WAIT_HWIF_READY_TIMEOUT	10000
+
 /**
  * hinic_msix_attr_set - set message attribute for msix entry
  * @hwif: the HW interface of a pci function device
@@ -187,20 +190,39 @@ void hinic_set_msix_state(struct hinic_hwif *hwif, u16 msix_idx,
  **/
 static int hwif_ready(struct hinic_hwif *hwif)
 {
-	struct pci_dev *pdev = hwif->pdev;
 	u32 addr, attr1;
 
 	addr   = HINIC_CSR_FUNC_ATTR1_ADDR;
 	attr1  = hinic_hwif_read_reg(hwif, addr);
 
-	if (!HINIC_FA1_GET(attr1, INIT_STATUS)) {
-		dev_err(&pdev->dev, "hwif status is not ready\n");
-		return -EFAULT;
+	if (!HINIC_FA1_GET(attr1, MGMT_INIT_STATUS))
+		return -EBUSY;
+
+	if (HINIC_IS_VF(hwif)) {
+		if (!HINIC_FA1_GET(attr1, PF_INIT_STATUS))
+			return -EBUSY;
 	}
 
 	return 0;
 }
 
+static int wait_hwif_ready(struct hinic_hwif *hwif)
+{
+	unsigned long timeout = 0;
+
+	do {
+		if (!hwif_ready(hwif))
+			return 0;
+
+		usleep_range(999, 1000);
+		timeout++;
+	} while (timeout <= WAIT_HWIF_READY_TIMEOUT);
+
+	dev_err(&hwif->pdev->dev, "Wait for hwif timeout\n");
+
+	return -EBUSY;
+}
+
 /**
  * set_hwif_attr - set the attributes in the relevant members in hwif
  * @hwif: the HW interface of a pci function device
@@ -373,7 +395,7 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
 		goto err_map_intr_bar;
 	}
 
-	err = hwif_ready(hwif);
+	err = wait_hwif_ready(hwif);
 	if (err) {
 		dev_err(&pdev->dev, "HW interface is not ready\n");
 		goto err_hwif_ready;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 53bb89c1dd26..5bb6ec4dcb7c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -55,13 +55,15 @@
 #define HINIC_FA1_IRQS_PER_FUNC_SHIFT                           20
 #define HINIC_FA1_DMA_ATTR_PER_FUNC_SHIFT                       24
 /* reserved members - off 27 */
-#define HINIC_FA1_INIT_STATUS_SHIFT                             30
+#define HINIC_FA1_MGMT_INIT_STATUS_SHIFT			30
+#define HINIC_FA1_PF_INIT_STATUS_SHIFT				31
 
 #define HINIC_FA1_AEQS_PER_FUNC_MASK                            0x3
 #define HINIC_FA1_CEQS_PER_FUNC_MASK                            0x7
 #define HINIC_FA1_IRQS_PER_FUNC_MASK                            0xF
 #define HINIC_FA1_DMA_ATTR_PER_FUNC_MASK                        0x7
-#define HINIC_FA1_INIT_STATUS_MASK                              0x1
+#define HINIC_FA1_MGMT_INIT_STATUS_MASK                         0x1
+#define HINIC_FA1_PF_INIT_STATUS_MASK				0x1
 
 #define HINIC_FA1_GET(val, member)                              \
 	(((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
index 564fb2294a29..bc2f87e6cb5d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c
@@ -627,7 +627,7 @@ wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func,
 	struct hinic_hwdev *hwdev = func_to_func->hwdev;
 	struct completion *done = &send_mbox->send_done;
 	u32 cnt = 0;
-	ulong jif;
+	unsigned long jif;
 
 	if (poll) {
 		while (cnt < MBOX_MSG_POLLING_TIMEOUT) {
@@ -869,7 +869,7 @@ int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func,
 {
 	struct hinic_recv_mbox *mbox_for_resp;
 	struct mbox_msg_info msg_info = {0};
-	ulong timeo;
+	unsigned long timeo;
 	int err;
 
 	mbox_for_resp = &func_to_func->mbox_resp[dst_func];
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index b66bb86cff96..3d6569d7bac8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -427,10 +427,6 @@ static int hinic_open(struct net_device *netdev)
 		goto err_func_port_state;
 	}
 
-	if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
-		/* Wait up to 3 sec between port enable to link state */
-		msleep(3000);
-
 	down(&nic_dev->mgmt_lock);
 
 	err = hinic_port_link_state(nic_dev, &link_state);
@@ -766,10 +762,12 @@ static void hinic_set_rx_mode(struct net_device *netdev)
 		  HINIC_RX_MODE_MC |
 		  HINIC_RX_MODE_BC;
 
-	if (netdev->flags & IFF_PROMISC)
-		rx_mode |= HINIC_RX_MODE_PROMISC;
-	else if (netdev->flags & IFF_ALLMULTI)
+	if (netdev->flags & IFF_PROMISC) {
+		if (!HINIC_IS_VF(nic_dev->hwdev->hwif))
+			rx_mode |= HINIC_RX_MODE_PROMISC;
+	} else if (netdev->flags & IFF_ALLMULTI) {
 		rx_mode |= HINIC_RX_MODE_MC_ALL;
+	}
 
 	rx_mode_work->rx_mode = rx_mode;
 
@@ -868,6 +866,9 @@ static const struct net_device_ops hinic_netdev_ops = {
 	.ndo_set_vf_vlan = hinic_ndo_set_vf_vlan,
 	.ndo_get_vf_config = hinic_ndo_get_vf_config,
 	.ndo_set_vf_trust = hinic_ndo_set_vf_trust,
+	.ndo_set_vf_rate = hinic_ndo_set_vf_bw,
+	.ndo_set_vf_spoofchk = hinic_ndo_set_vf_spoofchk,
+	.ndo_set_vf_link_state = hinic_ndo_set_vf_link_state,
 };
 
 static const struct net_device_ops hinicvf_netdev_ops = {
@@ -1232,6 +1233,8 @@ static void hinic_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
+	hinic_port_del_mac(nic_dev, netdev->dev_addr, 0);
+
 	hinic_hwdev_cb_unregister(nic_dev->hwdev,
 				  HINIC_MGMT_MSG_CMD_LINK_STATUS);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index b7fe0adcc29a..714d8279c591 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -66,15 +66,15 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		return -EFAULT;
 	}
 
-	if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status ==
-	    HINIC_PF_SET_VF_ALREADY) {
-		dev_warn(&pdev->dev, "PF has already set VF mac, Ignore set operation\n");
+	if (port_mac_cmd.status == HINIC_PF_SET_VF_ALREADY) {
+		dev_warn(&pdev->dev, "PF has already set VF mac, ignore %s operation\n",
+			 (op == MAC_SET) ? "set" : "del");
 		return HINIC_PF_SET_VF_ALREADY;
 	}
 
 	if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status ==
 	    HINIC_MGMT_STATUS_EXIST)
-		dev_warn(&pdev->dev, "MAC is repeated. Ignore set operation\n");
+		dev_warn(&pdev->dev, "MAC is repeated, ignore set operation\n");
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 5ad04fb6722a..f2781521970e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -506,6 +506,49 @@ struct hinic_cmd_vport_stats {
 	struct hinic_vport_stats stats;
 };
 
+struct hinic_tx_rate_cfg_max_min {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	min_rate;
+	u32	max_rate;
+	u8	rsvd2[8];
+};
+
+struct hinic_tx_rate_cfg {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	tx_rate;
+};
+
+enum nic_speed_level {
+	LINK_SPEED_10MB = 0,
+	LINK_SPEED_100MB,
+	LINK_SPEED_1GB,
+	LINK_SPEED_10GB,
+	LINK_SPEED_25GB,
+	LINK_SPEED_40GB,
+	LINK_SPEED_100GB,
+	LINK_SPEED_LEVELS,
+};
+
+struct hinic_spoofchk_set {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u8	state;
+	u8	rsvd1;
+	u16	func_id;
+};
+
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index fd4aaf43874a..efab2dd2c889 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -22,6 +22,7 @@ MODULE_PARM_DESC(set_vf_link_state, "Set vf link state, 0 represents link auto,
 
 #define HINIC_VLAN_PRIORITY_SHIFT 13
 #define HINIC_ADD_VLAN_IN_MAC 0x8000
+#define HINIC_TX_RATE_TABLE_FULL 12
 
 static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr,
 			 u16 vlan_id, u16 func_id)
@@ -129,6 +130,84 @@ static int hinic_set_vf_vlan(struct hinic_hwdev *hwdev, bool add, u16 vid,
 	return 0;
 }
 
+static int hinic_set_vf_tx_rate_max_min(struct hinic_hwdev *hwdev, u16 vf_id,
+					u32 max_rate, u32 min_rate)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	struct hinic_tx_rate_cfg_max_min rate_cfg = {0};
+	u16 out_size = sizeof(rate_cfg);
+	int err;
+
+	rate_cfg.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+	rate_cfg.max_rate = max_rate;
+	rate_cfg.min_rate = min_rate;
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE,
+				 &rate_cfg, sizeof(rate_cfg), &rate_cfg,
+				 &out_size);
+	if ((rate_cfg.status != HINIC_MGMT_CMD_UNSUPPORTED &&
+	     rate_cfg.status) || err || !out_size) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF(%d) max rate(%d), min rate(%d), err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), max_rate, min_rate, err,
+			rate_cfg.status, out_size);
+		return -EIO;
+	}
+
+	if (!rate_cfg.status) {
+		nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].max_rate = max_rate;
+		nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].min_rate = min_rate;
+	}
+
+	return rate_cfg.status;
+}
+
+static int hinic_set_vf_rate_limit(struct hinic_hwdev *hwdev, u16 vf_id,
+				   u32 tx_rate)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	struct hinic_tx_rate_cfg rate_cfg = {0};
+	u16 out_size = sizeof(rate_cfg);
+	int err;
+
+	rate_cfg.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+	rate_cfg.tx_rate = tx_rate;
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_VF_RATE,
+				 &rate_cfg, sizeof(rate_cfg), &rate_cfg,
+				 &out_size);
+	if (err || !out_size || rate_cfg.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF(%d) rate(%d), err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), tx_rate, err, rate_cfg.status,
+			out_size);
+		if (rate_cfg.status)
+			return rate_cfg.status;
+
+		return -EIO;
+	}
+
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].max_rate = tx_rate;
+	nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].min_rate = 0;
+
+	return 0;
+}
+
+static int hinic_set_vf_tx_rate(struct hinic_hwdev *hwdev, u16 vf_id,
+				u32 max_rate, u32 min_rate)
+{
+	int err;
+
+	err = hinic_set_vf_tx_rate_max_min(hwdev, vf_id, max_rate, min_rate);
+	if (err != HINIC_MGMT_CMD_UNSUPPORTED)
+		return err;
+
+	if (min_rate) {
+		dev_err(&hwdev->hwif->pdev->dev, "Current firmware doesn't support to set min tx rate\n");
+		return -EOPNOTSUPP;
+	}
+
+	dev_info(&hwdev->hwif->pdev->dev, "Current firmware doesn't support to set min tx rate, force min_tx_rate = max_tx_rate\n");
+
+	return hinic_set_vf_rate_limit(hwdev, vf_id, max_rate);
+}
+
 static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id)
 {
 	struct vf_data_storage *vf_info;
@@ -160,6 +239,17 @@ static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id)
 		}
 	}
 
+	if (vf_info->max_rate) {
+		err = hinic_set_vf_tx_rate(hwdev, vf_id, vf_info->max_rate,
+					   vf_info->min_rate);
+		if (err) {
+			dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF %d max rate: %d, min rate: %d\n",
+				HW_VF_ID_TO_OS(vf_id), vf_info->max_rate,
+				vf_info->min_rate);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -700,6 +790,185 @@ int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting)
 	return err;
 }
 
+int hinic_ndo_set_vf_bw(struct net_device *netdev,
+			int vf, int min_tx_rate, int max_tx_rate)
+{
+	u32 speeds[] = {SPEED_10, SPEED_100, SPEED_1000, SPEED_10000,
+			SPEED_25000, SPEED_40000, SPEED_100000};
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_port_cap port_cap = { 0 };
+	enum hinic_port_link_state link_state;
+	int err;
+
+	if (vf >= nic_dev->sriov_info.num_vfs) {
+		netif_err(nic_dev, drv, netdev, "VF number must be less than %d\n",
+			  nic_dev->sriov_info.num_vfs);
+		return -EINVAL;
+	}
+
+	if (max_tx_rate < min_tx_rate) {
+		netif_err(nic_dev, drv, netdev, "Max rate %d must be greater than or equal to min rate %d\n",
+			  max_tx_rate, min_tx_rate);
+		return -EINVAL;
+	}
+
+	err = hinic_port_link_state(nic_dev, &link_state);
+	if (err) {
+		netif_err(nic_dev, drv, netdev,
+			  "Get link status failed when setting vf tx rate\n");
+		return -EIO;
+	}
+
+	if (link_state == HINIC_LINK_STATE_DOWN) {
+		netif_err(nic_dev, drv, netdev,
+			  "Link status must be up when setting vf tx rate\n");
+		return -EPERM;
+	}
+
+	err = hinic_port_get_cap(nic_dev, &port_cap);
+	if (err || port_cap.speed > LINK_SPEED_100GB)
+		return -EIO;
+
+	/* rate limit cannot be less than 0 and greater than link speed */
+	if (max_tx_rate < 0 || max_tx_rate > speeds[port_cap.speed]) {
+		netif_err(nic_dev, drv, netdev, "Max tx rate must be in [0 - %d]\n",
+			  speeds[port_cap.speed]);
+		return -EINVAL;
+	}
+
+	err = hinic_set_vf_tx_rate(nic_dev->hwdev, OS_VF_ID_TO_HW(vf),
+				   max_tx_rate, min_tx_rate);
+	if (err) {
+		netif_err(nic_dev, drv, netdev,
+			  "Unable to set VF %d max rate %d min rate %d%s\n",
+			  vf, max_tx_rate, min_tx_rate,
+			  err == HINIC_TX_RATE_TABLE_FULL ?
+			  ", tx rate profile is full" : "");
+		return -EIO;
+	}
+
+	netif_info(nic_dev, drv, netdev,
+		   "Set VF %d max tx rate %d min tx rate %d successfully\n",
+		   vf, max_tx_rate, min_tx_rate);
+
+	return 0;
+}
+
+static int hinic_set_vf_spoofchk(struct hinic_hwdev *hwdev, u16 vf_id,
+				 bool spoofchk)
+{
+	struct hinic_spoofchk_set spoofchk_cfg = {0};
+	struct vf_data_storage *vf_infos = NULL;
+	u16 out_size = sizeof(spoofchk_cfg);
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	vf_infos = hwdev->func_to_io.vf_infos;
+
+	spoofchk_cfg.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id;
+	spoofchk_cfg.state = spoofchk ? 1 : 0;
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_ENABLE_SPOOFCHK,
+				 &spoofchk_cfg, sizeof(spoofchk_cfg),
+				 &spoofchk_cfg, &out_size);
+	if (spoofchk_cfg.status == HINIC_MGMT_CMD_UNSUPPORTED) {
+		err = HINIC_MGMT_CMD_UNSUPPORTED;
+	} else if (err || !out_size || spoofchk_cfg.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF(%d) spoofchk, err: %d, status: 0x%x, out size: 0x%x\n",
+			HW_VF_ID_TO_OS(vf_id), err, spoofchk_cfg.status,
+			out_size);
+		err = -EIO;
+	}
+
+	vf_infos[HW_VF_ID_TO_OS(vf_id)].spoofchk = spoofchk;
+
+	return err;
+}
+
+int hinic_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+	bool cur_spoofchk;
+	int err;
+
+	sriov_info = &nic_dev->sriov_info;
+	if (vf >= sriov_info->num_vfs)
+		return -EINVAL;
+
+	cur_spoofchk = nic_dev->hwdev->func_to_io.vf_infos[vf].spoofchk;
+
+	/* same request, so just return success */
+	if ((setting && cur_spoofchk) || (!setting && !cur_spoofchk))
+		return 0;
+
+	err = hinic_set_vf_spoofchk(sriov_info->hwdev,
+				    OS_VF_ID_TO_HW(vf), setting);
+
+	if (!err) {
+		netif_info(nic_dev, drv, netdev, "Set VF %d spoofchk %s successfully\n",
+			   vf, setting ? "on" : "off");
+	} else if (err == HINIC_MGMT_CMD_UNSUPPORTED) {
+		netif_err(nic_dev, drv, netdev,
+			  "Current firmware doesn't support to set vf spoofchk, need to upgrade latest firmware version\n");
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int hinic_set_vf_link_state(struct hinic_hwdev *hwdev, u16 vf_id,
+				   int link)
+{
+	struct hinic_func_to_io *nic_io = &hwdev->func_to_io;
+	struct vf_data_storage *vf_infos = nic_io->vf_infos;
+	u8 link_status = 0;
+
+	switch (link) {
+	case HINIC_IFLA_VF_LINK_STATE_AUTO:
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_forced = false;
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_up = nic_io->link_status ?
+			true : false;
+		link_status = nic_io->link_status;
+		break;
+	case HINIC_IFLA_VF_LINK_STATE_ENABLE:
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_forced = true;
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_up = true;
+		link_status = HINIC_LINK_UP;
+		break;
+	case HINIC_IFLA_VF_LINK_STATE_DISABLE:
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_forced = true;
+		vf_infos[HW_VF_ID_TO_OS(vf_id)].link_up = false;
+		link_status = HINIC_LINK_DOWN;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Notify the VF of its new link state */
+	hinic_notify_vf_link_status(hwdev, vf_id, link_status);
+
+	return 0;
+}
+
+int hinic_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_sriov_info *sriov_info;
+
+	sriov_info = &nic_dev->sriov_info;
+
+	if (vf_id >= sriov_info->num_vfs) {
+		netif_err(nic_dev, drv, netdev,
+			  "Invalid VF Identifier %d\n", vf_id);
+		return -EINVAL;
+	}
+
+	return hinic_set_vf_link_state(sriov_info->hwdev,
+				      OS_VF_ID_TO_HW(vf_id), link);
+}
+
 /* pf receive message from vf */
 static int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in,
 			       u16 in_size, void *buf_out, u16 *out_size)
@@ -801,6 +1070,12 @@ static void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id)
 	if (hinic_vf_info_vlanprio(nic_dev->hwdev, vf_id))
 		hinic_kill_vf_vlan(nic_dev->hwdev, vf_id);
 
+	if (vf_infos->max_rate)
+		hinic_set_vf_tx_rate(nic_dev->hwdev, vf_id, 0, 0);
+
+	if (vf_infos->spoofchk)
+		hinic_set_vf_spoofchk(nic_dev->hwdev, vf_id, false);
+
 	if (vf_infos->trust)
 		hinic_set_vf_trust(nic_dev->hwdev, vf_id, false);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
index 64affc7474b5..ba627a362f9a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h
@@ -86,6 +86,13 @@ int hinic_ndo_get_vf_config(struct net_device *netdev,
 
 int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting);
 
+int hinic_ndo_set_vf_bw(struct net_device *netdev,
+			int vf, int min_tx_rate, int max_tx_rate);
+
+int hinic_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
+
+int hinic_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link);
+
 void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev,
 				       u8 link_status);
 
-- 
cgit v1.2.3


From 18aa23b31f6c8e3f4b01b70a8a4eab873e2eb710 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:02 +0300
Subject: mlxsw: spectrum_matchall: Restrict sample action to be allowed only
 on ingress

HW supports packet sampling on ingress only. Check and fail if user
is adding sample on egress.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index da1c05f44cec..c75661521bbc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -212,6 +212,11 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 		mall_entry->mirror.to_dev = act->dev;
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
 		   protocol == htons(ETH_P_ALL)) {
+		if (!mall_entry->ingress) {
+			NL_SET_ERR_MSG(f->common.extack, "Sample is not supported on egress");
+			err = -EOPNOTSUPP;
+			goto errout;
+		}
 		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
 			NL_SET_ERR_MSG(f->common.extack, "Sample rate not supported");
 			err = -EOPNOTSUPP;
-- 
cgit v1.2.3


From 593bb843798636131bd6d9eb1633b1ee55a8a53b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:03 +0300
Subject: mlxsw: spectrum_flower: Expose a function to get min and max rule
 priority

Introduce an infrastructure that allows to get minimum and maximum
rule priority for specified chain. This is going to be used by
a subsequent patch to enforce ordering between flower and
matchall filters.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  7 ++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 13 +++++++-
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 39 +++++++++++++++++++---
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  3 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 20 +++++++++++
 5 files changed, 75 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a12ca673c224..d9a963c77401 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -739,6 +739,9 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_ruleset *ruleset);
 u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
+void mlxsw_sp_acl_ruleset_prio_get(struct mlxsw_sp_acl_ruleset *ruleset,
+				   unsigned int *p_min_prio,
+				   unsigned int *p_max_prio);
 
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
@@ -912,6 +915,10 @@ int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_flow_block *block,
 				   struct flow_cls_offload *f);
+int mlxsw_sp_flower_prio_get(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_flow_block *block,
+			     u32 chain_index, unsigned int *p_min_prio,
+			     unsigned int *p_max_prio);
 
 /* spectrum_qdisc.c */
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index c61f78e30397..47da9ee0045d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -51,6 +51,8 @@ struct mlxsw_sp_acl_ruleset {
 	struct mlxsw_sp_acl_ruleset_ht_key ht_key;
 	struct rhashtable rule_ht;
 	unsigned int ref_count;
+	unsigned int min_prio;
+	unsigned int max_prio;
 	unsigned long priv[];
 	/* priv has to be always the last item */
 };
@@ -178,7 +180,8 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 		goto err_rhashtable_init;
 
 	err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv,
-			       tmplt_elusage);
+			       tmplt_elusage, &ruleset->min_prio,
+			       &ruleset->max_prio);
 	if (err)
 		goto err_ops_ruleset_add;
 
@@ -293,6 +296,14 @@ u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset)
 	return ops->ruleset_group_id(ruleset->priv);
 }
 
+void mlxsw_sp_acl_ruleset_prio_get(struct mlxsw_sp_acl_ruleset *ruleset,
+				   unsigned int *p_min_prio,
+				   unsigned int *p_max_prio)
+{
+	*p_min_prio = ruleset->min_prio;
+	*p_max_prio = ruleset->max_prio;
+}
+
 struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 			  struct mlxsw_afa_block *afa_block)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index a6e30e020b5c..5c020403342f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -179,6 +179,8 @@ struct mlxsw_sp_acl_tcam_vgroup {
 	bool tmplt_elusage_set;
 	struct mlxsw_afk_element_usage tmplt_elusage;
 	bool vregion_rehash_enabled;
+	unsigned int *p_min_prio;
+	unsigned int *p_max_prio;
 };
 
 struct mlxsw_sp_acl_tcam_rehash_ctx {
@@ -316,13 +318,17 @@ mlxsw_sp_acl_tcam_vgroup_add(struct mlxsw_sp *mlxsw_sp,
 			     const struct mlxsw_sp_acl_tcam_pattern *patterns,
 			     unsigned int patterns_count,
 			     struct mlxsw_afk_element_usage *tmplt_elusage,
-			     bool vregion_rehash_enabled)
+			     bool vregion_rehash_enabled,
+			     unsigned int *p_min_prio,
+			     unsigned int *p_max_prio)
 {
 	int err;
 
 	vgroup->patterns = patterns;
 	vgroup->patterns_count = patterns_count;
 	vgroup->vregion_rehash_enabled = vregion_rehash_enabled;
+	vgroup->p_min_prio = p_min_prio;
+	vgroup->p_max_prio = p_max_prio;
 
 	if (tmplt_elusage) {
 		vgroup->tmplt_elusage_set = true;
@@ -416,6 +422,21 @@ mlxsw_sp_acl_tcam_vregion_max_prio(struct mlxsw_sp_acl_tcam_vregion *vregion)
 	return vchunk->priority;
 }
 
+static void
+mlxsw_sp_acl_tcam_vgroup_prio_update(struct mlxsw_sp_acl_tcam_vgroup *vgroup)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+
+	if (list_empty(&vgroup->vregion_list))
+		return;
+	vregion = list_first_entry(&vgroup->vregion_list,
+				   typeof(*vregion), list);
+	*vgroup->p_min_prio = mlxsw_sp_acl_tcam_vregion_prio(vregion);
+	vregion = list_last_entry(&vgroup->vregion_list,
+				  typeof(*vregion), list);
+	*vgroup->p_max_prio = mlxsw_sp_acl_tcam_vregion_max_prio(vregion);
+}
+
 static int
 mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp,
 				      struct mlxsw_sp_acl_tcam_group *group,
@@ -1035,6 +1056,7 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 	}
 	list_add_tail(&vchunk->list, pos);
 	mutex_unlock(&vregion->lock);
+	mlxsw_sp_acl_tcam_vgroup_prio_update(vgroup);
 
 	return vchunk;
 
@@ -1066,6 +1088,7 @@ mlxsw_sp_acl_tcam_vchunk_destroy(struct mlxsw_sp *mlxsw_sp,
 			       mlxsw_sp_acl_tcam_vchunk_ht_params);
 	mlxsw_sp_acl_tcam_vregion_put(mlxsw_sp, vchunk->vregion);
 	kfree(vchunk);
+	mlxsw_sp_acl_tcam_vgroup_prio_update(vgroup);
 }
 
 static struct mlxsw_sp_acl_tcam_vchunk *
@@ -1582,14 +1605,17 @@ static int
 mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam *tcam,
 				     void *ruleset_priv,
-				     struct mlxsw_afk_element_usage *tmplt_elusage)
+				     struct mlxsw_afk_element_usage *tmplt_elusage,
+				     unsigned int *p_min_prio,
+				     unsigned int *p_max_prio)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
 	return mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
 					    mlxsw_sp_acl_tcam_patterns,
 					    MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
-					    tmplt_elusage, true);
+					    tmplt_elusage, true,
+					    p_min_prio, p_max_prio);
 }
 
 static void
@@ -1698,7 +1724,9 @@ static int
 mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam *tcam,
 				 void *ruleset_priv,
-				 struct mlxsw_afk_element_usage *tmplt_elusage)
+				 struct mlxsw_afk_element_usage *tmplt_elusage,
+				 unsigned int *p_min_prio,
+				 unsigned int *p_max_prio)
 {
 	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 	int err;
@@ -1706,7 +1734,8 @@ mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 	err = mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
 					   mlxsw_sp_acl_tcam_patterns,
 					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
-					   tmplt_elusage, false);
+					   tmplt_elusage, false,
+					   p_min_prio, p_max_prio);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 96437992b102..a41df10ade9b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -42,7 +42,8 @@ struct mlxsw_sp_acl_profile_ops {
 	size_t ruleset_priv_size;
 	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv,
-			   struct mlxsw_afk_element_usage *tmplt_elusage);
+			   struct mlxsw_afk_element_usage *tmplt_elusage,
+			   unsigned int *p_min_prio, unsigned int *p_max_prio);
 	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
 	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
 			    struct mlxsw_sp_port *mlxsw_sp_port,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 0897ca1967ab..18d22217e435 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -647,3 +647,23 @@ void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 }
+
+int mlxsw_sp_flower_prio_get(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_flow_block *block,
+			     u32 chain_index, unsigned int *p_min_prio,
+			     unsigned int *p_max_prio)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset;
+
+	ruleset = mlxsw_sp_acl_ruleset_lookup(mlxsw_sp, block,
+					      chain_index,
+					      MLXSW_SP_ACL_PROFILE_FLOWER);
+	if (IS_ERR(ruleset))
+		/* In case there are no flower rules, the caller
+		 * receives -ENOENT to indicate there is no need
+		 * to check the priorities.
+		 */
+		return PTR_ERR(ruleset);
+	mlxsw_sp_acl_ruleset_prio_get(ruleset, p_min_prio, p_max_prio);
+	return 0;
+}
-- 
cgit v1.2.3


From 5a2939b9d7ddbdc399ce42cae8150c424e0bd764 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:04 +0300
Subject: mlxsw: spectrum_matchall: Put matchall list into substruct of flow
 struct

As there are going to be other matchall specific fields in flow
structure, put the existing list field into matchall substruct.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h          |  4 +++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c     |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c | 10 +++++-----
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index d9a963c77401..553693469805 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -636,7 +636,9 @@ struct mlxsw_sp_acl_rule_info {
 /* spectrum_flow.c */
 struct mlxsw_sp_flow_block {
 	struct list_head binding_list;
-	struct list_head mall_list;
+	struct {
+		struct list_head list;
+	} mall;
 	struct mlxsw_sp_acl_ruleset *ruleset_zero;
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned int rule_count;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
index ecab581ff956..76644f6a8121 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
@@ -18,7 +18,7 @@ mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net)
 	if (!block)
 		return NULL;
 	INIT_LIST_HEAD(&block->binding_list);
-	INIT_LIST_HEAD(&block->mall_list);
+	INIT_LIST_HEAD(&block->mall.list);
 	block->mlxsw_sp = mlxsw_sp;
 	block->net = net;
 	return block;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index c75661521bbc..d64ee31a611c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -37,7 +37,7 @@ mlxsw_sp_mall_entry_find(struct mlxsw_sp_flow_block *block, unsigned long cookie
 {
 	struct mlxsw_sp_mall_entry *mall_entry;
 
-	list_for_each_entry(mall_entry, &block->mall_list, list)
+	list_for_each_entry(mall_entry, &block->mall.list, list)
 		if (mall_entry->cookie == cookie)
 			return mall_entry;
 
@@ -244,7 +244,7 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 		block->egress_blocker_rule_count++;
 	else
 		block->ingress_blocker_rule_count++;
-	list_add_tail(&mall_entry->list, &block->mall_list);
+	list_add_tail(&mall_entry->list, &block->mall.list);
 	return 0;
 
 rollback:
@@ -285,7 +285,7 @@ int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
 	struct mlxsw_sp_mall_entry *mall_entry;
 	int err;
 
-	list_for_each_entry(mall_entry, &block->mall_list, list) {
+	list_for_each_entry(mall_entry, &block->mall.list, list) {
 		err = mlxsw_sp_mall_port_rule_add(mlxsw_sp_port, mall_entry);
 		if (err)
 			goto rollback;
@@ -293,7 +293,7 @@ int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
 	return 0;
 
 rollback:
-	list_for_each_entry_continue_reverse(mall_entry, &block->mall_list,
+	list_for_each_entry_continue_reverse(mall_entry, &block->mall.list,
 					     list)
 		mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
 	return err;
@@ -304,6 +304,6 @@ void mlxsw_sp_mall_port_unbind(struct mlxsw_sp_flow_block *block,
 {
 	struct mlxsw_sp_mall_entry *mall_entry;
 
-	list_for_each_entry(mall_entry, &block->mall_list, list)
+	list_for_each_entry(mall_entry, &block->mall.list, list)
 		mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
 }
-- 
cgit v1.2.3


From aed65285fb9e16328f9bbf14394fef5ddbe82815 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:05 +0300
Subject: mlxsw: spectrum_matchall: Expose a function to get min and max rule
 priority

Introduce an infrastructure that allows to get minimum and maximum
rule priority for specified chain. This is going to be used by
a subsequent patch to enforce ordering between flower and
matchall filters.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  4 +++
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 34 ++++++++++++++++++++++
 2 files changed, 38 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 553693469805..456dbaa5ee26 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -638,6 +638,8 @@ struct mlxsw_sp_flow_block {
 	struct list_head binding_list;
 	struct {
 		struct list_head list;
+		unsigned int min_prio;
+		unsigned int max_prio;
 	} mall;
 	struct mlxsw_sp_acl_ruleset *ruleset_zero;
 	struct mlxsw_sp *mlxsw_sp;
@@ -900,6 +902,8 @@ int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
 			    struct mlxsw_sp_port *mlxsw_sp_port);
 void mlxsw_sp_mall_port_unbind(struct mlxsw_sp_flow_block *block,
 			       struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_mall_prio_get(struct mlxsw_sp_flow_block *block, u32 chain_index,
+			   unsigned int *p_min_prio, unsigned int *p_max_prio);
 
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index d64ee31a611c..b11bab76b2e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -23,6 +23,7 @@ struct mlxsw_sp_mall_mirror_entry {
 struct mlxsw_sp_mall_entry {
 	struct list_head list;
 	unsigned long cookie;
+	unsigned int priority;
 	enum mlxsw_sp_mall_action_type type;
 	bool ingress;
 	union {
@@ -175,6 +176,22 @@ mlxsw_sp_mall_port_rule_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
+static void mlxsw_sp_mall_prio_update(struct mlxsw_sp_flow_block *block)
+{
+	struct mlxsw_sp_mall_entry *mall_entry;
+
+	if (list_empty(&block->mall.list))
+		return;
+	block->mall.min_prio = UINT_MAX;
+	block->mall.max_prio = 0;
+	list_for_each_entry(mall_entry, &block->mall.list, list) {
+		if (mall_entry->priority < block->mall.min_prio)
+			block->mall.min_prio = mall_entry->priority;
+		if (mall_entry->priority > block->mall.max_prio)
+			block->mall.max_prio = mall_entry->priority;
+	}
+}
+
 int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 			  struct tc_cls_matchall_offload *f)
 {
@@ -203,6 +220,7 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 	if (!mall_entry)
 		return -ENOMEM;
 	mall_entry->cookie = f->cookie;
+	mall_entry->priority = f->common.prio;
 	mall_entry->ingress = mlxsw_sp_flow_block_is_ingress_bound(block);
 
 	act = &f->rule->action.entries[0];
@@ -245,6 +263,7 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 	else
 		block->ingress_blocker_rule_count++;
 	list_add_tail(&mall_entry->list, &block->mall.list);
+	mlxsw_sp_mall_prio_update(block);
 	return 0;
 
 rollback:
@@ -277,6 +296,7 @@ void mlxsw_sp_mall_destroy(struct mlxsw_sp_flow_block *block,
 	list_for_each_entry(binding, &block->binding_list, list)
 		mlxsw_sp_mall_port_rule_del(binding->mlxsw_sp_port, mall_entry);
 	kfree_rcu(mall_entry, rcu); /* sample RX packets may be in-flight */
+	mlxsw_sp_mall_prio_update(block);
 }
 
 int mlxsw_sp_mall_port_bind(struct mlxsw_sp_flow_block *block,
@@ -307,3 +327,17 @@ void mlxsw_sp_mall_port_unbind(struct mlxsw_sp_flow_block *block,
 	list_for_each_entry(mall_entry, &block->mall.list, list)
 		mlxsw_sp_mall_port_rule_del(mlxsw_sp_port, mall_entry);
 }
+
+int mlxsw_sp_mall_prio_get(struct mlxsw_sp_flow_block *block, u32 chain_index,
+			   unsigned int *p_min_prio, unsigned int *p_max_prio)
+{
+	if (chain_index || list_empty(&block->mall.list))
+		/* In case there are no matchall rules, the caller
+		 * receives -ENOENT to indicate there is no need
+		 * to check the priorities.
+		 */
+		return -ENOENT;
+	*p_min_prio = block->mall.min_prio;
+	*p_max_prio = block->mall.max_prio;
+	return 0;
+}
-- 
cgit v1.2.3


From 18346b70ab776fa2cbb9a5f0f0f9c4700c470c5e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:06 +0300
Subject: mlxsw: spectrum_matchall: Forbid to insert matchall rules in
 collision with flower rules

On ingress, the matchall rules doing mirroring and sampling are offloaded
into hardware blocks that are processed before any flower rules.
On egress, the matchall mirroring rules are offloaded into hardware
block that is processed after all flower rules.

Therefore check the priorities of inserted matchall rules against
existing flower rules and ensure the correct ordering.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_flow.c    |  4 ++-
 .../ethernet/mellanox/mlxsw/spectrum_matchall.c    | 37 +++++++++++++++++++++-
 3 files changed, 41 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 456dbaa5ee26..147a5634244b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -894,7 +894,8 @@ extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
 extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_matchall.c */
-int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
+int mlxsw_sp_mall_replace(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_flow_block *block,
 			  struct tc_cls_matchall_offload *f);
 void mlxsw_sp_mall_destroy(struct mlxsw_sp_flow_block *block,
 			   struct tc_cls_matchall_offload *f);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
index 76644f6a8121..47b66f347ff1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c
@@ -135,9 +135,11 @@ static int mlxsw_sp_flow_block_unbind(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_flow_block_mall_cb(struct mlxsw_sp_flow_block *flow_block,
 				       struct tc_cls_matchall_offload *f)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_flow_block_mlxsw_sp(flow_block);
+
 	switch (f->command) {
 	case TC_CLSMATCHALL_REPLACE:
-		return mlxsw_sp_mall_replace(flow_block, f);
+		return mlxsw_sp_mall_replace(mlxsw_sp, flow_block, f);
 	case TC_CLSMATCHALL_DESTROY:
 		mlxsw_sp_mall_destroy(flow_block, f);
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
index b11bab76b2e1..f1a44a8eda55 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c
@@ -192,13 +192,17 @@ static void mlxsw_sp_mall_prio_update(struct mlxsw_sp_flow_block *block)
 	}
 }
 
-int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
+int mlxsw_sp_mall_replace(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_flow_block *block,
 			  struct tc_cls_matchall_offload *f)
 {
 	struct mlxsw_sp_flow_block_binding *binding;
 	struct mlxsw_sp_mall_entry *mall_entry;
 	__be16 protocol = f->common.protocol;
 	struct flow_action_entry *act;
+	unsigned int flower_min_prio;
+	unsigned int flower_max_prio;
+	bool flower_prio_valid;
 	int err;
 
 	if (!flow_offload_has_one_action(&f->rule->action)) {
@@ -216,6 +220,19 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 		return -EOPNOTSUPP;
 	}
 
+	err = mlxsw_sp_flower_prio_get(mlxsw_sp, block, f->common.chain_index,
+				       &flower_min_prio, &flower_max_prio);
+	if (err) {
+		if (err != -ENOENT) {
+			NL_SET_ERR_MSG(f->common.extack, "Failed to get flower priorities");
+			return err;
+		}
+		flower_prio_valid = false;
+		/* No flower filters are installed in specified chain. */
+	} else {
+		flower_prio_valid = true;
+	}
+
 	mall_entry = kzalloc(sizeof(*mall_entry), GFP_KERNEL);
 	if (!mall_entry)
 		return -ENOMEM;
@@ -226,6 +243,18 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 	act = &f->rule->action.entries[0];
 
 	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
+		if (flower_prio_valid && mall_entry->ingress &&
+		    mall_entry->priority >= flower_min_prio) {
+			NL_SET_ERR_MSG(f->common.extack, "Failed to add behind existing flower rules");
+			err = -EOPNOTSUPP;
+			goto errout;
+		}
+		if (flower_prio_valid && !mall_entry->ingress &&
+		    mall_entry->priority <= flower_max_prio) {
+			NL_SET_ERR_MSG(f->common.extack, "Failed to add in front of existing flower rules");
+			err = -EOPNOTSUPP;
+			goto errout;
+		}
 		mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR;
 		mall_entry->mirror.to_dev = act->dev;
 	} else if (act->id == FLOW_ACTION_SAMPLE &&
@@ -235,6 +264,12 @@ int mlxsw_sp_mall_replace(struct mlxsw_sp_flow_block *block,
 			err = -EOPNOTSUPP;
 			goto errout;
 		}
+		if (flower_prio_valid &&
+		    mall_entry->priority >= flower_min_prio) {
+			NL_SET_ERR_MSG(f->common.extack, "Failed to add behind existing flower rules");
+			err = -EOPNOTSUPP;
+			goto errout;
+		}
 		if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
 			NL_SET_ERR_MSG(f->common.extack, "Sample rate not supported");
 			err = -EOPNOTSUPP;
-- 
cgit v1.2.3


From 67ed68fc0c9aa4a456d03df216e571e0c6177097 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 May 2020 23:06:07 +0300
Subject: mlxsw: spectrum_flower: Forbid to insert flower rules in collision
 with matchall rules

On ingress, the matchall rules doing mirroring and sampling are offloaded
into hardware blocks that are processed before any flower rules.
On egress, the matchall mirroring rules are offloaded into hardware
block that is processed after all flower rules.

Therefore check the priorities of inserted flower rules against
existing matchall rules and ensure the correct ordering.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 32 ++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 18d22217e435..b286fe158820 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -505,6 +505,34 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 					     f->common.extack);
 }
 
+static int mlxsw_sp_flower_mall_prio_check(struct mlxsw_sp_flow_block *block,
+					   struct flow_cls_offload *f)
+{
+	bool ingress = mlxsw_sp_flow_block_is_ingress_bound(block);
+	unsigned int mall_min_prio;
+	unsigned int mall_max_prio;
+	int err;
+
+	err = mlxsw_sp_mall_prio_get(block, f->common.chain_index,
+				     &mall_min_prio, &mall_max_prio);
+	if (err) {
+		if (err == -ENOENT)
+			/* No matchall filters installed on this chain. */
+			return 0;
+		NL_SET_ERR_MSG(f->common.extack, "Failed to get matchall priorities");
+		return err;
+	}
+	if (ingress && f->common.prio <= mall_min_prio) {
+		NL_SET_ERR_MSG(f->common.extack, "Failed to add in front of existing matchall rules");
+		return -EOPNOTSUPP;
+	}
+	if (!ingress && f->common.prio >= mall_max_prio) {
+		NL_SET_ERR_MSG(f->common.extack, "Failed to add behind of existing matchall rules");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_flow_block *block,
 			    struct flow_cls_offload *f)
@@ -514,6 +542,10 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_rule *rule;
 	int err;
 
+	err = mlxsw_sp_flower_mall_prio_check(block, f);
+	if (err)
+		return err;
+
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
 					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
-- 
cgit v1.2.3


From 7a36e4918e30fbd3c820f723ef53d8505283c9e0 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Sat, 9 May 2020 18:43:10 +0800
Subject: octeontx2-pf: Use the napi_alloc_frag() to alloc the pool buffers

In the current codes, the octeontx2 uses its own method to allocate
the pool buffers, but there are some issues in this implementation.
1. We have to run the otx2_get_page() for each allocation cycle and
   this is pretty error prone. As I can see there is no invocation
   of the otx2_get_page() in otx2_pool_refill_task(), this will leave
   the allocated pages have the wrong refcount and may be freed wrongly.
2. It wastes memory. For example, if we only receive one packet in a
   NAPI RX cycle, and then allocate a 2K buffer with otx2_alloc_rbuf()
   to refill the pool buffers and leave the remain area of the allocated
   page wasted. On a kernel with 64K page, 62K area is wasted.

IMHO it is really unnecessary to implement our own method for the
buffers allocate, we can reuse the napi_alloc_frag() to simplify
our code.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/marvell/octeontx2/nic/otx2_common.c   | 52 +++++++++-------------
 .../ethernet/marvell/octeontx2/nic/otx2_common.h   | 15 +------
 .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.c |  3 +-
 .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.h |  4 --
 4 files changed, 24 insertions(+), 50 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index f1d2dea90a8c..5975521a4c86 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -379,40 +379,35 @@ void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx)
 		     (pfvf->hw.cq_ecount_wait - 1));
 }
 
-dma_addr_t otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			   gfp_t gfp)
+dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
 {
 	dma_addr_t iova;
+	u8 *buf;
 
-	/* Check if request can be accommodated in previous allocated page */
-	if (pool->page && ((pool->page_offset + pool->rbsize) <=
-	    (PAGE_SIZE << pool->rbpage_order))) {
-		pool->pageref++;
-		goto ret;
-	}
-
-	otx2_get_page(pool);
-
-	/* Allocate a new page */
-	pool->page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
-				 pool->rbpage_order);
-	if (unlikely(!pool->page))
+	buf = napi_alloc_frag(pool->rbsize);
+	if (unlikely(!buf))
 		return -ENOMEM;
 
-	pool->page_offset = 0;
-ret:
-	iova = (u64)otx2_dma_map_page(pfvf, pool->page, pool->page_offset,
-				      pool->rbsize, DMA_FROM_DEVICE);
-	if (!iova) {
-		if (!pool->page_offset)
-			__free_pages(pool->page, pool->rbpage_order);
-		pool->page = NULL;
+	iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
+				    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	if (unlikely(dma_mapping_error(pfvf->dev, iova))) {
+		page_frag_free(buf);
 		return -ENOMEM;
 	}
-	pool->page_offset += pool->rbsize;
+
 	return iova;
 }
 
+static dma_addr_t otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool)
+{
+	dma_addr_t addr;
+
+	local_bh_disable();
+	addr = __otx2_alloc_rbuf(pfvf, pool);
+	local_bh_enable();
+	return addr;
+}
+
 void otx2_tx_timeout(struct net_device *netdev, unsigned int txq)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
@@ -805,7 +800,7 @@ static void otx2_pool_refill_task(struct work_struct *work)
 	free_ptrs = cq->pool_ptrs;
 
 	while (cq->pool_ptrs) {
-		bufptr = otx2_alloc_rbuf(pfvf, rbpool, GFP_KERNEL);
+		bufptr = otx2_alloc_rbuf(pfvf, rbpool);
 		if (bufptr <= 0) {
 			/* Schedule a WQ if we fails to free atleast half of the
 			 * pointers else enable napi for this RQ.
@@ -1064,7 +1059,6 @@ static int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 		return err;
 
 	pool->rbsize = buf_size;
-	pool->rbpage_order = get_order(buf_size);
 
 	/* Initialize this pool's context via AF */
 	aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
@@ -1152,13 +1146,12 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
 			return -ENOMEM;
 
 		for (ptr = 0; ptr < num_sqbs; ptr++) {
-			bufptr = otx2_alloc_rbuf(pfvf, pool, GFP_KERNEL);
+			bufptr = otx2_alloc_rbuf(pfvf, pool);
 			if (bufptr <= 0)
 				return bufptr;
 			otx2_aura_freeptr(pfvf, pool_id, bufptr);
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
-		otx2_get_page(pool);
 	}
 
 	return 0;
@@ -1204,13 +1197,12 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
-			bufptr = otx2_alloc_rbuf(pfvf, pool, GFP_KERNEL);
+			bufptr = otx2_alloc_rbuf(pfvf, pool);
 			if (bufptr <= 0)
 				return bufptr;
 			otx2_aura_freeptr(pfvf, pool_id,
 					  bufptr + OTX2_HEAD_ROOM);
 		}
-		otx2_get_page(pool);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 0b1c653b3449..2fa29889522e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -434,18 +434,6 @@ static inline void otx2_aura_freeptr(struct otx2_nic *pfvf,
 		      otx2_get_regaddr(pfvf, NPA_LF_AURA_OP_FREE0));
 }
 
-/* Update page ref count */
-static inline void otx2_get_page(struct otx2_pool *pool)
-{
-	if (!pool->page)
-		return;
-
-	if (pool->pageref)
-		page_ref_add(pool->page, pool->pageref);
-	pool->pageref = 0;
-	pool->page = NULL;
-}
-
 static inline int otx2_get_pool_idx(struct otx2_nic *pfvf, int type, int idx)
 {
 	if (type == AURA_NIX_SQ)
@@ -589,8 +577,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl);
 int otx2_txsch_alloc(struct otx2_nic *pfvf);
 int otx2_txschq_stop(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
-dma_addr_t otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			   gfp_t gfp);
+dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool);
 int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable);
 void otx2_ctx_disable(struct mbox *mbox, int type, bool npa);
 int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 45abe0cd0e7b..b04f5429d72d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -286,7 +286,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf,
 
 	/* Refill pool with new buffers */
 	while (cq->pool_ptrs) {
-		bufptr = otx2_alloc_rbuf(pfvf, cq->rbpool, GFP_ATOMIC);
+		bufptr = __otx2_alloc_rbuf(pfvf, cq->rbpool);
 		if (unlikely(bufptr <= 0)) {
 			struct refill_work *work;
 			struct delayed_work *dwork;
@@ -304,7 +304,6 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf,
 		otx2_aura_freeptr(pfvf, cq->cq_idx, bufptr + OTX2_HEAD_ROOM);
 		cq->pool_ptrs--;
 	}
-	otx2_get_page(cq->rbpool);
 
 	return processed_cqe;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 4ab32d3adb78..da97f2d4416f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -113,11 +113,7 @@ struct otx2_cq_poll {
 struct otx2_pool {
 	struct qmem		*stack;
 	struct qmem		*fc_addr;
-	u8			rbpage_order;
 	u16			rbsize;
-	u32			page_offset;
-	u16			pageref;
-	struct page		*page;
 };
 
 struct otx2_cq_queue {
-- 
cgit v1.2.3


From 5705b45155c404a1eb2ccc92e95851cfa21d4f37 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 9 May 2020 17:27:37 +0800
Subject: net: hns3: remove a redundant register macro definition

HCLGE_MISC_VECTOR_INT_STS and HCLGE_VECTOR_PF_OTHER_INT_STS_REG
both represent the misc interrupt status register(0x20800), so
removes HCLGE_VECTOR_PF_OTHER_INT_STS_REG and replaces it with
HCLGE_MISC_VECTOR_INT_STS.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h  |  1 -
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 12 +++++-------
 2 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 876fd81ad2f1..608fe26fc3fe 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -16,7 +16,6 @@
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
 #define HCLGE_RAS_REG_ROCEE_ERR_MASK   0x3000000
 
-#define HCLGE_VECTOR0_PF_OTHER_INT_STS_REG   0x20800
 #define HCLGE_VECTOR0_REG_MSIX_MASK   0x1FF00
 
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN	0xFFFF0000
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 71a54ddb51f5..f0b1dc9f31ed 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2968,13 +2968,11 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
-	u32 rst_src_reg, cmdq_src_reg, msix_src_reg;
+	u32 cmdq_src_reg, msix_src_reg;
 
 	/* fetch the events from their corresponding regs */
-	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
-	msix_src_reg = hclge_read_dev(&hdev->hw,
-				      HCLGE_VECTOR0_PF_OTHER_INT_STS_REG);
+	msix_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
 	 * together then we will only process reset event in this go and will
@@ -2984,7 +2982,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 *
 	 * check for vector0 reset event sources
 	 */
-	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
+	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
 		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
@@ -2993,7 +2991,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
-	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
@@ -3483,7 +3481,7 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 	/* first, resolve any unknown reset type to the known type(s) */
 	if (test_bit(HNAE3_UNKNOWN_RESET, addr)) {
 		u32 msix_sts_reg = hclge_read_dev(&hdev->hw,
-					HCLGE_VECTOR0_PF_OTHER_INT_STS_REG);
+					HCLGE_MISC_VECTOR_INT_STS);
 		/* we will intentionally ignore any errors from this function
 		 *  as we will end up in *some* reset request in any case
 		 */
-- 
cgit v1.2.3


From 4279b4d5ec9c58f63fde23b2d86de4a1e494dc06 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 9 May 2020 17:27:38 +0800
Subject: net: hns3: modify two uncorrect macro names

According to the UM, command 0x0B03 and 0x0B13 are used to
query the statistics about TX and RX, not the status, so
modifies the unsuitable macro name of these two command.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 9a9d752aedc5..e3bab8f3847f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -184,11 +184,11 @@ enum hclge_opcode_type {
 	/* TQP commands */
 	HCLGE_OPC_CFG_TX_QUEUE		= 0x0B01,
 	HCLGE_OPC_QUERY_TX_POINTER	= 0x0B02,
-	HCLGE_OPC_QUERY_TX_STATUS	= 0x0B03,
+	HCLGE_OPC_QUERY_TX_STATS	= 0x0B03,
 	HCLGE_OPC_TQP_TX_QUEUE_TC	= 0x0B04,
 	HCLGE_OPC_CFG_RX_QUEUE		= 0x0B11,
 	HCLGE_OPC_QUERY_RX_POINTER	= 0x0B12,
-	HCLGE_OPC_QUERY_RX_STATUS	= 0x0B13,
+	HCLGE_OPC_QUERY_RX_STATS	= 0x0B13,
 	HCLGE_OPC_STASH_RX_QUEUE_LRO	= 0x0B16,
 	HCLGE_OPC_CFG_RX_QUEUE_LRO	= 0x0B17,
 	HCLGE_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index f0b1dc9f31ed..3ad6a6ae6c2f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -552,7 +552,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 		queue = handle->kinfo.tqp[i];
 		tqp = container_of(queue, struct hclge_tqp, q);
 		/* command : HCLGE_OPC_QUERY_IGU_STAT */
-		hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_RX_STATUS,
+		hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_RX_STATS,
 					   true);
 
 		desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
@@ -572,7 +572,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 		tqp = container_of(queue, struct hclge_tqp, q);
 		/* command : HCLGE_OPC_QUERY_IGU_STAT */
 		hclge_cmd_setup_basic_desc(&desc[0],
-					   HCLGE_OPC_QUERY_TX_STATUS,
+					   HCLGE_OPC_QUERY_TX_STATS,
 					   true);
 
 		desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
-- 
cgit v1.2.3


From a4de02287abb9947336dfdccc83f6c0cc182e7d9 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 9 May 2020 17:27:39 +0800
Subject: net: hns3: provide .get_cmdq_stat interface for the client

This patch provides a new interface for the client to query
whether CMDQ is ready to work.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h             | 1 +
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 5602bf226687..7506cabaa16e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -552,6 +552,7 @@ struct hnae3_ae_ops {
 	int (*set_vf_mac)(struct hnae3_handle *handle, int vf, u8 *p);
 	int (*get_module_eeprom)(struct hnae3_handle *handle, u32 offset,
 				 u32 len, u8 *data);
+	bool (*get_cmdq_stat)(struct hnae3_handle *handle);
 };
 
 struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3ad6a6ae6c2f..1ff896a9576c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6402,6 +6402,14 @@ static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle)
 	       hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING);
 }
 
+static bool hclge_get_cmdq_stat(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+}
+
 static bool hclge_ae_dev_resetting(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -11311,6 +11319,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_vf_rate = hclge_set_vf_rate,
 	.set_vf_mac = hclge_set_vf_mac,
 	.get_module_eeprom = hclge_get_module_eeprom,
+	.get_cmdq_stat = hclge_get_cmdq_stat,
 };
 
 static struct hnae3_ae_algo ae_algo = {
-- 
cgit v1.2.3


From b4401a044a1e6397d21806c210dd0d9b4da93e27 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Sat, 9 May 2020 17:27:40 +0800
Subject: net: hns3: optimized the judgment of the input parameters of dump ncl
 config

This patch optimizes the judgment of the input parameters of dump ncl
config by checking the number and value of the input parameters apart.
It's clearer and more reasonable.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c    | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 6cfa8253eefc..48c115c50db5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -1258,6 +1258,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 {
 #define HCLGE_MAX_NCL_CONFIG_OFFSET	4096
 #define HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD	(20 + 24 * 4)
+#define HCLGE_NCL_CONFIG_PARAM_NUM	2
 
 	struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM];
 	int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM;
@@ -1267,13 +1268,17 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
 	int ret;
 
 	ret = sscanf(cmd_buf, "%x %x", &offset, &length);
-	if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
-	    length > HCLGE_MAX_NCL_CONFIG_OFFSET - offset) {
-		dev_err(&hdev->pdev->dev, "Invalid offset or length.\n");
+	if (ret != HCLGE_NCL_CONFIG_PARAM_NUM) {
+		dev_err(&hdev->pdev->dev,
+			"Too few parameters, num = %d.\n", ret);
 		return;
 	}
-	if (offset < 0 || length <= 0) {
-		dev_err(&hdev->pdev->dev, "Non-positive offset or length.\n");
+
+	if (offset < 0 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
+	    length <= 0 || length > HCLGE_MAX_NCL_CONFIG_OFFSET - offset) {
+		dev_err(&hdev->pdev->dev,
+			"Invalid input, offset = %d, length = %d.\n",
+			offset, length);
 		return;
 	}
 
-- 
cgit v1.2.3


From 81c287e3dda20441c1469426fc9f44c9b2374fa9 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Sat, 9 May 2020 17:27:41 +0800
Subject: net: hns3: disable auto-negotiation off with 1000M setting in ethtool

The 802.3 specification does not specify the behavior of
auto-negotiation off with 1000M in PHY. Therefore, some PHY
compatibility issues occur. This patch forbids the setting of
this unreasonable mode by ethtool in driver.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 1a105f2f87a4..6b1545f982aa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -773,8 +773,13 @@ static int hns3_set_link_ksettings(struct net_device *netdev,
 		  cmd->base.autoneg, cmd->base.speed, cmd->base.duplex);
 
 	/* Only support ksettings_set for netdev with phy attached for now */
-	if (netdev->phydev)
+	if (netdev->phydev) {
+		if (cmd->base.speed == SPEED_1000 &&
+		    cmd->base.autoneg == AUTONEG_DISABLE)
+			return -EINVAL;
+
 		return phy_ethtool_ksettings_set(netdev->phydev, cmd);
+	}
 
 	if (handle->pdev->revision == 0x20)
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From c2dfc7d2a9be9a14897eab6dd27eeea1bd4ea79b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 7 May 2020 14:01:33 -0500
Subject: net: atarilance: Replace zero-length array with flexible-array

The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:

struct foo {
        int stuff;
        struct boo array[];
};

By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.

Also, notice that, dynamic memory allocations won't be affected by
this change:

"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]

sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.

This issue was found with the help of Coccinelle.

[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour")

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/atarilance.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c
index 4e36122609a3..961796abab35 100644
--- a/drivers/net/ethernet/amd/atarilance.c
+++ b/drivers/net/ethernet/amd/atarilance.c
@@ -156,7 +156,7 @@ struct lance_memory {
 	struct lance_init_block	init;
 	struct lance_tx_head	tx_head[TX_RING_SIZE];
 	struct lance_rx_head	rx_head[RX_RING_SIZE];
-	char					packet_area[0];	/* packet data follow after the
+	char					packet_area[];	/* packet data follow after the
 											 * init block and the ring
 											 * descriptors and are located
 											 * at runtime */
-- 
cgit v1.2.3


From 01f2b3dac8c4bebeb0ec15c4b7b59993766493cc Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Mon, 11 May 2020 05:58:57 +0000
Subject: hinic: add link_ksettings ethtool_ops support

add set_link_ksettings implementation and improve the implementation
of get_link_ksettings

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 420 +++++++++++++++++++++-
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c  |  13 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h  |  19 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_if.h   |   2 +-
 drivers/net/ethernet/huawei/hinic/hinic_port.c    | 129 +++++++
 drivers/net/ethernet/huawei/hinic/hinic_port.h    | 108 ++++++
 6 files changed, 682 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index 966aea949c0b..b426eeced069 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -33,6 +33,99 @@
 #include "hinic_rx.h"
 #include "hinic_dev.h"
 
+#define SET_LINK_STR_MAX_LEN	128
+
+#define GET_SUPPORTED_MODE	0
+#define GET_ADVERTISED_MODE	1
+
+#define ETHTOOL_ADD_SUPPORTED_SPEED_LINK_MODE(ecmd, mode)	\
+		((ecmd)->supported |=	\
+		(1UL << hw_to_ethtool_link_mode_table[mode].link_mode_bit))
+#define ETHTOOL_ADD_ADVERTISED_SPEED_LINK_MODE(ecmd, mode)	\
+		((ecmd)->advertising |=	\
+		(1UL << hw_to_ethtool_link_mode_table[mode].link_mode_bit))
+#define ETHTOOL_ADD_SUPPORTED_LINK_MODE(ecmd, mode)	\
+				((ecmd)->supported |= SUPPORTED_##mode)
+#define ETHTOOL_ADD_ADVERTISED_LINK_MODE(ecmd, mode)	\
+				((ecmd)->advertising |= ADVERTISED_##mode)
+
+struct hw2ethtool_link_mode {
+	enum ethtool_link_mode_bit_indices link_mode_bit;
+	u32 speed;
+	enum hinic_link_mode hw_link_mode;
+};
+
+struct cmd_link_settings {
+	u64	supported;
+	u64	advertising;
+
+	u32	speed;
+	u8	duplex;
+	u8	port;
+	u8	autoneg;
+};
+
+static u32 hw_to_ethtool_speed[LINK_SPEED_LEVELS] = {
+	SPEED_10, SPEED_100,
+	SPEED_1000, SPEED_10000,
+	SPEED_25000, SPEED_40000,
+	SPEED_100000
+};
+
+static struct hw2ethtool_link_mode
+	hw_to_ethtool_link_mode_table[HINIC_LINK_MODE_NUMBERS] = {
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+		.speed = SPEED_10000,
+		.hw_link_mode = HINIC_10GE_BASE_KR,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+		.speed = SPEED_40000,
+		.hw_link_mode = HINIC_40GE_BASE_KR4,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+		.speed = SPEED_40000,
+		.hw_link_mode = HINIC_40GE_BASE_CR4,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+		.speed = SPEED_100000,
+		.hw_link_mode = HINIC_100GE_BASE_KR4,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+		.speed = SPEED_100000,
+		.hw_link_mode = HINIC_100GE_BASE_CR4,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+		.speed = SPEED_25000,
+		.hw_link_mode = HINIC_25GE_BASE_KR_S,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+		.speed = SPEED_25000,
+		.hw_link_mode = HINIC_25GE_BASE_CR_S,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+		.speed = SPEED_25000,
+		.hw_link_mode = HINIC_25GE_BASE_KR,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+		.speed = SPEED_25000,
+		.hw_link_mode = HINIC_25GE_BASE_CR,
+	},
+	{
+		.link_mode_bit = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+		.speed = SPEED_1000,
+		.hw_link_mode = HINIC_GE_BASE_KX,
+	},
+};
+
 static void set_link_speed(struct ethtool_link_ksettings *link_ksettings,
 			   enum hinic_speed speed)
 {
@@ -71,18 +164,91 @@ static void set_link_speed(struct ethtool_link_ksettings *link_ksettings,
 	}
 }
 
+static int hinic_get_link_mode_index(enum hinic_link_mode link_mode)
+{
+	int i = 0;
+
+	for (i = 0; i < HINIC_LINK_MODE_NUMBERS; i++) {
+		if (link_mode == hw_to_ethtool_link_mode_table[i].hw_link_mode)
+			break;
+	}
+
+	return i;
+}
+
+static void hinic_add_ethtool_link_mode(struct cmd_link_settings *link_settings,
+					enum hinic_link_mode hw_link_mode,
+					u32 name)
+{
+	enum hinic_link_mode link_mode;
+	int idx = 0;
+
+	for (link_mode = 0; link_mode < HINIC_LINK_MODE_NUMBERS; link_mode++) {
+		if (hw_link_mode & ((u32)1 << link_mode)) {
+			idx = hinic_get_link_mode_index(link_mode);
+			if (idx >= HINIC_LINK_MODE_NUMBERS)
+				continue;
+
+			if (name == GET_SUPPORTED_MODE)
+				ETHTOOL_ADD_SUPPORTED_SPEED_LINK_MODE
+					(link_settings, idx);
+			else
+				ETHTOOL_ADD_ADVERTISED_SPEED_LINK_MODE
+					(link_settings, idx);
+		}
+	}
+}
+
+static void hinic_link_port_type(struct cmd_link_settings *link_settings,
+				 enum hinic_port_type port_type)
+{
+	switch (port_type) {
+	case HINIC_PORT_ELEC:
+	case HINIC_PORT_TP:
+		ETHTOOL_ADD_SUPPORTED_LINK_MODE(link_settings, TP);
+		ETHTOOL_ADD_ADVERTISED_LINK_MODE(link_settings, TP);
+		link_settings->port = PORT_TP;
+		break;
+
+	case HINIC_PORT_AOC:
+	case HINIC_PORT_FIBRE:
+		ETHTOOL_ADD_SUPPORTED_LINK_MODE(link_settings, FIBRE);
+		ETHTOOL_ADD_ADVERTISED_LINK_MODE(link_settings, FIBRE);
+		link_settings->port = PORT_FIBRE;
+		break;
+
+	case HINIC_PORT_COPPER:
+		ETHTOOL_ADD_SUPPORTED_LINK_MODE(link_settings, FIBRE);
+		ETHTOOL_ADD_ADVERTISED_LINK_MODE(link_settings, FIBRE);
+		link_settings->port = PORT_DA;
+		break;
+
+	case HINIC_PORT_BACKPLANE:
+		ETHTOOL_ADD_SUPPORTED_LINK_MODE(link_settings, Backplane);
+		ETHTOOL_ADD_ADVERTISED_LINK_MODE(link_settings, Backplane);
+		link_settings->port = PORT_NONE;
+		break;
+
+	default:
+		link_settings->port = PORT_OTHER;
+		break;
+	}
+}
+
 static int hinic_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings
 				    *link_ksettings)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_link_mode_cmd link_mode = { 0 };
+	struct hinic_pause_config pause_info = { 0 };
+	struct cmd_link_settings settings = { 0 };
 	enum hinic_port_link_state link_state;
 	struct hinic_port_cap port_cap;
 	int err;
 
+	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
-	ethtool_link_ksettings_add_link_mode(link_ksettings, supported,
-					     Autoneg);
 
 	link_ksettings->base.speed = SPEED_UNKNOWN;
 	link_ksettings->base.autoneg = AUTONEG_DISABLE;
@@ -92,14 +258,19 @@ static int hinic_get_link_ksettings(struct net_device *netdev,
 	if (err)
 		return err;
 
+	hinic_link_port_type(&settings, port_cap.port_type);
+	link_ksettings->base.port = settings.port;
+
 	err = hinic_port_link_state(nic_dev, &link_state);
 	if (err)
 		return err;
 
-	if (link_state != HINIC_LINK_STATE_UP)
-		return err;
-
-	set_link_speed(link_ksettings, port_cap.speed);
+	if (link_state == HINIC_LINK_STATE_UP) {
+		set_link_speed(link_ksettings, port_cap.speed);
+		link_ksettings->base.duplex =
+			(port_cap.duplex == HINIC_DUPLEX_FULL) ?
+			DUPLEX_FULL : DUPLEX_HALF;
+	}
 
 	if (!!(port_cap.autoneg_cap & HINIC_AUTONEG_SUPPORTED))
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -108,11 +279,243 @@ static int hinic_get_link_ksettings(struct net_device *netdev,
 	if (port_cap.autoneg_state == HINIC_AUTONEG_ACTIVE)
 		link_ksettings->base.autoneg = AUTONEG_ENABLE;
 
-	link_ksettings->base.duplex = (port_cap.duplex == HINIC_DUPLEX_FULL) ?
-					   DUPLEX_FULL : DUPLEX_HALF;
+	err = hinic_get_link_mode(nic_dev->hwdev, &link_mode);
+	if (err || link_mode.supported == HINIC_SUPPORTED_UNKNOWN ||
+	    link_mode.advertised == HINIC_SUPPORTED_UNKNOWN)
+		return -EIO;
+
+	hinic_add_ethtool_link_mode(&settings, link_mode.supported,
+				    GET_SUPPORTED_MODE);
+	hinic_add_ethtool_link_mode(&settings, link_mode.advertised,
+				    GET_ADVERTISED_MODE);
+
+	if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) {
+		err = hinic_get_hw_pause_info(nic_dev->hwdev, &pause_info);
+		if (err)
+			return err;
+		ETHTOOL_ADD_SUPPORTED_LINK_MODE(&settings, Pause);
+		if (pause_info.rx_pause && pause_info.tx_pause) {
+			ETHTOOL_ADD_ADVERTISED_LINK_MODE(&settings, Pause);
+		} else if (pause_info.tx_pause) {
+			ETHTOOL_ADD_ADVERTISED_LINK_MODE(&settings, Asym_Pause);
+		} else if (pause_info.rx_pause) {
+			ETHTOOL_ADD_ADVERTISED_LINK_MODE(&settings, Pause);
+			ETHTOOL_ADD_ADVERTISED_LINK_MODE(&settings, Asym_Pause);
+		}
+	}
+
+	bitmap_copy(link_ksettings->link_modes.supported,
+		    (unsigned long *)&settings.supported,
+		    __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_copy(link_ksettings->link_modes.advertising,
+		    (unsigned long *)&settings.advertising,
+		    __ETHTOOL_LINK_MODE_MASK_NBITS);
+
 	return 0;
 }
 
+static int hinic_ethtool_to_hw_speed_level(u32 speed)
+{
+	int i;
+
+	for (i = 0; i < LINK_SPEED_LEVELS; i++) {
+		if (hw_to_ethtool_speed[i] == speed)
+			break;
+	}
+
+	return i;
+}
+
+static bool hinic_is_support_speed(enum hinic_link_mode supported_link,
+				   u32 speed)
+{
+	enum hinic_link_mode link_mode;
+	int idx;
+
+	for (link_mode = 0; link_mode < HINIC_LINK_MODE_NUMBERS; link_mode++) {
+		if (!(supported_link & ((u32)1 << link_mode)))
+			continue;
+
+		idx = hinic_get_link_mode_index(link_mode);
+		if (idx >= HINIC_LINK_MODE_NUMBERS)
+			continue;
+
+		if (hw_to_ethtool_link_mode_table[idx].speed == speed)
+			return true;
+	}
+
+	return false;
+}
+
+static bool hinic_is_speed_legal(struct hinic_dev *nic_dev, u32 speed)
+{
+	struct hinic_link_mode_cmd link_mode = { 0 };
+	struct net_device *netdev = nic_dev->netdev;
+	enum nic_speed_level speed_level = 0;
+	int err;
+
+	err = hinic_get_link_mode(nic_dev->hwdev, &link_mode);
+	if (err)
+		return false;
+
+	if (link_mode.supported == HINIC_SUPPORTED_UNKNOWN ||
+	    link_mode.advertised == HINIC_SUPPORTED_UNKNOWN)
+		return false;
+
+	speed_level = hinic_ethtool_to_hw_speed_level(speed);
+	if (speed_level >= LINK_SPEED_LEVELS ||
+	    !hinic_is_support_speed(link_mode.supported, speed)) {
+		netif_err(nic_dev, drv, netdev,
+			  "Unsupported speed: %d\n", speed);
+		return false;
+	}
+
+	return true;
+}
+
+static int get_link_settings_type(struct hinic_dev *nic_dev,
+				  u8 autoneg, u32 speed, u32 *set_settings)
+{
+	struct hinic_port_cap port_cap = { 0 };
+	int err;
+
+	err = hinic_port_get_cap(nic_dev, &port_cap);
+	if (err)
+		return err;
+
+	/* always set autonegotiation */
+	if (port_cap.autoneg_cap)
+		*set_settings |= HILINK_LINK_SET_AUTONEG;
+
+	if (autoneg == AUTONEG_ENABLE) {
+		if (!port_cap.autoneg_cap) {
+			netif_err(nic_dev, drv, nic_dev->netdev, "Not support autoneg\n");
+			return -EOPNOTSUPP;
+		}
+	} else if (speed != (u32)SPEED_UNKNOWN) {
+		/* set speed only when autoneg is disabled */
+		if (!hinic_is_speed_legal(nic_dev, speed))
+			return -EINVAL;
+		*set_settings |= HILINK_LINK_SET_SPEED;
+	} else {
+		netif_err(nic_dev, drv, nic_dev->netdev, "Need to set speed when autoneg is off\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int set_link_settings_separate_cmd(struct hinic_dev *nic_dev,
+					  u32 set_settings, u8 autoneg,
+					  u32 speed)
+{
+	enum nic_speed_level speed_level = 0;
+	int err = 0;
+
+	if (set_settings & HILINK_LINK_SET_AUTONEG) {
+		err = hinic_set_autoneg(nic_dev->hwdev,
+					(autoneg == AUTONEG_ENABLE));
+		if (err)
+			netif_err(nic_dev, drv, nic_dev->netdev, "%s autoneg failed\n",
+				  (autoneg == AUTONEG_ENABLE) ?
+				  "Enable" : "Disable");
+		else
+			netif_info(nic_dev, drv, nic_dev->netdev, "%s autoneg successfully\n",
+				   (autoneg == AUTONEG_ENABLE) ?
+				   "Enable" : "Disable");
+	}
+
+	if (!err && (set_settings & HILINK_LINK_SET_SPEED)) {
+		speed_level = hinic_ethtool_to_hw_speed_level(speed);
+		err = hinic_set_speed(nic_dev->hwdev, speed_level);
+		if (err)
+			netif_err(nic_dev, drv, nic_dev->netdev, "Set speed %d failed\n",
+				  speed);
+		else
+			netif_info(nic_dev, drv, nic_dev->netdev, "Set speed %d successfully\n",
+				   speed);
+	}
+
+	return err;
+}
+
+static int hinic_set_settings_to_hw(struct hinic_dev *nic_dev,
+				    u32 set_settings, u8 autoneg, u32 speed)
+{
+	struct hinic_link_ksettings_info settings = {0};
+	char set_link_str[SET_LINK_STR_MAX_LEN] = {0};
+	struct net_device *netdev = nic_dev->netdev;
+	enum nic_speed_level speed_level = 0;
+	int err;
+
+	err = snprintf(set_link_str, SET_LINK_STR_MAX_LEN, "%s",
+		       (set_settings & HILINK_LINK_SET_AUTONEG) ?
+		       (autoneg ? "autong enable " : "autong disable ") : "");
+	if (err < 0 || err >= SET_LINK_STR_MAX_LEN) {
+		netif_err(nic_dev, drv, netdev, "Failed to snprintf link state, function return(%d) and dest_len(%d)\n",
+			  err, SET_LINK_STR_MAX_LEN);
+		return -EFAULT;
+	}
+
+	if (set_settings & HILINK_LINK_SET_SPEED) {
+		speed_level = hinic_ethtool_to_hw_speed_level(speed);
+		err = snprintf(set_link_str, SET_LINK_STR_MAX_LEN,
+			       "%sspeed %d ", set_link_str, speed);
+		if (err <= 0 || err >= SET_LINK_STR_MAX_LEN) {
+			netif_err(nic_dev, drv, netdev, "Failed to snprintf link speed, function return(%d) and dest_len(%d)\n",
+				  err, SET_LINK_STR_MAX_LEN);
+			return -EFAULT;
+		}
+	}
+
+	settings.func_id = HINIC_HWIF_FUNC_IDX(nic_dev->hwdev->hwif);
+	settings.valid_bitmap = set_settings;
+	settings.autoneg = autoneg;
+	settings.speed = speed_level;
+
+	err = hinic_set_link_settings(nic_dev->hwdev, &settings);
+	if (err != HINIC_MGMT_CMD_UNSUPPORTED) {
+		if (err)
+			netif_err(nic_dev, drv, netdev, "Set %s failed\n",
+				  set_link_str);
+		else
+			netif_info(nic_dev, drv, netdev, "Set %s successfully\n",
+				   set_link_str);
+
+		return err;
+	}
+
+	return set_link_settings_separate_cmd(nic_dev, set_settings, autoneg,
+					      speed);
+}
+
+static int set_link_settings(struct net_device *netdev, u8 autoneg, u32 speed)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	u32 set_settings = 0;
+	int err;
+
+	err = get_link_settings_type(nic_dev, autoneg, speed, &set_settings);
+	if (err)
+		return err;
+
+	if (set_settings)
+		err = hinic_set_settings_to_hw(nic_dev, set_settings,
+					       autoneg, speed);
+	else
+		netif_info(nic_dev, drv, netdev, "Nothing changed, exit without setting anything\n");
+
+	return err;
+}
+
+static int hinic_set_link_ksettings(struct net_device *netdev, const struct
+				    ethtool_link_ksettings *link_settings)
+{
+	/* only support to set autoneg and speed */
+	return set_link_settings(netdev, link_settings->base.autoneg,
+				 link_settings->base.speed);
+}
+
 static void hinic_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *info)
 {
@@ -741,6 +1144,7 @@ static void hinic_get_strings(struct net_device *netdev,
 
 static const struct ethtool_ops hinic_ethtool_ops = {
 	.get_link_ksettings = hinic_get_link_ksettings,
+	.set_link_ksettings = hinic_set_link_ksettings,
 	.get_drvinfo = hinic_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = hinic_get_ringparam,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 1ce8b8d572cf..2879b0445eba 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -219,6 +219,19 @@ int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
 				 HINIC_MGMT_MSG_SYNC);
 }
 
+int hinic_hilink_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_hilink_cmd cmd,
+			 void *buf_in, u16 in_size, void *buf_out,
+			 u16 *out_size)
+{
+	struct hinic_pfhwdev *pfhwdev;
+
+	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
+
+	return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_HILINK, cmd,
+				 buf_in, in_size, buf_out, out_size,
+				 HINIC_MGMT_MSG_SYNC);
+}
+
 /**
  * init_fw_ctxt- Init Firmware tables before network mgmt and io operations
  * @hwdev: the NIC HW device
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index c8f62a024a58..ce57914bef72 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -54,6 +54,9 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_SET_RX_MODE      = 12,
 
+	HINIC_PORT_CMD_GET_PAUSE_INFO	= 20,
+	HINIC_PORT_CMD_SET_PAUSE_INFO	= 21,
+
 	HINIC_PORT_CMD_GET_LINK_STATE   = 24,
 
 	HINIC_PORT_CMD_SET_LRO		= 25,
@@ -116,11 +119,23 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_CAP          = 170,
 
+	HINIC_PORT_CMD_GET_LINK_MODE	= 217,
+
+	HINIC_PORT_CMD_SET_SPEED	= 218,
+
+	HINIC_PORT_CMD_SET_AUTONEG	= 219,
+
 	HINIC_PORT_CMD_SET_LRO_TIMER	= 244,
 
 	HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 249,
 };
 
+/* cmd of mgmt CPU message for HILINK module */
+enum hinic_hilink_cmd {
+	HINIC_HILINK_CMD_GET_LINK_INFO		= 0x3,
+	HINIC_HILINK_CMD_SET_LINK_SETTINGS	= 0x8,
+};
+
 enum hinic_ucode_cmd {
 	HINIC_UCODE_CMD_MODIFY_QUEUE_CONTEXT    = 0,
 	HINIC_UCODE_CMD_CLEAN_QUEUE_CONTEXT,
@@ -328,6 +343,10 @@ int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd,
 		       void *buf_in, u16 in_size, void *buf_out,
 		       u16 *out_size);
 
+int hinic_hilink_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_hilink_cmd cmd,
+			 void *buf_in, u16 in_size, void *buf_out,
+			 u16 *out_size);
+
 int hinic_hwdev_ifup(struct hinic_hwdev *hwdev);
 
 void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 5bb6ec4dcb7c..0872e035faa1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -192,7 +192,7 @@ enum hinic_mod_type {
 	HINIC_MOD_COMM  = 0,    /* HW communication module */
 	HINIC_MOD_L2NIC = 1,    /* L2NIC module */
 	HINIC_MOD_CFGM  = 7,    /* Configuration module */
-
+	HINIC_MOD_HILINK = 14,  /* Hilink module */
 	HINIC_MOD_MAX   = 15
 };
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 714d8279c591..2edb6127f9fb 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -1072,3 +1072,132 @@ int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver)
 
 	return 0;
 }
+
+int hinic_get_link_mode(struct hinic_hwdev *hwdev,
+			struct hinic_link_mode_cmd *link_mode)
+{
+	u16 out_size;
+	int err;
+
+	if (!hwdev || !link_mode)
+		return -EINVAL;
+
+	out_size = sizeof(*link_mode);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_MODE,
+				 link_mode, sizeof(*link_mode),
+				 link_mode, &out_size);
+	if (err || !out_size || link_mode->status) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"Failed to get link mode, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, link_mode->status, out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic_set_autoneg(struct hinic_hwdev *hwdev, bool enable)
+{
+	struct hinic_set_autoneg_cmd autoneg = {0};
+	u16 out_size = sizeof(autoneg);
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	autoneg.func_id = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+	autoneg.enable = enable;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_AUTONEG,
+				 &autoneg, sizeof(autoneg),
+				 &autoneg, &out_size);
+	if (err || !out_size || autoneg.status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to %s autoneg, err: %d, status: 0x%x, out size: 0x%x\n",
+			enable ? "enable" : "disable", err, autoneg.status,
+			out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic_set_speed(struct hinic_hwdev *hwdev, enum nic_speed_level speed)
+{
+	struct hinic_speed_cmd speed_info = {0};
+	u16 out_size = sizeof(speed_info);
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	speed_info.func_id = HINIC_HWIF_FUNC_IDX(hwdev->hwif);
+	speed_info.speed = speed;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_SPEED,
+				 &speed_info, sizeof(speed_info),
+				 &speed_info, &out_size);
+	if (err || !out_size || speed_info.status) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"Failed to set speed, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, speed_info.status, out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic_set_link_settings(struct hinic_hwdev *hwdev,
+			    struct hinic_link_ksettings_info *info)
+{
+	u16 out_size = sizeof(*info);
+	int err;
+
+	err = hinic_hilink_msg_cmd(hwdev, HINIC_HILINK_CMD_SET_LINK_SETTINGS,
+				   info, sizeof(*info), info, &out_size);
+	if ((info->status != HINIC_MGMT_CMD_UNSUPPORTED &&
+	     info->status) || err || !out_size) {
+		dev_err(&hwdev->hwif->pdev->dev,
+			"Failed to set link settings, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, info->status, out_size);
+		return -EFAULT;
+	}
+
+	return info->status;
+}
+
+int hinic_get_hw_pause_info(struct hinic_hwdev *hwdev,
+			    struct hinic_pause_config *pause_info)
+{
+	u16 out_size = sizeof(*pause_info);
+	int err;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_PAUSE_INFO,
+				 pause_info, sizeof(*pause_info),
+				 pause_info, &out_size);
+	if (err || !out_size || pause_info->status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to get pause info, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, pause_info->status, out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic_set_hw_pause_info(struct hinic_hwdev *hwdev,
+			    struct hinic_pause_config *pause_info)
+{
+	u16 out_size = sizeof(*pause_info);
+	int err;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_PAUSE_INFO,
+				 pause_info, sizeof(*pause_info),
+				 pause_info, &out_size);
+	if (err || !out_size || pause_info->status) {
+		dev_err(&hwdev->hwif->pdev->dev, "Failed to set pause info, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, pause_info->status, out_size);
+		return -EIO;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index f2781521970e..5f34308abd2b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -79,6 +79,42 @@ enum hinic_speed {
 	HINIC_SPEED_UNKNOWN = 0xFF,
 };
 
+enum hinic_link_mode {
+	HINIC_10GE_BASE_KR = 0,
+	HINIC_40GE_BASE_KR4 = 1,
+	HINIC_40GE_BASE_CR4 = 2,
+	HINIC_100GE_BASE_KR4 = 3,
+	HINIC_100GE_BASE_CR4 = 4,
+	HINIC_25GE_BASE_KR_S = 5,
+	HINIC_25GE_BASE_CR_S = 6,
+	HINIC_25GE_BASE_KR = 7,
+	HINIC_25GE_BASE_CR = 8,
+	HINIC_GE_BASE_KX = 9,
+	HINIC_LINK_MODE_NUMBERS,
+
+	HINIC_SUPPORTED_UNKNOWN = 0xFFFF,
+};
+
+enum hinic_port_type {
+	HINIC_PORT_TP,		/* BASET */
+	HINIC_PORT_AUI,
+	HINIC_PORT_MII,
+	HINIC_PORT_FIBRE,	/* OPTICAL */
+	HINIC_PORT_BNC,
+	HINIC_PORT_ELEC,
+	HINIC_PORT_COPPER,	/* PORT_DA */
+	HINIC_PORT_AOC,
+	HINIC_PORT_BACKPLANE,
+	HINIC_PORT_NONE = 0xEF,
+	HINIC_PORT_OTHER = 0xFF,
+};
+
+enum hinic_valid_link_settings {
+	HILINK_LINK_SET_SPEED = 0x1,
+	HILINK_LINK_SET_AUTONEG = 0x2,
+	HILINK_LINK_SET_FEC = 0x4,
+};
+
 enum hinic_tso_state {
 	HINIC_TSO_DISABLE = 0,
 	HINIC_TSO_ENABLE  = 1,
@@ -179,6 +215,50 @@ struct hinic_port_cap {
 	u8      rsvd2[3];
 };
 
+struct hinic_link_mode_cmd {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u16	supported;	/* 0xFFFF represents invalid value */
+	u16	advertised;
+};
+
+struct hinic_speed_cmd {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	speed;
+};
+
+struct hinic_set_autoneg_cmd {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	enable;	/* 1: enable , 0: disable */
+};
+
+struct hinic_link_ksettings_info {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+
+	u32	valid_bitmap;
+	u32	speed;		/* enum nic_speed_level */
+	u8	autoneg;	/* 0 - off; 1 - on */
+	u8	fec;		/* 0 - RSFEC; 1 - BASEFEC; 2 - NOFEC */
+	u8	rsvd2[18];	/* reserved for duplex, port, etc. */
+};
+
 struct hinic_tso_config {
 	u8	status;
 	u8	version;
@@ -549,6 +629,18 @@ struct hinic_spoofchk_set {
 	u16	func_id;
 };
 
+struct hinic_pause_config {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	auto_neg;
+	u32	rx_pause;
+	u32	tx_pause;
+};
+
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
@@ -628,4 +720,20 @@ int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en);
 
 int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver);
 
+int hinic_set_link_settings(struct hinic_hwdev *hwdev,
+			    struct hinic_link_ksettings_info *info);
+
+int hinic_get_link_mode(struct hinic_hwdev *hwdev,
+			struct hinic_link_mode_cmd *link_mode);
+
+int hinic_set_autoneg(struct hinic_hwdev *hwdev, bool enable);
+
+int hinic_set_speed(struct hinic_hwdev *hwdev, enum nic_speed_level speed);
+
+int hinic_get_hw_pause_info(struct hinic_hwdev *hwdev,
+			    struct hinic_pause_config *pause_info);
+
+int hinic_set_hw_pause_info(struct hinic_hwdev *hwdev,
+			    struct hinic_pause_config *pause_info);
+
 #endif
-- 
cgit v1.2.3


From 73e030977f7884dbe1be0018bab517e8d02760f8 Mon Sep 17 00:00:00 2001
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Mon, 11 May 2020 15:41:41 +0530
Subject: net: qed*: Reduce RX and TX default ring count when running inside
 kdump kernel

Normally kdump kernel(s) run under severe memory constraint with the
basic idea being to save the crashdump vmcore reliably when the primary
kernel panics/hangs.

Currently the qed* ethernet driver ends up consuming a lot of memory in
the kdump kernel, leading to kdump kernel panic when one tries to save
the vmcore via ssh/nfs (thus utilizing the services of the underlying
qed* network interfaces).

An example OOM message log seen in the kdump kernel can be seen here
[1], with crashkernel size reservation of 512M.

Using tools like memstrack (see [2]), we can track the modules taking up
the bulk of memory in the kdump kernel and organize the memory usage
output as per 'highest allocator first'. An example log for the OOM case
indicates that the qed* modules end up allocating approximately 216M
memory, which is a large part of the total crashkernel size:

 dracut-pre-pivot[676]: ======== Report format module_summary: ========
 dracut-pre-pivot[676]: Module qed using 149.6MB (2394 pages), peak allocation 149.6MB (2394 pages)
 dracut-pre-pivot[676]: Module qede using 65.3MB (1045 pages), peak allocation 65.3MB (1045 pages)

This patch reduces the default RX and TX ring count from 1024 to 64
when running inside kdump kernel, which leads to a significant memory
saving.

An example log with the patch applied shows the reduced memory
allocation in the kdump kernel:
 dracut-pre-pivot[674]: ======== Report format module_summary: ========
 dracut-pre-pivot[674]: Module qed using 141.8MB (2268 pages), peak allocation 141.8MB (2268 pages)
 <..snip..>
[dracut-pre-pivot[674]: Module qede using 4.8MB (76 pages), peak allocation 4.9MB (78 pages)

Tested crashdump vmcore save via ssh/nfs protocol using underlying qed*
network interface after applying this patch.

[1] OOM log:
------------

 kworker/0:6: page allocation failure: order:6,
 mode:0x60c0c0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null)
 kworker/0:6 cpuset=/ mems_allowed=0
 CPU: 0 PID: 145 Comm: kworker/0:6 Not tainted 4.18.0-109.el8.aarch64 #1
 Hardware name: To be filled by O.E.M. Saber/Saber, BIOS 0ACKL025
 01/18/2019
 Workqueue: events work_for_cpu_fn
 Call trace:
  dump_backtrace+0x0/0x188
  show_stack+0x24/0x30
  dump_stack+0x90/0xb4
  warn_alloc+0xf4/0x178
  __alloc_pages_nodemask+0xcac/0xd58
  alloc_pages_current+0x8c/0xf8
  kmalloc_order_trace+0x38/0x108
  qed_iov_alloc+0x40/0x248 [qed]
  qed_resc_alloc+0x224/0x518 [qed]
  qed_slowpath_start+0x254/0x928 [qed]
   __qede_probe+0xf8/0x5e0 [qede]
  qede_probe+0x68/0xd8 [qede]
  local_pci_probe+0x44/0xa8
  work_for_cpu_fn+0x20/0x30
  process_one_work+0x1ac/0x3e8
  worker_thread+0x44/0x448
  kthread+0x130/0x138
  ret_from_fork+0x10/0x18
  Cannot start slowpath
  qede: probe of 0000:05:00.1 failed with error -12

[2]. Memstrack tool: https://github.com/ryncsn/memstrack

Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: Ariel Elior <aelior@marvell.com>
Cc: GR-everest-linux-l2@marvell.com
Cc: Manish Chopra <manishc@marvell.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      |  2 ++
 drivers/net/ethernet/qlogic/qede/qede_main.c | 11 +++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 1a708f95ce94..f6f0b51620ab 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -575,12 +575,14 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
 #define NUM_RX_BDS_MAX		(RX_RING_SIZE - 1)
 #define NUM_RX_BDS_MIN		128
+#define NUM_RX_BDS_KDUMP_MIN	63
 #define NUM_RX_BDS_DEF		((u16)BIT(10) - 1)
 
 #define TX_RING_SIZE_POW	13
 #define TX_RING_SIZE		((u16)BIT(TX_RING_SIZE_POW))
 #define NUM_TX_BDS_MAX		(TX_RING_SIZE - 1)
 #define NUM_TX_BDS_MIN		128
+#define NUM_TX_BDS_KDUMP_MIN	63
 #define NUM_TX_BDS_DEF		NUM_TX_BDS_MAX
 
 #define QEDE_MIN_PKT_LEN		64
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 256506024b88..8cb2408b12ac 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -29,6 +29,7 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
+#include <linux/crash_dump.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/version.h>
@@ -715,8 +716,14 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev,
 	edev->dp_module = dp_module;
 	edev->dp_level = dp_level;
 	edev->ops = qed_ops;
-	edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
-	edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+
+	if (is_kdump_kernel()) {
+		edev->q_num_rx_buffers = NUM_RX_BDS_KDUMP_MIN;
+		edev->q_num_tx_buffers = NUM_TX_BDS_KDUMP_MIN;
+	} else {
+		edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
+		edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+	}
 
 	DP_INFO(edev, "Allocated netdev with %d tx queues and %d rx queues\n",
 		info->num_queues, info->num_queues);
-- 
cgit v1.2.3


From 37d4f8a6b41f622608671ab8434194c819a5e444 Mon Sep 17 00:00:00 2001
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Mon, 11 May 2020 15:41:42 +0530
Subject: net: qed: Disable SRIOV functionality inside kdump kernel

Since we have kdump kernel(s) running under severe memory constraint
it makes sense to disable the qed SRIOV functionality when running the
kdump kernel as kdump configurations on several distributions don't
support SRIOV targets for saving the vmcore (see [1] for example).

Currently the qed SRIOV functionality ends up consuming memory in
the kdump kernel, when we don't really use the same.

An example log seen in the kdump kernel with the SRIOV functionality
enabled can be seen below (obtained via memstrack tool, see [2]):
 dracut-pre-pivot[676]: ======== Report format module_summary: ========
 dracut-pre-pivot[676]: Module qed using 149.6MB (2394 pages), peak allocation 149.6MB (2394 pages)

This patch disables the SRIOV functionality inside kdump kernel and with
the same applied the memory consumption goes down:
 dracut-pre-pivot[671]: ======== Report format module_summary: ========
 dracut-pre-pivot[671]: Module qed using 124.6MB (1993 pages), peak allocation 124.7MB (1995 pages)

[1]. https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/8/html/managing_monitoring_and_updating_the_kernel/installing-and-configuring-kdump_managing-monitoring-and-updating-the-kernel#supported-kdump-targets_supported-kdump-configurations-and-targets
[2]. Memstrack tool: https://github.com/ryncsn/memstrack

Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: Ariel Elior <aelior@marvell.com>
Cc: GR-everest-linux-l2@marvell.com
Cc: Manish Chopra <manishc@marvell.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_sriov.h  | 10 +++++++---
 drivers/net/ethernet/qlogic/qede/qede_main.c |  2 +-
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index 368e88565783..aabeaf03135e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -32,6 +32,7 @@
 
 #ifndef _QED_SRIOV_H
 #define _QED_SRIOV_H
+#include <linux/crash_dump.h>
 #include <linux/types.h>
 #include "qed_vf.h"
 
@@ -40,9 +41,12 @@
 #define QED_VF_ARRAY_LENGTH (3)
 
 #ifdef CONFIG_QED_SRIOV
-#define IS_VF(cdev)             ((cdev)->b_is_vf)
-#define IS_PF(cdev)             (!((cdev)->b_is_vf))
-#define IS_PF_SRIOV(p_hwfn)     (!!((p_hwfn)->cdev->p_iov_info))
+#define IS_VF(cdev)             (is_kdump_kernel() ? \
+				 (0) : ((cdev)->b_is_vf))
+#define IS_PF(cdev)             (is_kdump_kernel() ? \
+				 (1) : !((cdev)->b_is_vf))
+#define IS_PF_SRIOV(p_hwfn)     (is_kdump_kernel() ? \
+				 (0) : !!((p_hwfn)->cdev->p_iov_info))
 #else
 #define IS_VF(cdev)             (0)
 #define IS_PF(cdev)             (1)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8cb2408b12ac..300405369c37 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1214,7 +1214,7 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	case QEDE_PRIVATE_VF:
 		if (debug & QED_LOG_VERBOSE_MASK)
 			dev_err(&pdev->dev, "Probing a VF\n");
-		is_vf = true;
+		is_vf = is_kdump_kernel() ? false : true;
 		break;
 	default:
 		if (debug & QED_LOG_VERBOSE_MASK)
-- 
cgit v1.2.3


From dfcabb078847479cc2874c11af3f6cb3b79ddd03 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:28:20 +0100
Subject: sfc: move vport_id to struct efx_nic

Remove some usage of ef10-specific nic_data structs from common MCDI
 functions, in preparation for using them from a non-EF10 driver.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c           | 16 ++++++++--------
 drivers/net/ethernet/sfc/ef10_sriov.c     | 27 +++++++++++++--------------
 drivers/net/ethernet/sfc/mcdi_filters.c   |  5 ++---
 drivers/net/ethernet/sfc/mcdi_functions.c |  8 ++------
 drivers/net/ethernet/sfc/mcdi_port.c      |  7 ++-----
 drivers/net/ethernet/sfc/net_driver.h     |  2 ++
 drivers/net/ethernet/sfc/nic.h            |  2 --
 7 files changed, 29 insertions(+), 38 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 3f16bd807c6e..0ad311ff6796 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -553,7 +553,7 @@ static int efx_ef10_probe(struct efx_nic *efx)
 
 	efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
 
-	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+	efx->vport_id = EVB_PORT_ID_ASSIGNED;
 
 	/* In case we're recovering from a crash (kexec), we want to
 	 * cancel any outstanding request by the previous user of this
@@ -1335,7 +1335,7 @@ static void efx_ef10_table_reset_mc_allocations(struct efx_nic *efx)
 
 	/* Driver-created vswitches and vports must be re-created */
 	nic_data->must_probe_vswitching = true;
-	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+	efx->vport_id = EVB_PORT_ID_ASSIGNED;
 #ifdef CONFIG_SFC_SRIOV
 	if (nic_data->vf)
 		for (i = 0; i < efx->vf_count; i++)
@@ -3158,22 +3158,22 @@ static int efx_ef10_vport_set_mac_address(struct efx_nic *efx)
 	efx_mcdi_filter_table_remove(efx);
 	up_write(&efx->filter_sem);
 
-	rc = efx_ef10_vadaptor_free(efx, nic_data->vport_id);
+	rc = efx_ef10_vadaptor_free(efx, efx->vport_id);
 	if (rc)
 		goto restore_filters;
 
 	ether_addr_copy(mac_old, nic_data->vport_mac);
-	rc = efx_ef10_vport_del_mac(efx, nic_data->vport_id,
+	rc = efx_ef10_vport_del_mac(efx, efx->vport_id,
 				    nic_data->vport_mac);
 	if (rc)
 		goto restore_vadaptor;
 
-	rc = efx_ef10_vport_add_mac(efx, nic_data->vport_id,
+	rc = efx_ef10_vport_add_mac(efx, efx->vport_id,
 				    efx->net_dev->dev_addr);
 	if (!rc) {
 		ether_addr_copy(nic_data->vport_mac, efx->net_dev->dev_addr);
 	} else {
-		rc2 = efx_ef10_vport_add_mac(efx, nic_data->vport_id, mac_old);
+		rc2 = efx_ef10_vport_add_mac(efx, efx->vport_id, mac_old);
 		if (rc2) {
 			/* Failed to add original MAC, so clear vport_mac */
 			eth_zero_addr(nic_data->vport_mac);
@@ -3182,7 +3182,7 @@ static int efx_ef10_vport_set_mac_address(struct efx_nic *efx)
 	}
 
 restore_vadaptor:
-	rc2 = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	rc2 = efx_ef10_vadaptor_alloc(efx, efx->vport_id);
 	if (rc2)
 		goto reset_nic;
 restore_filters:
@@ -3225,7 +3225,7 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx)
 	ether_addr_copy(MCDI_PTR(inbuf, VADAPTOR_SET_MAC_IN_MACADDR),
 			efx->net_dev->dev_addr);
 	MCDI_SET_DWORD(inbuf, VADAPTOR_SET_MAC_IN_UPSTREAM_PORT_ID,
-		       nic_data->vport_id);
+		       efx->vport_id);
 	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
 				sizeof(inbuf), NULL, 0, NULL);
 
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 4580b30caae1..21fa6c0e8873 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -232,15 +232,14 @@ fail:
 
 static int efx_ef10_vadaptor_alloc_set_features(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	u32 port_flags;
 	int rc;
 
-	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	rc = efx_ef10_vadaptor_alloc(efx, efx->vport_id);
 	if (rc)
 		goto fail_vadaptor_alloc;
 
-	rc = efx_ef10_vadaptor_query(efx, nic_data->vport_id,
+	rc = efx_ef10_vadaptor_query(efx, efx->vport_id,
 				     &port_flags, NULL, NULL);
 	if (rc)
 		goto fail_vadaptor_query;
@@ -281,11 +280,11 @@ int efx_ef10_vswitching_probe_pf(struct efx_nic *efx)
 
 	rc = efx_ef10_vport_alloc(efx, EVB_PORT_ID_ASSIGNED,
 				  MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
-				  EFX_EF10_NO_VLAN, &nic_data->vport_id);
+				  EFX_EF10_NO_VLAN, &efx->vport_id);
 	if (rc)
 		goto fail2;
 
-	rc = efx_ef10_vport_add_mac(efx, nic_data->vport_id, net_dev->dev_addr);
+	rc = efx_ef10_vport_add_mac(efx, efx->vport_id, net_dev->dev_addr);
 	if (rc)
 		goto fail3;
 	ether_addr_copy(nic_data->vport_mac, net_dev->dev_addr);
@@ -296,11 +295,11 @@ int efx_ef10_vswitching_probe_pf(struct efx_nic *efx)
 
 	return 0;
 fail4:
-	efx_ef10_vport_del_mac(efx, nic_data->vport_id, nic_data->vport_mac);
+	efx_ef10_vport_del_mac(efx, efx->vport_id, nic_data->vport_mac);
 	eth_zero_addr(nic_data->vport_mac);
 fail3:
-	efx_ef10_vport_free(efx, nic_data->vport_id);
-	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+	efx_ef10_vport_free(efx, efx->vport_id);
+	efx->vport_id = EVB_PORT_ID_ASSIGNED;
 fail2:
 	efx_ef10_vswitch_free(efx, EVB_PORT_ID_ASSIGNED);
 fail1:
@@ -355,22 +354,22 @@ void efx_ef10_vswitching_remove_pf(struct efx_nic *efx)
 
 	efx_ef10_sriov_free_vf_vswitching(efx);
 
-	efx_ef10_vadaptor_free(efx, nic_data->vport_id);
+	efx_ef10_vadaptor_free(efx, efx->vport_id);
 
-	if (nic_data->vport_id == EVB_PORT_ID_ASSIGNED)
+	if (efx->vport_id == EVB_PORT_ID_ASSIGNED)
 		return; /* No vswitch was ever created */
 
 	if (!is_zero_ether_addr(nic_data->vport_mac)) {
-		efx_ef10_vport_del_mac(efx, nic_data->vport_id,
+		efx_ef10_vport_del_mac(efx, efx->vport_id,
 				       efx->net_dev->dev_addr);
 		eth_zero_addr(nic_data->vport_mac);
 	}
-	efx_ef10_vport_free(efx, nic_data->vport_id);
-	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+	efx_ef10_vport_free(efx, efx->vport_id);
+	efx->vport_id = EVB_PORT_ID_ASSIGNED;
 
 	/* Only free the vswitch if no VFs are assigned */
 	if (!pci_vfs_assigned(efx->pci_dev))
-		efx_ef10_vswitch_free(efx, nic_data->vport_id);
+		efx_ef10_vswitch_free(efx, efx->vport_id);
 }
 
 void efx_ef10_vswitching_remove_vf(struct efx_nic *efx)
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index 4310ae5bd898..e6268556b030 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -186,7 +186,6 @@ static void efx_mcdi_filter_push_prep(struct efx_nic *efx,
 				      struct efx_rss_context *ctx,
 				      bool replacing)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	u32 flags = spec->flags;
 
 	memset(inbuf, 0, MC_CMD_FILTER_OP_EXT_IN_LEN);
@@ -211,7 +210,7 @@ static void efx_mcdi_filter_push_prep(struct efx_nic *efx,
 		efx_mcdi_filter_push_prep_set_match_fields(efx, spec, inbuf);
 	}
 
-	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_PORT_ID, nic_data->vport_id);
+	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_PORT_ID, efx->vport_id);
 	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_DEST,
 		       spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ?
 		       MC_CMD_FILTER_OP_IN_RX_DEST_DROP :
@@ -1944,7 +1943,7 @@ static int efx_mcdi_filter_alloc_rss_context(struct efx_nic *efx, bool exclusive
 		return -EOPNOTSUPP;
 
 	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID,
-		       nic_data->vport_id);
+		       efx->vport_id);
 	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE, alloc_type);
 	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_NUM_QUEUES, rss_spread);
 
diff --git a/drivers/net/ethernet/sfc/mcdi_functions.c b/drivers/net/ethernet/sfc/mcdi_functions.c
index dcfe78b0fa5a..962d8395d958 100644
--- a/drivers/net/ethernet/sfc/mcdi_functions.c
+++ b/drivers/net/ethernet/sfc/mcdi_functions.c
@@ -168,21 +168,18 @@ int efx_mcdi_tx_init(struct efx_tx_queue *tx_queue, bool tso_v2)
 	size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
 	struct efx_channel *channel = tx_queue->channel;
 	struct efx_nic *efx = tx_queue->efx;
-	struct efx_ef10_nic_data *nic_data;
 	dma_addr_t dma_addr;
 	size_t inlen;
 	int rc, i;
 
 	BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0);
 
-	nic_data = efx->nic_data;
-
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_LABEL, tx_queue->queue);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_INSTANCE, tx_queue->queue);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
-	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, nic_data->vport_id);
+	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, efx->vport_id);
 
 	dma_addr = tx_queue->txd.buf.dma_addr;
 
@@ -276,7 +273,6 @@ void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
 	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
 	size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
 	struct efx_nic *efx = rx_queue->efx;
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	dma_addr_t dma_addr;
 	size_t inlen;
 	int rc;
@@ -295,7 +291,7 @@ void efx_mcdi_rx_init(struct efx_rx_queue *rx_queue)
 			      INIT_RXQ_IN_FLAG_PREFIX, 1,
 			      INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
-	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, nic_data->vport_id);
+	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, efx->vport_id);
 
 	dma_addr = rx_queue->rxd.buf.dma_addr;
 
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index ab5227b13ae6..b807871d8f69 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -722,11 +722,8 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx,
 			      MAC_STATS_IN_PERIOD_MS, period);
 	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
 
-	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
-		struct efx_ef10_nic_data *nic_data = efx->nic_data;
-
-		MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, nic_data->vport_id);
-	}
+	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
+		MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, efx->vport_id);
 
 	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
 				NULL, 0, NULL);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b084e623b5f4..d43f22c8f31c 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -887,6 +887,7 @@ struct efx_async_filter_insertion {
  * @rss_context: Main RSS context.  Its @list member is the head of the list of
  *	RSS contexts created by user requests
  * @rss_lock: Protects custom RSS context software state in @rss_context.list
+ * @vport_id: The function's vport ID, only relevant for PFs
  * @int_error_count: Number of internal errors seen recently
  * @int_error_expire: Time at which error count will be expired
  * @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
@@ -1044,6 +1045,7 @@ struct efx_nic {
 	bool rx_scatter;
 	struct efx_rss_context rss_context;
 	struct mutex rss_lock;
+	u32 vport_id;
 
 	unsigned int_error_count;
 	unsigned long int_error_expire;
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 6670fda8f35a..9e2e387a4b1c 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -385,7 +385,6 @@ enum {
  * %MC_CMD_GET_CAPABILITIES response)
  * @rx_dpcpu_fw_id: Firmware ID of the RxDPCPU
  * @tx_dpcpu_fw_id: Firmware ID of the TxDPCPU
- * @vport_id: The function's vport ID, only relevant for PFs
  * @must_probe_vswitching: Flag: vswitching has yet to be setup after MC reboot
  * @pf_index: The number for this PF, or the parent PF if this is a VF
 #ifdef CONFIG_SFC_SRIOV
@@ -423,7 +422,6 @@ struct efx_ef10_nic_data {
 	u32 datapath_caps2;
 	unsigned int rx_dpcpu_fw_id;
 	unsigned int tx_dpcpu_fw_id;
-	unsigned int vport_id;
 	bool must_probe_vswitching;
 	unsigned int pf_index;
 	u8 port_id[ETH_ALEN];
-- 
cgit v1.2.3


From be904b855200ef4672c765918b31338b59c4847c Mon Sep 17 00:00:00 2001
From: Tom Zhao <tzhao@solarflare.com>
Date: Mon, 11 May 2020 13:28:40 +0100
Subject: sfc: make capability checking a nic_type function

Various MCDI functions (especially in filter handling) need to check the
 datapath caps, but those live in nic_data (since they don't exist on
 Siena).  Decouple from ef10-specific data structures by adding check_caps
 to the nic_type, to allow using these functions from non-ef10 drivers.

Also add a convenience macro efx_has_cap() to reduce the amount of
 boilerplate involved in calling it.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       | 18 ++++++++++++++++++
 drivers/net/ethernet/sfc/mcdi.h       | 12 ++++++++++++
 drivers/net/ethernet/sfc/net_driver.h |  3 +++
 drivers/net/ethernet/sfc/siena.c      |  7 +++++++
 4 files changed, 40 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 0ad311ff6796..7b3c6214dee6 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3961,6 +3961,22 @@ out_unlock:
 	return rc;
 }
 
+static unsigned int ef10_check_caps(const struct efx_nic *efx,
+				    u8 flag,
+				    u32 offset)
+{
+	const struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	switch (offset) {
+	case(MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_OFST):
+		return nic_data->datapath_caps & BIT_ULL(flag);
+	case(MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_OFST):
+		return nic_data->datapath_caps2 & BIT_ULL(flag);
+	default:
+		return 0;
+	}
+}
+
 #define EF10_OFFLOAD_FEATURES		\
 	(NETIF_F_IP_CSUM |		\
 	 NETIF_F_HW_VLAN_CTAG_FILTER |	\
@@ -4073,6 +4089,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
 			    1 << HWTSTAMP_FILTER_ALL,
 	.rx_hash_key_size = 40,
+	.check_caps = ef10_check_caps,
 };
 
 const struct efx_nic_type efx_hunt_a0_nic_type = {
@@ -4208,4 +4225,5 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
 			    1 << HWTSTAMP_FILTER_ALL,
 	.rx_hash_key_size = 40,
+	.check_caps = ef10_check_caps,
 };
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 54a45010b576..b107e4c00285 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -326,6 +326,18 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
 #define MCDI_EVENT_FIELD(_ev, _field)			\
 	EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field)
 
+#define MCDI_CAPABILITY(field)						\
+	MC_CMD_GET_CAPABILITIES_V4_OUT_ ## field ## _LBN
+
+#define MCDI_CAPABILITY_OFST(field) \
+	MC_CMD_GET_CAPABILITIES_V4_OUT_ ## field ## _OFST
+
+/* field is FLAGS1 or FLAGS2 */
+#define efx_has_cap(efx, flag, field) \
+	efx->type->check_caps(efx, \
+			      MCDI_CAPABILITY(flag), \
+			      MCDI_CAPABILITY_OFST(field))
+
 void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len);
 int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 			   u16 *fw_subtype_list, u32 *capabilities);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index d43f22c8f31c..bdeea48ff938 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1354,6 +1354,9 @@ struct efx_nic_type {
 	void (*get_wol)(struct efx_nic *efx, struct ethtool_wolinfo *wol);
 	int (*set_wol)(struct efx_nic *efx, u32 type);
 	void (*resume_wol)(struct efx_nic *efx);
+	unsigned int (*check_caps)(const struct efx_nic *efx,
+				   u8 flag,
+				   u32 offset);
 	int (*test_chip)(struct efx_nic *efx, struct efx_self_tests *tests);
 	int (*test_nvram)(struct efx_nic *efx);
 	void (*mcdi_request)(struct efx_nic *efx,
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index baa464161626..ed1cb6caa69d 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -948,6 +948,13 @@ fail:
 
 #endif /* CONFIG_SFC_MTD */
 
+unsigned int siena_check_caps(const struct efx_nic *efx,
+			      u8 flag, u32 offset)
+{
+	/* Siena did not support MC_CMD_GET_CAPABILITIES */
+	return 0;
+}
+
 /**************************************************************************
  *
  * Revision-dependent attributes used by efx.c and nic.c
-- 
cgit v1.2.3


From 484a75b1dbc492cca4893718e70daccc05c2ce0b Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:28:56 +0100
Subject: sfc: use efx_has_cap for capability checks outside of NIC-specific
 code

Removes some efx_ef10_nic_data references from common code.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mcdi_filters.c | 13 ++++---------
 drivers/net/ethernet/sfc/ptp.c          |  7 +------
 2 files changed, 5 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index e6268556b030..39f8a91c1222 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -829,8 +829,7 @@ static int efx_mcdi_filter_insert_def(struct efx_nic *efx,
 		efx_filter_set_uc_def(&spec);
 
 	if (encap_type) {
-		if (nic_data->datapath_caps &
-		    (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN))
+		if (efx_has_cap(efx, VXLAN_NVGRE, FLAGS1))
 			efx_filter_set_encap_type(&spec, encap_type);
 		else
 			/*
@@ -1309,8 +1308,7 @@ int efx_mcdi_filter_table_probe(struct efx_nic *efx)
 	rc = efx_mcdi_filter_table_probe_matches(efx, table, false);
 	if (rc)
 		goto fail;
-	if (nic_data->datapath_caps &
-		   (1 << MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN))
+	if (efx_has_cap(efx, VXLAN_NVGRE, FLAGS1))
 		rc = efx_mcdi_filter_table_probe_matches(efx, table, true);
 	if (rc)
 		goto fail;
@@ -1920,7 +1918,6 @@ static int efx_mcdi_filter_alloc_rss_context(struct efx_nic *efx, bool exclusive
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_ALLOC_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN);
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	size_t outlen;
 	int rc;
 	u32 alloc_type = exclusive ?
@@ -1938,8 +1935,7 @@ static int efx_mcdi_filter_alloc_rss_context(struct efx_nic *efx, bool exclusive
 		return 0;
 	}
 
-	if (nic_data->datapath_caps &
-	    1 << MC_CMD_GET_CAPABILITIES_OUT_RX_RSS_LIMITED_LBN)
+	if (efx_has_cap(efx, RX_RSS_LIMITED, FLAGS1))
 		return -EOPNOTSUPP;
 
 	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID,
@@ -1960,8 +1956,7 @@ static int efx_mcdi_filter_alloc_rss_context(struct efx_nic *efx, bool exclusive
 	if (context_size)
 		*context_size = rss_spread;
 
-	if (nic_data->datapath_caps &
-	    1 << MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN)
+	if (efx_has_cap(efx, ADDITIONAL_RSS_MODES, FLAGS1))
 		efx_mcdi_set_rss_context_flags(efx, ctx);
 
 	return 0;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 59b4f16896a8..04c7283d205e 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -352,12 +352,7 @@ static int efx_phc_enable(struct ptp_clock_info *ptp,
 
 bool efx_ptp_use_mac_tx_timestamps(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-
-	return ((efx_nic_rev(efx) >= EFX_REV_HUNT_A0) &&
-		(nic_data->datapath_caps2 &
-		 (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_LBN)
-		));
+	return efx_has_cap(efx, TX_MAC_TIMESTAMPING, FLAGS2);
 }
 
 /* PTP 'extra' channel is still a traffic channel, but we only create TX queues
-- 
cgit v1.2.3


From e4fe938cff0464643b1fbca872e5e10b1ec4c478 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:29:09 +0100
Subject: sfc: move 'must restore' flags out of ef10-specific nic_data

Common code in mcdi_filters.c uses these flags, so by moving them to
 either struct efx_nic (in the case of must_realloc_vis) or struct
 efx_mcdi_filter_table (for must_restore_rss_contexts and
 must_restore_filters), decouple this code from ef10's nic_data.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c         | 14 ++++++--------
 drivers/net/ethernet/sfc/mcdi_filters.c | 24 ++++++++++++++++--------
 drivers/net/ethernet/sfc/mcdi_filters.h |  6 ++++++
 drivers/net/ethernet/sfc/net_driver.h   |  2 ++
 drivers/net/ethernet/sfc/nic.h          |  7 -------
 5 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7b3c6214dee6..b33bd6b77501 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1281,13 +1281,13 @@ static int efx_ef10_init_nic(struct efx_nic *efx)
 		nic_data->must_check_datapath_caps = false;
 	}
 
-	if (nic_data->must_realloc_vis) {
+	if (efx->must_realloc_vis) {
 		/* We cannot let the number of VIs change now */
 		rc = efx_ef10_alloc_vis(efx, nic_data->n_allocated_vis,
 					nic_data->n_allocated_vis);
 		if (rc)
 			return rc;
-		nic_data->must_realloc_vis = false;
+		efx->must_realloc_vis = false;
 	}
 
 	if (nic_data->must_restore_piobufs && nic_data->n_piobufs) {
@@ -1326,9 +1326,8 @@ static void efx_ef10_table_reset_mc_allocations(struct efx_nic *efx)
 #endif
 
 	/* All our allocations have been reset */
-	nic_data->must_realloc_vis = true;
-	nic_data->must_restore_rss_contexts = true;
-	nic_data->must_restore_filters = true;
+	efx->must_realloc_vis = true;
+	efx_mcdi_filter_table_reset_mc_allocations(efx);
 	nic_data->must_restore_piobufs = true;
 	efx_ef10_forget_old_piobufs(efx);
 	efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
@@ -3100,16 +3099,15 @@ void efx_ef10_handle_drain_event(struct efx_nic *efx)
 
 static int efx_ef10_fini_dmaq(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
+	struct efx_channel *channel;
 	int pending;
 
 	/* If the MC has just rebooted, the TX/RX queues will have already been
 	 * torn down, but efx->active_queues needs to be set to zero.
 	 */
-	if (nic_data->must_realloc_vis) {
+	if (efx->must_realloc_vis) {
 		atomic_set(&efx->active_queues, 0);
 		return 0;
 	}
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index 39f8a91c1222..bb29fc0063bf 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -331,7 +331,6 @@ static s32 efx_mcdi_filter_insert_locked(struct efx_nic *efx,
 					 bool replace_equal)
 {
 	DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	struct efx_mcdi_filter_table *table;
 	struct efx_filter_spec *saved_spec;
 	struct efx_rss_context *ctx = NULL;
@@ -460,7 +459,7 @@ static s32 efx_mcdi_filter_insert_locked(struct efx_nic *efx,
 	rc = efx_mcdi_filter_push(efx, spec, &table->entry[ins_index].handle,
 				  ctx, replacing);
 
-	if (rc == -EINVAL && nic_data->must_realloc_vis)
+	if (rc == -EINVAL && efx->must_realloc_vis)
 		/* The MC rebooted under us, causing it to reject our filter
 		 * insertion as pointing to an invalid VI (spec->dmaq_id).
 		 */
@@ -1355,6 +1354,16 @@ fail:
 	return rc;
 }
 
+void efx_mcdi_filter_table_reset_mc_allocations(struct efx_nic *efx)
+{
+	struct efx_mcdi_filter_table *table = efx->filter_state;
+
+	if (table) {
+		table->must_restore_filters = true;
+		table->must_restore_rss_contexts = true;
+	}
+}
+
 /*
  * Caller must hold efx->filter_sem for read if race against
  * efx_mcdi_filter_table_remove() is possible
@@ -1362,7 +1371,6 @@ fail:
 void efx_mcdi_filter_table_restore(struct efx_nic *efx)
 {
 	struct efx_mcdi_filter_table *table = efx->filter_state;
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	unsigned int invalid_filters = 0, failed = 0;
 	struct efx_mcdi_filter_vlan *vlan;
 	struct efx_filter_spec *spec;
@@ -1374,7 +1382,7 @@ void efx_mcdi_filter_table_restore(struct efx_nic *efx)
 
 	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
 
-	if (!nic_data->must_restore_filters)
+	if (!table->must_restore_filters)
 		return;
 
 	if (!table)
@@ -1453,7 +1461,7 @@ not_restored:
 		netif_err(efx, hw, efx->net_dev,
 			  "unable to restore %u filters\n", failed);
 	else
-		nic_data->must_restore_filters = false;
+		table->must_restore_filters = false;
 }
 
 void efx_mcdi_filter_table_remove(struct efx_nic *efx)
@@ -2176,13 +2184,13 @@ int efx_mcdi_rx_pull_rss_config(struct efx_nic *efx)
 
 void efx_mcdi_rx_restore_rss_contexts(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_mcdi_filter_table *table = efx->filter_state;
 	struct efx_rss_context *ctx;
 	int rc;
 
 	WARN_ON(!mutex_is_locked(&efx->rss_lock));
 
-	if (!nic_data->must_restore_rss_contexts)
+	if (!table->must_restore_rss_contexts)
 		return;
 
 	list_for_each_entry(ctx, &efx->rss_context.list, list) {
@@ -2198,7 +2206,7 @@ void efx_mcdi_rx_restore_rss_contexts(struct efx_nic *efx)
 				   "; RSS filters may fail to be applied\n",
 				   ctx->user_id, rc);
 	}
-	nic_data->must_restore_rss_contexts = false;
+	table->must_restore_rss_contexts = false;
 }
 
 int efx_mcdi_pf_rx_push_rss_config(struct efx_nic *efx, bool user,
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.h b/drivers/net/ethernet/sfc/mcdi_filters.h
index 1837f4f5d661..884ba9731131 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.h
+++ b/drivers/net/ethernet/sfc/mcdi_filters.h
@@ -75,6 +75,10 @@ struct efx_mcdi_filter_table {
 /* Whether in multicast promiscuous mode when last changed */
 	bool mc_promisc_last;
 	bool mc_overflow; /* Too many MC addrs; should always imply mc_promisc */
+	/* RSS contexts have yet to be restored after MC reboot */
+	bool must_restore_rss_contexts;
+	/* filters have yet to be restored after MC reboot */
+	bool must_restore_filters;
 	bool vlan_filter;
 	struct list_head vlan_list;
 };
@@ -83,6 +87,8 @@ int efx_mcdi_filter_table_probe(struct efx_nic *efx);
 void efx_mcdi_filter_table_remove(struct efx_nic *efx);
 void efx_mcdi_filter_table_restore(struct efx_nic *efx);
 
+void efx_mcdi_filter_table_reset_mc_allocations(struct efx_nic *efx);
+
 /*
  * The filter table(s) are managed by firmware and we have write-only
  * access.  When removing filters we must identify them to the
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index bdeea48ff938..ae9756811dfe 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -890,6 +890,7 @@ struct efx_async_filter_insertion {
  * @vport_id: The function's vport ID, only relevant for PFs
  * @int_error_count: Number of internal errors seen recently
  * @int_error_expire: Time at which error count will be expired
+ * @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot
  * @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
  *	acknowledge but do nothing else.
  * @irq_status: Interrupt status buffer
@@ -1050,6 +1051,7 @@ struct efx_nic {
 	unsigned int_error_count;
 	unsigned long int_error_expire;
 
+	bool must_realloc_vis;
 	bool irq_soft_enabled;
 	struct efx_buffer irq_status;
 	unsigned irq_zero_count;
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 9e2e387a4b1c..46583ba8fa24 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -360,10 +360,6 @@ enum {
  * @warm_boot_count: Last seen MC warm boot count
  * @vi_base: Absolute index of first VI in this function
  * @n_allocated_vis: Number of VIs allocated to this function
- * @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot
- * @must_restore_rss_contexts: Flag: RSS contexts have yet to be restored after
- *	MC reboot
- * @must_restore_filters: Flag: filters have yet to be restored after MC reboot
  * @n_piobufs: Number of PIO buffers allocated to this function
  * @wc_membase: Base address of write-combining mapping of the memory BAR
  * @pio_write_base: Base address for writing PIO buffers
@@ -403,9 +399,6 @@ struct efx_ef10_nic_data {
 	u16 warm_boot_count;
 	unsigned int vi_base;
 	unsigned int n_allocated_vis;
-	bool must_realloc_vis;
-	bool must_restore_rss_contexts;
-	bool must_restore_filters;
 	unsigned int n_piobufs;
 	void __iomem *wc_membase, *pio_write_base;
 	unsigned int pio_write_vi_base;
-- 
cgit v1.2.3


From fd14e5fd136b1868d10f032a389a36603fb3a119 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:29:23 +0100
Subject: sfc: rework handling of (firmware) multicast chaining state

Store the mc_chaining bit in struct efx_mcdi_filter_table, so that common
 code in mcdi_filters.c doesn't need to get it from ef10-specific nic_data.
Also, probe the firmware workaround just before the call to
 efx_mcdi_filter_table_probe(), rather than in a random other part of the
 driver bringup, to ensure that (a) it gets probed in time and (b) it gets
 reprobed as necessary on resets, no matter how the surrounding code gets
 reorganised and reordered.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c         | 141 +++++++++++++++++---------------
 drivers/net/ethernet/sfc/mcdi_filters.c |  15 ++--
 drivers/net/ethernet/sfc/mcdi_filters.h |   9 +-
 3 files changed, 90 insertions(+), 75 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index b33bd6b77501..0779dda7d29f 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2388,6 +2388,76 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	}
 }
 
+static int efx_ef10_probe_multicast_chaining(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	unsigned int enabled, implemented;
+	bool want_workaround_26807;
+	int rc;
+
+	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);
+	if (rc == -ENOSYS) {
+		/* GET_WORKAROUNDS was implemented before this workaround,
+		 * thus it must be unavailable in this firmware.
+		 */
+		nic_data->workaround_26807 = false;
+		return 0;
+	}
+	if (rc)
+		return rc;
+	want_workaround_26807 =
+		implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807;
+	nic_data->workaround_26807 =
+		!!(enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807);
+
+	if (want_workaround_26807 && !nic_data->workaround_26807) {
+		unsigned int flags;
+
+		rc = efx_mcdi_set_workaround(efx,
+					     MC_CMD_WORKAROUND_BUG26807,
+					     true, &flags);
+		if (!rc) {
+			if (flags &
+			    1 << MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_LBN) {
+				netif_info(efx, drv, efx->net_dev,
+					   "other functions on NIC have been reset\n");
+
+				/* With MCFW v4.6.x and earlier, the
+				 * boot count will have incremented,
+				 * so re-read the warm_boot_count
+				 * value now to ensure this function
+				 * doesn't think it has changed next
+				 * time it checks.
+				 */
+				rc = efx_ef10_get_warm_boot_count(efx);
+				if (rc >= 0) {
+					nic_data->warm_boot_count = rc;
+					rc = 0;
+				}
+			}
+			nic_data->workaround_26807 = true;
+		} else if (rc == -EPERM) {
+			rc = 0;
+		}
+	}
+	return rc;
+}
+
+static int efx_ef10_filter_table_probe(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	int rc = efx_ef10_probe_multicast_chaining(efx);
+
+	if (rc)
+		return rc;
+	rc = efx_mcdi_filter_table_probe(efx, nic_data->workaround_26807);
+
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
 /* This creates an entry in the RX descriptor queue */
 static inline void
 efx_ef10_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
@@ -2463,75 +2533,14 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 {
 	struct efx_nic *efx = channel->efx;
 	struct efx_ef10_nic_data *nic_data;
-	unsigned int enabled, implemented;
 	bool use_v2, cut_thru;
-	int rc;
 
 	nic_data = efx->nic_data;
 	use_v2 = nic_data->datapath_caps2 &
 			    1 << MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN;
 	cut_thru = !(nic_data->datapath_caps &
 			      1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
-	rc = efx_mcdi_ev_init(channel, cut_thru, use_v2);
-
-	/* IRQ return is ignored */
-	if (channel->channel || rc)
-		return rc;
-
-	/* Successfully created event queue on channel 0 */
-	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);
-	if (rc == -ENOSYS) {
-		/* GET_WORKAROUNDS was implemented before this workaround,
-		 * thus it must be unavailable in this firmware.
-		 */
-		nic_data->workaround_26807 = false;
-		rc = 0;
-	} else if (rc) {
-		goto fail;
-	} else {
-		nic_data->workaround_26807 =
-			!!(enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807);
-
-		if (implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807 &&
-		    !nic_data->workaround_26807) {
-			unsigned int flags;
-
-			rc = efx_mcdi_set_workaround(efx,
-						     MC_CMD_WORKAROUND_BUG26807,
-						     true, &flags);
-
-			if (!rc) {
-				if (flags &
-				    1 << MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_LBN) {
-					netif_info(efx, drv, efx->net_dev,
-						   "other functions on NIC have been reset\n");
-
-					/* With MCFW v4.6.x and earlier, the
-					 * boot count will have incremented,
-					 * so re-read the warm_boot_count
-					 * value now to ensure this function
-					 * doesn't think it has changed next
-					 * time it checks.
-					 */
-					rc = efx_ef10_get_warm_boot_count(efx);
-					if (rc >= 0) {
-						nic_data->warm_boot_count = rc;
-						rc = 0;
-					}
-				}
-				nic_data->workaround_26807 = true;
-			} else if (rc == -EPERM) {
-				rc = 0;
-			}
-		}
-	}
-
-	if (!rc)
-		return 0;
-
-fail:
-	efx_mcdi_ev_fini(channel);
-	return rc;
+	return efx_mcdi_ev_init(channel, cut_thru, use_v2);
 }
 
 static void efx_ef10_handle_rx_wrong_queue(struct efx_rx_queue *rx_queue,
@@ -3185,7 +3194,7 @@ restore_vadaptor:
 		goto reset_nic;
 restore_filters:
 	down_write(&efx->filter_sem);
-	rc2 = efx_mcdi_filter_table_probe(efx);
+	rc2 = efx_ef10_filter_table_probe(efx);
 	up_write(&efx->filter_sem);
 	if (rc2)
 		goto reset_nic;
@@ -3227,7 +3236,7 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx)
 	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
 				sizeof(inbuf), NULL, 0, NULL);
 
-	efx_mcdi_filter_table_probe(efx);
+	efx_ef10_filter_table_probe(efx);
 	up_write(&efx->filter_sem);
 	mutex_unlock(&efx->mac_lock);
 
@@ -4041,7 +4050,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.ev_process = efx_ef10_ev_process,
 	.ev_read_ack = efx_ef10_ev_read_ack,
 	.ev_test_generate = efx_ef10_ev_test_generate,
-	.filter_table_probe = efx_mcdi_filter_table_probe,
+	.filter_table_probe = efx_ef10_filter_table_probe,
 	.filter_table_restore = efx_mcdi_filter_table_restore,
 	.filter_table_remove = efx_mcdi_filter_table_remove,
 	.filter_update_rx_scatter = efx_mcdi_update_rx_scatter,
@@ -4154,7 +4163,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.ev_process = efx_ef10_ev_process,
 	.ev_read_ack = efx_ef10_ev_read_ack,
 	.ev_test_generate = efx_ef10_ev_test_generate,
-	.filter_table_probe = efx_mcdi_filter_table_probe,
+	.filter_table_probe = efx_ef10_filter_table_probe,
 	.filter_table_restore = efx_mcdi_filter_table_restore,
 	.filter_table_remove = efx_mcdi_filter_table_remove,
 	.filter_update_rx_scatter = efx_mcdi_update_rx_scatter,
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index bb29fc0063bf..d3c2e6eb3191 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -811,7 +811,7 @@ static int efx_mcdi_filter_insert_def(struct efx_nic *efx,
 				      enum efx_encap_type encap_type,
 				      bool multicast, bool rollback)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_mcdi_filter_table *table = efx->filter_state;
 	enum efx_filter_flags filter_flags;
 	struct efx_filter_spec spec;
 	u8 baddr[ETH_ALEN];
@@ -896,7 +896,7 @@ static int efx_mcdi_filter_insert_def(struct efx_nic *efx,
 
 		EFX_WARN_ON_PARANOID(*id != EFX_EF10_FILTER_ID_INVALID);
 		*id = efx_mcdi_filter_get_unsafe_id(rc);
-		if (!nic_data->workaround_26807 && !encap_type) {
+		if (!table->mc_chaining && !encap_type) {
 			/* Also need an Ethernet broadcast filter */
 			efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
 					   filter_flags, 0);
@@ -962,7 +962,6 @@ static void efx_mcdi_filter_vlan_sync_rx_mode(struct efx_nic *efx,
 					      struct efx_mcdi_filter_vlan *vlan)
 {
 	struct efx_mcdi_filter_table *table = efx->filter_state;
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 
 	/*
 	 * Do not install unspecified VID if VLAN filtering is enabled.
@@ -1009,11 +1008,10 @@ static void efx_mcdi_filter_vlan_sync_rx_mode(struct efx_nic *efx,
 	 * If changing promiscuous state with cascaded multicast filters, remove
 	 * old filters first, so that packets are dropped rather than duplicated
 	 */
-	if (nic_data->workaround_26807 &&
-	    table->mc_promisc_last != table->mc_promisc)
+	if (table->mc_chaining && table->mc_promisc_last != table->mc_promisc)
 		efx_mcdi_filter_remove_old(efx);
 	if (table->mc_promisc) {
-		if (nic_data->workaround_26807) {
+		if (table->mc_chaining) {
 			/*
 			 * If we failed to insert promiscuous filters, rollback
 			 * and fall back to individual multicast filters
@@ -1048,7 +1046,7 @@ static void efx_mcdi_filter_vlan_sync_rx_mode(struct efx_nic *efx,
 		 */
 		if (efx_mcdi_filter_insert_addr_list(efx, vlan, true, true)) {
 			/* Changing promisc state, so remove old filters */
-			if (nic_data->workaround_26807)
+			if (table->mc_chaining)
 				efx_mcdi_filter_remove_old(efx);
 			if (efx_mcdi_filter_insert_def(efx, vlan,
 						       EFX_ENCAP_TYPE_NONE,
@@ -1285,7 +1283,7 @@ efx_mcdi_filter_table_probe_matches(struct efx_nic *efx,
 	return 0;
 }
 
-int efx_mcdi_filter_table_probe(struct efx_nic *efx)
+int efx_mcdi_filter_table_probe(struct efx_nic *efx, bool multicast_chaining)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	struct net_device *net_dev = efx->net_dev;
@@ -1303,6 +1301,7 @@ int efx_mcdi_filter_table_probe(struct efx_nic *efx)
 	if (!table)
 		return -ENOMEM;
 
+	table->mc_chaining = multicast_chaining;
 	table->rx_match_count = 0;
 	rc = efx_mcdi_filter_table_probe_matches(efx, table, false);
 	if (rc)
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.h b/drivers/net/ethernet/sfc/mcdi_filters.h
index 884ba9731131..15b5d62e3670 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.h
+++ b/drivers/net/ethernet/sfc/mcdi_filters.h
@@ -79,11 +79,18 @@ struct efx_mcdi_filter_table {
 	bool must_restore_rss_contexts;
 	/* filters have yet to be restored after MC reboot */
 	bool must_restore_filters;
+	/* Multicast filter chaining allows less-specific filters to receive
+	 * multicast packets that matched more-specific filters.  Early EF10
+	 * firmware didn't support this (SF bug 26807); if mc_chaining == false
+	 * then we still subscribe the dev_mc_list even when mc_promisc to
+	 * prevent another VI stealing the traffic.
+	 */
+	bool mc_chaining;
 	bool vlan_filter;
 	struct list_head vlan_list;
 };
 
-int efx_mcdi_filter_table_probe(struct efx_nic *efx);
+int efx_mcdi_filter_table_probe(struct efx_nic *efx, bool multicast_chaining);
 void efx_mcdi_filter_table_remove(struct efx_nic *efx);
 void efx_mcdi_filter_table_restore(struct efx_nic *efx);
 
-- 
cgit v1.2.3


From dbf2c669062c1247345c0a3c0c3112e386ffe3f0 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:29:34 +0100
Subject: sfc: move rx_rss_context_exclusive into struct efx_mcdi_filter_table

It's both set and used solely by mcdi_filters.c, so there's no reason
 for it to be in ef10-specific nic_data.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mcdi_filters.c | 10 +++++-----
 drivers/net/ethernet/sfc/mcdi_filters.h |  2 ++
 drivers/net/ethernet/sfc/nic.h          |  2 --
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index d3c2e6eb3191..e99b3149c4ae 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -2031,14 +2031,14 @@ void efx_mcdi_rx_free_indir_table(struct efx_nic *efx)
 static int efx_mcdi_filter_rx_push_shared_rss_config(struct efx_nic *efx,
 					      unsigned *context_size)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_mcdi_filter_table *table = efx->filter_state;
 	int rc = efx_mcdi_filter_alloc_rss_context(efx, false, &efx->rss_context,
 					    context_size);
 
 	if (rc != 0)
 		return rc;
 
-	nic_data->rx_rss_context_exclusive = false;
+	table->rx_rss_context_exclusive = false;
 	efx_set_default_rx_indir_table(efx, &efx->rss_context);
 	return 0;
 }
@@ -2047,12 +2047,12 @@ static int efx_mcdi_filter_rx_push_exclusive_rss_config(struct efx_nic *efx,
 						 const u32 *rx_indir_table,
 						 const u8 *key)
 {
+	struct efx_mcdi_filter_table *table = efx->filter_state;
 	u32 old_rx_rss_context = efx->rss_context.context_id;
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	int rc;
 
 	if (efx->rss_context.context_id == EFX_MCDI_RSS_CONTEXT_INVALID ||
-	    !nic_data->rx_rss_context_exclusive) {
+	    !table->rx_rss_context_exclusive) {
 		rc = efx_mcdi_filter_alloc_rss_context(efx, true, &efx->rss_context,
 						NULL);
 		if (rc == -EOPNOTSUPP)
@@ -2069,7 +2069,7 @@ static int efx_mcdi_filter_rx_push_exclusive_rss_config(struct efx_nic *efx,
 	if (efx->rss_context.context_id != old_rx_rss_context &&
 	    old_rx_rss_context != EFX_MCDI_RSS_CONTEXT_INVALID)
 		WARN_ON(efx_mcdi_filter_free_rss_context(efx, old_rx_rss_context) != 0);
-	nic_data->rx_rss_context_exclusive = true;
+	table->rx_rss_context_exclusive = true;
 	if (rx_indir_table != efx->rss_context.rx_indir_table)
 		memcpy(efx->rss_context.rx_indir_table, rx_indir_table,
 		       sizeof(efx->rss_context.rx_indir_table));
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.h b/drivers/net/ethernet/sfc/mcdi_filters.h
index 15b5d62e3670..03a8bf74c733 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.h
+++ b/drivers/net/ethernet/sfc/mcdi_filters.h
@@ -55,6 +55,8 @@ struct efx_mcdi_filter_table {
 	u32 rx_match_mcdi_flags[
 		MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM * 2];
 	unsigned int rx_match_count;
+	/* Our RSS context is exclusive (as opposed to shared) */
+	bool rx_rss_context_exclusive;
 
 	struct rw_semaphore lock; /* Protects entries */
 	struct {
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 46583ba8fa24..8f73c5d996eb 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -368,7 +368,6 @@ enum {
  * @piobuf_size: size of a single PIO buffer
  * @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC
  *	reboot
- * @rx_rss_context_exclusive: Whether our RSS context is exclusive or shared
  * @stats: Hardware statistics
  * @workaround_35388: Flag: firmware supports workaround for bug 35388
  * @workaround_26807: Flag: firmware supports workaround for bug 26807
@@ -405,7 +404,6 @@ struct efx_ef10_nic_data {
 	unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT];
 	u16 piobuf_size;
 	bool must_restore_piobufs;
-	bool rx_rss_context_exclusive;
 	u64 stats[EF10_STAT_COUNT];
 	bool workaround_35388;
 	bool workaround_26807;
-- 
cgit v1.2.3


From ed02112cff9212232cc42f871cbe84c2c4c81850 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:29:45 +0100
Subject: sfc: make filter table probe caller responsible for adding VLANs

By making the caller of efx_mcdi_filter_table_probe() loop over the
 vlan_list calling efx_mcdi_filter_add_vlan(), instead of doing it in
 efx_mcdi_filter_table_probe(), the latter avoids looking in ef10-
 specific nic_data.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c         | 10 ++++++++++
 drivers/net/ethernet/sfc/mcdi_filters.c | 12 ------------
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 0779dda7d29f..d7d2edc4d81a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2447,6 +2447,7 @@ static int efx_ef10_filter_table_probe(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	int rc = efx_ef10_probe_multicast_chaining(efx);
+	struct efx_mcdi_filter_vlan *vlan;
 
 	if (rc)
 		return rc;
@@ -2455,7 +2456,16 @@ static int efx_ef10_filter_table_probe(struct efx_nic *efx)
 	if (rc)
 		return rc;
 
+	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
+		rc = efx_mcdi_filter_add_vlan(efx, vlan->vid);
+		if (rc)
+			goto fail_add_vlan;
+	}
 	return 0;
+
+fail_add_vlan:
+	efx_mcdi_filter_table_remove(efx);
+	return rc;
 }
 
 /* This creates an entry in the RX descriptor queue */
diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index e99b3149c4ae..88de95a8c08c 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -1285,10 +1285,8 @@ efx_mcdi_filter_table_probe_matches(struct efx_nic *efx,
 
 int efx_mcdi_filter_table_probe(struct efx_nic *efx, bool multicast_chaining)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	struct net_device *net_dev = efx->net_dev;
 	struct efx_mcdi_filter_table *table;
-	struct efx_mcdi_filter_vlan *vlan;
 	int rc;
 
 	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
@@ -1337,17 +1335,7 @@ int efx_mcdi_filter_table_probe(struct efx_nic *efx, bool multicast_chaining)
 
 	efx->filter_state = table;
 
-	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
-		rc = efx_mcdi_filter_add_vlan(efx, vlan->vid);
-		if (rc)
-			goto fail_add_vlan;
-	}
-
 	return 0;
-
-fail_add_vlan:
-	efx_mcdi_filter_cleanup_vlans(efx);
-	efx->filter_state = NULL;
 fail:
 	kfree(table);
 	return rc;
-- 
cgit v1.2.3


From 9b46132cff75653f02241640b44b31c29499afc1 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 11 May 2020 13:30:00 +0100
Subject: sfc: make firmware-variant printing a nic_type function

Instead of having efx_mcdi_print_fwver() look at efx_nic_rev and
 conditionally poke around inside ef10-specific nic_data, add a new
 efx->type->print_additional_fwver() method to do this work.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       | 15 +++++++++++++++
 drivers/net/ethernet/sfc/mcdi.c       | 25 +++++++++----------------
 drivers/net/ethernet/sfc/net_driver.h |  3 +++
 3 files changed, 27 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index d7d2edc4d81a..e634e8110585 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3978,6 +3978,19 @@ out_unlock:
 	return rc;
 }
 
+/* EF10 may have multiple datapath firmware variants within a
+ * single version.  Report which variants are running.
+ */
+static size_t efx_ef10_print_additional_fwver(struct efx_nic *efx, char *buf,
+					      size_t len)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	return scnprintf(buf, len, " rx%x tx%x",
+			 nic_data->rx_dpcpu_fw_id,
+			 nic_data->tx_dpcpu_fw_id);
+}
+
 static unsigned int ef10_check_caps(const struct efx_nic *efx,
 				    u8 flag,
 				    u32 offset)
@@ -4107,6 +4120,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 			    1 << HWTSTAMP_FILTER_ALL,
 	.rx_hash_key_size = 40,
 	.check_caps = ef10_check_caps,
+	.print_additional_fwver = efx_ef10_print_additional_fwver,
 };
 
 const struct efx_nic_type efx_hunt_a0_nic_type = {
@@ -4243,4 +4257,5 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 			    1 << HWTSTAMP_FILTER_ALL,
 	.rx_hash_key_size = 40,
 	.check_caps = ef10_check_caps,
+	.print_additional_fwver = efx_ef10_print_additional_fwver,
 };
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 15c731d04065..a8cc3881edce 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1425,23 +1425,16 @@ void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
 			   le16_to_cpu(ver_words[2]),
 			   le16_to_cpu(ver_words[3]));
 
-	/* EF10 may have multiple datapath firmware variants within a
-	 * single version.  Report which variants are running.
-	 */
-	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
-		struct efx_ef10_nic_data *nic_data = efx->nic_data;
-
-		offset += scnprintf(buf + offset, len - offset, " rx%x tx%x",
-				    nic_data->rx_dpcpu_fw_id,
-				    nic_data->tx_dpcpu_fw_id);
+	if (efx->type->print_additional_fwver)
+		offset += efx->type->print_additional_fwver(efx, buf + offset,
+							    len - offset);
 
-		/* It's theoretically possible for the string to exceed 31
-		 * characters, though in practice the first three version
-		 * components are short enough that this doesn't happen.
-		 */
-		if (WARN_ON(offset >= len))
-			buf[0] = 0;
-	}
+	/* It's theoretically possible for the string to exceed 31
+	 * characters, though in practice the first three version
+	 * components are short enough that this doesn't happen.
+	 */
+	if (WARN_ON(offset >= len))
+		buf[0] = 0;
 
 	return;
 
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index ae9756811dfe..1afb58feb9ab 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1296,6 +1296,7 @@ struct efx_udp_tunnel {
  * @udp_tnl_add_port: Add a UDP tunnel port
  * @udp_tnl_has_port: Check if a port has been added as UDP tunnel
  * @udp_tnl_del_port: Remove a UDP tunnel port
+ * @print_additional_fwver: Dump NIC-specific additional FW version info
  * @revision: Hardware architecture revision
  * @txd_ptr_tbl_base: TX descriptor ring base address
  * @rxd_ptr_tbl_base: RX descriptor ring base address
@@ -1469,6 +1470,8 @@ struct efx_nic_type {
 	int (*udp_tnl_add_port)(struct efx_nic *efx, struct efx_udp_tunnel tnl);
 	bool (*udp_tnl_has_port)(struct efx_nic *efx, __be16 port);
 	int (*udp_tnl_del_port)(struct efx_nic *efx, struct efx_udp_tunnel tnl);
+	size_t (*print_additional_fwver)(struct efx_nic *efx, char *buf,
+					 size_t len);
 
 	int revision;
 	unsigned int txd_ptr_tbl_base;
-- 
cgit v1.2.3


From 5b3f3f2a71ed1cecf6fcf9e8c858a89589415449 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:27 -0700
Subject: ionic: support longer tx sg lists

The version 1 Tx queues can use longer SG lists than the
original version 0 queues, but we need to check to see if the
firmware supports the v1 Tx queues.  This implements the queue
type query for all queue types, and uses the information to
set up for using the longer Tx SG lists.

Because the Tx SG list can be longer, we need to limit the
max ring length to be sure we stay inside the boundaries of a
DMA allocation max size, so we lower the max Tx ring size.

The driver sets its highest known version in the Q_IDENTITY
command, and the FW returns the highest version that it knows,
bounded by the driver's version.  The negotiated version number
is later used in the Q_INIT commands.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_dev.c    |  14 +++
 drivers/net/ethernet/pensando/ionic/ionic_dev.h    |   7 +-
 .../net/ethernet/pensando/ionic/ionic_ethtool.c    |   4 +-
 drivers/net/ethernet/pensando/ionic/ionic_if.h     | 112 +++++++++++++++++---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c    | 114 ++++++++++++++++++++-
 drivers/net/ethernet/pensando/ionic/ionic_lif.h    |  13 +++
 drivers/net/ethernet/pensando/ionic/ionic_main.c   |   2 +
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c   |  27 +++--
 8 files changed, 263 insertions(+), 30 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index f4ae40ae1e53..d83eff0ae0ac 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -388,6 +388,19 @@ int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data)
 }
 
 /* LIF commands */
+void ionic_dev_cmd_queue_identify(struct ionic_dev *idev,
+				  u16 lif_type, u8 qtype, u8 qver)
+{
+	union ionic_dev_cmd cmd = {
+		.q_identify.opcode = IONIC_CMD_Q_IDENTIFY,
+		.q_identify.lif_type = lif_type,
+		.q_identify.type = qtype,
+		.q_identify.ver = qver,
+	};
+
+	ionic_dev_cmd_go(idev, &cmd);
+}
+
 void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver)
 {
 	union ionic_dev_cmd cmd = {
@@ -431,6 +444,7 @@ void ionic_dev_cmd_adminq_init(struct ionic_dev *idev, struct ionic_qcq *qcq,
 		.q_init.opcode = IONIC_CMD_Q_INIT,
 		.q_init.lif_index = cpu_to_le16(lif_index),
 		.q_init.type = q->type,
+		.q_init.ver = qcq->q.lif->qtype_info[q->type].version,
 		.q_init.index = cpu_to_le32(q->index),
 		.q_init.flags = cpu_to_le16(IONIC_QINIT_F_IRQ |
 					    IONIC_QINIT_F_ENA),
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 587398b01997..33519a8765eb 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -12,7 +12,8 @@
 
 #define IONIC_MIN_MTU			ETH_MIN_MTU
 #define IONIC_MAX_MTU			9194
-#define IONIC_MAX_TXRX_DESC		16384
+#define IONIC_MAX_TX_DESC		8192
+#define IONIC_MAX_RX_DESC		16384
 #define IONIC_MIN_TXRX_DESC		16
 #define IONIC_DEF_TXRX_DESC		4096
 #define IONIC_LIFS_MAX			1024
@@ -83,6 +84,8 @@ static_assert(sizeof(struct ionic_q_init_cmd) == 64);
 static_assert(sizeof(struct ionic_q_init_comp) == 16);
 static_assert(sizeof(struct ionic_q_control_cmd) == 64);
 static_assert(sizeof(ionic_q_control_comp) == 16);
+static_assert(sizeof(struct ionic_q_identify_cmd) == 64);
+static_assert(sizeof(struct ionic_q_identify_comp) == 16);
 
 static_assert(sizeof(struct ionic_rx_mode_set_cmd) == 64);
 static_assert(sizeof(ionic_rx_mode_set_comp) == 16);
@@ -283,6 +286,8 @@ void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type);
 void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type);
 
 int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data);
+void ionic_dev_cmd_queue_identify(struct ionic_dev *idev,
+				  u16 lif_type, u8 qtype, u8 qver);
 void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver);
 void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index,
 			    dma_addr_t addr);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 6996229facfd..3f9a73aaef61 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -458,9 +458,9 @@ static void ionic_get_ringparam(struct net_device *netdev,
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
-	ring->tx_max_pending = IONIC_MAX_TXRX_DESC;
+	ring->tx_max_pending = IONIC_MAX_TX_DESC;
 	ring->tx_pending = lif->ntxq_descs;
-	ring->rx_max_pending = IONIC_MAX_TXRX_DESC;
+	ring->rx_max_pending = IONIC_MAX_RX_DESC;
 	ring->rx_pending = lif->nrxq_descs;
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index ceeb7629e7a0..799f3ea599e9 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -40,6 +40,7 @@ enum ionic_cmd_opcode {
 	IONIC_CMD_RX_FILTER_DEL			= 32,
 
 	/* Queue commands */
+	IONIC_CMD_Q_IDENTIFY			= 39,
 	IONIC_CMD_Q_INIT			= 40,
 	IONIC_CMD_Q_CONTROL			= 41,
 
@@ -469,6 +470,66 @@ struct ionic_lif_init_comp {
 	u8 rsvd2[12];
 };
 
+ /**
+  * struct ionic_q_identify_cmd - queue identify command
+  * @opcode:     opcode
+  * @lif_type:   LIF type (enum ionic_lif_type)
+  * @type:       Logical queue type (enum ionic_logical_qtype)
+  * @ver:        Highest queue type version that the driver supports
+  */
+struct ionic_q_identify_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 lif_type;
+	u8     type;
+	u8     ver;
+	u8     rsvd2[58];
+};
+
+/**
+ * struct ionic_q_identify_comp - queue identify command completion
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
+ * @ver:        Queue type version that can be used with FW
+ */
+struct ionic_q_identify_comp {
+	u8     status;
+	u8     rsvd;
+	__le16 comp_index;
+	u8     ver;
+	u8     rsvd2[11];
+};
+
+/**
+ * union ionic_q_identity - queue identity information
+ *     @version:        Queue type version that can be used with FW
+ *     @supported:      Bitfield of queue versions, first bit = ver 0
+ *     @features:       Queue features
+ *     @desc_sz:        Descriptor size
+ *     @comp_sz:        Completion descriptor size
+ *     @sg_desc_sz:     Scatter/Gather descriptor size
+ *     @max_sg_elems:   Maximum number of Scatter/Gather elements
+ *     @sg_desc_stride: Number of Scatter/Gather elements per descriptor
+ */
+union ionic_q_identity {
+	struct {
+		u8      version;
+		u8      supported;
+		u8      rsvd[6];
+#define IONIC_QIDENT_F_CQ	0x01	/* queue has completion ring */
+#define IONIC_QIDENT_F_SG	0x02	/* queue has scatter/gather ring */
+#define IONIC_QIDENT_F_EQ	0x04	/* queue can use event queue */
+#define IONIC_QIDENT_F_CMB	0x08	/* queue is in cmb bar */
+		__le64  features;
+		__le16  desc_sz;
+		__le16  comp_sz;
+		__le16  sg_desc_sz;
+		__le16  max_sg_elems;
+		__le16  sg_desc_stride;
+	};
+	__le32 words[478];
+};
+
 /**
  * struct ionic_q_init_cmd - Queue init command
  * @opcode:       opcode
@@ -733,20 +794,31 @@ static inline void decode_txq_desc_cmd(u64 cmd, u8 *opcode, u8 *flags,
 	*addr = (cmd >> IONIC_TXQ_DESC_ADDR_SHIFT) & IONIC_TXQ_DESC_ADDR_MASK;
 };
 
-#define IONIC_TX_MAX_SG_ELEMS	8
-#define IONIC_RX_MAX_SG_ELEMS	8
-
 /**
- * struct ionic_txq_sg_desc - Transmit scatter-gather (SG) list
+ * struct ionic_txq_sg_elem - Transmit scatter-gather (SG) descriptor element
  * @addr:      DMA address of SG element data buffer
  * @len:       Length of SG element data buffer, in bytes
  */
+struct ionic_txq_sg_elem {
+	__le64 addr;
+	__le16 len;
+	__le16 rsvd[3];
+};
+
+/**
+ * struct ionic_txq_sg_desc - Transmit scatter-gather (SG) list
+ * @elems:     Scatter-gather elements
+ */
 struct ionic_txq_sg_desc {
-	struct ionic_txq_sg_elem {
-		__le64 addr;
-		__le16 len;
-		__le16 rsvd[3];
-	} elems[IONIC_TX_MAX_SG_ELEMS];
+#define IONIC_TX_MAX_SG_ELEMS		8
+#define IONIC_TX_SG_DESC_STRIDE		8
+	struct ionic_txq_sg_elem elems[IONIC_TX_MAX_SG_ELEMS];
+};
+
+struct ionic_txq_sg_desc_v1 {
+#define IONIC_TX_MAX_SG_ELEMS_V1		15
+#define IONIC_TX_SG_DESC_STRIDE_V1		16
+	struct ionic_txq_sg_elem elems[IONIC_TX_SG_DESC_STRIDE_V1];
 };
 
 /**
@@ -791,16 +863,24 @@ struct ionic_rxq_desc {
 };
 
 /**
- * struct ionic_rxq_sg_desc - Receive scatter-gather (SG) list
+ * struct ionic_rxq_sg_desc - Receive scatter-gather (SG) descriptor element
  * @addr:      DMA address of SG element data buffer
  * @len:       Length of SG element data buffer, in bytes
  */
+struct ionic_rxq_sg_elem {
+	__le64 addr;
+	__le16 len;
+	__le16 rsvd[3];
+};
+
+/**
+ * struct ionic_rxq_sg_desc - Receive scatter-gather (SG) list
+ * @elems:     Scatter-gather elements
+ */
 struct ionic_rxq_sg_desc {
-	struct ionic_rxq_sg_elem {
-		__le64 addr;
-		__le16 len;
-		__le16 rsvd[3];
-	} elems[IONIC_RX_MAX_SG_ELEMS];
+#define IONIC_RX_MAX_SG_ELEMS		8
+#define IONIC_RX_SG_DESC_STRIDE		8
+	struct ionic_rxq_sg_elem elems[IONIC_RX_SG_DESC_STRIDE];
 };
 
 /**
@@ -2389,6 +2469,7 @@ union ionic_dev_cmd {
 	struct ionic_qos_init_cmd qos_init;
 	struct ionic_qos_reset_cmd qos_reset;
 
+	struct ionic_q_identify_cmd q_identify;
 	struct ionic_q_init_cmd q_init;
 };
 
@@ -2421,6 +2502,7 @@ union ionic_dev_cmd_comp {
 	ionic_qos_init_comp qos_init;
 	ionic_qos_reset_comp qos_reset;
 
+	struct ionic_q_identify_comp q_identify;
 	struct ionic_q_init_comp q_init;
 };
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index d5293bfded29..0049f537ee40 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -17,6 +17,16 @@
 #include "ionic_ethtool.h"
 #include "ionic_debugfs.h"
 
+/* queuetype support level */
+static const u8 ionic_qtype_versions[IONIC_QTYPE_MAX] = {
+	[IONIC_QTYPE_ADMINQ]  = 0,   /* 0 = Base version with CQ support */
+	[IONIC_QTYPE_NOTIFYQ] = 0,   /* 0 = Base version */
+	[IONIC_QTYPE_RXQ]     = 0,   /* 0 = Base version with CQ+SG support */
+	[IONIC_QTYPE_TXQ]     = 1,   /* 0 = Base version with CQ+SG support
+				      * 1 =   ... with Tx SG version 1
+				      */
+};
+
 static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode);
 static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
 static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
@@ -27,6 +37,7 @@ static void ionic_lif_set_netdev_info(struct ionic_lif *lif);
 
 static int ionic_start_queues(struct ionic_lif *lif);
 static void ionic_stop_queues(struct ionic_lif *lif);
+static void ionic_lif_queue_identify(struct ionic_lif *lif);
 
 static void ionic_lif_deferred_work(struct work_struct *work)
 {
@@ -597,6 +608,7 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 			.opcode = IONIC_CMD_Q_INIT,
 			.lif_index = cpu_to_le16(lif->index),
 			.type = q->type,
+			.ver = lif->qtype_info[q->type].version,
 			.index = cpu_to_le32(q->index),
 			.flags = cpu_to_le16(IONIC_QINIT_F_IRQ |
 					     IONIC_QINIT_F_SG),
@@ -614,6 +626,8 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	dev_dbg(dev, "txq_init.index %d\n", ctx.cmd.q_init.index);
 	dev_dbg(dev, "txq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base);
 	dev_dbg(dev, "txq_init.ring_size %d\n", ctx.cmd.q_init.ring_size);
+	dev_dbg(dev, "txq_init.flags 0x%x\n", ctx.cmd.q_init.flags);
+	dev_dbg(dev, "txq_init.ver %d\n", ctx.cmd.q_init.ver);
 
 	q->tail = q->info;
 	q->head = q->tail;
@@ -646,6 +660,7 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 			.opcode = IONIC_CMD_Q_INIT,
 			.lif_index = cpu_to_le16(lif->index),
 			.type = q->type,
+			.ver = lif->qtype_info[q->type].version,
 			.index = cpu_to_le32(q->index),
 			.flags = cpu_to_le16(IONIC_QINIT_F_IRQ |
 					     IONIC_QINIT_F_SG),
@@ -663,6 +678,8 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	dev_dbg(dev, "rxq_init.index %d\n", ctx.cmd.q_init.index);
 	dev_dbg(dev, "rxq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base);
 	dev_dbg(dev, "rxq_init.ring_size %d\n", ctx.cmd.q_init.ring_size);
+	dev_dbg(dev, "rxq_init.flags 0x%x\n", ctx.cmd.q_init.flags);
+	dev_dbg(dev, "rxq_init.ver %d\n", ctx.cmd.q_init.ver);
 
 	q->tail = q->info;
 	q->head = q->tail;
@@ -726,7 +743,7 @@ static bool ionic_notifyq_service(struct ionic_cq *cq,
 		}
 		break;
 	default:
-		netdev_warn(netdev, "Notifyq unknown event ecode=%d eid=%lld\n",
+		netdev_warn(netdev, "Notifyq event ecode=%d eid=%lld\n",
 			    comp->event.ecode, eid);
 		break;
 	}
@@ -1509,17 +1526,25 @@ static void ionic_txrx_free(struct ionic_lif *lif)
 
 static int ionic_txrx_alloc(struct ionic_lif *lif)
 {
+	unsigned int sg_desc_sz;
 	unsigned int flags;
 	unsigned int i;
 	int err = 0;
 
+	if (lif->qtype_info[IONIC_QTYPE_TXQ].version >= 1 &&
+	    lif->qtype_info[IONIC_QTYPE_TXQ].sg_desc_sz ==
+					  sizeof(struct ionic_txq_sg_desc_v1))
+		sg_desc_sz = sizeof(struct ionic_txq_sg_desc_v1);
+	else
+		sg_desc_sz = sizeof(struct ionic_txq_sg_desc);
+
 	flags = IONIC_QCQ_F_TX_STATS | IONIC_QCQ_F_SG;
 	for (i = 0; i < lif->nxqs; i++) {
 		err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags,
 				      lif->ntxq_descs,
 				      sizeof(struct ionic_txq_desc),
 				      sizeof(struct ionic_txq_comp),
-				      sizeof(struct ionic_txq_sg_desc),
+				      sg_desc_sz,
 				      lif->kern_pid, &lif->txqcqs[i].qcq);
 		if (err)
 			goto err_out;
@@ -2065,9 +2090,17 @@ int ionic_lifs_alloc(struct ionic *ionic)
 
 	/* only build the first lif, others are for later features */
 	set_bit(0, ionic->lifbits);
+
 	lif = ionic_lif_alloc(ionic, 0);
+	if (IS_ERR_OR_NULL(lif)) {
+		clear_bit(0, ionic->lifbits);
+		return -ENOMEM;
+	}
+
+	lif->lif_type = IONIC_LIF_TYPE_CLASSIC;
+	ionic_lif_queue_identify(lif);
 
-	return PTR_ERR_OR_ZERO(lif);
+	return 0;
 }
 
 static void ionic_lif_reset(struct ionic_lif *lif)
@@ -2291,6 +2324,7 @@ static int ionic_lif_notifyq_init(struct ionic_lif *lif)
 			.opcode = IONIC_CMD_Q_INIT,
 			.lif_index = cpu_to_le16(lif->index),
 			.type = q->type,
+			.ver = lif->qtype_info[q->type].version,
 			.index = cpu_to_le32(q->index),
 			.flags = cpu_to_le16(IONIC_QINIT_F_IRQ |
 					     IONIC_QINIT_F_ENA),
@@ -2573,6 +2607,80 @@ void ionic_lifs_unregister(struct ionic *ionic)
 		unregister_netdev(ionic->master_lif->netdev);
 }
 
+static void ionic_lif_queue_identify(struct ionic_lif *lif)
+{
+	struct ionic *ionic = lif->ionic;
+	union ionic_q_identity *q_ident;
+	struct ionic_dev *idev;
+	int qtype;
+	int err;
+
+	idev = &lif->ionic->idev;
+	q_ident = (union ionic_q_identity *)&idev->dev_cmd_regs->data;
+
+	for (qtype = 0; qtype < ARRAY_SIZE(ionic_qtype_versions); qtype++) {
+		struct ionic_qtype_info *qti = &lif->qtype_info[qtype];
+
+		/* filter out the ones we know about */
+		switch (qtype) {
+		case IONIC_QTYPE_ADMINQ:
+		case IONIC_QTYPE_NOTIFYQ:
+		case IONIC_QTYPE_RXQ:
+		case IONIC_QTYPE_TXQ:
+			break;
+		default:
+			continue;
+		}
+
+		memset(qti, 0, sizeof(*qti));
+
+		mutex_lock(&ionic->dev_cmd_lock);
+		ionic_dev_cmd_queue_identify(idev, lif->lif_type, qtype,
+					     ionic_qtype_versions[qtype]);
+		err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
+		if (!err) {
+			qti->version   = q_ident->version;
+			qti->supported = q_ident->supported;
+			qti->features  = le64_to_cpu(q_ident->features);
+			qti->desc_sz   = le16_to_cpu(q_ident->desc_sz);
+			qti->comp_sz   = le16_to_cpu(q_ident->comp_sz);
+			qti->sg_desc_sz   = le16_to_cpu(q_ident->sg_desc_sz);
+			qti->max_sg_elems = le16_to_cpu(q_ident->max_sg_elems);
+			qti->sg_desc_stride = le16_to_cpu(q_ident->sg_desc_stride);
+		}
+		mutex_unlock(&ionic->dev_cmd_lock);
+
+		if (err == -EINVAL) {
+			dev_err(ionic->dev, "qtype %d not supported\n", qtype);
+			continue;
+		} else if (err == -EIO) {
+			dev_err(ionic->dev, "q_ident failed, not supported on older FW\n");
+			return;
+		} else if (err) {
+			dev_err(ionic->dev, "q_ident failed, qtype %d: %d\n",
+				qtype, err);
+			return;
+		}
+
+		dev_dbg(ionic->dev, " qtype[%d].version = %d\n",
+			qtype, qti->version);
+		dev_dbg(ionic->dev, " qtype[%d].supported = 0x%02x\n",
+			qtype, qti->supported);
+		dev_dbg(ionic->dev, " qtype[%d].features = 0x%04llx\n",
+			qtype, qti->features);
+		dev_dbg(ionic->dev, " qtype[%d].desc_sz = %d\n",
+			qtype, qti->desc_sz);
+		dev_dbg(ionic->dev, " qtype[%d].comp_sz = %d\n",
+			qtype, qti->comp_sz);
+		dev_dbg(ionic->dev, " qtype[%d].sg_desc_sz = %d\n",
+			qtype, qti->sg_desc_sz);
+		dev_dbg(ionic->dev, " qtype[%d].max_sg_elems = %d\n",
+			qtype, qti->max_sg_elems);
+		dev_dbg(ionic->dev, " qtype[%d].sg_desc_stride = %d\n",
+			qtype, qti->sg_desc_stride);
+	}
+}
+
 int ionic_lif_identify(struct ionic *ionic, u8 lif_type,
 		       union ionic_lif_identity *lid)
 {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 5d4ffda5c05f..1a30f0fb20b9 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -133,6 +133,17 @@ enum ionic_lif_state_flags {
 	IONIC_LIF_F_STATE_SIZE
 };
 
+struct ionic_qtype_info {
+	u8  version;
+	u8  supported;
+	u64 features;
+	u16 desc_sz;
+	u16 comp_sz;
+	u16 sg_desc_sz;
+	u16 max_sg_elems;
+	u16 sg_desc_stride;
+};
+
 #define IONIC_LIF_NAME_MAX_SZ		32
 struct ionic_lif {
 	char name[IONIC_LIF_NAME_MAX_SZ];
@@ -161,11 +172,13 @@ struct ionic_lif {
 	bool mc_overflow;
 	unsigned int nmcast;
 	bool uc_overflow;
+	u16 lif_type;
 	unsigned int nucast;
 
 	struct ionic_lif_info *info;
 	dma_addr_t info_pa;
 	u32 info_sz;
+	struct ionic_qtype_info qtype_info[IONIC_QTYPE_MAX];
 
 	u16 rss_types;
 	u8 rss_hash_key[IONIC_RSS_HASH_KEY_SIZE];
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 3ed150512091..8e2436d14621 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -152,6 +152,8 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode)
 		return "IONIC_CMD_RX_FILTER_ADD";
 	case IONIC_CMD_RX_FILTER_DEL:
 		return "IONIC_CMD_RX_FILTER_DEL";
+	case IONIC_CMD_Q_IDENTIFY:
+		return "IONIC_CMD_Q_IDENTIFY";
 	case IONIC_CMD_Q_INIT:
 		return "IONIC_CMD_Q_INIT";
 	case IONIC_CMD_Q_CONTROL:
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index d233b6e77b1e..6b14e55a6780 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -10,8 +10,10 @@
 #include "ionic_lif.h"
 #include "ionic_txrx.h"
 
-static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info,
-			   struct ionic_cq_info *cq_info, void *cb_arg);
+static void ionic_rx_clean(struct ionic_queue *q,
+			   struct ionic_desc_info *desc_info,
+			   struct ionic_cq_info *cq_info,
+			   void *cb_arg);
 
 static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell,
 				  ionic_desc_cb cb_func, void *cb_arg)
@@ -140,8 +142,10 @@ static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q,
 	return skb;
 }
 
-static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info,
-			   struct ionic_cq_info *cq_info, void *cb_arg)
+static void ionic_rx_clean(struct ionic_queue *q,
+			   struct ionic_desc_info *desc_info,
+			   struct ionic_cq_info *cq_info,
+			   void *cb_arg)
 {
 	struct ionic_rxq_comp *comp = cq_info->cq_desc;
 	struct ionic_qcq *qcq = q_to_qcq(q);
@@ -475,7 +479,8 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t len)
+static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
+				      void *data, size_t len)
 {
 	struct ionic_tx_stats *stats = q_to_tx_stats(q);
 	struct device *dev = q->lif->ionic->dev;
@@ -491,7 +496,8 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t
 	return dma_addr;
 }
 
-static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, const skb_frag_t *frag,
+static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
+				    const skb_frag_t *frag,
 				    size_t offset, size_t len)
 {
 	struct ionic_tx_stats *stats = q_to_tx_stats(q);
@@ -507,8 +513,10 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, const skb_frag_t *fra
 	return dma_addr;
 }
 
-static void ionic_tx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info,
-			   struct ionic_cq_info *cq_info, void *cb_arg)
+static void ionic_tx_clean(struct ionic_queue *q,
+			   struct ionic_desc_info *desc_info,
+			   struct ionic_cq_info *cq_info,
+			   void *cb_arg)
 {
 	struct ionic_txq_sg_desc *sg_desc = desc_info->sg_desc;
 	struct ionic_txq_sg_elem *elem = sg_desc->elems;
@@ -989,6 +997,7 @@ static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb)
 
 static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb)
 {
+	int sg_elems = q->lif->qtype_info[IONIC_QTYPE_TXQ].max_sg_elems;
 	struct ionic_tx_stats *stats = q_to_tx_stats(q);
 	int err;
 
@@ -997,7 +1006,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb)
 		return (skb->len / skb_shinfo(skb)->gso_size) + 1;
 
 	/* If non-TSO, just need 1 desc and nr_frags sg elems */
-	if (skb_shinfo(skb)->nr_frags <= IONIC_TX_MAX_SG_ELEMS)
+	if (skb_shinfo(skb)->nr_frags <= sg_elems)
 		return 1;
 
 	/* Too many frags, so linearize */
-- 
cgit v1.2.3


From c4e7a75a096c02035a102686e2569e7b0341a122 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:28 -0700
Subject: ionic: updates to ionic FW api description

Lots of comment cleanup for better documentation, a few new
fields added, and a few minor mistakes fixed up.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_if.h | 979 +++++++++++++++----------
 1 file changed, 576 insertions(+), 403 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 799f3ea599e9..7e22ba4ed915 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) OR BSD-2-Clause */
-/* Copyright (c) 2017-2019 Pensando Systems, Inc.  All rights reserved. */
+/* Copyright (c) 2017-2020 Pensando Systems, Inc.  All rights reserved. */
 
 #ifndef _IONIC_IF_H_
 #define _IONIC_IF_H_
@@ -9,7 +9,7 @@
 #define IONIC_IFNAMSIZ				16
 
 /**
- * Commands
+ * enum ionic_cmd_opcode - Device commands
  */
 enum ionic_cmd_opcode {
 	IONIC_CMD_NOP				= 0,
@@ -58,6 +58,7 @@ enum ionic_cmd_opcode {
 	IONIC_CMD_QOS_CLASS_IDENTIFY		= 240,
 	IONIC_CMD_QOS_CLASS_INIT		= 241,
 	IONIC_CMD_QOS_CLASS_RESET		= 242,
+	IONIC_CMD_QOS_CLASS_UPDATE		= 243,
 
 	/* Firmware commands */
 	IONIC_CMD_FW_DOWNLOAD			= 254,
@@ -65,7 +66,7 @@ enum ionic_cmd_opcode {
 };
 
 /**
- * Command Return codes
+ * enum ionic_status_code - Device command return codes
  */
 enum ionic_status_code {
 	IONIC_RC_SUCCESS	= 0,	/* Success */
@@ -98,6 +99,7 @@ enum ionic_notifyq_opcode {
 	IONIC_EVENT_RESET		= 2,
 	IONIC_EVENT_HEARTBEAT		= 3,
 	IONIC_EVENT_LOG			= 4,
+	IONIC_EVENT_XCVR		= 5,
 };
 
 /**
@@ -115,12 +117,11 @@ struct ionic_admin_cmd {
 
 /**
  * struct ionic_admin_comp - General admin command completion format
- * @status:     The status of the command (enum status_code)
- * @comp_index: The index in the descriptor ring for which this
- *              is the completion.
- * @cmd_data:   Command-specific bytes.
- * @color:      Color bit.  (Always 0 for commands issued to the
- *              Device Cmd Registers.)
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
+ * @cmd_data:   Command-specific bytes
+ * @color:      Color bit (Always 0 for commands issued to the
+ *              Device Cmd Registers)
  */
 struct ionic_admin_comp {
 	u8     status;
@@ -147,7 +148,7 @@ struct ionic_nop_cmd {
 
 /**
  * struct ionic_nop_comp - NOP command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  */
 struct ionic_nop_comp {
 	u8 status;
@@ -157,7 +158,7 @@ struct ionic_nop_comp {
 /**
  * struct ionic_dev_init_cmd - Device init command
  * @opcode:    opcode
- * @type:      device type
+ * @type:      Device type
  */
 struct ionic_dev_init_cmd {
 	u8     opcode;
@@ -167,7 +168,7 @@ struct ionic_dev_init_cmd {
 
 /**
  * struct init_comp - Device init command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  */
 struct ionic_dev_init_comp {
 	u8 status;
@@ -185,7 +186,7 @@ struct ionic_dev_reset_cmd {
 
 /**
  * struct reset_comp - Reset command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  */
 struct ionic_dev_reset_comp {
 	u8 status;
@@ -206,8 +207,8 @@ struct ionic_dev_identify_cmd {
 };
 
 /**
- * struct dev_identify_comp - Driver/device identify command completion
- * @status: The status of the command (enum status_code)
+ * struct ionic_dev_identify_comp - Driver/device identify command completion
+ * @status: Status of the command (enum ionic_status_code)
  * @ver:    Version of identify returned by device
  */
 struct ionic_dev_identify_comp {
@@ -226,8 +227,8 @@ enum ionic_os_type {
 };
 
 /**
- * union drv_identity - driver identity information
- * @os_type:          OS type (see enum os_type)
+ * union ionic_drv_identity - driver identity information
+ * @os_type:          OS type (see enum ionic_os_type)
  * @os_dist:          OS distribution, numeric format
  * @os_dist_str:      OS distribution, string format
  * @kernel_ver:       Kernel version, numeric format
@@ -243,26 +244,26 @@ union ionic_drv_identity {
 		char   kernel_ver_str[32];
 		char   driver_ver_str[32];
 	};
-	__le32 words[512];
+	__le32 words[478];
 };
 
 /**
- * union dev_identity - device identity information
+ * union ionic_dev_identity - device identity information
  * @version:          Version of device identify
  * @type:             Identify type (0 for now)
  * @nports:           Number of ports provisioned
  * @nlifs:            Number of LIFs provisioned
  * @nintrs:           Number of interrupts provisioned
  * @ndbpgs_per_lif:   Number of doorbell pages per LIF
- * @intr_coal_mult:   Interrupt coalescing multiplication factor.
+ * @intr_coal_mult:   Interrupt coalescing multiplication factor
  *                    Scale user-supplied interrupt coalescing
  *                    value in usecs to device units using:
  *                    device units = usecs * mult / div
- * @intr_coal_div:    Interrupt coalescing division factor.
+ * @intr_coal_div:    Interrupt coalescing division factor
  *                    Scale user-supplied interrupt coalescing
  *                    value in usecs to device units using:
  *                    device units = usecs * mult / div
- *
+ * @eq_count:         Number of shared event queues
  */
 union ionic_dev_identity {
 	struct {
@@ -276,8 +277,9 @@ union ionic_dev_identity {
 		__le32 ndbpgs_per_lif;
 		__le32 intr_coal_mult;
 		__le32 intr_coal_div;
+		__le32 eq_count;
 	};
-	__le32 words[512];
+	__le32 words[478];
 };
 
 enum ionic_lif_type {
@@ -287,10 +289,10 @@ enum ionic_lif_type {
 };
 
 /**
- * struct ionic_lif_identify_cmd - lif identify command
+ * struct ionic_lif_identify_cmd - LIF identify command
  * @opcode:  opcode
- * @type:    lif type (enum lif_type)
- * @ver:     version of identify returned by device
+ * @type:    LIF type (enum ionic_lif_type)
+ * @ver:     Version of identify returned by device
  */
 struct ionic_lif_identify_cmd {
 	u8 opcode;
@@ -300,9 +302,9 @@ struct ionic_lif_identify_cmd {
 };
 
 /**
- * struct ionic_lif_identify_comp - lif identify command completion
- * @status:  status of the command (enum status_code)
- * @ver:     version of identify returned by device
+ * struct ionic_lif_identify_comp - LIF identify command completion
+ * @status:  Status of the command (enum ionic_status_code)
+ * @ver:     Version of identify returned by device
  */
 struct ionic_lif_identify_comp {
 	u8 status;
@@ -310,13 +312,24 @@ struct ionic_lif_identify_comp {
 	u8 rsvd2[14];
 };
 
+/**
+ * enum ionic_lif_capability - LIF capabilities
+ * @IONIC_LIF_CAP_ETH:     LIF supports Ethernet
+ * @IONIC_LIF_CAP_RDMA:    LIF support RDMA
+ */
 enum ionic_lif_capability {
 	IONIC_LIF_CAP_ETH        = BIT(0),
 	IONIC_LIF_CAP_RDMA       = BIT(1),
 };
 
 /**
- * Logical Queue Types
+ * enum ionic_logical_qtype - Logical Queue Types
+ * @IONIC_QTYPE_ADMINQ:    Administrative Queue
+ * @IONIC_QTYPE_NOTIFYQ:   Notify Queue
+ * @IONIC_QTYPE_RXQ:       Receive Queue
+ * @IONIC_QTYPE_TXQ:       Transmit Queue
+ * @IONIC_QTYPE_EQ:        Event Queue
+ * @IONIC_QTYPE_MAX:       Max queue type supported
  */
 enum ionic_logical_qtype {
 	IONIC_QTYPE_ADMINQ  = 0,
@@ -328,10 +341,10 @@ enum ionic_logical_qtype {
 };
 
 /**
- * struct ionic_lif_logical_qtype - Descriptor of logical to hardware queue type.
- * @qtype:          Hardware Queue Type.
- * @qid_count:      Number of Queue IDs of the logical type.
- * @qid_base:       Minimum Queue ID of the logical type.
+ * struct ionic_lif_logical_qtype - Descriptor of logical to HW queue type
+ * @qtype:          Hardware Queue Type
+ * @qid_count:      Number of Queue IDs of the logical type
+ * @qid_base:       Minimum Queue ID of the logical type
  */
 struct ionic_lif_logical_qtype {
 	u8     qtype;
@@ -340,6 +353,12 @@ struct ionic_lif_logical_qtype {
 	__le32 qid_base;
 };
 
+/**
+ * enum ionic_lif_state - LIF state
+ * @IONIC_LIF_DISABLE:     LIF disabled
+ * @IONIC_LIF_ENABLE:      LIF enabled
+ * @IONIC_LIF_HANG_RESET:  LIF hung, being reset
+ */
 enum ionic_lif_state {
 	IONIC_LIF_DISABLE	= 0,
 	IONIC_LIF_ENABLE	= 1,
@@ -347,13 +366,13 @@ enum ionic_lif_state {
 };
 
 /**
- * LIF configuration
- * @state:          lif state (enum lif_state)
- * @name:           lif name
- * @mtu:            mtu
- * @mac:            station mac address
- * @features:       features (enum ionic_eth_hw_features)
- * @queue_count:    queue counts per queue-type
+ * union ionic_lif_config - LIF configuration
+ * @state:          LIF state (enum ionic_lif_state)
+ * @name:           LIF name
+ * @mtu:            MTU
+ * @mac:            Station MAC address
+ * @features:       Features (enum ionic_eth_hw_features)
+ * @queue_count:    Queue counts per queue-type
  */
 union ionic_lif_config {
 	struct {
@@ -370,37 +389,36 @@ union ionic_lif_config {
 };
 
 /**
- * struct ionic_lif_identity - lif identity information (type-specific)
+ * struct ionic_lif_identity - LIF identity information (type-specific)
  *
- * @capabilities    LIF capabilities
+ * @capabilities:        LIF capabilities
  *
- * Ethernet:
- *     @version:          Ethernet identify structure version.
- *     @features:         Ethernet features supported on this lif type.
- *     @max_ucast_filters:  Number of perfect unicast addresses supported.
- *     @max_mcast_filters:  Number of perfect multicast addresses supported.
- *     @min_frame_size:   Minimum size of frames to be sent
- *     @max_frame_size:   Maximim size of frames to be sent
- *     @config:           LIF config struct with features, mtu, mac, q counts
+ * @eth:                    Ethernet identify structure
+ *     @version:            Ethernet identify structure version
+ *     @max_ucast_filters:  Number of perfect unicast addresses supported
+ *     @max_mcast_filters:  Number of perfect multicast addresses supported
+ *     @min_frame_size:     Minimum size of frames to be sent
+ *     @max_frame_size:     Maximim size of frames to be sent
+ *     @config:             LIF config struct with features, mtu, mac, q counts
  *
- * RDMA:
- *     @version:         RDMA version of opcodes and queue descriptors.
- *     @qp_opcodes:      Number of rdma queue pair opcodes supported.
- *     @admin_opcodes:   Number of rdma admin opcodes supported.
- *     @npts_per_lif:    Page table size per lif
- *     @nmrs_per_lif:    Number of memory regions per lif
- *     @nahs_per_lif:    Number of address handles per lif
- *     @max_stride:      Max work request stride.
- *     @cl_stride:       Cache line stride.
- *     @pte_stride:      Page table entry stride.
- *     @rrq_stride:      Remote RQ work request stride.
- *     @rsq_stride:      Remote SQ work request stride.
+ * @rdma:                RDMA identify structure
+ *     @version:         RDMA version of opcodes and queue descriptors
+ *     @qp_opcodes:      Number of RDMA queue pair opcodes supported
+ *     @admin_opcodes:   Number of RDMA admin opcodes supported
+ *     @npts_per_lif:    Page table size per LIF
+ *     @nmrs_per_lif:    Number of memory regions per LIF
+ *     @nahs_per_lif:    Number of address handles per LIF
+ *     @max_stride:      Max work request stride
+ *     @cl_stride:       Cache line stride
+ *     @pte_stride:      Page table entry stride
+ *     @rrq_stride:      Remote RQ work request stride
+ *     @rsq_stride:      Remote SQ work request stride
  *     @dcqcn_profiles:  Number of DCQCN profiles
- *     @aq_qtype:        RDMA Admin Qtype.
- *     @sq_qtype:        RDMA Send Qtype.
- *     @rq_qtype:        RDMA Receive Qtype.
- *     @cq_qtype:        RDMA Completion Qtype.
- *     @eq_qtype:        RDMA Event Qtype.
+ *     @aq_qtype:        RDMA Admin Qtype
+ *     @sq_qtype:        RDMA Send Qtype
+ *     @rq_qtype:        RDMA Receive Qtype
+ *     @cq_qtype:        RDMA Completion Qtype
+ *     @eq_qtype:        RDMA Event Qtype
  */
 union ionic_lif_identity {
 	struct {
@@ -440,15 +458,15 @@ union ionic_lif_identity {
 			struct ionic_lif_logical_qtype eq_qtype;
 		} __packed rdma;
 	} __packed;
-	__le32 words[512];
+	__le32 words[478];
 };
 
 /**
  * struct ionic_lif_init_cmd - LIF init command
- * @opcode:       opcode
- * @type:         LIF type (enum lif_type)
+ * @opcode:       Opcode
+ * @type:         LIF type (enum ionic_lif_type)
  * @index:        LIF index
- * @info_pa:      destination address for lif info (struct ionic_lif_info)
+ * @info_pa:      Destination address for LIF info (struct ionic_lif_info)
  */
 struct ionic_lif_init_cmd {
 	u8     opcode;
@@ -461,7 +479,8 @@ struct ionic_lif_init_cmd {
 
 /**
  * struct ionic_lif_init_comp - LIF init command completion
- * @status: The status of the command (enum status_code)
+ * @status:	Status of the command (enum ionic_status_code)
+ * @hw_index:	Hardware index of the initialized LIF
  */
 struct ionic_lif_init_comp {
 	u8 status;
@@ -534,10 +553,10 @@ union ionic_q_identity {
  * struct ionic_q_init_cmd - Queue init command
  * @opcode:       opcode
  * @type:         Logical queue type
- * @ver:          Queue version (defines opcode/descriptor scope)
+ * @ver:          Queue type version
  * @lif_index:    LIF index
- * @index:        (lif, qtype) relative admin queue index
- * @intr_index:   Interrupt control register index
+ * @index:        (LIF, qtype) relative admin queue index
+ * @intr_index:   Interrupt control register index, or Event queue index
  * @pid:          Process ID
  * @flags:
  *    IRQ:        Interrupt requested on completion
@@ -555,12 +574,11 @@ union ionic_q_identity {
  *                descriptors.  Values of ring_size <2 and >16 are
  *                reserved.
  *    EQ:         Enable the Event Queue
- * @cos:          Class of service for this queue.
+ * @cos:          Class of service for this queue
  * @ring_size:    Queue ring size, encoded as a log2(size)
  * @ring_base:    Queue ring base address
  * @cq_ring_base: Completion queue ring base address
  * @sg_ring_base: Scatter/Gather ring base address
- * @eq_index:	  Event queue index
  */
 struct ionic_q_init_cmd {
 	u8     opcode;
@@ -577,29 +595,27 @@ struct ionic_q_init_cmd {
 #define IONIC_QINIT_F_ENA	0x02	/* Enable the queue */
 #define IONIC_QINIT_F_SG	0x04	/* Enable scatter/gather on the queue */
 #define IONIC_QINIT_F_EQ	0x08	/* Enable event queue */
-#define IONIC_QINIT_F_DEBUG 0x80	/* Enable queue debugging */
+#define IONIC_QINIT_F_CMB	0x10	/* Enable cmb-based queue */
+#define IONIC_QINIT_F_DEBUG	0x80	/* Enable queue debugging */
 	u8     cos;
 	u8     ring_size;
 	__le64 ring_base;
 	__le64 cq_ring_base;
 	__le64 sg_ring_base;
-	__le32 eq_index;
-	u8     rsvd2[16];
+	u8     rsvd2[20];
 } __packed;
 
 /**
  * struct ionic_q_init_comp - Queue init command completion
- * @status:     The status of the command (enum status_code)
- * @ver:        Queue version (defines opcode/descriptor scope)
- * @comp_index: The index in the descriptor ring for which this
- *              is the completion.
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
  * @hw_index:   Hardware Queue ID
  * @hw_type:    Hardware Queue type
  * @color:      Color
  */
 struct ionic_q_init_comp {
 	u8     status;
-	u8     ver;
+	u8     rsvd;
 	__le16 comp_index;
 	__le32 hw_index;
 	u8     hw_type;
@@ -620,10 +636,9 @@ enum ionic_txq_desc_opcode {
 
 /**
  * struct ionic_txq_desc - Ethernet Tx queue descriptor format
- * @opcode:       Tx operation, see TXQ_DESC_OPCODE_*:
+ * @cmd:          Tx operation, see IONIC_TXQ_DESC_OPCODE_*:
  *
  *                   IONIC_TXQ_DESC_OPCODE_CSUM_NONE:
- *
  *                      Non-offload send.  No segmentation,
  *                      fragmentation or checksum calc/insertion is
  *                      performed by device; packet is prepared
@@ -631,7 +646,6 @@ enum ionic_txq_desc_opcode {
  *                      no further manipulation from device.
  *
  *                   IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL:
- *
  *                      Offload 16-bit L4 checksum
  *                      calculation/insertion.  The device will
  *                      calculate the L4 checksum value and
@@ -640,14 +654,16 @@ enum ionic_txq_desc_opcode {
  *                      is calculated starting at @csum_start bytes
  *                      into the packet to the end of the packet.
  *                      The checksum insertion position is given
- *                      in @csum_offset.  This feature is only
- *                      applicable to protocols such as TCP, UDP
- *                      and ICMP where a standard (i.e. the
- *                      'IP-style' checksum) one's complement
- *                      16-bit checksum is used, using an IP
- *                      pseudo-header to seed the calculation.
- *                      Software will preload the L4 checksum
- *                      field with the IP pseudo-header checksum.
+ *                      in @csum_offset, which is the offset from
+ *                      @csum_start to the checksum field in the L4
+ *                      header.  This feature is only applicable to
+ *                      protocols such as TCP, UDP and ICMP where a
+ *                      standard (i.e. the 'IP-style' checksum)
+ *                      one's complement 16-bit checksum is used,
+ *                      using an IP pseudo-header to seed the
+ *                      calculation.  Software will preload the L4
+ *                      checksum field with the IP pseudo-header
+ *                      checksum.
  *
  *                      For tunnel encapsulation, @csum_start and
  *                      @csum_offset refer to the inner L4
@@ -663,7 +679,6 @@ enum ionic_txq_desc_opcode {
  *                      for more info).
  *
  *                   IONIC_TXQ_DESC_OPCODE_CSUM_HW:
- *
  *                      Offload 16-bit checksum computation to hardware.
  *                      If @csum_l3 is set then the packet's L3 checksum is
  *                      updated. Similarly, if @csum_l4 is set the the L4
@@ -671,7 +686,6 @@ enum ionic_txq_desc_opcode {
  *                      checksums are also updated.
  *
  *                   IONIC_TXQ_DESC_OPCODE_TSO:
- *
  *                      Device preforms TCP segmentation offload
  *                      (TSO).  @hdr_len is the number of bytes
  *                      to the end of TCP header (the offset to
@@ -698,40 +712,41 @@ enum ionic_txq_desc_opcode {
  *                      clear CWR in remaining segments.
  * @flags:
  *                vlan:
- *                    Insert an L2 VLAN header using @vlan_tci.
+ *                    Insert an L2 VLAN header using @vlan_tci
  *                encap:
- *                    Calculate encap header checksum.
+ *                    Calculate encap header checksum
  *                csum_l3:
- *                    Compute L3 header checksum.
+ *                    Compute L3 header checksum
  *                csum_l4:
- *                    Compute L4 header checksum.
+ *                    Compute L4 header checksum
  *                tso_sot:
  *                    TSO start
  *                tso_eot:
  *                    TSO end
  * @num_sg_elems: Number of scatter-gather elements in SG
  *                descriptor
- * @addr:         First data buffer's DMA address.
- *                (Subsequent data buffers are on txq_sg_desc).
+ * @addr:         First data buffer's DMA address
+ *                (Subsequent data buffers are on txq_sg_desc)
  * @len:          First data buffer's length, in bytes
  * @vlan_tci:     VLAN tag to insert in the packet (if requested
  *                by @V-bit).  Includes .1p and .1q tags
  * @hdr_len:      Length of packet headers, including
- *                encapsulating outer header, if applicable.
- *                Valid for opcodes TXQ_DESC_OPCODE_CALC_CSUM and
- *                TXQ_DESC_OPCODE_TSO.  Should be set to zero for
+ *                encapsulating outer header, if applicable
+ *                Valid for opcodes IONIC_TXQ_DESC_OPCODE_CALC_CSUM and
+ *                IONIC_TXQ_DESC_OPCODE_TSO.  Should be set to zero for
  *                all other modes.  For
- *                TXQ_DESC_OPCODE_CALC_CSUM, @hdr_len is length
+ *                IONIC_TXQ_DESC_OPCODE_CALC_CSUM, @hdr_len is length
  *                of headers up to inner-most L4 header.  For
- *                TXQ_DESC_OPCODE_TSO, @hdr_len is up to
+ *                IONIC_TXQ_DESC_OPCODE_TSO, @hdr_len is up to
  *                inner-most L4 payload, so inclusive of
  *                inner-most L4 header.
- * @mss:          Desired MSS value for TSO.  Only applicable for
- *                TXQ_DESC_OPCODE_TSO.
- * @csum_start:   Offset into inner-most L3 header of checksum
- * @csum_offset:  Offset into inner-most L4 header of checksum
+ * @mss:          Desired MSS value for TSO; only applicable for
+ *                IONIC_TXQ_DESC_OPCODE_TSO
+ * @csum_start:   Offset from packet to first byte checked in L4 checksum
+ * @csum_offset:  Offset from csum_start to L4 checksum field
  */
-
+struct ionic_txq_desc {
+	__le64  cmd;
 #define IONIC_TXQ_DESC_OPCODE_MASK		0xf
 #define IONIC_TXQ_DESC_OPCODE_SHIFT		4
 #define IONIC_TXQ_DESC_FLAGS_MASK		0xf
@@ -753,8 +768,6 @@ enum ionic_txq_desc_opcode {
 #define IONIC_TXQ_DESC_FLAG_TSO_SOT		0x4
 #define IONIC_TXQ_DESC_FLAG_TSO_EOT		0x8
 
-struct ionic_txq_desc {
-	__le64  cmd;
 	__le16  len;
 	union {
 		__le16  vlan_tci;
@@ -823,10 +836,9 @@ struct ionic_txq_sg_desc_v1 {
 
 /**
  * struct ionic_txq_comp - Ethernet transmit queue completion descriptor
- * @status:     The status of the command (enum status_code)
- * @comp_index: The index in the descriptor ring for which this
- *                 is the completion.
- * @color:      Color bit.
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
+ * @color:      Color bit
  */
 struct ionic_txq_comp {
 	u8     status;
@@ -843,16 +855,15 @@ enum ionic_rxq_desc_opcode {
 
 /**
  * struct ionic_rxq_desc - Ethernet Rx queue descriptor format
- * @opcode:       Rx operation, see RXQ_DESC_OPCODE_*:
- *
- *                   RXQ_DESC_OPCODE_SIMPLE:
+ * @opcode:       Rx operation, see IONIC_RXQ_DESC_OPCODE_*:
  *
+ *                   IONIC_RXQ_DESC_OPCODE_SIMPLE:
  *                      Receive full packet into data buffer
  *                      starting at @addr.  Results of
  *                      receive, including actual bytes received,
  *                      are recorded in Rx completion descriptor.
  *
- * @len:          Data buffer's length, in bytes.
+ * @len:          Data buffer's length, in bytes
  * @addr:         Data buffer's DMA address
  */
 struct ionic_rxq_desc {
@@ -863,7 +874,7 @@ struct ionic_rxq_desc {
 };
 
 /**
- * struct ionic_rxq_sg_desc - Receive scatter-gather (SG) descriptor element
+ * struct ionic_rxq_sg_elem - Receive scatter-gather (SG) descriptor element
  * @addr:      DMA address of SG element data buffer
  * @len:       Length of SG element data buffer, in bytes
  */
@@ -885,12 +896,11 @@ struct ionic_rxq_sg_desc {
 
 /**
  * struct ionic_rxq_comp - Ethernet receive queue completion descriptor
- * @status:       The status of the command (enum status_code)
+ * @status:       Status of the command (enum ionic_status_code)
  * @num_sg_elems: Number of SG elements used by this descriptor
- * @comp_index:   The index in the descriptor ring for which this
- *                is the completion.
+ * @comp_index:   Index in the descriptor ring for which this is the completion
  * @rss_hash:     32-bit RSS hash
- * @csum:         16-bit sum of the packet's L2 payload.
+ * @csum:         16-bit sum of the packet's L2 payload
  *                If the packet's L2 payload is odd length, an extra
  *                zero-value byte is included in the @csum calculation but
  *                not included in @len.
@@ -898,33 +908,51 @@ struct ionic_rxq_sg_desc {
  *                set.  Includes .1p and .1q tags.
  * @len:          Received packet length, in bytes.  Excludes FCS.
  * @csum_calc     L2 payload checksum is computed or not
- * @csum_tcp_ok:  The TCP checksum calculated by the device
- *                matched the checksum in the receive packet's
- *                TCP header
- * @csum_tcp_bad: The TCP checksum calculated by the device did
- *                not match the checksum in the receive packet's
- *                TCP header.
- * @csum_udp_ok:  The UDP checksum calculated by the device
- *                matched the checksum in the receive packet's
- *                UDP header
- * @csum_udp_bad: The UDP checksum calculated by the device did
- *                not match the checksum in the receive packet's
- *                UDP header.
- * @csum_ip_ok:   The IPv4 checksum calculated by the device
- *                matched the checksum in the receive packet's
- *                first IPv4 header.  If the receive packet
- *                contains both a tunnel IPv4 header and a
- *                transport IPv4 header, the device validates the
- *                checksum for the both IPv4 headers.
- * @csum_ip_bad:  The IPv4 checksum calculated by the device did
- *                not match the checksum in the receive packet's
- *                first IPv4 header. If the receive packet
- *                contains both a tunnel IPv4 header and a
- *                transport IPv4 header, the device validates the
- *                checksum for both IP headers.
- * @VLAN:         VLAN header was stripped and placed in @vlan_tci.
- * @pkt_type:     Packet type
- * @color:        Color bit.
+ * @csum_flags:   See IONIC_RXQ_COMP_CSUM_F_*:
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_TCP_OK:
+ *                    The TCP checksum calculated by the device
+ *                    matched the checksum in the receive packet's
+ *                    TCP header.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_TCP_BAD:
+ *                    The TCP checksum calculated by the device did
+ *                    not match the checksum in the receive packet's
+ *                    TCP header.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_UDP_OK:
+ *                    The UDP checksum calculated by the device
+ *                    matched the checksum in the receive packet's
+ *                    UDP header
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_UDP_BAD:
+ *                    The UDP checksum calculated by the device did
+ *                    not match the checksum in the receive packet's
+ *                    UDP header.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_IP_OK:
+ *                    The IPv4 checksum calculated by the device
+ *                    matched the checksum in the receive packet's
+ *                    first IPv4 header.  If the receive packet
+ *                    contains both a tunnel IPv4 header and a
+ *                    transport IPv4 header, the device validates the
+ *                    checksum for the both IPv4 headers.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_IP_BAD:
+ *                    The IPv4 checksum calculated by the device did
+ *                    not match the checksum in the receive packet's
+ *                    first IPv4 header. If the receive packet
+ *                    contains both a tunnel IPv4 header and a
+ *                    transport IPv4 header, the device validates the
+ *                    checksum for both IP headers.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_VLAN:
+ *                    The VLAN header was stripped and placed in @vlan_tci.
+ *
+ *                  IONIC_RXQ_COMP_CSUM_F_CALC:
+ *                    The checksum was calculated by the device.
+ *
+ * @pkt_type_color: Packet type and color bit; see IONIC_RXQ_COMP_PKT_TYPE_MASK
  */
 struct ionic_rxq_comp {
 	u8     status;
@@ -971,8 +999,8 @@ enum ionic_eth_hw_features {
 	IONIC_ETH_HW_TSO_ECN		= BIT(10),
 	IONIC_ETH_HW_TSO_GRE		= BIT(11),
 	IONIC_ETH_HW_TSO_GRE_CSUM	= BIT(12),
-	IONIC_ETH_HW_TSO_IPXIP4	= BIT(13),
-	IONIC_ETH_HW_TSO_IPXIP6	= BIT(14),
+	IONIC_ETH_HW_TSO_IPXIP4		= BIT(13),
+	IONIC_ETH_HW_TSO_IPXIP6		= BIT(14),
 	IONIC_ETH_HW_TSO_UDP		= BIT(15),
 	IONIC_ETH_HW_TSO_UDP_CSUM	= BIT(16),
 };
@@ -1003,7 +1031,10 @@ enum q_control_oper {
 };
 
 /**
- * Physical connection type
+ * enum ionic_phy_type - Physical connection type
+ * @IONIC_PHY_TYPE_NONE:    No PHY installed
+ * @IONIC_PHY_TYPE_COPPER:  Copper PHY
+ * @IONIC_PHY_TYPE_FIBER:   Fiber PHY
  */
 enum ionic_phy_type {
 	IONIC_PHY_TYPE_NONE	= 0,
@@ -1012,18 +1043,23 @@ enum ionic_phy_type {
 };
 
 /**
- * Transceiver status
+ * enum ionic_xcvr_state - Transceiver status
+ * @IONIC_XCVR_STATE_REMOVED:        Transceiver removed
+ * @IONIC_XCVR_STATE_INSERTED:       Transceiver inserted
+ * @IONIC_XCVR_STATE_PENDING:        Transceiver pending
+ * @IONIC_XCVR_STATE_SPROM_READ:     Transceiver data read
+ * @IONIC_XCVR_STATE_SPROM_READ_ERR: Transceiver data read error
  */
 enum ionic_xcvr_state {
 	IONIC_XCVR_STATE_REMOVED	 = 0,
 	IONIC_XCVR_STATE_INSERTED	 = 1,
 	IONIC_XCVR_STATE_PENDING	 = 2,
 	IONIC_XCVR_STATE_SPROM_READ	 = 3,
-	IONIC_XCVR_STATE_SPROM_READ_ERR  = 4,
+	IONIC_XCVR_STATE_SPROM_READ_ERR	 = 4,
 };
 
 /**
- * Supported link modes
+ * enum ionic_xcvr_pid - Supported link modes
  */
 enum ionic_xcvr_pid {
 	IONIC_XCVR_PID_UNKNOWN           = 0,
@@ -1057,64 +1093,83 @@ enum ionic_xcvr_pid {
 	IONIC_XCVR_PID_SFP_10GBASE_CU   = 68,
 	IONIC_XCVR_PID_QSFP_100G_CWDM4  = 69,
 	IONIC_XCVR_PID_QSFP_100G_PSM4   = 70,
+	IONIC_XCVR_PID_SFP_25GBASE_ACC  = 71,
 };
 
 /**
- * Port types
+ * enum ionic_port_type - Port types
+ * @IONIC_PORT_TYPE_NONE:           Port type not configured
+ * @IONIC_PORT_TYPE_ETH:            Port carries ethernet traffic (inband)
+ * @IONIC_PORT_TYPE_MGMT:           Port carries mgmt traffic (out-of-band)
  */
 enum ionic_port_type {
-	IONIC_PORT_TYPE_NONE = 0,  /* port type not configured */
-	IONIC_PORT_TYPE_ETH  = 1,  /* port carries ethernet traffic (inband) */
-	IONIC_PORT_TYPE_MGMT = 2,  /* port carries mgmt traffic (out-of-band) */
+	IONIC_PORT_TYPE_NONE = 0,
+	IONIC_PORT_TYPE_ETH  = 1,
+	IONIC_PORT_TYPE_MGMT = 2,
 };
 
 /**
- * Port config state
+ * enum ionic_port_admin_state - Port config state
+ * @IONIC_PORT_ADMIN_STATE_NONE:    Port admin state not configured
+ * @IONIC_PORT_ADMIN_STATE_DOWN:    Port admin disabled
+ * @IONIC_PORT_ADMIN_STATE_UP:      Port admin enabled
  */
 enum ionic_port_admin_state {
-	IONIC_PORT_ADMIN_STATE_NONE = 0,   /* port admin state not configured */
-	IONIC_PORT_ADMIN_STATE_DOWN = 1,   /* port is admin disabled */
-	IONIC_PORT_ADMIN_STATE_UP   = 2,   /* port is admin enabled */
+	IONIC_PORT_ADMIN_STATE_NONE = 0,
+	IONIC_PORT_ADMIN_STATE_DOWN = 1,
+	IONIC_PORT_ADMIN_STATE_UP   = 2,
 };
 
 /**
- * Port operational status
+ * enum ionic_port_oper_status - Port operational status
+ * @IONIC_PORT_OPER_STATUS_NONE:    Port disabled
+ * @IONIC_PORT_OPER_STATUS_UP:      Port link status up
+ * @IONIC_PORT_OPER_STATUS_DOWN:    Port link status down
  */
 enum ionic_port_oper_status {
-	IONIC_PORT_OPER_STATUS_NONE  = 0,	/* port is disabled */
-	IONIC_PORT_OPER_STATUS_UP    = 1,	/* port is linked up */
-	IONIC_PORT_OPER_STATUS_DOWN  = 2,	/* port link status is down */
+	IONIC_PORT_OPER_STATUS_NONE  = 0,
+	IONIC_PORT_OPER_STATUS_UP    = 1,
+	IONIC_PORT_OPER_STATUS_DOWN  = 2,
 };
 
 /**
- * Ethernet Forward error correction (fec) modes
+ * enum ionic_port_fec_type - Ethernet Forward error correction (FEC) modes
+ * @IONIC_PORT_FEC_TYPE_NONE:       FEC Disabled
+ * @IONIC_PORT_FEC_TYPE_FC:         FireCode FEC
+ * @IONIC_PORT_FEC_TYPE_RS:         ReedSolomon FEC
  */
 enum ionic_port_fec_type {
-	IONIC_PORT_FEC_TYPE_NONE = 0,		/* Disabled */
-	IONIC_PORT_FEC_TYPE_FC   = 1,		/* FireCode */
-	IONIC_PORT_FEC_TYPE_RS   = 2,		/* ReedSolomon */
+	IONIC_PORT_FEC_TYPE_NONE = 0,
+	IONIC_PORT_FEC_TYPE_FC   = 1,
+	IONIC_PORT_FEC_TYPE_RS   = 2,
 };
 
 /**
- * Ethernet pause (flow control) modes
+ * enum ionic_port_pause_type - Ethernet pause (flow control) modes
+ * @IONIC_PORT_PAUSE_TYPE_NONE:     Disable Pause
+ * @IONIC_PORT_PAUSE_TYPE_LINK:     Link level pause
+ * @IONIC_PORT_PAUSE_TYPE_PFC:      Priority-Flow Control
  */
 enum ionic_port_pause_type {
-	IONIC_PORT_PAUSE_TYPE_NONE = 0,	/* Disable Pause */
-	IONIC_PORT_PAUSE_TYPE_LINK = 1,	/* Link level pause */
-	IONIC_PORT_PAUSE_TYPE_PFC  = 2,	/* Priority-Flow control */
+	IONIC_PORT_PAUSE_TYPE_NONE = 0,
+	IONIC_PORT_PAUSE_TYPE_LINK = 1,
+	IONIC_PORT_PAUSE_TYPE_PFC  = 2,
 };
 
 /**
- * Loopback modes
+ * enum ionic_port_loopback_mode - Loopback modes
+ * @IONIC_PORT_LOOPBACK_MODE_NONE:  Disable loopback
+ * @IONIC_PORT_LOOPBACK_MODE_MAC:   MAC loopback
+ * @IONIC_PORT_LOOPBACK_MODE_PHY:   PHY/SerDes loopback
  */
 enum ionic_port_loopback_mode {
-	IONIC_PORT_LOOPBACK_MODE_NONE = 0,	/* Disable loopback */
-	IONIC_PORT_LOOPBACK_MODE_MAC  = 1,	/* MAC loopback */
-	IONIC_PORT_LOOPBACK_MODE_PHY  = 2,	/* PHY/Serdes loopback */
+	IONIC_PORT_LOOPBACK_MODE_NONE = 0,
+	IONIC_PORT_LOOPBACK_MODE_MAC  = 1,
+	IONIC_PORT_LOOPBACK_MODE_PHY  = 2,
 };
 
 /**
- * Transceiver Status information
+ * struct ionic_xcvr_status - Transceiver Status information
  * @state:    Transceiver status (enum ionic_xcvr_state)
  * @phy:      Physical connection type (enum ionic_phy_type)
  * @pid:      Transceiver link mode (enum pid)
@@ -1128,7 +1183,7 @@ struct ionic_xcvr_status {
 };
 
 /**
- * Port configuration
+ * union ionic_port_config - Port configuration
  * @speed:              port speed (in Mbps)
  * @mtu:                mtu
  * @state:              port admin state (enum port_admin_state)
@@ -1161,17 +1216,21 @@ union ionic_port_config {
 };
 
 /**
- * Port Status information
+ * struct ionic_port_status - Port Status information
  * @status:             link status (enum ionic_port_oper_status)
  * @id:                 port id
  * @speed:              link speed (in Mbps)
+ * @link_down_count:    number of times link went from from up to down
+ * @fec_type:           fec type (enum ionic_port_fec_type)
  * @xcvr:               tranceiver status
  */
 struct ionic_port_status {
 	__le32 id;
 	__le32 speed;
 	u8     status;
-	u8     rsvd[51];
+	__le16 link_down_count;
+	u8     fec_type;
+	u8     rsvd[48];
 	struct ionic_xcvr_status  xcvr;
 } __packed;
 
@@ -1190,7 +1249,7 @@ struct ionic_port_identify_cmd {
 
 /**
  * struct ionic_port_identify_comp - Port identify command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  * @ver:    Version of identify returned by device
  */
 struct ionic_port_identify_comp {
@@ -1215,7 +1274,7 @@ struct ionic_port_init_cmd {
 
 /**
  * struct ionic_port_init_comp - Port initialization command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  */
 struct ionic_port_init_comp {
 	u8 status;
@@ -1235,7 +1294,7 @@ struct ionic_port_reset_cmd {
 
 /**
  * struct ionic_port_reset_comp - Port reset command completion
- * @status: The status of the command (enum status_code)
+ * @status: Status of the command (enum ionic_status_code)
  */
 struct ionic_port_reset_comp {
 	u8 status;
@@ -1243,15 +1302,23 @@ struct ionic_port_reset_comp {
 };
 
 /**
- * enum stats_ctl_cmd - List of commands for stats control
+ * enum ionic_stats_ctl_cmd - List of commands for stats control
+ * @IONIC_STATS_CTL_RESET:      Reset statistics
  */
 enum ionic_stats_ctl_cmd {
 	IONIC_STATS_CTL_RESET		= 0,
 };
 
-
 /**
  * enum ionic_port_attr - List of device attributes
+ * @IONIC_PORT_ATTR_STATE:      Port state attribute
+ * @IONIC_PORT_ATTR_SPEED:      Port speed attribute
+ * @IONIC_PORT_ATTR_MTU:        Port MTU attribute
+ * @IONIC_PORT_ATTR_AUTONEG:    Port autonegotation attribute
+ * @IONIC_PORT_ATTR_FEC:        Port FEC attribute
+ * @IONIC_PORT_ATTR_PAUSE:      Port pause attribute
+ * @IONIC_PORT_ATTR_LOOPBACK:   Port loopback attribute
+ * @IONIC_PORT_ATTR_STATS_CTRL: Port statistics control attribute
  */
 enum ionic_port_attr {
 	IONIC_PORT_ATTR_STATE		= 0,
@@ -1266,9 +1333,17 @@ enum ionic_port_attr {
 
 /**
  * struct ionic_port_setattr_cmd - Set port attributes on the NIC
- * @opcode:     Opcode
- * @index:      port index
- * @attr:       Attribute type (enum ionic_port_attr)
+ * @opcode:         Opcode
+ * @index:          Port index
+ * @attr:           Attribute type (enum ionic_port_attr)
+ * @state:          Port state
+ * @speed:          Port speed
+ * @mtu:            Port MTU
+ * @an_enable:      Port autonegotiation setting
+ * @fec_type:       Port FEC type setting
+ * @pause_type:     Port pause type setting
+ * @loopback_mode:  Port loopback mode
+ * @stats_ctl:      Port stats setting
  */
 struct ionic_port_setattr_cmd {
 	u8     opcode;
@@ -1283,14 +1358,14 @@ struct ionic_port_setattr_cmd {
 		u8      fec_type;
 		u8      pause_type;
 		u8      loopback_mode;
-		u8	stats_ctl;
+		u8      stats_ctl;
 		u8      rsvd2[60];
 	};
 };
 
 /**
  * struct ionic_port_setattr_comp - Port set attr command completion
- * @status:     The status of the command (enum status_code)
+ * @status:     Status of the command (enum ionic_status_code)
  * @color:      Color bit
  */
 struct ionic_port_setattr_comp {
@@ -1314,8 +1389,15 @@ struct ionic_port_getattr_cmd {
 
 /**
  * struct ionic_port_getattr_comp - Port get attr command completion
- * @status:     The status of the command (enum status_code)
- * @color:      Color bit
+ * @status:         Status of the command (enum ionic_status_code)
+ * @state:          Port state
+ * @speed:          Port speed
+ * @mtu:            Port MTU
+ * @an_enable:      Port autonegotiation setting
+ * @fec_type:       Port FEC type setting
+ * @pause_type:     Port pause type setting
+ * @loopback_mode:  Port loopback mode
+ * @color:          Color bit
  */
 struct ionic_port_getattr_comp {
 	u8     status;
@@ -1334,12 +1416,12 @@ struct ionic_port_getattr_comp {
 };
 
 /**
- * struct ionic_lif_status - Lif status register
+ * struct ionic_lif_status - LIF status register
  * @eid:             most recent NotifyQ event id
- * @port_num:        port the lif is connected to
+ * @port_num:        port the LIF is connected to
  * @link_status:     port status (enum ionic_port_oper_status)
  * @link_speed:      speed of link in Mbps
- * @link_down_count: number of times link status changes
+ * @link_down_count: number of times link went from up to down
  */
 struct ionic_lif_status {
 	__le64 eid;
@@ -1373,6 +1455,9 @@ enum ionic_dev_state {
 
 /**
  * enum ionic_dev_attr - List of device attributes
+ * @IONIC_DEV_ATTR_STATE:     Device state attribute
+ * @IONIC_DEV_ATTR_NAME:      Device name attribute
+ * @IONIC_DEV_ATTR_FEATURES:  Device feature attributes
  */
 enum ionic_dev_attr {
 	IONIC_DEV_ATTR_STATE    = 0,
@@ -1402,7 +1487,7 @@ struct ionic_dev_setattr_cmd {
 
 /**
  * struct ionic_dev_setattr_comp - Device set attr command completion
- * @status:     The status of the command (enum status_code)
+ * @status:     Status of the command (enum ionic_status_code)
  * @features:   Device features
  * @color:      Color bit
  */
@@ -1429,7 +1514,7 @@ struct ionic_dev_getattr_cmd {
 
 /**
  * struct ionic_dev_setattr_comp - Device set attr command completion
- * @status:     The status of the command (enum status_code)
+ * @status:     Status of the command (enum ionic_status_code)
  * @features:   Device features
  * @color:      Color bit
  */
@@ -1459,6 +1544,13 @@ enum ionic_rss_hash_types {
 
 /**
  * enum ionic_lif_attr - List of LIF attributes
+ * @IONIC_LIF_ATTR_STATE:       LIF state attribute
+ * @IONIC_LIF_ATTR_NAME:        LIF name attribute
+ * @IONIC_LIF_ATTR_MTU:         LIF MTU attribute
+ * @IONIC_LIF_ATTR_MAC:         LIF MAC attribute
+ * @IONIC_LIF_ATTR_FEATURES:    LIF features attribute
+ * @IONIC_LIF_ATTR_RSS:         LIF RSS attribute
+ * @IONIC_LIF_ATTR_STATS_CTRL:  LIF statistics control attribute
  */
 enum ionic_lif_attr {
 	IONIC_LIF_ATTR_STATE        = 0,
@@ -1473,18 +1565,18 @@ enum ionic_lif_attr {
 /**
  * struct ionic_lif_setattr_cmd - Set LIF attributes on the NIC
  * @opcode:     Opcode
- * @type:       Attribute type (enum ionic_lif_attr)
+ * @attr:       Attribute type (enum ionic_lif_attr)
  * @index:      LIF index
- * @state:      lif state (enum lif_state)
+ * @state:      LIF state (enum ionic_lif_state)
  * @name:       The netdev name string, 0 terminated
  * @mtu:        Mtu
  * @mac:        Station mac
  * @features:   Features (enum ionic_eth_hw_features)
  * @rss:        RSS properties
- *              @types:     The hash types to enable (see rss_hash_types).
- *              @key:       The hash secret key.
- *              @addr:      Address for the indirection table shared memory.
- * @stats_ctl:  stats control commands (enum stats_ctl_cmd)
+ *              @types:     The hash types to enable (see rss_hash_types)
+ *              @key:       The hash secret key
+ *              @addr:      Address for the indirection table shared memory
+ * @stats_ctl:  stats control commands (enum ionic_stats_ctl_cmd)
  */
 struct ionic_lif_setattr_cmd {
 	u8     opcode;
@@ -1502,16 +1594,15 @@ struct ionic_lif_setattr_cmd {
 			u8     rsvd[6];
 			__le64 addr;
 		} rss;
-		u8	stats_ctl;
+		u8      stats_ctl;
 		u8      rsvd[60];
 	} __packed;
 };
 
 /**
  * struct ionic_lif_setattr_comp - LIF set attr command completion
- * @status:     The status of the command (enum status_code)
- * @comp_index: The index in the descriptor ring for which this
- *              is the completion.
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
  * @features:   features (enum ionic_eth_hw_features)
  * @color:      Color bit
  */
@@ -1541,10 +1632,9 @@ struct ionic_lif_getattr_cmd {
 
 /**
  * struct ionic_lif_getattr_comp - LIF get attr command completion
- * @status:     The status of the command (enum status_code)
- * @comp_index: The index in the descriptor ring for which this
- *              is the completion.
- * @state:      lif state (enum lif_state)
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
+ * @state:      LIF state (enum ionic_lif_state)
  * @name:       The netdev name string, 0 terminated
  * @mtu:        Mtu
  * @mac:        Station mac
@@ -1566,11 +1656,12 @@ struct ionic_lif_getattr_comp {
 };
 
 enum ionic_rx_mode {
-	IONIC_RX_MODE_F_UNICAST    = BIT(0),
-	IONIC_RX_MODE_F_MULTICAST  = BIT(1),
-	IONIC_RX_MODE_F_BROADCAST  = BIT(2),
-	IONIC_RX_MODE_F_PROMISC    = BIT(3),
-	IONIC_RX_MODE_F_ALLMULTI   = BIT(4),
+	IONIC_RX_MODE_F_UNICAST		= BIT(0),
+	IONIC_RX_MODE_F_MULTICAST	= BIT(1),
+	IONIC_RX_MODE_F_BROADCAST	= BIT(2),
+	IONIC_RX_MODE_F_PROMISC		= BIT(3),
+	IONIC_RX_MODE_F_ALLMULTI	= BIT(4),
+	IONIC_RX_MODE_F_RDMA_SNIFFER	= BIT(5),
 };
 
 /**
@@ -1578,11 +1669,12 @@ enum ionic_rx_mode {
  * @opcode:     opcode
  * @lif_index:  LIF index
  * @rx_mode:    Rx mode flags:
- *                  IONIC_RX_MODE_F_UNICAST: Accept known unicast packets.
- *                  IONIC_RX_MODE_F_MULTICAST: Accept known multicast packets.
- *                  IONIC_RX_MODE_F_BROADCAST: Accept broadcast packets.
- *                  IONIC_RX_MODE_F_PROMISC: Accept any packets.
- *                  IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets.
+ *                  IONIC_RX_MODE_F_UNICAST: Accept known unicast packets
+ *                  IONIC_RX_MODE_F_MULTICAST: Accept known multicast packets
+ *                  IONIC_RX_MODE_F_BROADCAST: Accept broadcast packets
+ *                  IONIC_RX_MODE_F_PROMISC: Accept any packets
+ *                  IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets
+ *                  IONIC_RX_MODE_F_RDMA_SNIFFER: Sniff RDMA packets
  */
 struct ionic_rx_mode_set_cmd {
 	u8     opcode;
@@ -1606,9 +1698,14 @@ enum ionic_rx_filter_match_type {
  * @qtype:      Queue type
  * @lif_index:  LIF index
  * @qid:        Queue ID
- * @match:      Rx filter match type.  (See IONIC_RX_FILTER_MATCH_xxx)
- * @vlan:       VLAN ID
- * @addr:       MAC address (network-byte order)
+ * @match:      Rx filter match type (see IONIC_RX_FILTER_MATCH_xxx)
+ * @vlan:       VLAN filter
+ *              @vlan:  VLAN ID
+ * @mac:        MAC filter
+ *              @addr:  MAC address (network-byte order)
+ * @mac_vlan:   MACVLAN filter
+ *              @vlan:  VLAN ID
+ *              @addr:  MAC address (network-byte order)
  */
 struct ionic_rx_filter_add_cmd {
 	u8     opcode;
@@ -1633,11 +1730,10 @@ struct ionic_rx_filter_add_cmd {
 
 /**
  * struct ionic_rx_filter_add_comp - Add LIF Rx filter command completion
- * @status:     The status of the command (enum status_code)
- * @comp_index: The index in the descriptor ring for which this
- *              is the completion.
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
  * @filter_id:  Filter ID
- * @color:      Color bit.
+ * @color:      Color bit
  */
 struct ionic_rx_filter_add_comp {
 	u8     status;
@@ -1664,63 +1760,6 @@ struct ionic_rx_filter_del_cmd {
 
 typedef struct ionic_admin_comp ionic_rx_filter_del_comp;
 
-/**
- * struct ionic_qos_identify_cmd - QoS identify command
- * @opcode:    opcode
- * @ver:     Highest version of identify supported by driver
- *
- */
-struct ionic_qos_identify_cmd {
-	u8 opcode;
-	u8 ver;
-	u8 rsvd[62];
-};
-
-/**
- * struct ionic_qos_identify_comp - QoS identify command completion
- * @status: The status of the command (enum status_code)
- * @ver:    Version of identify returned by device
- */
-struct ionic_qos_identify_comp {
-	u8 status;
-	u8 ver;
-	u8 rsvd[14];
-};
-
-#define IONIC_QOS_CLASS_MAX		7
-#define IONIC_QOS_CLASS_NAME_SZ		32
-#define IONIC_QOS_DSCP_MAX_VALUES	64
-
-/**
- * enum ionic_qos_class
- */
-enum ionic_qos_class {
-	IONIC_QOS_CLASS_DEFAULT		= 0,
-	IONIC_QOS_CLASS_USER_DEFINED_1	= 1,
-	IONIC_QOS_CLASS_USER_DEFINED_2	= 2,
-	IONIC_QOS_CLASS_USER_DEFINED_3	= 3,
-	IONIC_QOS_CLASS_USER_DEFINED_4	= 4,
-	IONIC_QOS_CLASS_USER_DEFINED_5	= 5,
-	IONIC_QOS_CLASS_USER_DEFINED_6	= 6,
-};
-
-/**
- * enum ionic_qos_class_type - Traffic classification criteria
- */
-enum ionic_qos_class_type {
-	IONIC_QOS_CLASS_TYPE_NONE	= 0,
-	IONIC_QOS_CLASS_TYPE_PCP	= 1,	/* Dot1Q pcp */
-	IONIC_QOS_CLASS_TYPE_DSCP	= 2,	/* IP dscp */
-};
-
-/**
- * enum ionic_qos_sched_type - Qos class scheduling type
- */
-enum ionic_qos_sched_type {
-	IONIC_QOS_SCHED_TYPE_STRICT	= 0,	/* Strict priority */
-	IONIC_QOS_SCHED_TYPE_DWRR	= 1,	/* Deficit weighted round-robin */
-};
-
 enum ionic_vf_attr {
 	IONIC_VF_ATTR_SPOOFCHK	= 1,
 	IONIC_VF_ATTR_TRUST	= 2,
@@ -1732,26 +1771,29 @@ enum ionic_vf_attr {
 };
 
 /**
- * VF link status
+ * enum ionic_vf_link_status - Virtual Function link status
+ * @IONIC_VF_LINK_STATUS_AUTO:   Use link state of the uplink
+ * @IONIC_VF_LINK_STATUS_UP:     Link always up
+ * @IONIC_VF_LINK_STATUS_DOWN:   Link always down
  */
 enum ionic_vf_link_status {
-	IONIC_VF_LINK_STATUS_AUTO = 0,	/* link state of the uplink */
-	IONIC_VF_LINK_STATUS_UP   = 1,	/* link is always up */
-	IONIC_VF_LINK_STATUS_DOWN = 2,	/* link is always down */
+	IONIC_VF_LINK_STATUS_AUTO = 0,
+	IONIC_VF_LINK_STATUS_UP   = 1,
+	IONIC_VF_LINK_STATUS_DOWN = 2,
 };
 
 /**
  * struct ionic_vf_setattr_cmd - Set VF attributes on the NIC
  * @opcode:     Opcode
- * @index:      VF index
  * @attr:       Attribute type (enum ionic_vf_attr)
- *	macaddr		mac address
- *	vlanid		vlan ID
- *	maxrate		max Tx rate in Mbps
- *	spoofchk	enable address spoof checking
- *	trust		enable VF trust
- *	linkstate	set link up or down
- *	stats_pa	set DMA address for VF stats
+ * @vf_index:   VF index
+ *	@macaddr:	mac address
+ *	@vlanid:	vlan ID
+ *	@maxrate:	max Tx rate in Mbps
+ *	@spoofchk:	enable address spoof checking
+ *	@trust:		enable VF trust
+ *	@linkstate:	set link up or down
+ *	@stats_pa:	set DMA address for VF stats
  */
 struct ionic_vf_setattr_cmd {
 	u8     opcode;
@@ -1781,8 +1823,8 @@ struct ionic_vf_setattr_comp {
 /**
  * struct ionic_vf_getattr_cmd - Get VF attributes from the NIC
  * @opcode:     Opcode
- * @index:      VF index
  * @attr:       Attribute type (enum ionic_vf_attr)
+ * @vf_index:   VF index
  */
 struct ionic_vf_getattr_cmd {
 	u8     opcode;
@@ -1809,19 +1851,85 @@ struct ionic_vf_getattr_comp {
 };
 
 /**
- * union ionic_qos_config - Qos configuration structure
+ * struct ionic_qos_identify_cmd - QoS identify command
+ * @opcode:  opcode
+ * @ver:     Highest version of identify supported by driver
+ *
+ */
+struct ionic_qos_identify_cmd {
+	u8 opcode;
+	u8 ver;
+	u8 rsvd[62];
+};
+
+/**
+ * struct ionic_qos_identify_comp - QoS identify command completion
+ * @status: Status of the command (enum ionic_status_code)
+ * @ver:    Version of identify returned by device
+ */
+struct ionic_qos_identify_comp {
+	u8 status;
+	u8 ver;
+	u8 rsvd[14];
+};
+
+#define IONIC_QOS_TC_MAX		8
+/* Capri max supported, should be renamed. */
+#define IONIC_QOS_CLASS_MAX		7
+#define IONIC_QOS_PCP_MAX		8
+#define IONIC_QOS_CLASS_NAME_SZ	32
+#define IONIC_QOS_DSCP_MAX		64
+#define IONIC_QOS_ALL_PCP		0xFF
+
+/**
+ * enum ionic_qos_class
+ */
+enum ionic_qos_class {
+	IONIC_QOS_CLASS_DEFAULT		= 0,
+	IONIC_QOS_CLASS_USER_DEFINED_1	= 1,
+	IONIC_QOS_CLASS_USER_DEFINED_2	= 2,
+	IONIC_QOS_CLASS_USER_DEFINED_3	= 3,
+	IONIC_QOS_CLASS_USER_DEFINED_4	= 4,
+	IONIC_QOS_CLASS_USER_DEFINED_5	= 5,
+	IONIC_QOS_CLASS_USER_DEFINED_6	= 6,
+};
+
+/**
+ * enum ionic_qos_class_type - Traffic classification criteria
+ * @IONIC_QOS_CLASS_TYPE_NONE:    No QoS
+ * @IONIC_QOS_CLASS_TYPE_PCP:     Dot1Q PCP
+ * @IONIC_QOS_CLASS_TYPE_DSCP:    IP DSCP
+ */
+enum ionic_qos_class_type {
+	IONIC_QOS_CLASS_TYPE_NONE	= 0,
+	IONIC_QOS_CLASS_TYPE_PCP	= 1,
+	IONIC_QOS_CLASS_TYPE_DSCP	= 2,
+};
+
+/**
+ * enum ionic_qos_sched_type - QoS class scheduling type
+ * @IONIC_QOS_SCHED_TYPE_STRICT:  Strict priority
+ * @IONIC_QOS_SCHED_TYPE_DWRR:    Deficit weighted round-robin
+ */
+enum ionic_qos_sched_type {
+	IONIC_QOS_SCHED_TYPE_STRICT	= 0,
+	IONIC_QOS_SCHED_TYPE_DWRR	= 1,
+};
+
+/**
+ * union ionic_qos_config - QoS configuration structure
  * @flags:		Configuration flags
  *	IONIC_QOS_CONFIG_F_ENABLE		enable
- *	IONIC_QOS_CONFIG_F_DROP			drop/nodrop
+ *	IONIC_QOS_CONFIG_F_NO_DROP		drop/nodrop
  *	IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP		enable dot1q pcp rewrite
  *	IONIC_QOS_CONFIG_F_RW_IP_DSCP		enable ip dscp rewrite
- * @sched_type:		Qos class scheduling type (enum ionic_qos_sched_type)
- * @class_type:		Qos class type (enum ionic_qos_class_type)
- * @pause_type:		Qos pause type (enum ionic_qos_pause_type)
- * @name:		Qos class name
+ * @sched_type:		QoS class scheduling type (enum ionic_qos_sched_type)
+ * @class_type:		QoS class type (enum ionic_qos_class_type)
+ * @pause_type:		QoS pause type (enum ionic_qos_pause_type)
+ * @name:		QoS class name
  * @mtu:		MTU of the class
- * @pfc_dot1q_pcp:	Pcp value for pause frames (valid iff F_NODROP)
- * @dwrr_weight:	Qos class scheduling weight
+ * @pfc_cos:		Priority-Flow Control class of service
+ * @dwrr_weight:	QoS class scheduling weight
  * @strict_rlmt:	Rate limit for strict priority scheduling
  * @rw_dot1q_pcp:	Rewrite dot1q pcp to this value	(valid iff F_RW_DOT1Q_PCP)
  * @rw_ip_dscp:		Rewrite ip dscp to this value	(valid iff F_RW_IP_DSCP)
@@ -1832,7 +1940,8 @@ struct ionic_vf_getattr_comp {
 union ionic_qos_config {
 	struct {
 #define IONIC_QOS_CONFIG_F_ENABLE		BIT(0)
-#define IONIC_QOS_CONFIG_F_DROP			BIT(1)
+#define IONIC_QOS_CONFIG_F_NO_DROP		BIT(1)
+/* Used to rewrite PCP or DSCP value. */
 #define IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP		BIT(2)
 #define IONIC_QOS_CONFIG_F_RW_IP_DSCP		BIT(3)
 		u8      flags;
@@ -1849,6 +1958,7 @@ union ionic_qos_config {
 			__le64  strict_rlmt;
 		};
 		/* marking */
+		/* Used to rewrite PCP or DSCP value. */
 		union {
 			u8      rw_dot1q_pcp;
 			u8      rw_ip_dscp;
@@ -1858,7 +1968,7 @@ union ionic_qos_config {
 			u8      dot1q_pcp;
 			struct {
 				u8      ndscp;
-				u8      ip_dscp[IONIC_QOS_DSCP_MAX_VALUES];
+				u8      ip_dscp[IONIC_QOS_DSCP_MAX];
 			};
 		};
 	};
@@ -1877,15 +1987,15 @@ union ionic_qos_identity {
 		u8     version;
 		u8     type;
 		u8     rsvd[62];
-		union  ionic_qos_config config[IONIC_QOS_CLASS_MAX];
+		union ionic_qos_config config[IONIC_QOS_CLASS_MAX];
 	};
-	__le32 words[512];
+	__le32 words[478];
 };
 
 /**
- * struct qos_init_cmd - QoS config init command
+ * struct ionic_qos_init_cmd - QoS config init command
  * @opcode:	Opcode
- * @group:	Qos class id
+ * @group:	QoS class id
  * @info_pa:	destination address for qos info
  */
 struct ionic_qos_init_cmd {
@@ -1899,8 +2009,9 @@ struct ionic_qos_init_cmd {
 typedef struct ionic_admin_comp ionic_qos_init_comp;
 
 /**
- * struct ionic_qos_reset_cmd - Qos config reset command
+ * struct ionic_qos_reset_cmd - QoS config reset command
  * @opcode:	Opcode
+ * @group:	QoS class id
  */
 struct ionic_qos_reset_cmd {
 	u8    opcode;
@@ -1927,10 +2038,16 @@ struct ionic_fw_download_cmd {
 
 typedef struct ionic_admin_comp ionic_fw_download_comp;
 
+/**
+ * enum ionic_fw_control_oper - FW control operations
+ * @IONIC_FW_RESET:     Reset firmware
+ * @IONIC_FW_INSTALL:   Install firmware
+ * @IONIC_FW_ACTIVATE:  Activate firmware
+ */
 enum ionic_fw_control_oper {
-	IONIC_FW_RESET		= 0,	/* Reset firmware */
-	IONIC_FW_INSTALL	= 1,	/* Install firmware */
-	IONIC_FW_ACTIVATE	= 2,	/* Activate firmware */
+	IONIC_FW_RESET		= 0,
+	IONIC_FW_INSTALL	= 1,
+	IONIC_FW_ACTIVATE	= 2,
 };
 
 /**
@@ -1949,8 +2066,10 @@ struct ionic_fw_control_cmd {
 
 /**
  * struct ionic_fw_control_comp - Firmware control copletion
- * @opcode:    opcode
- * @slot:      slot where the firmware was installed
+ * @status:     Status of the command (enum ionic_status_code)
+ * @comp_index: Index in the descriptor ring for which this is the completion
+ * @slot:       Slot where the firmware was installed
+ * @color:      Color bit
  */
 struct ionic_fw_control_comp {
 	u8     status;
@@ -1968,11 +2087,11 @@ struct ionic_fw_control_comp {
 /**
  * struct ionic_rdma_reset_cmd - Reset RDMA LIF cmd
  * @opcode:        opcode
- * @lif_index:     lif index
+ * @lif_index:     LIF index
  *
- * There is no rdma specific dev command completion struct.  Completion uses
+ * There is no RDMA specific dev command completion struct.  Completion uses
  * the common struct ionic_admin_comp.  Only the status is indicated.
- * Nonzero status means the LIF does not support rdma.
+ * Nonzero status means the LIF does not support RDMA.
  **/
 struct ionic_rdma_reset_cmd {
 	u8     opcode;
@@ -1984,30 +2103,29 @@ struct ionic_rdma_reset_cmd {
 /**
  * struct ionic_rdma_queue_cmd - Create RDMA Queue command
  * @opcode:        opcode, 52, 53
- * @lif_index      lif index
- * @qid_ver:       (qid | (rdma version << 24))
+ * @lif_index:     LIF index
+ * @qid_ver:       (qid | (RDMA version << 24))
  * @cid:           intr, eq_id, or cq_id
  * @dbid:          doorbell page id
  * @depth_log2:    log base two of queue depth
  * @stride_log2:   log base two of queue stride
  * @dma_addr:      address of the queue memory
- * @xxx_table_index: temporary, but should not need pgtbl for contig. queues.
  *
- * The same command struct is used to create an rdma event queue, completion
- * queue, or rdma admin queue.  The cid is an interrupt number for an event
+ * The same command struct is used to create an RDMA event queue, completion
+ * queue, or RDMA admin queue.  The cid is an interrupt number for an event
  * queue, an event queue id for a completion queue, or a completion queue id
- * for an rdma admin queue.
+ * for an RDMA admin queue.
  *
  * The queue created via a dev command must be contiguous in dma space.
  *
  * The dev commands are intended only to be used during driver initialization,
- * to create queues supporting the rdma admin queue.  Other queues, and other
- * types of rdma resources like memory regions, will be created and registered
- * via the rdma admin queue, and will support a more complete interface
+ * to create queues supporting the RDMA admin queue.  Other queues, and other
+ * types of RDMA resources like memory regions, will be created and registered
+ * via the RDMA admin queue, and will support a more complete interface
  * providing scatter gather lists for larger, scattered queue buffers and
  * memory registration.
  *
- * There is no rdma specific dev command completion struct.  Completion uses
+ * There is no RDMA specific dev command completion struct.  Completion uses
  * the common struct ionic_admin_comp.  Only the status is indicated.
  **/
 struct ionic_rdma_queue_cmd {
@@ -2020,8 +2138,7 @@ struct ionic_rdma_queue_cmd {
 	u8     depth_log2;
 	u8     stride_log2;
 	__le64 dma_addr;
-	u8     rsvd2[36];
-	__le32 xxx_table_index;
+	u8     rsvd2[40];
 };
 
 /******************************************************************
@@ -2029,7 +2146,7 @@ struct ionic_rdma_queue_cmd {
  ******************************************************************/
 
 /**
- * struct ionic_notifyq_event
+ * struct ionic_notifyq_event - Generic event reporting structure
  * @eid:   event number
  * @ecode: event code
  * @data:  unspecified data about the event
@@ -2044,9 +2161,9 @@ struct ionic_notifyq_event {
 };
 
 /**
- * struct ionic_link_change_event
+ * struct ionic_link_change_event - Link change event notification
  * @eid:		event number
- * @ecode:		event code = EVENT_OPCODE_LINK_CHANGE
+ * @ecode:		event code = IONIC_EVENT_LINK_CHANGE
  * @link_status:	link up or down, with error bits (enum port_status)
  * @link_speed:		speed of the network link
  *
@@ -2061,9 +2178,9 @@ struct ionic_link_change_event {
 };
 
 /**
- * struct ionic_reset_event
+ * struct ionic_reset_event - Reset event notification
  * @eid:		event number
- * @ecode:		event code = EVENT_OPCODE_RESET
+ * @ecode:		event code = IONIC_EVENT_RESET
  * @reset_code:		reset type
  * @state:		0=pending, 1=complete, 2=error
  *
@@ -2079,11 +2196,9 @@ struct ionic_reset_event {
 };
 
 /**
- * struct ionic_heartbeat_event
+ * struct ionic_heartbeat_event - Sent periodically by NIC to indicate health
  * @eid:	event number
- * @ecode:	event code = EVENT_OPCODE_HEARTBEAT
- *
- * Sent periodically by the NIC to indicate continued health
+ * @ecode:	event code = IONIC_EVENT_HEARTBEAT
  */
 struct ionic_heartbeat_event {
 	__le64 eid;
@@ -2092,12 +2207,10 @@ struct ionic_heartbeat_event {
 };
 
 /**
- * struct ionic_log_event
+ * struct ionic_log_event - Sent to notify the driver of an internal error
  * @eid:	event number
- * @ecode:	event code = EVENT_OPCODE_LOG
+ * @ecode:	event code = IONIC_EVENT_LOG
  * @data:	log data
- *
- * Sent to notify the driver of an internal error.
  */
 struct ionic_log_event {
 	__le64 eid;
@@ -2106,7 +2219,18 @@ struct ionic_log_event {
 };
 
 /**
- * struct ionic_port_stats
+ * struct ionic_xcvr_event - Transceiver change event
+ * @eid:	event number
+ * @ecode:	event code = IONIC_EVENT_XCVR
+ */
+struct ionic_xcvr_event {
+	__le64 eid;
+	__le16 ecode;
+	u8     rsvd[54];
+};
+
+/**
+ * struct ionic_port_stats - Port statistics structure
  */
 struct ionic_port_stats {
 	__le64 frames_rx_ok;
@@ -2211,28 +2335,61 @@ struct ionic_mgmt_port_stats {
 	__le64 frames_rx_multicast;
 	__le64 frames_rx_broadcast;
 	__le64 frames_rx_pause;
-	__le64 frames_rx_bad_length0;
-	__le64 frames_rx_undersized1;
-	__le64 frames_rx_oversized2;
-	__le64 frames_rx_fragments3;
-	__le64 frames_rx_jabber4;
-	__le64 frames_rx_64b5;
-	__le64 frames_rx_65b_127b6;
-	__le64 frames_rx_128b_255b7;
-	__le64 frames_rx_256b_511b8;
-	__le64 frames_rx_512b_1023b9;
-	__le64 frames_rx_1024b_1518b0;
-	__le64 frames_rx_gt_1518b1;
-	__le64 frames_rx_fifo_full2;
-	__le64 frames_tx_ok3;
-	__le64 frames_tx_all4;
-	__le64 frames_tx_bad5;
-	__le64 octets_tx_ok6;
-	__le64 octets_tx_total7;
-	__le64 frames_tx_unicast8;
-	__le64 frames_tx_multicast9;
-	__le64 frames_tx_broadcast0;
-	__le64 frames_tx_pause1;
+	__le64 frames_rx_bad_length;
+	__le64 frames_rx_undersized;
+	__le64 frames_rx_oversized;
+	__le64 frames_rx_fragments;
+	__le64 frames_rx_jabber;
+	__le64 frames_rx_64b;
+	__le64 frames_rx_65b_127b;
+	__le64 frames_rx_128b_255b;
+	__le64 frames_rx_256b_511b;
+	__le64 frames_rx_512b_1023b;
+	__le64 frames_rx_1024b_1518b;
+	__le64 frames_rx_gt_1518b;
+	__le64 frames_rx_fifo_full;
+	__le64 frames_tx_ok;
+	__le64 frames_tx_all;
+	__le64 frames_tx_bad;
+	__le64 octets_tx_ok;
+	__le64 octets_tx_total;
+	__le64 frames_tx_unicast;
+	__le64 frames_tx_multicast;
+	__le64 frames_tx_broadcast;
+	__le64 frames_tx_pause;
+};
+
+enum ionic_pb_buffer_drop_stats {
+	IONIC_BUFFER_INTRINSIC_DROP = 0,
+	IONIC_BUFFER_DISCARDED,
+	IONIC_BUFFER_ADMITTED,
+	IONIC_BUFFER_OUT_OF_CELLS_DROP,
+	IONIC_BUFFER_OUT_OF_CELLS_DROP_2,
+	IONIC_BUFFER_OUT_OF_CREDIT_DROP,
+	IONIC_BUFFER_TRUNCATION_DROP,
+	IONIC_BUFFER_PORT_DISABLED_DROP,
+	IONIC_BUFFER_COPY_TO_CPU_TAIL_DROP,
+	IONIC_BUFFER_SPAN_TAIL_DROP,
+	IONIC_BUFFER_MIN_SIZE_VIOLATION_DROP,
+	IONIC_BUFFER_ENQUEUE_ERROR_DROP,
+	IONIC_BUFFER_INVALID_PORT_DROP,
+	IONIC_BUFFER_INVALID_OUTPUT_QUEUE_DROP,
+	IONIC_BUFFER_DROP_MAX,
+};
+
+/**
+ * struct port_pb_stats - packet buffers system stats
+ * uses ionic_pb_buffer_drop_stats for drop_counts[]
+ */
+struct ionic_port_pb_stats {
+	__le64 sop_count_in;
+	__le64 eop_count_in;
+	__le64 sop_count_out;
+	__le64 eop_count_out;
+	__le64 drop_counts[IONIC_BUFFER_DROP_MAX];
+	__le64 input_queue_buffer_occupancy[IONIC_QOS_TC_MAX];
+	__le64 input_queue_port_monitor[IONIC_QOS_TC_MAX];
+	__le64 output_queue_port_monitor[IONIC_QOS_TC_MAX];
 };
 
 /**
@@ -2264,22 +2421,31 @@ union ionic_port_identity {
 		u8     rsvd2[44];
 		union ionic_port_config config;
 	};
-	__le32 words[512];
+	__le32 words[478];
 };
 
 /**
  * struct ionic_port_info - port info structure
- * @port_status:     port status
- * @port_stats:      port stats
+ * @config:          Port configuration data
+ * @status:          Port status data
+ * @stats:           Port statistics data
+ * @mgmt_stats:      Port management statistics data
+ * @port_pb_drop_stats:   uplink pb drop stats
  */
 struct ionic_port_info {
 	union ionic_port_config config;
 	struct ionic_port_status status;
-	struct ionic_port_stats stats;
+	union {
+		struct ionic_port_stats      stats;
+		struct ionic_mgmt_port_stats mgmt_stats;
+	};
+	/* room for pb_stats to start at 2k offset */
+	u8                          rsvd[760];
+	struct ionic_port_pb_stats  pb_stats;
 };
 
 /**
- * struct ionic_lif_stats
+ * struct ionic_lif_stats - LIF statistics structure
  */
 struct ionic_lif_stats {
 	/* RX */
@@ -2332,7 +2498,7 @@ struct ionic_lif_stats {
 	__le64 tx_queue_error;
 	__le64 tx_desc_fetch_error;
 	__le64 tx_desc_data_error;
-	__le64 rsvd9;
+	__le64 tx_queue_empty;
 	__le64 rsvd10;
 	__le64 rsvd11;
 	__le64 rsvd12;
@@ -2433,7 +2599,10 @@ struct ionic_lif_stats {
 };
 
 /**
- * struct ionic_lif_info - lif info structure
+ * struct ionic_lif_info - LIF info structure
+ * @config:	LIF configuration structure
+ * @status:	LIF status structure
+ * @stats:	LIF statistics structure
  */
 struct ionic_lif_info {
 	union ionic_lif_config config;
@@ -2471,6 +2640,7 @@ union ionic_dev_cmd {
 
 	struct ionic_q_identify_cmd q_identify;
 	struct ionic_q_init_cmd q_init;
+	struct ionic_q_control_cmd q_control;
 };
 
 union ionic_dev_cmd_comp {
@@ -2507,15 +2677,15 @@ union ionic_dev_cmd_comp {
 };
 
 /**
- * union dev_info - Device info register format (read-only)
- * @signature:       Signature value of 0x44455649 ('DEVI').
- * @version:         Current version of info.
- * @asic_type:       Asic type.
- * @asic_rev:        Asic revision.
- * @fw_status:       Firmware status.
- * @fw_heartbeat:    Firmware heartbeat counter.
- * @serial_num:      Serial number.
- * @fw_version:      Firmware version.
+ * union ionic_dev_info_regs - Device info register format (read-only)
+ * @signature:       Signature value of 0x44455649 ('DEVI')
+ * @version:         Current version of info
+ * @asic_type:       Asic type
+ * @asic_rev:        Asic revision
+ * @fw_status:       Firmware status
+ * @fw_heartbeat:    Firmware heartbeat counter
+ * @serial_num:      Serial number
+ * @fw_version:      Firmware version
  */
 union ionic_dev_info_regs {
 #define IONIC_DEVINFO_FWVERS_BUFLEN 32
@@ -2536,10 +2706,10 @@ union ionic_dev_info_regs {
 
 /**
  * union ionic_dev_cmd_regs - Device command register format (read-write)
- * @doorbell:        Device Cmd Doorbell, write-only.
+ * @doorbell:        Device Cmd Doorbell, write-only
  *                   Write a 1 to signal device to process cmd,
  *                   poll done for completion.
- * @done:            Done indicator, bit 0 == 1 when command is complete.
+ * @done:            Done indicator, bit 0 == 1 when command is complete
  * @cmd:             Opcode-specific command bytes
  * @comp:            Opcode-specific response bytes
  * @data:            Opcode-specific side-data
@@ -2557,7 +2727,7 @@ union ionic_dev_cmd_regs {
 };
 
 /**
- * union ionic_dev_regs - Device register format in for bar 0 page 0
+ * union ionic_dev_regs - Device register format for bar 0 page 0
  * @info:            Device info registers
  * @devcmd:          Device command registers
  */
@@ -2572,6 +2742,7 @@ union ionic_dev_regs {
 union ionic_adminq_cmd {
 	struct ionic_admin_cmd cmd;
 	struct ionic_nop_cmd nop;
+	struct ionic_q_identify_cmd q_identify;
 	struct ionic_q_init_cmd q_init;
 	struct ionic_q_control_cmd q_control;
 	struct ionic_lif_setattr_cmd lif_setattr;
@@ -2588,6 +2759,7 @@ union ionic_adminq_cmd {
 union ionic_adminq_comp {
 	struct ionic_admin_comp comp;
 	struct ionic_nop_comp nop;
+	struct ionic_q_identify_comp q_identify;
 	struct ionic_q_init_comp q_init;
 	struct ionic_lif_setattr_comp lif_setattr;
 	struct ionic_lif_getattr_comp lif_getattr;
@@ -2613,14 +2785,14 @@ union ionic_adminq_comp {
 /**
  * struct ionic_doorbell - Doorbell register layout
  * @p_index: Producer index
- * @ring:    Selects the specific ring of the queue to update.
+ * @ring:    Selects the specific ring of the queue to update
  *           Type-specific meaning:
- *              ring=0: Default producer/consumer queue.
+ *              ring=0: Default producer/consumer queue
  *              ring=1: (CQ, EQ) Re-Arm queue.  RDMA CQs
  *              send events to EQs when armed.  EQs send
  *              interrupts when armed.
- * @qid:     The queue id selects the queue destination for the
- *           producer index and flags.
+ * @qid_lo:  Queue destination for the producer index and flags (low bits)
+ * @qid_hi:  Queue destination for the producer index and flags (high bits)
  */
 struct ionic_doorbell {
 	__le16 p_index;
@@ -2653,6 +2825,7 @@ struct ionic_identity {
 	union ionic_lif_identity lif;
 	union ionic_port_identity port;
 	union ionic_qos_identity qos;
+	union ionic_q_identity txq;
 };
 
 #endif /* _IONIC_IF_H_ */
-- 
cgit v1.2.3


From a836c352291d4ad4031743a97a61f7916fe519b7 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:29 -0700
Subject: ionic: protect vf calls from fw reset

When going into a firmware upgrade cycle, we set the device as
not present to keep some user commands from trying to change
the driver while we're only half there.  Unfortunately, the
ndo_vf_* calls don't check netif_device_present() so we need
to add a check in the callbacks.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 26 ++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 0049f537ee40..5f63c611d1fd 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1707,7 +1707,7 @@ int ionic_stop(struct net_device *netdev)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
-	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+	if (!netif_device_present(netdev))
 		return 0;
 
 	ionic_stop_queues(lif);
@@ -1724,6 +1724,9 @@ static int ionic_get_vf_config(struct net_device *netdev,
 	struct ionic *ionic = lif->ionic;
 	int ret = 0;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_read(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1751,6 +1754,9 @@ static int ionic_get_vf_stats(struct net_device *netdev, int vf,
 	struct ionic_lif_stats *vs;
 	int ret = 0;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_read(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1786,6 +1792,9 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	if (!(is_zero_ether_addr(mac) || is_valid_ether_addr(mac)))
 		return -EINVAL;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1817,6 +1826,9 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 	if (proto != htons(ETH_P_8021Q))
 		return -EPROTONOSUPPORT;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1843,6 +1855,9 @@ static int ionic_set_vf_rate(struct net_device *netdev, int vf,
 	if (tx_min)
 		return -EINVAL;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1865,6 +1880,9 @@ static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set)
 	u8 data = set;  /* convert to u8 for config */
 	int ret;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1887,6 +1905,9 @@ static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set)
 	u8 data = set;  /* convert to u8 for config */
 	int ret;
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
@@ -1923,6 +1944,9 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set)
 		return -EINVAL;
 	}
 
+	if (!netif_device_present(netdev))
+		return -EBUSY;
+
 	down_write(&ionic->vf_op_lock);
 
 	if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
-- 
cgit v1.2.3


From cba155d591aa28689332bc568632d2f868690be1 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:30 -0700
Subject: ionic: add support for more xcvr types

Add a couple more SFP and QSFP transceiver types to our
ethtool get link ksettings.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 3f9a73aaef61..170e72f31197 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -159,6 +159,8 @@ static int ionic_get_link_ksettings(struct net_device *netdev,
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100000baseSR4_Full);
 		break;
+	case IONIC_XCVR_PID_QSFP_100G_CWDM4:
+	case IONIC_XCVR_PID_QSFP_100G_PSM4:
 	case IONIC_XCVR_PID_QSFP_100G_LR4:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100000baseLR4_ER4_Full);
@@ -178,6 +180,7 @@ static int ionic_get_link_ksettings(struct net_device *netdev,
 		break;
 	case IONIC_XCVR_PID_SFP_25GBASE_SR:
 	case IONIC_XCVR_PID_SFP_25GBASE_AOC:
+	case IONIC_XCVR_PID_SFP_25GBASE_ACC:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseSR_Full);
 		break;
-- 
cgit v1.2.3


From 62ba8766f775e5e26c21731c695f68541d504ea6 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:31 -0700
Subject: ionic: shorter dev cmd wait time

Shorten our msleep time while polling for the dev command
request to finish.  Yes, checkpatch.pl complains that the
msleep might actually go longer - that won't hurt, but we'll
take the shorter time if we can get it.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 8e2436d14621..c3f0f84164d3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -358,7 +358,7 @@ try_again:
 		done = ionic_dev_cmd_done(idev);
 		if (done)
 			break;
-		msleep(20);
+		msleep(5);
 		hb = ionic_heartbeat_check(ionic);
 	} while (!done && !hb && time_before(jiffies, max_wait));
 	duration = jiffies - start_time;
-- 
cgit v1.2.3


From 5c7843112543c7726e7fe31ecc76476f296b7960 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:32 -0700
Subject: ionic: reset device at probe

Once we're talking to the device, tell it to reset to
be sure we've got a fresh, clean environment.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index c3f0f84164d3..92110abcff96 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -415,6 +415,7 @@ int ionic_setup(struct ionic *ionic)
 	err = ionic_dev_setup(ionic);
 	if (err)
 		return err;
+	ionic_reset(ionic);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 36ac2c50924892a28e17ff463e354fec7650ee19 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:33 -0700
Subject: ionic: ionic_intr_free parameter change

Change the ionic_intr_free parameter from struct ionic_lif to
struct ionic since that's what it actually cares about.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 5f63c611d1fd..9bf142446645 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -197,10 +197,10 @@ static int ionic_intr_alloc(struct ionic_lif *lif, struct ionic_intr_info *intr)
 	return 0;
 }
 
-static void ionic_intr_free(struct ionic_lif *lif, int index)
+static void ionic_intr_free(struct ionic *ionic, int index)
 {
-	if (index != INTR_INDEX_NOT_ASSIGNED && index < lif->ionic->nintrs)
-		clear_bit(index, lif->ionic->intrs);
+	if (index != INTR_INDEX_NOT_ASSIGNED && index < ionic->nintrs)
+		clear_bit(index, ionic->intrs);
 }
 
 static int ionic_qcq_enable(struct ionic_qcq *qcq)
@@ -310,7 +310,7 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		irq_set_affinity_hint(qcq->intr.vector, NULL);
 		devm_free_irq(dev, qcq->intr.vector, &qcq->napi);
 		qcq->intr.vector = 0;
-		ionic_intr_free(lif, qcq->intr.index);
+		ionic_intr_free(lif->ionic, qcq->intr.index);
 	}
 
 	devm_kfree(dev, qcq->cq.info);
@@ -356,7 +356,7 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq,
 				      struct ionic_qcq *n_qcq)
 {
 	if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) {
-		ionic_intr_free(n_qcq->cq.lif, n_qcq->intr.index);
+		ionic_intr_free(n_qcq->cq.lif->ionic, n_qcq->intr.index);
 		n_qcq->flags &= ~IONIC_QCQ_F_INTR;
 	}
 
@@ -508,7 +508,7 @@ err_out_free_irq:
 		devm_free_irq(dev, new->intr.vector, &new->napi);
 err_out_free_intr:
 	if (flags & IONIC_QCQ_F_INTR)
-		ionic_intr_free(lif, new->intr.index);
+		ionic_intr_free(lif->ionic, new->intr.index);
 err_out:
 	dev_err(dev, "qcq alloc of %s%d failed %d\n", name, index, err);
 	return err;
-- 
cgit v1.2.3


From c06107cabea356db62f45bf8049a260c238fadf2 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:34 -0700
Subject: ionic: more ionic name tweaks

Fix up a few more local names that need an "ionic" prefix.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_dev.h     | 10 +++++-----
 drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 13 +++++++------
 drivers/net/ethernet/pensando/ionic/ionic_lif.c     |  4 ++--
 3 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 33519a8765eb..525434f10025 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -182,7 +182,7 @@ struct ionic_desc_info {
 	void *cb_arg;
 };
 
-#define QUEUE_NAME_MAX_SZ		32
+#define IONIC_QUEUE_NAME_MAX_SZ		32
 
 struct ionic_queue {
 	u64 dbell_count;
@@ -207,14 +207,14 @@ struct ionic_queue {
 	unsigned int desc_size;
 	unsigned int sg_desc_size;
 	unsigned int pid;
-	char name[QUEUE_NAME_MAX_SZ];
+	char name[IONIC_QUEUE_NAME_MAX_SZ];
 };
 
-#define INTR_INDEX_NOT_ASSIGNED		-1
-#define INTR_NAME_MAX_SZ		32
+#define IONIC_INTR_INDEX_NOT_ASSIGNED	-1
+#define IONIC_INTR_NAME_MAX_SZ		32
 
 struct ionic_intr_info {
-	char name[INTR_NAME_MAX_SZ];
+	char name[IONIC_INTR_NAME_MAX_SZ];
 	unsigned int index;
 	unsigned int vector;
 	u64 rearm_count;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 170e72f31197..f7e3ce3de04d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -12,10 +12,11 @@
 #include "ionic_stats.h"
 
 static const char ionic_priv_flags_strings[][ETH_GSTRING_LEN] = {
-#define PRIV_F_SW_DBG_STATS		BIT(0)
+#define IONIC_PRIV_F_SW_DBG_STATS	BIT(0)
 	"sw-dbg-stats",
 };
-#define PRIV_FLAGS_COUNT ARRAY_SIZE(ionic_priv_flags_strings)
+
+#define IONIC_PRIV_FLAGS_COUNT ARRAY_SIZE(ionic_priv_flags_strings)
 
 static void ionic_get_stats_strings(struct ionic_lif *lif, u8 *buf)
 {
@@ -58,7 +59,7 @@ static int ionic_get_sset_count(struct net_device *netdev, int sset)
 		count = ionic_get_stats_count(lif);
 		break;
 	case ETH_SS_PRIV_FLAGS:
-		count = PRIV_FLAGS_COUNT;
+		count = IONIC_PRIV_FLAGS_COUNT;
 		break;
 	}
 	return count;
@@ -75,7 +76,7 @@ static void ionic_get_strings(struct net_device *netdev,
 		break;
 	case ETH_SS_PRIV_FLAGS:
 		memcpy(buf, ionic_priv_flags_strings,
-		       PRIV_FLAGS_COUNT * ETH_GSTRING_LEN);
+		       IONIC_PRIV_FLAGS_COUNT * ETH_GSTRING_LEN);
 		break;
 	}
 }
@@ -557,7 +558,7 @@ static u32 ionic_get_priv_flags(struct net_device *netdev)
 	u32 priv_flags = 0;
 
 	if (test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state))
-		priv_flags |= PRIV_F_SW_DBG_STATS;
+		priv_flags |= IONIC_PRIV_F_SW_DBG_STATS;
 
 	return priv_flags;
 }
@@ -567,7 +568,7 @@ static int ionic_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 	struct ionic_lif *lif = netdev_priv(netdev);
 
 	clear_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state);
-	if (priv_flags & PRIV_F_SW_DBG_STATS)
+	if (priv_flags & IONIC_PRIV_F_SW_DBG_STATS)
 		set_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state);
 
 	return 0;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 9bf142446645..4da94c07d1d3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -199,7 +199,7 @@ static int ionic_intr_alloc(struct ionic_lif *lif, struct ionic_intr_info *intr)
 
 static void ionic_intr_free(struct ionic *ionic, int index)
 {
-	if (index != INTR_INDEX_NOT_ASSIGNED && index < ionic->nintrs)
+	if (index != IONIC_INTR_INDEX_NOT_ASSIGNED && index < ionic->nintrs)
 		clear_bit(index, ionic->intrs);
 }
 
@@ -455,7 +455,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type,
 			cpumask_set_cpu(new->intr.cpu,
 					&new->intr.affinity_mask);
 	} else {
-		new->intr.index = INTR_INDEX_NOT_ASSIGNED;
+		new->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED;
 	}
 
 	new->cq.info = devm_kzalloc(dev, sizeof(*new->cq.info) * num_descs,
-- 
cgit v1.2.3


From f64e0c5698b7b1abb08b3d5bc07f95db45e87d76 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 11 May 2020 17:59:35 -0700
Subject: ionic: add more ethtool stats

Add hardware port stats and a few more driver collected
statistics to the ethtool stats output.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c   |   4 +-
 drivers/net/ethernet/pensando/ionic/ionic_lif.h   |  15 ++-
 drivers/net/ethernet/pensando/ionic/ionic_stats.c | 136 +++++++++++++++++++++-
 drivers/net/ethernet/pensando/ionic/ionic_stats.h |   6 +
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c  |  22 ++--
 5 files changed, 170 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 4da94c07d1d3..80b4d8332109 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -792,8 +792,8 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget)
 	return max(n_work, a_work);
 }
 
-static void ionic_get_stats64(struct net_device *netdev,
-			      struct rtnl_link_stats64 *ns)
+void ionic_get_stats64(struct net_device *netdev,
+		       struct rtnl_link_stats64 *ns)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	struct ionic_lif_stats *ls;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 1a30f0fb20b9..c3428034a17b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -20,11 +20,13 @@ struct ionic_tx_stats {
 	u64 bytes;
 	u64 clean;
 	u64 linearize;
-	u64 no_csum;
+	u64 csum_none;
 	u64 csum;
 	u64 crc32_csum;
 	u64 tso;
+	u64 tso_bytes;
 	u64 frags;
+	u64 vlan_inserted;
 	u64 sg_cntr[IONIC_MAX_NUM_SG_CNTR];
 };
 
@@ -38,6 +40,7 @@ struct ionic_rx_stats {
 	u64 csum_error;
 	u64 buffers_posted;
 	u64 dropped;
+	u64 vlan_stripped;
 };
 
 #define IONIC_QCQ_F_INITED		BIT(0)
@@ -114,11 +117,17 @@ struct ionic_lif_sw_stats {
 	u64 rx_packets;
 	u64 rx_bytes;
 	u64 tx_tso;
-	u64 tx_no_csum;
+	u64 tx_tso_bytes;
+	u64 tx_csum_none;
 	u64 tx_csum;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
 	u64 rx_csum_error;
+	u64 hw_tx_dropped;
+	u64 hw_rx_dropped;
+	u64 hw_rx_over_errors;
+	u64 hw_rx_missed_errors;
+	u64 hw_tx_aborted_errors;
 };
 
 enum ionic_lif_state_flags {
@@ -240,6 +249,8 @@ static inline u32 ionic_coal_hw_to_usec(struct ionic *ionic, u32 units)
 }
 
 void ionic_link_status_check_request(struct ionic_lif *lif);
+void ionic_get_stats64(struct net_device *netdev,
+		       struct rtnl_link_stats64 *ns);
 void ionic_lif_deferred_enqueue(struct ionic_deferred *def,
 				struct ionic_deferred_work *work);
 int ionic_lifs_alloc(struct ionic *ionic);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index 8f2a8fb029f1..2a1885da58a6 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -15,11 +15,109 @@ static const struct ionic_stat_desc ionic_lif_stats_desc[] = {
 	IONIC_LIF_STAT_DESC(rx_packets),
 	IONIC_LIF_STAT_DESC(rx_bytes),
 	IONIC_LIF_STAT_DESC(tx_tso),
-	IONIC_LIF_STAT_DESC(tx_no_csum),
+	IONIC_LIF_STAT_DESC(tx_tso_bytes),
+	IONIC_LIF_STAT_DESC(tx_csum_none),
 	IONIC_LIF_STAT_DESC(tx_csum),
 	IONIC_LIF_STAT_DESC(rx_csum_none),
 	IONIC_LIF_STAT_DESC(rx_csum_complete),
 	IONIC_LIF_STAT_DESC(rx_csum_error),
+	IONIC_LIF_STAT_DESC(hw_tx_dropped),
+	IONIC_LIF_STAT_DESC(hw_rx_dropped),
+	IONIC_LIF_STAT_DESC(hw_rx_over_errors),
+	IONIC_LIF_STAT_DESC(hw_rx_missed_errors),
+	IONIC_LIF_STAT_DESC(hw_tx_aborted_errors),
+};
+
+static const struct ionic_stat_desc ionic_port_stats_desc[] = {
+	IONIC_PORT_STAT_DESC(frames_rx_ok),
+	IONIC_PORT_STAT_DESC(frames_rx_all),
+	IONIC_PORT_STAT_DESC(frames_rx_bad_fcs),
+	IONIC_PORT_STAT_DESC(frames_rx_bad_all),
+	IONIC_PORT_STAT_DESC(octets_rx_ok),
+	IONIC_PORT_STAT_DESC(octets_rx_all),
+	IONIC_PORT_STAT_DESC(frames_rx_unicast),
+	IONIC_PORT_STAT_DESC(frames_rx_multicast),
+	IONIC_PORT_STAT_DESC(frames_rx_broadcast),
+	IONIC_PORT_STAT_DESC(frames_rx_pause),
+	IONIC_PORT_STAT_DESC(frames_rx_bad_length),
+	IONIC_PORT_STAT_DESC(frames_rx_undersized),
+	IONIC_PORT_STAT_DESC(frames_rx_oversized),
+	IONIC_PORT_STAT_DESC(frames_rx_fragments),
+	IONIC_PORT_STAT_DESC(frames_rx_jabber),
+	IONIC_PORT_STAT_DESC(frames_rx_pripause),
+	IONIC_PORT_STAT_DESC(frames_rx_stomped_crc),
+	IONIC_PORT_STAT_DESC(frames_rx_too_long),
+	IONIC_PORT_STAT_DESC(frames_rx_vlan_good),
+	IONIC_PORT_STAT_DESC(frames_rx_dropped),
+	IONIC_PORT_STAT_DESC(frames_rx_less_than_64b),
+	IONIC_PORT_STAT_DESC(frames_rx_64b),
+	IONIC_PORT_STAT_DESC(frames_rx_65b_127b),
+	IONIC_PORT_STAT_DESC(frames_rx_128b_255b),
+	IONIC_PORT_STAT_DESC(frames_rx_256b_511b),
+	IONIC_PORT_STAT_DESC(frames_rx_512b_1023b),
+	IONIC_PORT_STAT_DESC(frames_rx_1024b_1518b),
+	IONIC_PORT_STAT_DESC(frames_rx_1519b_2047b),
+	IONIC_PORT_STAT_DESC(frames_rx_2048b_4095b),
+	IONIC_PORT_STAT_DESC(frames_rx_4096b_8191b),
+	IONIC_PORT_STAT_DESC(frames_rx_8192b_9215b),
+	IONIC_PORT_STAT_DESC(frames_rx_other),
+	IONIC_PORT_STAT_DESC(frames_tx_ok),
+	IONIC_PORT_STAT_DESC(frames_tx_all),
+	IONIC_PORT_STAT_DESC(frames_tx_bad),
+	IONIC_PORT_STAT_DESC(octets_tx_ok),
+	IONIC_PORT_STAT_DESC(octets_tx_total),
+	IONIC_PORT_STAT_DESC(frames_tx_unicast),
+	IONIC_PORT_STAT_DESC(frames_tx_multicast),
+	IONIC_PORT_STAT_DESC(frames_tx_broadcast),
+	IONIC_PORT_STAT_DESC(frames_tx_pause),
+	IONIC_PORT_STAT_DESC(frames_tx_pripause),
+	IONIC_PORT_STAT_DESC(frames_tx_vlan),
+	IONIC_PORT_STAT_DESC(frames_tx_less_than_64b),
+	IONIC_PORT_STAT_DESC(frames_tx_64b),
+	IONIC_PORT_STAT_DESC(frames_tx_65b_127b),
+	IONIC_PORT_STAT_DESC(frames_tx_128b_255b),
+	IONIC_PORT_STAT_DESC(frames_tx_256b_511b),
+	IONIC_PORT_STAT_DESC(frames_tx_512b_1023b),
+	IONIC_PORT_STAT_DESC(frames_tx_1024b_1518b),
+	IONIC_PORT_STAT_DESC(frames_tx_1519b_2047b),
+	IONIC_PORT_STAT_DESC(frames_tx_2048b_4095b),
+	IONIC_PORT_STAT_DESC(frames_tx_4096b_8191b),
+	IONIC_PORT_STAT_DESC(frames_tx_8192b_9215b),
+	IONIC_PORT_STAT_DESC(frames_tx_other),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_0),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_1),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_2),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_3),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_4),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_5),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_6),
+	IONIC_PORT_STAT_DESC(frames_tx_pri_7),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_0),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_1),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_2),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_3),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_4),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_5),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_6),
+	IONIC_PORT_STAT_DESC(frames_rx_pri_7),
+	IONIC_PORT_STAT_DESC(tx_pripause_0_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_1_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_2_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_3_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_4_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_5_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_6_1us_count),
+	IONIC_PORT_STAT_DESC(tx_pripause_7_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_0_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_1_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_2_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_3_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_4_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_5_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_6_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pripause_7_1us_count),
+	IONIC_PORT_STAT_DESC(rx_pause_1us_count),
+	IONIC_PORT_STAT_DESC(frames_tx_truncated),
 };
 
 static const struct ionic_stat_desc ionic_tx_stats_desc[] = {
@@ -29,6 +127,11 @@ static const struct ionic_stat_desc ionic_tx_stats_desc[] = {
 	IONIC_TX_STAT_DESC(dma_map_err),
 	IONIC_TX_STAT_DESC(linearize),
 	IONIC_TX_STAT_DESC(frags),
+	IONIC_TX_STAT_DESC(tso),
+	IONIC_TX_STAT_DESC(tso_bytes),
+	IONIC_TX_STAT_DESC(csum_none),
+	IONIC_TX_STAT_DESC(csum),
+	IONIC_TX_STAT_DESC(vlan_inserted),
 };
 
 static const struct ionic_stat_desc ionic_rx_stats_desc[] = {
@@ -40,6 +143,7 @@ static const struct ionic_stat_desc ionic_rx_stats_desc[] = {
 	IONIC_RX_STAT_DESC(csum_complete),
 	IONIC_RX_STAT_DESC(csum_error),
 	IONIC_RX_STAT_DESC(dropped),
+	IONIC_RX_STAT_DESC(vlan_stripped),
 };
 
 static const struct ionic_stat_desc ionic_txq_stats_desc[] = {
@@ -62,6 +166,7 @@ static const struct ionic_stat_desc ionic_dbg_napi_stats_desc[] = {
 };
 
 #define IONIC_NUM_LIF_STATS ARRAY_SIZE(ionic_lif_stats_desc)
+#define IONIC_NUM_PORT_STATS ARRAY_SIZE(ionic_port_stats_desc)
 #define IONIC_NUM_TX_STATS ARRAY_SIZE(ionic_tx_stats_desc)
 #define IONIC_NUM_RX_STATS ARRAY_SIZE(ionic_rx_stats_desc)
 #define IONIC_NUM_TX_Q_STATS ARRAY_SIZE(ionic_txq_stats_desc)
@@ -76,6 +181,7 @@ static void ionic_get_lif_stats(struct ionic_lif *lif,
 {
 	struct ionic_tx_stats *tstats;
 	struct ionic_rx_stats *rstats;
+	struct rtnl_link_stats64 ns;
 	struct ionic_qcq *txqcq;
 	struct ionic_qcq *rxqcq;
 	int q_num;
@@ -89,7 +195,8 @@ static void ionic_get_lif_stats(struct ionic_lif *lif,
 			stats->tx_packets += tstats->pkts;
 			stats->tx_bytes += tstats->bytes;
 			stats->tx_tso += tstats->tso;
-			stats->tx_no_csum += tstats->no_csum;
+			stats->tx_tso_bytes += tstats->tso_bytes;
+			stats->tx_csum_none += tstats->csum_none;
 			stats->tx_csum += tstats->csum;
 		}
 
@@ -103,6 +210,13 @@ static void ionic_get_lif_stats(struct ionic_lif *lif,
 			stats->rx_csum_error += rstats->csum_error;
 		}
 	}
+
+	ionic_get_stats64(lif->netdev, &ns);
+	stats->hw_tx_dropped = ns.tx_dropped;
+	stats->hw_rx_dropped = ns.rx_dropped;
+	stats->hw_rx_over_errors = ns.rx_over_errors;
+	stats->hw_rx_missed_errors = ns.rx_missed_errors;
+	stats->hw_tx_aborted_errors = ns.tx_aborted_errors;
 }
 
 static u64 ionic_sw_stats_get_count(struct ionic_lif *lif)
@@ -118,6 +232,9 @@ static u64 ionic_sw_stats_get_count(struct ionic_lif *lif)
 	/* rx stats */
 	total += MAX_Q(lif) * IONIC_NUM_RX_STATS;
 
+	/* port stats */
+	total += IONIC_NUM_PORT_STATS;
+
 	if (test_bit(IONIC_LIF_F_UP, lif->state) &&
 	    test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state)) {
 		/* tx debug stats */
@@ -144,6 +261,13 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 		snprintf(*buf, ETH_GSTRING_LEN, ionic_lif_stats_desc[i].name);
 		*buf += ETH_GSTRING_LEN;
 	}
+
+	for (i = 0; i < IONIC_NUM_PORT_STATS; i++) {
+		snprintf(*buf, ETH_GSTRING_LEN,
+			 ionic_port_stats_desc[i].name);
+		*buf += ETH_GSTRING_LEN;
+	}
+
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
 		for (i = 0; i < IONIC_NUM_TX_STATS; i++) {
 			snprintf(*buf, ETH_GSTRING_LEN, "tx_%d_%s",
@@ -225,6 +349,7 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 
 static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 {
+	struct ionic_port_stats *port_stats;
 	struct ionic_lif_sw_stats lif_stats;
 	struct ionic_qcq *txqcq, *rxqcq;
 	struct ionic_tx_stats *txstats;
@@ -238,6 +363,13 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 		(*buf)++;
 	}
 
+	port_stats = &lif->ionic->idev.port_info->stats;
+	for (i = 0; i < IONIC_NUM_PORT_STATS; i++) {
+		**buf = IONIC_READ_STAT_LE64(port_stats,
+					     &ionic_port_stats_desc[i]);
+		(*buf)++;
+	}
+
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
 		txstats = &lif_to_txstats(lif, q_num);
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.h b/drivers/net/ethernet/pensando/ionic/ionic_stats.h
index d2c1122a2c6e..3f543512616e 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.h
@@ -11,6 +11,9 @@
 	.offset = IONIC_STAT_TO_OFFSET(type, stat_name) \
 }
 
+#define IONIC_PORT_STAT_DESC(stat_name) \
+	IONIC_STAT_DESC(struct ionic_port_stats, stat_name)
+
 #define IONIC_LIF_STAT_DESC(stat_name) \
 	IONIC_STAT_DESC(struct ionic_lif_sw_stats, stat_name)
 
@@ -45,6 +48,9 @@ extern const int ionic_num_stats_grps;
 #define IONIC_READ_STAT64(base_ptr, desc_ptr) \
 	(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
 
+#define IONIC_READ_STAT_LE64(base_ptr, desc_ptr) \
+	__le64_to_cpu(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
+
 struct ionic_stat_desc {
 	char name[ETH_GSTRING_LEN];
 	u64 offset;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 6b14e55a6780..b7f900c11834 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -214,10 +214,11 @@ static void ionic_rx_clean(struct ionic_queue *q,
 		     (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_IP_BAD)))
 		stats->csum_error++;
 
-	if (likely(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
-		if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_VLAN)
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-					       le16_to_cpu(comp->vlan_tci));
+	if (likely(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+	    (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_VLAN)) {
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       le16_to_cpu(comp->vlan_tci));
+		stats->vlan_stripped++;
 	}
 
 	if (le16_to_cpu(comp->len) <= q->lif->rx_copybreak)
@@ -860,6 +861,7 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb)
 	stats->pkts += total_pkts;
 	stats->bytes += total_bytes;
 	stats->tso++;
+	stats->tso_bytes += total_bytes;
 
 	return 0;
 
@@ -898,9 +900,12 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb)
 				  flags, skb_shinfo(skb)->nr_frags, dma_addr);
 	desc->cmd = cpu_to_le64(cmd);
 	desc->len = cpu_to_le16(skb_headlen(skb));
-	desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb));
 	desc->csum_start = cpu_to_le16(skb_checksum_start_offset(skb));
 	desc->csum_offset = cpu_to_le16(skb->csum_offset);
+	if (has_vlan) {
+		desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb));
+		stats->vlan_inserted++;
+	}
 
 	if (skb->csum_not_inet)
 		stats->crc32_csum++;
@@ -935,9 +940,12 @@ static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb)
 				  flags, skb_shinfo(skb)->nr_frags, dma_addr);
 	desc->cmd = cpu_to_le64(cmd);
 	desc->len = cpu_to_le16(skb_headlen(skb));
-	desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb));
+	if (has_vlan) {
+		desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb));
+		stats->vlan_inserted++;
+	}
 
-	stats->no_csum++;
+	stats->csum_none++;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 527c1e615b4c6616abb5c7b14c2ff5b04a029175 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 12 May 2020 14:24:34 +0100
Subject: sfc: actually wire up siena_check_caps()

Assign it to siena_a0_nic_type.check_caps function pointer.

Fixes: be904b855200 ("sfc: make capability checking a nic_type function")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/siena.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index ed1cb6caa69d..d8b052979b1b 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -1093,4 +1093,5 @@ const struct efx_nic_type siena_a0_nic_type = {
 			     1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT |
 			     1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT),
 	.rx_hash_key_size = 16,
+	.check_caps = siena_check_caps,
 };
-- 
cgit v1.2.3


From 1b0cde4091877cd7fe4b29f67645cc391b86c9ca Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 12 May 2020 14:24:58 +0100
Subject: sfc: siena_check_caps() can be static

Reported-by: Jakub Kicinski <kuba@kernel.org>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/siena.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index d8b052979b1b..891e9fb6abec 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -948,8 +948,8 @@ fail:
 
 #endif /* CONFIG_SFC_MTD */
 
-unsigned int siena_check_caps(const struct efx_nic *efx,
-			      u8 flag, u32 offset)
+static unsigned int siena_check_caps(const struct efx_nic *efx,
+				     u8 flag, u32 offset)
 {
 	/* Siena did not support MC_CMD_GET_CAPABILITIES */
 	return 0;
-- 
cgit v1.2.3


From 14c129e30152f7d74c8b25ec06ae742f4291e166 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 4 May 2020 08:30:09 +0300
Subject: {IB/net}/mlx5: Simplify don't trap code

The fs_core already supports creation of rules with multiple
actions/destinations. Refactor fs_core to handle the case
when don't trap rule is created with destination. Adapt the
calling code in the driver.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                 | 47 +++-----------
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 79 +++++++++++++----------
 2 files changed, 56 insertions(+), 70 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 65e0e24d463b..566b42f3fb18 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3698,12 +3698,13 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		if (!dest_num)
 			rule_dst = NULL;
 	} else {
+		if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)
+			flow_act.action |=
+				MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
 		if (is_egress)
 			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-		else
-			flow_act.action |=
-				dest_num ?  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
-					MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+		else if (dest_num)
+			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
 	if ((spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG)  &&
@@ -3747,30 +3748,6 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0, NULL);
 }
 
-static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *dev,
-							  struct mlx5_ib_flow_prio *ft_prio,
-							  struct ib_flow_attr *flow_attr,
-							  struct mlx5_flow_destination *dst)
-{
-	struct mlx5_ib_flow_handler *handler_dst = NULL;
-	struct mlx5_ib_flow_handler *handler = NULL;
-
-	handler = create_flow_rule(dev, ft_prio, flow_attr, NULL);
-	if (!IS_ERR(handler)) {
-		handler_dst = create_flow_rule(dev, ft_prio,
-					       flow_attr, dst);
-		if (IS_ERR(handler_dst)) {
-			mlx5_del_flow_rules(handler->rule);
-			ft_prio->refcount--;
-			kfree(handler);
-			handler = handler_dst;
-		} else {
-			list_add(&handler_dst->list, &handler->list);
-		}
-	}
-
-	return handler;
-}
 enum {
 	LEFTOVERS_MC,
 	LEFTOVERS_UC,
@@ -3974,15 +3951,11 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	}
 
 	if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
-		if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)  {
-			handler = create_dont_trap_rule(dev, ft_prio,
-							flow_attr, dst);
-		} else {
-			underlay_qpn = (mqp->flags & MLX5_IB_QP_UNDERLAY) ?
-					mqp->underlay_qpn : 0;
-			handler = _create_flow_rule(dev, ft_prio, flow_attr,
-						    dst, underlay_qpn, ucmd);
-		}
+		underlay_qpn = (mqp->flags & IB_QP_CREATE_SOURCE_QPN) ?
+				       mqp->underlay_qpn :
+				       0;
+		handler = _create_flow_rule(dev, ft_prio, flow_attr, dst,
+					    underlay_qpn, ucmd);
 	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
 		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
 		handler = create_leftovers_rule(dev, ft_prio, flow_attr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d5defe09339a..705f433e2590 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -254,7 +254,7 @@ static void del_sw_flow_group(struct fs_node *node);
 static void del_sw_fte(struct fs_node *node);
 static void del_sw_prio(struct fs_node *node);
 static void del_sw_ns(struct fs_node *node);
-/* Delete rule (destination) is special case that 
+/* Delete rule (destination) is special case that
  * requires to lock the FTE for all the deletion process.
  */
 static void del_sw_hw_rule(struct fs_node *node);
@@ -1899,48 +1899,61 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
 	static const struct mlx5_flow_spec zero_spec = {};
-	struct mlx5_flow_destination gen_dest = {};
+	struct mlx5_flow_destination *gen_dest = NULL;
 	struct mlx5_flow_table *next_ft = NULL;
 	struct mlx5_flow_handle *handle = NULL;
 	u32 sw_action = flow_act->action;
 	struct fs_prio *prio;
+	int i;
 
 	if (!spec)
 		spec = &zero_spec;
 
-	fs_get_obj(prio, ft->node.parent);
-	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
-		if (!fwd_next_prio_supported(ft))
-			return ERR_PTR(-EOPNOTSUPP);
-		if (num_dest)
-			return ERR_PTR(-EINVAL);
-		mutex_lock(&root->chain_lock);
-		next_ft = find_next_chained_ft(prio);
-		if (next_ft) {
-			gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-			gen_dest.ft = next_ft;
-			dest = &gen_dest;
-			num_dest = 1;
-			flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		} else {
-			mutex_unlock(&root->chain_lock);
-			return ERR_PTR(-EOPNOTSUPP);
-		}
-	}
+	if (!(sw_action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO))
+		return _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 
-	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
+	if (!fwd_next_prio_supported(ft))
+		return ERR_PTR(-EOPNOTSUPP);
 
-	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
-		if (!IS_ERR_OR_NULL(handle) &&
-		    (list_empty(&handle->rule[0]->next_ft))) {
-			mutex_lock(&next_ft->lock);
-			list_add(&handle->rule[0]->next_ft,
-				 &next_ft->fwd_rules);
-			mutex_unlock(&next_ft->lock);
-			handle->rule[0]->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
-		}
-		mutex_unlock(&root->chain_lock);
-	}
+	mutex_lock(&root->chain_lock);
+	fs_get_obj(prio, ft->node.parent);
+	next_ft = find_next_chained_ft(prio);
+	if (!next_ft) {
+		handle = ERR_PTR(-EOPNOTSUPP);
+		goto unlock;
+	}
+
+	gen_dest = kcalloc(num_dest + 1, sizeof(*dest),
+			   GFP_KERNEL);
+	if (!gen_dest) {
+		handle = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
+	for (i = 0; i < num_dest; i++)
+		gen_dest[i] = dest[i];
+	gen_dest[i].type =
+		MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	gen_dest[i].ft = next_ft;
+	dest = gen_dest;
+	num_dest++;
+	flow_act->action &=
+		~MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
+	if (IS_ERR(handle))
+		goto unlock;
+
+	if (list_empty(&handle->rule[num_dest - 1]->next_ft)) {
+		mutex_lock(&next_ft->lock);
+		list_add(&handle->rule[num_dest - 1]->next_ft,
+			 &next_ft->fwd_rules);
+		mutex_unlock(&next_ft->lock);
+		handle->rule[num_dest - 1]->sw_action =
+			MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+	}
+unlock:
+	mutex_unlock(&root->chain_lock);
+	kfree(gen_dest);
 	return handle;
 }
 EXPORT_SYMBOL(mlx5_add_flow_rules);
-- 
cgit v1.2.3


From 9254f8ed15b6dcc9b04b9ad32863a7518cc5a5b1 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 4 May 2020 08:30:10 +0300
Subject: net/mlx5: Add support in forward to namespace

Currently, fs_core supports rule of forward the traffic
to continue matching in the next priority, now we add support
to forward the traffic matching in the next namespace.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 57 +++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  2 +
 include/linux/mlx5/fs.h                           |  1 +
 3 files changed, 51 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 705f433e2590..41aa1fa0c69e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -384,6 +384,12 @@ static struct fs_prio *find_prio(struct mlx5_flow_namespace *ns,
 	return NULL;
 }
 
+static bool is_fwd_next_action(u32 action)
+{
+	return action & (MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO |
+			 MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS);
+}
+
 static bool check_valid_spec(const struct mlx5_flow_spec *spec)
 {
 	int i;
@@ -502,7 +508,7 @@ static void del_sw_hw_rule(struct fs_node *node)
 	fs_get_obj(rule, node);
 	fs_get_obj(fte, rule->node.parent);
 	trace_mlx5_fs_del_rule(rule);
-	if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
+	if (is_fwd_next_action(rule->sw_action)) {
 		mutex_lock(&rule->dest_attr.ft->lock);
 		list_del(&rule->next_ft);
 		mutex_unlock(&rule->dest_attr.ft->lock);
@@ -826,6 +832,36 @@ static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio)
 	return find_closest_ft(prio, true);
 }
 
+static struct fs_prio *find_fwd_ns_prio(struct mlx5_flow_root_namespace *root,
+					struct mlx5_flow_namespace *ns)
+{
+	struct mlx5_flow_namespace *root_ns = &root->ns;
+	struct fs_prio *iter_prio;
+	struct fs_prio *prio;
+
+	fs_get_obj(prio, ns->node.parent);
+	list_for_each_entry(iter_prio, &root_ns->node.children, node.list) {
+		if (iter_prio == prio &&
+		    !list_is_last(&prio->node.children, &iter_prio->node.list))
+			return list_next_entry(iter_prio, node.list);
+	}
+	return NULL;
+}
+
+static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft,
+						struct mlx5_flow_act *flow_act)
+{
+	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
+	struct fs_prio *prio;
+
+	if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS)
+		prio = find_fwd_ns_prio(root, ft->ns);
+	else
+		fs_get_obj(prio, ft->node.parent);
+
+	return (prio) ? find_next_chained_ft(prio) : NULL;
+}
+
 static int connect_fts_in_prio(struct mlx5_core_dev *dev,
 			       struct fs_prio *prio,
 			       struct mlx5_flow_table *ft)
@@ -976,6 +1012,10 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev,
 	list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules);
 	mutex_unlock(&old_next_ft->lock);
 	list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) {
+		if ((iter->sw_action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS) &&
+		    iter->ft->ns == new_next_ft->ns)
+			continue;
+
 		err = _mlx5_modify_rule_destination(iter, &dest);
 		if (err)
 			pr_err("mlx5_core: failed to modify rule to point on flow table %d\n",
@@ -1077,6 +1117,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	next_ft = unmanaged ? ft_attr->next_ft :
 			      find_next_chained_ft(fs_prio);
 	ft->def_miss_action = ns->def_miss_action;
+	ft->ns = ns;
 	err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft);
 	if (err)
 		goto free_ft;
@@ -1903,21 +1944,19 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	struct mlx5_flow_table *next_ft = NULL;
 	struct mlx5_flow_handle *handle = NULL;
 	u32 sw_action = flow_act->action;
-	struct fs_prio *prio;
 	int i;
 
 	if (!spec)
 		spec = &zero_spec;
 
-	if (!(sw_action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO))
+	if (!is_fwd_next_action(sw_action))
 		return _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 
 	if (!fwd_next_prio_supported(ft))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	mutex_lock(&root->chain_lock);
-	fs_get_obj(prio, ft->node.parent);
-	next_ft = find_next_chained_ft(prio);
+	next_ft = find_next_fwd_ft(ft, flow_act);
 	if (!next_ft) {
 		handle = ERR_PTR(-EOPNOTSUPP);
 		goto unlock;
@@ -1936,8 +1975,8 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	gen_dest[i].ft = next_ft;
 	dest = gen_dest;
 	num_dest++;
-	flow_act->action &=
-		~MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+	flow_act->action &= ~(MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO |
+			      MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS);
 	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 	if (IS_ERR(handle))
@@ -1948,8 +1987,8 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		list_add(&handle->rule[num_dest - 1]->next_ft,
 			 &next_ft->fwd_rules);
 		mutex_unlock(&next_ft->lock);
-		handle->rule[num_dest - 1]->sw_action =
-			MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+		handle->rule[num_dest - 1]->sw_action = sw_action;
+		handle->rule[num_dest - 1]->ft = ft;
 	}
 unlock:
 	mutex_unlock(&root->chain_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 508108c58dae..825b662f809b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -138,6 +138,7 @@ struct fs_node {
 
 struct mlx5_flow_rule {
 	struct fs_node				node;
+	struct mlx5_flow_table			*ft;
 	struct mlx5_flow_destination		dest_attr;
 	/* next_ft should be accessed under chain_lock and only of
 	 * destination type is FWD_NEXT_fT.
@@ -175,6 +176,7 @@ struct mlx5_flow_table {
 	u32				flags;
 	struct rhltable			fgs_hash;
 	enum mlx5_flow_table_miss_action def_miss_action;
+	struct mlx5_flow_namespace	*ns;
 };
 
 struct mlx5_ft_underlay_qp {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index e2d13e074067..6c5aa0a21425 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -42,6 +42,7 @@ enum {
 	MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO	= 1 << 16,
 	MLX5_FLOW_CONTEXT_ACTION_ENCRYPT	= 1 << 17,
 	MLX5_FLOW_CONTEXT_ACTION_DECRYPT	= 1 << 18,
+	MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS	= 1 << 19,
 };
 
 enum {
-- 
cgit v1.2.3


From 3649abe43251de4357bdd6ef0163de25f96554e9 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:10:58 +0200
Subject: net: stmmac: dwmac-meson8b: use FIELD_PREP instead of open-coding it

Use FIELD_PREP() to shift a value to the correct offset based on a
bitmask instead of open-coding the logic.
No functional changes.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index a3934ca6a043..c9ec0cb68082 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2016 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/device.h>
@@ -32,7 +33,6 @@
 #define PRG_ETH0_CLK_M250_SEL_SHIFT	4
 #define PRG_ETH0_CLK_M250_SEL_MASK	GENMASK(4, 4)
 
-#define PRG_ETH0_TXDLY_SHIFT		5
 #define PRG_ETH0_TXDLY_MASK		GENMASK(6, 5)
 
 /* divider for the result of m250_sel */
@@ -262,7 +262,8 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 					PRG_ETH0_INVERTED_RMII_CLK, 0);
 
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TXDLY_MASK,
-					tx_dly_val << PRG_ETH0_TXDLY_SHIFT);
+					FIELD_PREP(PRG_ETH0_TXDLY_MASK,
+						   tx_dly_val));
 
 		/* Configure the 125MHz RGMII TX clock, the IP block changes
 		 * the output automatically (= without us having to configure
-- 
cgit v1.2.3


From 889df20305ffeae0a6bbd435761810ba658e223d Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:10:59 +0200
Subject: net: stmmac: dwmac-meson8b: Move the documentation for the TX delay

Move the documentation for the TX delay above the PRG_ETH0_TXDLY_MASK
definition. Future commits will add more registers also with
documentation above their register bit definitions. Move the existing
comment so it will be consistent with the upcoming changes.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index c9ec0cb68082..1d7526ee09dd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -33,6 +33,10 @@
 #define PRG_ETH0_CLK_M250_SEL_SHIFT	4
 #define PRG_ETH0_CLK_M250_SEL_MASK	GENMASK(4, 4)
 
+/* TX clock delay in ns = "8ns / 4 * tx_dly_val" (where 8ns are exactly one
+ * cycle of the 125MHz RGMII TX clock):
+ * 0ns = 0x0, 2ns = 0x1, 4ns = 0x2, 6ns = 0x3
+ */
 #define PRG_ETH0_TXDLY_MASK		GENMASK(6, 5)
 
 /* divider for the result of m250_sel */
@@ -248,10 +252,6 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 	switch (dwmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
-		/* TX clock delay in ns = "8ns / 4 * tx_dly_val" (where
-		 * 8ns are exactly one cycle of the 125MHz RGMII TX clock):
-		 * 0ns = 0x0, 2ns = 0x1, 4ns = 0x2, 6ns = 0x3
-		 */
 		tx_dly_val = dwmac->tx_delay_ns >> 1;
 		/* fall through */
 
-- 
cgit v1.2.3


From c92d1d2311a0513d8f7f8311f5c2b1d7e78005a0 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:11:00 +0200
Subject: net: stmmac: dwmac-meson8b: Add the PRG_ETH0_ADJ_* bits

The PRG_ETH0_ADJ_* are used for applying the RGMII RX delay. The public
datasheets only have very limited description for these registers, but
Jianxin Pan provided more detailed documentation from an (unnamed)
Amlogic engineer. Add the PRG_ETH0_ADJ_* bits along with the improved
description.

Suggested-by: Jianxin Pan <jianxin.pan@amlogic.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 1d7526ee09dd..70075628c58e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -48,6 +48,27 @@
 #define PRG_ETH0_INVERTED_RMII_CLK	BIT(11)
 #define PRG_ETH0_TX_AND_PHY_REF_CLK	BIT(12)
 
+/* Bypass (= 0, the signal from the GPIO input directly connects to the
+ * internal sampling) or enable (= 1) the internal logic for RXEN and RXD[3:0]
+ * timing tuning.
+ */
+#define PRG_ETH0_ADJ_ENABLE		BIT(13)
+/* Controls whether the RXEN and RXD[3:0] signals should be aligned with the
+ * input RX rising/falling edge and sent to the Ethernet internals. This sets
+ * the automatically delay and skew automatically (internally).
+ */
+#define PRG_ETH0_ADJ_SETUP		BIT(14)
+/* An internal counter based on the "timing-adjustment" clock. The counter is
+ * cleared on both, the falling and rising edge of the RX_CLK. This selects the
+ * delay (= the counter value) when to start sampling RXEN and RXD[3:0].
+ */
+#define PRG_ETH0_ADJ_DELAY		GENMASK(19, 15)
+/* Adjusts the skew between each bit of RXEN and RXD[3:0]. If a signal has a
+ * large input delay, the bit for that signal (RXEN = bit 0, RXD[3] = bit 1,
+ * ...) can be configured to be 1 to compensate for a delay of about 1ns.
+ */
+#define PRG_ETH0_ADJ_SKEW		GENMASK(24, 20)
+
 #define MUX_CLK_NUM_PARENTS		2
 
 struct meson8b_dwmac;
-- 
cgit v1.2.3


From e4227bff804fc77e2f78c77470d3fbd2d4a6a8d0 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:11:01 +0200
Subject: net: stmmac: dwmac-meson8b: Fetch the "timing-adjustment" clock

The PRG_ETHERNET registers have a built-in timing adjustment circuit
which can provide the RX delay in RGMII mode. This is driven by an
external (to this IP, but internal to the SoC) clock input. Fetch this
clock as optional (even though it's there on all supported SoCs) since
we just learned about it and existing .dtbs don't specify it.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 70075628c58e..41f3ef6bea66 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -85,6 +85,7 @@ struct meson8b_dwmac {
 	phy_interface_t			phy_mode;
 	struct clk			*rgmii_tx_clk;
 	u32				tx_delay_ns;
+	struct clk			*timing_adj_clk;
 };
 
 struct meson8b_dwmac_clk_configs {
@@ -380,6 +381,13 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 				 &dwmac->tx_delay_ns))
 		dwmac->tx_delay_ns = 2;
 
+	dwmac->timing_adj_clk = devm_clk_get_optional(dwmac->dev,
+						      "timing-adjustment");
+	if (IS_ERR(dwmac->timing_adj_clk)) {
+		ret = PTR_ERR(dwmac->timing_adj_clk);
+		goto err_remove_config_dt;
+	}
+
 	ret = meson8b_init_rgmii_tx_clk(dwmac);
 	if (ret)
 		goto err_remove_config_dt;
-- 
cgit v1.2.3


From a54dc4a4904568fe2c6b2ba249dcc97612affebb Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:11:02 +0200
Subject: net: stmmac: dwmac-meson8b: Make the clock enabling code re-usable

The timing adjustment clock will need similar logic as the RGMII clock:
It has to be enabled in the driver conditionally and when the driver is
unloaded it should be disabled again. Extract the existing code for the
RGMII clock into a new function so it can be re-used.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-meson8b.c    | 23 +++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 41f3ef6bea66..d31f79c455de 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -266,6 +266,22 @@ static int meson_axg_set_phy_mode(struct meson8b_dwmac *dwmac)
 	return 0;
 }
 
+static int meson8b_devm_clk_prepare_enable(struct meson8b_dwmac *dwmac,
+					   struct clk *clk)
+{
+	int ret;
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	devm_add_action_or_reset(dwmac->dev,
+				 (void(*)(void *))clk_disable_unprepare,
+				 dwmac->rgmii_tx_clk);
+
+	return 0;
+}
+
 static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 {
 	int ret;
@@ -299,16 +315,13 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 			return ret;
 		}
 
-		ret = clk_prepare_enable(dwmac->rgmii_tx_clk);
+		ret = meson8b_devm_clk_prepare_enable(dwmac,
+						      dwmac->rgmii_tx_clk);
 		if (ret) {
 			dev_err(dwmac->dev,
 				"failed to enable the RGMII TX clock\n");
 			return ret;
 		}
-
-		devm_add_action_or_reset(dwmac->dev,
-					(void(*)(void *))clk_disable_unprepare,
-					dwmac->rgmii_tx_clk);
 		break;
 
 	case PHY_INTERFACE_MODE_RMII:
-- 
cgit v1.2.3


From 9308c47640d515d16e06a7fdf333c51a39c1b0b1 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Tue, 12 May 2020 23:11:03 +0200
Subject: net: stmmac: dwmac-meson8b: add support for the RX delay
 configuration

Configure the PRG_ETH0_ADJ_* bits to enable or disable the RX delay
based on the various RGMII PHY modes. For now the only supported RX
delay settings are:
- disabled, use for example for phy-mode "rgmii-id"
- 0ns - this is treated identical to "disabled", used for example on
  boards where the PHY provides 2ns TX delay and the PCB trace length
  already adds 2ns RX delay
- 2ns - for whenever the PHY cannot add the RX delay and the traces on
  the PCB don't add any RX delay

Disabling the RX delay (in case u-boot enables it, which is the case
for example on Meson8b Odroid-C1) simply means that PRG_ETH0_ADJ_ENABLE,
PRG_ETH0_ADJ_SETUP, PRG_ETH0_ADJ_DELAY and PRG_ETH0_ADJ_SKEW should be
disabled (just disabling PRG_ETH0_ADJ_ENABLE may be enough, since that
disables the whole re-timing logic - but I find it makes more sense to
clear the other bits as well since they depend on that setting).

u-boot on Odroid-C1 uses the following steps to enable a 2ns RX delay:
- enabling enabling the timing adjustment clock
- enabling the timing adjustment logic by setting PRG_ETH0_ADJ_ENABLE
- setting the PRG_ETH0_ADJ_SETUP bit

The documentation for the PRG_ETH0_ADJ_DELAY and PRG_ETH0_ADJ_SKEW
registers indicates that we can even set different RX delays. However,
I could not find out how this works exactly, so for now we only support
a 2ns RX delay using the exact same way that Odroid-C1's u-boot does.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-meson8b.c    | 85 ++++++++++++++++------
 1 file changed, 62 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index d31f79c455de..234e8b6816ce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -85,6 +85,7 @@ struct meson8b_dwmac {
 	phy_interface_t			phy_mode;
 	struct clk			*rgmii_tx_clk;
 	u32				tx_delay_ns;
+	u32				rx_delay_ns;
 	struct clk			*timing_adj_clk;
 };
 
@@ -284,25 +285,64 @@ static int meson8b_devm_clk_prepare_enable(struct meson8b_dwmac *dwmac,
 
 static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 {
+	u32 tx_dly_config, rx_dly_config, delay_config;
 	int ret;
-	u8 tx_dly_val = 0;
+
+	tx_dly_config = FIELD_PREP(PRG_ETH0_TXDLY_MASK,
+				   dwmac->tx_delay_ns >> 1);
+
+	if (dwmac->rx_delay_ns == 2)
+		rx_dly_config = PRG_ETH0_ADJ_ENABLE | PRG_ETH0_ADJ_SETUP;
+	else
+		rx_dly_config = 0;
 
 	switch (dwmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
+		delay_config = tx_dly_config | rx_dly_config;
+		break;
 	case PHY_INTERFACE_MODE_RGMII_RXID:
-		tx_dly_val = dwmac->tx_delay_ns >> 1;
-		/* fall through */
-
-	case PHY_INTERFACE_MODE_RGMII_ID:
+		delay_config = tx_dly_config;
+		break;
 	case PHY_INTERFACE_MODE_RGMII_TXID:
+		delay_config = rx_dly_config;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RMII:
+		delay_config = 0;
+		break;
+	default:
+		dev_err(dwmac->dev, "unsupported phy-mode %s\n",
+			phy_modes(dwmac->phy_mode));
+		return -EINVAL;
+	};
+
+	if (rx_dly_config & PRG_ETH0_ADJ_ENABLE) {
+		if (!dwmac->timing_adj_clk) {
+			dev_err(dwmac->dev,
+				"The timing-adjustment clock is mandatory for the RX delay re-timing\n");
+			return -EINVAL;
+		}
+
+		/* The timing adjustment logic is driven by a separate clock */
+		ret = meson8b_devm_clk_prepare_enable(dwmac,
+						      dwmac->timing_adj_clk);
+		if (ret) {
+			dev_err(dwmac->dev,
+				"Failed to enable the timing-adjustment clock\n");
+			return ret;
+		}
+	}
+
+	meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TXDLY_MASK |
+				PRG_ETH0_ADJ_ENABLE | PRG_ETH0_ADJ_SETUP |
+				PRG_ETH0_ADJ_DELAY | PRG_ETH0_ADJ_SKEW,
+				delay_config);
+
+	if (phy_interface_mode_is_rgmii(dwmac->phy_mode)) {
 		/* only relevant for RMII mode -> disable in RGMII mode */
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
 					PRG_ETH0_INVERTED_RMII_CLK, 0);
 
-		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TXDLY_MASK,
-					FIELD_PREP(PRG_ETH0_TXDLY_MASK,
-						   tx_dly_val));
-
 		/* Configure the 125MHz RGMII TX clock, the IP block changes
 		 * the output automatically (= without us having to configure
 		 * a register) based on the line-speed (125MHz for Gbit speeds,
@@ -322,24 +362,11 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
 				"failed to enable the RGMII TX clock\n");
 			return ret;
 		}
-		break;
-
-	case PHY_INTERFACE_MODE_RMII:
+	} else {
 		/* invert internal clk_rmii_i to generate 25/2.5 tx_rx_clk */
 		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
 					PRG_ETH0_INVERTED_RMII_CLK,
 					PRG_ETH0_INVERTED_RMII_CLK);
-
-		/* TX clock delay cannot be configured in RMII mode */
-		meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_TXDLY_MASK,
-					0);
-
-		break;
-
-	default:
-		dev_err(dwmac->dev, "unsupported phy-mode %s\n",
-			phy_modes(dwmac->phy_mode));
-		return -EINVAL;
 	}
 
 	/* enable TX_CLK and PHY_REF_CLK generator */
@@ -394,6 +421,18 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 				 &dwmac->tx_delay_ns))
 		dwmac->tx_delay_ns = 2;
 
+	/* use 0ns as fallback since this is what most boards actually use */
+	if (of_property_read_u32(pdev->dev.of_node, "amlogic,rx-delay-ns",
+				 &dwmac->rx_delay_ns))
+		dwmac->rx_delay_ns = 0;
+
+	if (dwmac->rx_delay_ns != 0 && dwmac->rx_delay_ns != 2) {
+		dev_err(&pdev->dev,
+			"The only allowed RX delays values are: 0ns, 2ns");
+		ret = -EINVAL;
+		goto err_remove_config_dt;
+	}
+
 	dwmac->timing_adj_clk = devm_clk_get_optional(dwmac->dev,
 						      "timing-adjustment");
 	if (IS_ERR(dwmac->timing_adj_clk)) {
-- 
cgit v1.2.3


From 6545be82807cc01712411321730656ad8ad30474 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 12 May 2020 18:13:55 +0100
Subject: sfc: fix dereference of table before it is null checked

Currently pointer table is being dereferenced on a null check of
table->must_restore_filters before it is being null checked, leading
to a potential null pointer dereference issue.  Fix this by null
checking table before dereferencing it when checking for a null
table->must_restore_filters.

Addresses-Coverity: ("Dereference before null check")
Fixes: e4fe938cff04 ("sfc: move 'must restore' flags out of ef10-specific nic_data")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/mcdi_filters.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c
index 88de95a8c08c..455a62814fb9 100644
--- a/drivers/net/ethernet/sfc/mcdi_filters.c
+++ b/drivers/net/ethernet/sfc/mcdi_filters.c
@@ -1369,10 +1369,7 @@ void efx_mcdi_filter_table_restore(struct efx_nic *efx)
 
 	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
 
-	if (!table->must_restore_filters)
-		return;
-
-	if (!table)
+	if (!table || !table->must_restore_filters)
 		return;
 
 	down_write(&table->lock);
-- 
cgit v1.2.3


From 5e3768a436bb70c9c3e27aaba6b73f8ef8f5dcf3 Mon Sep 17 00:00:00 2001
From: Daniel González Cabanelas <dgcbueu@gmail.com>
Date: Tue, 12 May 2020 19:59:48 +0200
Subject: net: mvneta: speed down the PHY, if WoL used, to save energy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some PHYs connected to this ethernet hardware support the WoL feature.
But when WoL is enabled and the machine is powered off, the PHY remains
waiting for a magic packet at max speed (i.e. 1Gbps), which is a waste of
energy.

Slow down the PHY speed before stopping the ethernet if WoL is enabled,
and save some energy while the machine is powered off or sleeping.

Tested using an Armada 370 based board (LS421DE) equipped with a Marvell
88E1518 PHY.

Signed-off-by: Daniel González Cabanelas <dgcbueu@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 51889770958d..e0e9e56830c0 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3561,6 +3561,10 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 		    MVNETA_CAUSE_LINK_CHANGE);
 
 	phylink_start(pp->phylink);
+
+	/* We may have called phy_speed_down before */
+	phy_speed_up(pp->dev->phydev);
+
 	netif_tx_start_all_queues(pp->dev);
 }
 
@@ -3568,6 +3572,9 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
+	if (device_may_wakeup(&pp->dev->dev))
+		phy_speed_down(pp->dev->phydev, false);
+
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
@@ -4040,6 +4047,10 @@ static int mvneta_mdio_probe(struct mvneta_port *pp)
 	phylink_ethtool_get_wol(pp->phylink, &wol);
 	device_set_wakeup_capable(&pp->dev->dev, !!wol.supported);
 
+	/* PHY WoL may be enabled but device wakeup disabled */
+	if (wol.supported)
+		device_set_wakeup_enable(&pp->dev->dev, !!wol.wolopts);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 96b8e87838a1acfcb1a168537a44f727dda7f53f Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 14 May 2020 20:41:22 +0800
Subject: net: hns3: modify some incorrect spelling

This patch modifies some incorrect spelling.

Reported-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h            |  2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 14 +++++++-------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 21a736174fda..1ffe8fac702d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -24,7 +24,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_GET_RETA,		/* (VF -> PF) get RETA */
 	HCLGE_MBX_GET_RSS_KEY,		/* (VF -> PF) get RSS key */
 	HCLGE_MBX_GET_MAC_ADDR,		/* (VF -> PF) get MAC addr */
-	HCLGE_MBX_PF_VF_RESP,		/* (PF -> VF) generate respone to VF */
+	HCLGE_MBX_PF_VF_RESP,		/* (PF -> VF) generate response to VF */
 	HCLGE_MBX_GET_BDNUM,		/* (VF -> PF) get BD num */
 	HCLGE_MBX_GET_BUFSIZE,		/* (VF -> PF) get buffer size */
 	HCLGE_MBX_GET_STREAMID,		/* (VF -> PF) get stream id */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 48c115c50db5..26f6f068b01d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -691,7 +691,7 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev,
 	enum hclge_opcode_type cmd;
 	struct hclge_desc desc;
 	int queue_id, group_id;
-	u32 qset_maping[32];
+	u32 qset_mapping[32];
 	int tc_id, qset_id;
 	int pri_id, ret;
 	u32 i;
@@ -746,7 +746,7 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev,
 		if (ret)
 			goto err_tm_map_cmd_send;
 
-		qset_maping[group_id] =
+		qset_mapping[group_id] =
 			le32_to_cpu(bp_to_qs_map_cmd->qs_bit_map);
 	}
 
@@ -756,11 +756,11 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev,
 	for (group_id = 0; group_id < 4; group_id++) {
 		dev_info(&hdev->pdev->dev,
 			 "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
-			 group_id * 256, qset_maping[(u32)(i + 7)],
-			 qset_maping[(u32)(i + 6)], qset_maping[(u32)(i + 5)],
-			 qset_maping[(u32)(i + 4)], qset_maping[(u32)(i + 3)],
-			 qset_maping[(u32)(i + 2)], qset_maping[(u32)(i + 1)],
-			 qset_maping[i]);
+			 group_id * 256, qset_mapping[(u32)(i + 7)],
+			 qset_mapping[(u32)(i + 6)], qset_mapping[(u32)(i + 5)],
+			 qset_mapping[(u32)(i + 4)], qset_mapping[(u32)(i + 3)],
+			 qset_mapping[(u32)(i + 2)], qset_mapping[(u32)(i + 1)],
+			 qset_mapping[i]);
 		i += 8;
 	}
 
-- 
cgit v1.2.3


From 727f514bd677420d4253ad84509710040e808899 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 14 May 2020 20:41:23 +0800
Subject: net: hns3: remove a duplicated printing in hclge_configure()

Since hclge_get_cfg() already has error print, so hclge_configure()
should not print error when calling hclge_get_cfg() fail.

Reported-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 1ff896a9576c..b796d3fb5b0b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1363,10 +1363,8 @@ static int hclge_configure(struct hclge_dev *hdev)
 	int ret;
 
 	ret = hclge_get_cfg(hdev, &cfg);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "get mac mode error %d.\n", ret);
+	if (ret)
 		return ret;
-	}
 
 	hdev->num_vmdq_vport = cfg.vmdq_vport_num;
 	hdev->base_tqp_pid = 0;
-- 
cgit v1.2.3


From cb25a6072b517b34d88f05ae29971c595d77df6e Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 14 May 2020 20:41:24 +0800
Subject: net: hns3: modify an incorrect error log in hclge_mbx_handler()

When handling HCLGE_MBX_GET_LINK_STATUS, PF will return the link
status to the VF, so the error log of hclge_get_link_info() is
incorrect.

Reported-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index ac70fafd15d5..0874ae47cb03 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -742,7 +742,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 			ret = hclge_get_link_info(vport, req);
 			if (ret)
 				dev_err(&hdev->pdev->dev,
-					"PF fail(%d) to get link stat for VF\n",
+					"failed to inform link stat to VF, ret = %d\n",
 					ret);
 			break;
 		case HCLGE_MBX_QUEUE_RESET:
-- 
cgit v1.2.3


From bd13f7e12936b83a363ffada725bdf0fe229f337 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 14 May 2020 20:41:25 +0800
Subject: net: hns3: remove some unused macros

There are some macros defined in hns3_enet.h, but not used in
anywhere.

Reported-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 240ba06cd0eb..60f82ad89957 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -46,23 +46,6 @@ enum hns3_nic_state {
 #define HNS3_RING_CFG_VF_NUM_REG		0x00080
 #define HNS3_RING_ASID_REG			0x0008C
 #define HNS3_RING_EN_REG			0x00090
-#define HNS3_RING_T0_BE_RST			0x00094
-#define HNS3_RING_COULD_BE_RST			0x00098
-#define HNS3_RING_WRR_WEIGHT_REG		0x0009c
-
-#define HNS3_RING_INTMSK_RXWL_REG		0x000A0
-#define HNS3_RING_INTSTS_RX_RING_REG		0x000A4
-#define HNS3_RX_RING_INT_STS_REG		0x000A8
-#define HNS3_RING_INTMSK_TXWL_REG		0x000AC
-#define HNS3_RING_INTSTS_TX_RING_REG		0x000B0
-#define HNS3_TX_RING_INT_STS_REG		0x000B4
-#define HNS3_RING_INTMSK_RX_OVERTIME_REG	0x000B8
-#define HNS3_RING_INTSTS_RX_OVERTIME_REG	0x000BC
-#define HNS3_RING_INTMSK_TX_OVERTIME_REG	0x000C4
-#define HNS3_RING_INTSTS_TX_OVERTIME_REG	0x000C8
-
-#define HNS3_RING_MB_CTRL_REG			0x00100
-#define HNS3_RING_MB_DATA_BASE_REG		0x00200
 
 #define HNS3_TX_REG_OFFSET			0x40
 
-- 
cgit v1.2.3


From 5c6cfd309faa7a1958c14b937ba9b95abb1427de Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 14 May 2020 20:41:26 +0800
Subject: net: hns3: remove unnecessary frag list checking in
 hns3_nic_net_xmit()

The skb_has_frag_list() in hns3_nic_net_xmit() is redundant, since
skb_walk_frags() includes this checking implicitly.

Reported-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index c79d6a391105..9fe40c7773b4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1445,9 +1445,6 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	bd_num += ret;
 
-	if (!skb_has_frag_list(skb))
-		goto out;
-
 	skb_walk_frags(skb, frag_skb) {
 		ret = hns3_fill_skb_to_desc(ring, frag_skb,
 					    DESC_TYPE_FRAGLIST_SKB);
@@ -1456,7 +1453,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 		bd_num += ret;
 	}
-out:
+
 	pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) :
 					(ring->desc_num - 1);
 	ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |=
-- 
cgit v1.2.3


From d639836ab3363f935a9a4336cb4ea3828d0437dd Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:17 +0300
Subject: net: qed: adding hw_err states and handling

Here we introduce qed device error tracking flags and error types.

qed_hw_err_notify is an entrace point to report errors.
It'll notify higher level drivers (qede/qedr/etc) to handle and recover
the error.

List of posible errors comes from hardware interfaces, but could be
extended in future.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h      |  2 ++
 drivers/net/ethernet/qlogic/qed/qed_hw.c   | 32 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_hw.h   | 15 ++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_main.c | 29 +++++++++++++++++++++++++++
 include/linux/qed/qed_if.h                 | 12 +++++++++++
 5 files changed, 90 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index fa41bf08a589..12c40ce3d876 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -1020,6 +1020,8 @@ u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
 void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type);
 void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 4ab8cfaf63d1..90b777019cf5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -837,6 +837,38 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...)
+{
+	char buf[QED_HW_ERR_MAX_STR_SIZE];
+	va_list vl;
+	int len;
+
+	if (fmt) {
+		va_start(vl, fmt);
+		len = vsnprintf(buf, QED_HW_ERR_MAX_STR_SIZE, fmt, vl);
+		va_end(vl);
+
+		if (len > QED_HW_ERR_MAX_STR_SIZE - 1)
+			len = QED_HW_ERR_MAX_STR_SIZE - 1;
+
+		DP_NOTICE(p_hwfn, "%s", buf);
+	}
+
+	/* Fan failure cannot be masked by handling of another HW error */
+	if (p_hwfn->cdev->recov_in_prog &&
+	    err_type != QED_HW_ERR_FAN_FAIL) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_DRV,
+			   "Recovery is in progress. Avoid notifying about HW error %d.\n",
+			   err_type);
+		return;
+	}
+
+	qed_hw_error_occurred(p_hwfn, err_type);
+}
+
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index 505e94db939d..f5b109b04b66 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -315,4 +315,19 @@ int qed_init_fw_data(struct qed_dev *cdev,
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase);
 
+#define QED_HW_ERR_MAX_STR_SIZE 256
+
+/**
+ * @brief qed_hw_err_notify - Notify upper layer driver and management FW
+ *	about a HW error.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param err_type
+ * @param fmt - debug data buffer to send to the MFW
+ * @param ... - buffer format args
+ */
+void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
+		       struct qed_ptt *p_ptt,
+		       enum qed_hw_err_type err_type, char *fmt, ...);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 38a1d26ca9db..d7c9d94e4c59 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -2468,6 +2468,35 @@ void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
 		ops->schedule_recovery_handler(cookie);
 }
 
+char *qed_hw_err_type_descr[] = {
+	[QED_HW_ERR_FAN_FAIL]		= "Fan Failure",
+	[QED_HW_ERR_MFW_RESP_FAIL]	= "MFW Response Failure",
+	[QED_HW_ERR_HW_ATTN]		= "HW Attention",
+	[QED_HW_ERR_DMAE_FAIL]		= "DMAE Failure",
+	[QED_HW_ERR_RAMROD_FAIL]	= "Ramrod Failure",
+	[QED_HW_ERR_FW_ASSERT]		= "FW Assertion",
+	[QED_HW_ERR_LAST]		= "Unknown",
+};
+
+void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
+			   enum qed_hw_err_type err_type)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+	char *err_str;
+
+	if (err_type > QED_HW_ERR_LAST)
+		err_type = QED_HW_ERR_LAST;
+	err_str = qed_hw_err_type_descr[err_type];
+
+	DP_NOTICE(p_hwfn, "HW error occurred [%s]\n", err_str);
+
+	/* Call the HW error handler of the protocol driver
+	 */
+	if (ops && ops->schedule_hw_err_handler)
+		ops->schedule_hw_err_handler(cookie, err_type);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 8f29e0d8a7b3..1b7d9548ee43 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -607,6 +607,16 @@ struct qed_sb_info {
 	struct qed_dev *cdev;
 };
 
+enum qed_hw_err_type {
+	QED_HW_ERR_FAN_FAIL,
+	QED_HW_ERR_MFW_RESP_FAIL,
+	QED_HW_ERR_HW_ATTN,
+	QED_HW_ERR_DMAE_FAIL,
+	QED_HW_ERR_RAMROD_FAIL,
+	QED_HW_ERR_FW_ASSERT,
+	QED_HW_ERR_LAST,
+};
+
 enum qed_dev_type {
 	QED_DEV_TYPE_BB,
 	QED_DEV_TYPE_AH,
@@ -814,6 +824,8 @@ struct qed_common_cb_ops {
 	void	(*link_update)(void			*dev,
 			       struct qed_link_output	*link);
 	void (*schedule_recovery_handler)(void *dev);
+	void (*schedule_hw_err_handler)(void *dev,
+					enum qed_hw_err_type err_type);
 	void	(*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type);
 	void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data);
 	void (*get_protocol_tlv_data)(void *dev, void *data);
-- 
cgit v1.2.3


From a8736ea83b80526529e21db29595e5337bfa95c2 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:18 +0300
Subject: net: qede: add hw err scheduled handler

qede (ethernet level driver) registers a callback handler.
This handler maintains eth dev state flags/bits to track error processing.

It implements in place processing part for nonsleeping context (WARN_ON
trigger), and a deferred (delayed work) part which triggers recovery
process for recoverable errors.

In later patches this atomic handler will come with more meat.

We introduce err_flags on ethdevice structure, its being used to record
error handling properties.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      | 13 +++-
 drivers/net/ethernet/qlogic/qede/qede_main.c | 95 +++++++++++++++++++++++++++-
 2 files changed, 106 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index f6f0b51620ab..695d645d9ba9 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -278,6 +278,14 @@ struct qede_dev {
 	struct qede_rdma_dev		rdma_info;
 
 	struct bpf_prog *xdp_prog;
+
+	unsigned long err_flags;
+#define QEDE_ERR_IS_HANDLED	31
+#define QEDE_ERR_ATTN_CLR_EN	0
+#define QEDE_ERR_GET_DBG_INFO	1
+#define QEDE_ERR_IS_RECOVERABLE	2
+#define QEDE_ERR_WARN		3
+
 	struct qede_dump_info		dump_info;
 };
 
@@ -485,12 +493,15 @@ struct qede_fastpath {
 
 #define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
+#define QEDE_SP_RSVD1                   2
+#define QEDE_SP_RSVD2                   3
+#define QEDE_SP_HW_ERR                  4
+#define QEDE_SP_ARFS_CONFIG             5
 #define QEDE_SP_AER			7
 
 #ifdef CONFIG_RFS_ACCEL
 int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id);
-#define QEDE_SP_ARFS_CONFIG	4
 #define QEDE_SP_TASK_POLL_DELAY	(5 * HZ)
 #endif
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 300405369c37..e67d5da23792 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -139,10 +139,12 @@ static void qede_shutdown(struct pci_dev *pdev);
 static void qede_link_update(void *dev, struct qed_link_output *link);
 static void qede_schedule_recovery_handler(void *dev);
 static void qede_recovery_handler(struct qede_dev *edev);
+static void qede_schedule_hw_err_handler(void *dev,
+					 enum qed_hw_err_type err_type);
 static void qede_get_eth_tlv_data(void *edev, void *data);
 static void qede_get_generic_tlv_data(void *edev,
 				      struct qed_generic_tlvs *data);
-
+static void qede_generic_hw_err_handler(struct qede_dev *edev);
 #ifdef CONFIG_QED_SRIOV
 static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos,
 			    __be16 vlan_proto)
@@ -230,6 +232,7 @@ static struct qed_eth_cb_ops qede_ll_ops = {
 #endif
 		.link_update = qede_link_update,
 		.schedule_recovery_handler = qede_schedule_recovery_handler,
+		.schedule_hw_err_handler = qede_schedule_hw_err_handler,
 		.get_generic_tlv_data = qede_get_generic_tlv_data,
 		.get_protocol_tlv_data = qede_get_eth_tlv_data,
 	},
@@ -1009,6 +1012,8 @@ static void qede_sp_task(struct work_struct *work)
 			qede_process_arfs_filters(edev, false);
 	}
 #endif
+	if (test_and_clear_bit(QEDE_SP_HW_ERR, &edev->sp_flags))
+		qede_generic_hw_err_handler(edev);
 	__qede_unlock(edev);
 
 	if (test_and_clear_bit(QEDE_SP_AER, &edev->sp_flags)) {
@@ -2509,6 +2514,94 @@ err:
 	qede_recovery_failed(edev);
 }
 
+static void qede_atomic_hw_err_handler(struct qede_dev *edev)
+{
+	DP_NOTICE(edev,
+		  "Generic non-sleepable HW error handling started - err_flags 0x%lx\n",
+		  edev->err_flags);
+
+	/* Get a call trace of the flow that led to the error */
+	WARN_ON(test_bit(QEDE_ERR_WARN, &edev->err_flags));
+
+	DP_NOTICE(edev, "Generic non-sleepable HW error handling is done\n");
+}
+
+static void qede_generic_hw_err_handler(struct qede_dev *edev)
+{
+	struct qed_dev *cdev = edev->cdev;
+
+	DP_NOTICE(edev,
+		  "Generic sleepable HW error handling started - err_flags 0x%lx\n",
+		  edev->err_flags);
+
+	/* Trigger a recovery process.
+	 * This is placed in the sleep requiring section just to make
+	 * sure it is the last one, and that all the other operations
+	 * were completed.
+	 */
+	if (test_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags))
+		edev->ops->common->recovery_process(cdev);
+
+	clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
+
+	DP_NOTICE(edev, "Generic sleepable HW error handling is done\n");
+}
+
+static void qede_set_hw_err_flags(struct qede_dev *edev,
+				  enum qed_hw_err_type err_type)
+{
+	unsigned long err_flags = 0;
+
+	switch (err_type) {
+	case QED_HW_ERR_DMAE_FAIL:
+		set_bit(QEDE_ERR_WARN, &err_flags);
+		fallthrough;
+	case QED_HW_ERR_MFW_RESP_FAIL:
+	case QED_HW_ERR_HW_ATTN:
+	case QED_HW_ERR_RAMROD_FAIL:
+	case QED_HW_ERR_FW_ASSERT:
+		set_bit(QEDE_ERR_ATTN_CLR_EN, &err_flags);
+		set_bit(QEDE_ERR_GET_DBG_INFO, &err_flags);
+		break;
+
+	default:
+		DP_NOTICE(edev, "Unexpected HW error [%d]\n", err_type);
+		break;
+	}
+
+	edev->err_flags |= err_flags;
+}
+
+static void qede_schedule_hw_err_handler(void *dev,
+					 enum qed_hw_err_type err_type)
+{
+	struct qede_dev *edev = dev;
+
+	/* Fan failure cannot be masked by handling of another HW error or by a
+	 * concurrent recovery process.
+	 */
+	if ((test_and_set_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags) ||
+	     edev->state == QEDE_STATE_RECOVERY) &&
+	     err_type != QED_HW_ERR_FAN_FAIL) {
+		DP_INFO(edev,
+			"Avoid scheduling an error handling while another HW error is being handled\n");
+		return;
+	}
+
+	if (err_type >= QED_HW_ERR_LAST) {
+		DP_NOTICE(edev, "Unknown HW error [%d]\n", err_type);
+		clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
+		return;
+	}
+
+	qede_set_hw_err_flags(edev, err_type);
+	qede_atomic_hw_err_handler(edev);
+	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+
+	DP_INFO(edev, "Scheduled a error handler [err_type %d]\n", err_type);
+}
+
 static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;
-- 
cgit v1.2.3


From 2ec276d5b224d0d409ad3ad790b68f6d13822250 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:19 +0300
Subject: net: qed: invoke err notify on critical areas

In a number of critical places not only debug trace should be printed,
but the appropriate hw error condition should be raised and error
handling/recovery should start.

Introduce our new qed_hw_err_notify invocation in these places to
record and indicate critical error conditions in hardware.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c |  4 +++-
 drivers/net/ethernet/qlogic/qed/qed_hw.c  |  7 ++++---
 drivers/net/ethernet/qlogic/qed/qed_int.c | 20 ++++++++++++++++----
 drivers/net/ethernet/qlogic/qed/qed_mcp.c |  2 ++
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 16 ++++++++++------
 5 files changed, 35 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 7119a18af19e..6e857468e993 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3085,7 +3085,9 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			rc = qed_final_cleanup(p_hwfn, p_hwfn->p_main_ptt,
 					       p_hwfn->rel_pf_id, false);
 			if (rc) {
-				DP_NOTICE(p_hwfn, "Final cleanup failed\n");
+				qed_hw_err_notify(p_hwfn, p_hwfn->p_main_ptt,
+						  QED_HW_ERR_RAMROD_FAIL,
+						  "Final cleanup failed\n");
 				goto load_err;
 			}
 		}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 90b777019cf5..2d176e1b508c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -762,9 +762,10 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 							    dst_type,
 							    length_cur);
 		if (qed_status) {
-			DP_NOTICE(p_hwfn,
-				  "qed_dmae_execute_sub_operation Failed with error 0x%x. source_addr 0x%llx, destination addr 0x%llx, size_in_dwords 0x%x\n",
-				  qed_status, src_addr, dst_addr, length_cur);
+			qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_DMAE_FAIL,
+					  "qed_dmae_execute_sub_operation Failed with error 0x%x. source_addr 0x%llx, destination addr 0x%llx, size_in_dwords 0x%x\n",
+					  qed_status, src_addr,
+					  dst_addr, length_cur);
 			break;
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 9f5113639eaf..1b1447b2f059 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -363,6 +363,14 @@ static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
 	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
 }
 
+static int qed_fw_assertion(struct qed_hwfn *p_hwfn)
+{
+	qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_FW_ASSERT,
+			  "FW assertion!\n");
+
+	return -EINVAL;
+}
+
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
 #define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
 #define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@@ -606,7 +614,8 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 	{
 		{       /* After Invert 4 */
 			{"General Attention 32", ATTENTION_SINGLE,
-			 NULL, MAX_BLOCK_ID},
+			 qed_fw_assertion,
+			 MAX_BLOCK_ID},
 			{"General Attention %d",
 			 (2 << ATTENTION_LENGTH_SHIFT) |
 			 (33 << ATTENTION_OFFSET_SHIFT), NULL, MAX_BLOCK_ID},
@@ -927,9 +936,12 @@ qed_int_deassertion_aeu_bit(struct qed_hwfn *p_hwfn,
 		qed_int_attn_print(p_hwfn, p_aeu->block_index,
 				   ATTN_TYPE_INTERRUPT, !b_fatal);
 
-
-	/* If the attention is benign, no need to prevent it */
-	if (!rc)
+	/* Reach assertion if attention is fatal */
+	if (b_fatal)
+		qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_HW_ATTN,
+				  "`%s': Fatal attention\n",
+				  p_bit_name);
+	else /* If the attention is benign, no need to prevent it */
 		goto out;
 
 	/* Prevent this Attention from being asserted in the future */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 280527cc0578..46653afc385c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -575,6 +575,8 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
 		if (!QED_MB_FLAGS_IS_SET(p_mb_params, AVOID_BLOCK))
 			qed_mcp_cmd_set_blocking(p_hwfn, true);
 
+		qed_hw_err_notify(p_hwfn, p_ptt,
+				  QED_HW_ERR_MFW_RESP_FAIL, NULL);
 		return -EAGAIN;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index f5f3c03b9dd2..790c28d696a0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -160,12 +160,16 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
 		return 0;
 	}
 err:
-	DP_NOTICE(p_hwfn,
-		  "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
-		  le32_to_cpu(p_ent->elem.hdr.cid),
-		  p_ent->elem.hdr.cmd_id,
-		  p_ent->elem.hdr.protocol_id,
-		  le16_to_cpu(p_ent->elem.hdr.echo));
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EBUSY;
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_RAMROD_FAIL,
+			  "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
+			  le32_to_cpu(p_ent->elem.hdr.cid),
+			  p_ent->elem.hdr.cmd_id,
+			  p_ent->elem.hdr.protocol_id,
+			  le16_to_cpu(p_ent->elem.hdr.echo));
+	qed_ptt_release(p_hwfn, p_ptt);
 
 	return -EBUSY;
 }
-- 
cgit v1.2.3


From d8d6c5a7be97304f4baa67a31d6bfa86ff457980 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:20 +0300
Subject: net: qed: critical err reporting to management firmware

On various critical errors, notification handler should also report
the err information into the management firmware.

MFW can interact with server/motherboard backend agents - these are
used by server manufacturers to monitor server HW health.

Thus, it is important for driver to report on any faulty conditions

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h |  19 +++++
 drivers/net/ethernet/qlogic/qed/qed_hw.c  |   3 +
 drivers/net/ethernet/qlogic/qed/qed_mcp.c | 124 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_mcp.h |  15 ++++
 4 files changed, 161 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 4597015b8bff..21d53b00c2e6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12492,6 +12492,8 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_GET_ENGINE_CONFIG		0x00370000
 #define DRV_MSG_CODE_GET_PPFID_BITMAP		0x43000000
 
+#define DRV_MSG_CODE_DEBUG_DATA_SEND		0xc0040000
+
 #define RESOURCE_CMD_REQ_RESC_MASK		0x0000001F
 #define RESOURCE_CMD_REQ_RESC_SHIFT		0
 #define RESOURCE_CMD_REQ_OPCODE_MASK		0x000000E0
@@ -12626,6 +12628,17 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE		0x00000002
 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK		0x00010000
 
+/* DRV_MSG_CODE_DEBUG_DATA_SEND parameters */
+#define DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE_OFFSET	0
+#define DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE_MASK		0xFF
+
+/* Driver attributes params */
+#define DRV_MB_PARAM_ATTRIBUTE_KEY_OFFSET		0
+#define DRV_MB_PARAM_ATTRIBUTE_KEY_MASK			0x00FFFFFF
+#define DRV_MB_PARAM_ATTRIBUTE_CMD_OFFSET		24
+#define DRV_MB_PARAM_ATTRIBUTE_CMD_MASK			0xFF000000
+
+#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_OFFSET		0
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ID_SHIFT		0
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ID_MASK		0x0000FFFF
 #define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_SHIFT		16
@@ -12678,6 +12691,12 @@ struct public_drv_mb {
 #define FW_MSG_CODE_DRV_CFG_PF_VFS_MSIX_DONE	0x00870000
 #define FW_MSG_SEQ_NUMBER_MASK			0x0000ffff
 
+#define FW_MSG_CODE_DEBUG_DATA_SEND_INV_ARG	0xb0070000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_BUF_FULL	0xb0080000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_NO_BUF	0xb0090000
+#define FW_MSG_CODE_DEBUG_NOT_ENABLED		0xb00a0000
+#define FW_MSG_CODE_DEBUG_DATA_SEND_OK		0xb00b0000
+
 	u32 fw_mb_param;
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 2d176e1b508c..5fa251489536 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -868,6 +868,9 @@ void qed_hw_err_notify(struct qed_hwfn *p_hwfn,
 	}
 
 	qed_hw_error_occurred(p_hwfn, err_type);
+
+	if (fmt)
+		qed_mcp_send_raw_debug_data(p_hwfn, p_ptt, buf, len);
 }
 
 int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 46653afc385c..db7cf120527a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -3821,3 +3821,127 @@ int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 				  DRV_MSG_CODE_SET_NVM_CFG_OPTION,
 				  mb_param, &resp, &param, len, (u32 *)p_buf);
 }
+
+#define QED_MCP_DBG_DATA_MAX_SIZE               MCP_DRV_NVM_BUF_LEN
+#define QED_MCP_DBG_DATA_MAX_HEADER_SIZE        sizeof(u32)
+#define QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE \
+	(QED_MCP_DBG_DATA_MAX_SIZE - QED_MCP_DBG_DATA_MAX_HEADER_SIZE)
+
+static int
+__qed_mcp_send_debug_data(struct qed_hwfn *p_hwfn,
+			  struct qed_ptt *p_ptt, u8 *p_buf, u8 size)
+{
+	struct qed_mcp_mb_params mb_params;
+	int rc;
+
+	if (size > QED_MCP_DBG_DATA_MAX_SIZE) {
+		DP_ERR(p_hwfn,
+		       "Debug data size is %d while it should not exceed %d\n",
+		       size, QED_MCP_DBG_DATA_MAX_SIZE);
+		return -EINVAL;
+	}
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_DEBUG_DATA_SEND;
+	SET_MFW_FIELD(mb_params.param, DRV_MSG_CODE_DEBUG_DATA_SEND_SIZE, size);
+	mb_params.p_data_src = p_buf;
+	mb_params.data_src_size = size;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	if (mb_params.mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The DEBUG_DATA_SEND command is unsupported by the MFW\n");
+		return -EOPNOTSUPP;
+	} else if (mb_params.mcp_resp == (u32)FW_MSG_CODE_DEBUG_NOT_ENABLED) {
+		DP_INFO(p_hwfn, "The DEBUG_DATA_SEND command is not enabled\n");
+		return -EBUSY;
+	} else if (mb_params.mcp_resp != (u32)FW_MSG_CODE_DEBUG_DATA_SEND_OK) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to send debug data to the MFW [resp 0x%08x]\n",
+			  mb_params.mcp_resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum qed_mcp_dbg_data_type {
+	QED_MCP_DBG_DATA_TYPE_RAW,
+};
+
+/* Header format: [31:28] PFID, [27:20] flags, [19:12] type, [11:0] S/N */
+#define QED_MCP_DBG_DATA_HDR_SN_OFFSET  0
+#define QED_MCP_DBG_DATA_HDR_SN_MASK            0x00000fff
+#define QED_MCP_DBG_DATA_HDR_TYPE_OFFSET        12
+#define QED_MCP_DBG_DATA_HDR_TYPE_MASK  0x000ff000
+#define QED_MCP_DBG_DATA_HDR_FLAGS_OFFSET       20
+#define QED_MCP_DBG_DATA_HDR_FLAGS_MASK 0x0ff00000
+#define QED_MCP_DBG_DATA_HDR_PF_OFFSET  28
+#define QED_MCP_DBG_DATA_HDR_PF_MASK            0xf0000000
+
+#define QED_MCP_DBG_DATA_HDR_FLAGS_FIRST        0x1
+#define QED_MCP_DBG_DATA_HDR_FLAGS_LAST 0x2
+
+static int
+qed_mcp_send_debug_data(struct qed_hwfn *p_hwfn,
+			struct qed_ptt *p_ptt,
+			enum qed_mcp_dbg_data_type type, u8 *p_buf, u32 size)
+{
+	u8 raw_data[QED_MCP_DBG_DATA_MAX_SIZE], *p_tmp_buf = p_buf;
+	u32 tmp_size = size, *p_header, *p_payload;
+	u8 flags = 0;
+	u16 seq;
+	int rc;
+
+	p_header = (u32 *)raw_data;
+	p_payload = (u32 *)(raw_data + QED_MCP_DBG_DATA_MAX_HEADER_SIZE);
+
+	seq = (u16)atomic_inc_return(&p_hwfn->mcp_info->dbg_data_seq);
+
+	/* First chunk is marked as 'first' */
+	flags |= QED_MCP_DBG_DATA_HDR_FLAGS_FIRST;
+
+	*p_header = 0;
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_SN, seq);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_TYPE, type);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS, flags);
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_PF, p_hwfn->abs_pf_id);
+
+	while (tmp_size > QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE) {
+		memcpy(p_payload, p_tmp_buf, QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE);
+		rc = __qed_mcp_send_debug_data(p_hwfn, p_ptt, raw_data,
+					       QED_MCP_DBG_DATA_MAX_SIZE);
+		if (rc)
+			return rc;
+
+		/* Clear the 'first' marking after sending the first chunk */
+		if (p_tmp_buf == p_buf) {
+			flags &= ~QED_MCP_DBG_DATA_HDR_FLAGS_FIRST;
+			SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS,
+				      flags);
+		}
+
+		p_tmp_buf += QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE;
+		tmp_size -= QED_MCP_DBG_DATA_MAX_PAYLOAD_SIZE;
+	}
+
+	/* Last chunk is marked as 'last' */
+	flags |= QED_MCP_DBG_DATA_HDR_FLAGS_LAST;
+	SET_MFW_FIELD(*p_header, QED_MCP_DBG_DATA_HDR_FLAGS, flags);
+	memcpy(p_payload, p_tmp_buf, tmp_size);
+
+	/* Casting the left size to u8 is ok since at this point it is <= 32 */
+	return __qed_mcp_send_debug_data(p_hwfn, p_ptt, raw_data,
+					 (u8)(QED_MCP_DBG_DATA_MAX_HEADER_SIZE +
+					 tmp_size));
+}
+
+int
+qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt, u8 *p_buf, u32 size)
+{
+	return qed_mcp_send_debug_data(p_hwfn, p_ptt,
+				       QED_MCP_DBG_DATA_TYPE_RAW, p_buf, size);
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 9c4c2763de8d..bc248418a5f5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -685,6 +685,18 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn,
  */
 int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
+/**
+ * @brief Send raw debug data to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_buf - raw debug data buffer
+ * @param size - buffer size
+ */
+int
+qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn,
+			    struct qed_ptt *p_ptt, u8 *p_buf, u32 size);
+
 /* Using hwfn number (and not pf_num) is required since in CMT mode,
  * same pf_num may be used by two different hwfn
  * TODO - this shouldn't really be in .h file, but until all fields
@@ -731,6 +743,9 @@ struct qed_mcp_info {
 
 	/* Capabilties negotiated with the MFW */
 	u32					capabilities;
+
+	/* S/N for debug data mailbox commands */
+	atomic_t dbg_data_seq;
 };
 
 struct qed_mcp_mb_params {
-- 
cgit v1.2.3


From ca352f00756e7bd7d31a353a8586a29429810a95 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:21 +0300
Subject: net: qed: cleanup debug related declarations

Thats probably a legacy code had double declaration of some fields.
Cleanup this, removing copy and fixing references.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h       | 11 +++--------
 drivers/net/ethernet/qlogic/qed/qed_debug.c | 26 +++++++++++++-------------
 2 files changed, 16 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 12c40ce3d876..07f6ef930b52 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -740,12 +740,6 @@ struct qed_dbg_feature {
 	u32 dumped_dwords;
 };
 
-struct qed_dbg_params {
-	struct qed_dbg_feature features[DBG_FEATURE_NUM];
-	u8 engine_for_debug;
-	bool print_data;
-};
-
 struct qed_dev {
 	u32	dp_module;
 	u8	dp_level;
@@ -872,17 +866,18 @@ struct qed_dev {
 	} protocol_ops;
 	void				*ops_cookie;
 
-	struct qed_dbg_params		dbg_params;
-
 #ifdef CONFIG_QED_LL2
 	struct qed_cb_ll2_info		*ll2;
 	u8				ll2_mac_address[ETH_ALEN];
 #endif
 	struct qed_dbg_feature dbg_features[DBG_FEATURE_NUM];
+	u8 engine_for_debug;
 	bool disable_ilt_dump;
 	DECLARE_HASHTABLE(connections, 10);
 	const struct firmware		*firmware;
 
+	bool print_dbg_data;
+
 	u32 rdma_max_sge;
 	u32 rdma_max_inline;
 	u32 rdma_max_srq_sge;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index f4eebaabb6d0..57a0dab88431 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7453,7 +7453,7 @@ static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
 				      enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
-	    &p_hwfn->cdev->dbg_params.features[feature_idx];
+	    &p_hwfn->cdev->dbg_features[feature_idx];
 	u32 text_size_bytes, null_char_pos, i;
 	enum dbg_status rc;
 	char *text_buf;
@@ -7502,7 +7502,7 @@ static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
 		text_buf[i] = '\n';
 
 	/* Dump printable feature to log */
-	if (p_hwfn->cdev->dbg_params.print_data)
+	if (p_hwfn->cdev->print_dbg_data)
 		qed_dbg_print_feature(text_buf, text_size_bytes);
 
 	/* Free the old dump_buf and point the dump_buf to the newly allocagted
@@ -7523,7 +7523,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
 				    enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
-	    &p_hwfn->cdev->dbg_params.features[feature_idx];
+	    &p_hwfn->cdev->dbg_features[feature_idx];
 	u32 buf_size_dwords;
 	enum dbg_status rc;
 
@@ -7648,7 +7648,7 @@ static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
 			     enum qed_nvm_images image_id)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	u32 len_rounded, i;
 	__be32 val;
 	int rc;
@@ -7780,7 +7780,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 {
 	u8 cur_engine, omit_engine = 0, org_engine;
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
 	int grc_params[MAX_DBG_GRC_PARAMS], i;
 	u32 offset = 0, feature_size;
@@ -8000,7 +8000,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 int qed_dbg_all_data_size(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	u32 regs_len = 0, image_len = 0, ilt_len = 0, total_ilt_len = 0;
 	u8 cur_engine, org_engine;
 
@@ -8059,9 +8059,9 @@ int qed_dbg_feature(struct qed_dev *cdev, void *buffer,
 		    enum qed_dbg_features feature, u32 *num_dumped_bytes)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct qed_dbg_feature *qed_feature =
-		&cdev->dbg_params.features[feature];
+		&cdev->dbg_features[feature];
 	enum dbg_status dbg_rc;
 	struct qed_ptt *p_ptt;
 	int rc = 0;
@@ -8084,7 +8084,7 @@ int qed_dbg_feature(struct qed_dev *cdev, void *buffer,
 	DP_VERBOSE(cdev, QED_MSG_DEBUG,
 		   "copying debugfs feature to external buffer\n");
 	memcpy(buffer, qed_feature->dump_buf, qed_feature->buf_size);
-	*num_dumped_bytes = cdev->dbg_params.features[feature].dumped_dwords *
+	*num_dumped_bytes = cdev->dbg_features[feature].dumped_dwords *
 			    4;
 
 out:
@@ -8095,7 +8095,7 @@ out:
 int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature)
 {
 	struct qed_hwfn *p_hwfn =
-		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
+		&cdev->hwfns[cdev->engine_for_debug];
 	struct qed_dbg_feature *qed_feature = &cdev->dbg_features[feature];
 	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
 	u32 buf_size_dwords;
@@ -8120,14 +8120,14 @@ int qed_dbg_feature_size(struct qed_dev *cdev, enum qed_dbg_features feature)
 
 u8 qed_get_debug_engine(struct qed_dev *cdev)
 {
-	return cdev->dbg_params.engine_for_debug;
+	return cdev->engine_for_debug;
 }
 
 void qed_set_debug_engine(struct qed_dev *cdev, int engine_number)
 {
 	DP_VERBOSE(cdev, QED_MSG_DEBUG, "set debug engine to %d\n",
 		   engine_number);
-	cdev->dbg_params.engine_for_debug = engine_number;
+	cdev->engine_for_debug = engine_number;
 }
 
 void qed_dbg_pf_init(struct qed_dev *cdev)
@@ -8146,7 +8146,7 @@ void qed_dbg_pf_init(struct qed_dev *cdev)
 	}
 
 	/* Set the hwfn to be 0 as default */
-	cdev->dbg_params.engine_for_debug = 0;
+	cdev->engine_for_debug = 0;
 }
 
 void qed_dbg_pf_exit(struct qed_dev *cdev)
-- 
cgit v1.2.3


From 936c7ba4dd5e94a3fc784f2296de5d577a9b5e43 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:22 +0300
Subject: net: qed: attention clearing properties

On different hardware events we have to respond differently,
on some of hardware indications hw attention (error condition)
should be cleared by the driver to continue normal functioning.

Here we introduce attention clear flags, and put them on some
important events (in aeu_descs).

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h        |  3 +++
 drivers/net/ethernet/qlogic/qed/qed_int.c    | 22 ++++++++++++++++++----
 drivers/net/ethernet/qlogic/qed/qed_int.h    | 11 +++++++++++
 drivers/net/ethernet/qlogic/qed/qed_main.c   |  7 ++++++-
 drivers/net/ethernet/qlogic/qede/qede_main.c |  6 ++++++
 include/linux/qed/qed_if.h                   |  9 +++++++++
 6 files changed, 53 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 07f6ef930b52..66ed39d6f357 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -838,6 +838,9 @@ struct qed_dev {
 	/* Recovery */
 	bool recov_in_prog;
 
+	/* Indicates whether should prevent attentions from being reasserted */
+	bool attn_clr_en;
+
 	/* LLH info */
 	u8 ppfid_bitmap;
 	struct qed_llh_info *p_llh_info;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 1b1447b2f059..b7b974f0ef21 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -96,6 +96,7 @@ struct aeu_invert_reg_bit {
 #define ATTENTION_BB(value)             (value << ATTENTION_BB_SHIFT)
 #define ATTENTION_BB_DIFFERENT          BIT(23)
 
+#define ATTENTION_CLEAR_ENABLE          BIT(28)
 	unsigned int flags;
 
 	/* Callback to call if attention will be triggered */
@@ -371,6 +372,13 @@ static int qed_fw_assertion(struct qed_hwfn *p_hwfn)
 	return -EINVAL;
 }
 
+static int qed_general_attention_35(struct qed_hwfn *p_hwfn)
+{
+	DP_INFO(p_hwfn, "General attention 35!\n");
+
+	return 0;
+}
+
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
 #define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
 #define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@@ -613,14 +621,15 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 
 	{
 		{       /* After Invert 4 */
-			{"General Attention 32", ATTENTION_SINGLE,
-			 qed_fw_assertion,
+			{"General Attention 32", ATTENTION_SINGLE |
+			 ATTENTION_CLEAR_ENABLE, qed_fw_assertion,
 			 MAX_BLOCK_ID},
 			{"General Attention %d",
 			 (2 << ATTENTION_LENGTH_SHIFT) |
 			 (33 << ATTENTION_OFFSET_SHIFT), NULL, MAX_BLOCK_ID},
-			{"General Attention 35", ATTENTION_SINGLE,
-			 NULL, MAX_BLOCK_ID},
+			{"General Attention 35", ATTENTION_SINGLE |
+			 ATTENTION_CLEAR_ENABLE, qed_general_attention_35,
+			 MAX_BLOCK_ID},
 			{"NWS Parity",
 			 ATTENTION_PAR | ATTENTION_BB_DIFFERENT |
 			 ATTENTION_BB(AEU_INVERT_REG_SPECIAL_CNIG_0),
@@ -2361,6 +2370,11 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev)
 		cdev->hwfns[i].b_int_requested = false;
 }
 
+void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable)
+{
+	cdev->attn_clr_en = clr_enable;
+}
+
 int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			  u8 timer_res, u16 sb_id, bool tx)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 9ad568d93ae6..e09db3386367 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -190,6 +190,17 @@ void qed_int_get_num_sbs(struct qed_hwfn	*p_hwfn,
  */
 void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
+/**
+ * @brief qed_int_attn_clr_enable - sets whether the general behavior is
+ *        preventing attentions from being reasserted, or following the
+ *        attributes of the specific attention.
+ *
+ * @param cdev
+ * @param clr_enable
+ *
+ */
+void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable);
+
 /**
  * @brief - Doorbell Recovery handler.
  *          Run doorbell recovery in case of PF overflow (and flush DORQ if
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index d7c9d94e4c59..83e798d4eebb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -2491,10 +2491,14 @@ void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
 
 	DP_NOTICE(p_hwfn, "HW error occurred [%s]\n", err_str);
 
-	/* Call the HW error handler of the protocol driver
+	/* Call the HW error handler of the protocol driver.
+	 * If it is not available - perform a minimal handling of preventing
+	 * HW attentions from being reasserted.
 	 */
 	if (ops && ops->schedule_hw_err_handler)
 		ops->schedule_hw_err_handler(cookie, err_type);
+	else
+		qed_int_attn_clr_enable(p_hwfn->cdev, true);
 }
 
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
@@ -2718,6 +2722,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.set_led = &qed_set_led,
 	.recovery_process = &qed_recovery_process,
 	.recovery_prolog = &qed_recovery_prolog,
+	.attn_clr_enable = &qed_int_attn_clr_enable,
 	.update_drv_state = &qed_update_drv_state,
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index e67d5da23792..ee7662da6413 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2516,6 +2516,8 @@ err:
 
 static void qede_atomic_hw_err_handler(struct qede_dev *edev)
 {
+	struct qed_dev *cdev = edev->cdev;
+
 	DP_NOTICE(edev,
 		  "Generic non-sleepable HW error handling started - err_flags 0x%lx\n",
 		  edev->err_flags);
@@ -2523,6 +2525,10 @@ static void qede_atomic_hw_err_handler(struct qede_dev *edev)
 	/* Get a call trace of the flow that led to the error */
 	WARN_ON(test_bit(QEDE_ERR_WARN, &edev->err_flags));
 
+	/* Prevent HW attentions from being reasserted */
+	if (test_bit(QEDE_ERR_ATTN_CLR_EN, &edev->err_flags))
+		edev->ops->common->attn_clr_enable(cdev, true);
+
 	DP_NOTICE(edev, "Generic non-sleepable HW error handling is done\n");
 }
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 1b7d9548ee43..978e91e9ab65 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1046,6 +1046,15 @@ struct qed_common_ops {
  */
 	int (*set_led)(struct qed_dev *cdev,
 		       enum qed_led_mode mode);
+
+/**
+ * @brief attn_clr_enable - Prevent attentions from being reasserted
+ *
+ * @param cdev
+ * @param clr_enable
+ */
+	void (*attn_clr_enable)(struct qed_dev *cdev, bool clr_enable);
+
 /**
  * @brief db_recovery_add - add doorbell information to the doorbell
  * recovery mechanism.
-- 
cgit v1.2.3


From 7d9acd87bd55f401ada67b9c6a9c83a7e68c4ddf Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:23 +0300
Subject: net: qede: optional hw recovery procedure

Driver has an ability to initiate a recovery process as a reaction to
detected errors. But the codepath (recovery_process) was disabled and
never active.

Here we add ethtool private flag to allow user have the recovery
procedure activated.

We still do not enable this by default though, since in some configurations
this is not desirable. E.g. this may impact other PFs/VFs.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 812c7766e096..24cc68391ac4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -190,12 +190,14 @@ static const struct {
 enum {
 	QEDE_PRI_FLAG_CMT,
 	QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */
+	QEDE_PRI_FLAG_RECOVER_ON_ERROR,
 	QEDE_PRI_FLAG_LEN,
 };
 
 static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = {
 	"Coupled-Function",
 	"SmartAN capable",
+	"Recover on error",
 };
 
 enum qede_ethtool_tests {
@@ -417,9 +419,30 @@ static u32 qede_get_priv_flags(struct net_device *dev)
 	if (edev->dev_info.common.smart_an)
 		flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT);
 
+	if (edev->err_flags & BIT(QEDE_ERR_IS_RECOVERABLE))
+		flags |= BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR);
+
 	return flags;
 }
 
+static int qede_set_priv_flags(struct net_device *dev, u32 flags)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u32 cflags = qede_get_priv_flags(dev);
+	u32 dflags = flags ^ cflags;
+
+	/* can only change RECOVER_ON_ERROR flag */
+	if (dflags & ~BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR))
+		return -EINVAL;
+
+	if (flags & BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR))
+		set_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags);
+	else
+		clear_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags);
+
+	return 0;
+}
+
 struct qede_link_mode_mapping {
 	u32 qed_link_mode;
 	u32 ethtool_link_mode;
@@ -2098,6 +2121,7 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.set_phys_id = qede_set_phys_id,
 	.get_ethtool_stats = qede_get_ethtool_stats,
 	.get_priv_flags = qede_get_priv_flags,
+	.set_priv_flags = qede_set_priv_flags,
 	.get_sset_count = qede_get_sset_count,
 	.get_rxnfc = qede_get_rxnfc,
 	.set_rxnfc = qede_set_rxnfc,
-- 
cgit v1.2.3


From 5144e9f439d53460c38eb5c34dd67837ac512db1 Mon Sep 17 00:00:00 2001
From: Denis Bolotin <dbolotin@marvell.com>
Date: Thu, 14 May 2020 12:57:24 +0300
Subject: net: qede: Implement ndo_tx_timeout

Upon tx timeout detection we do disable carrier and print TX queue
info on TX timeout. We then raise hw error condition and trigger
service task to handle this.

This handler will capture extra debug info and then optionally
trigger recovery procedure to try restore function.

Signed-off-by: Denis Bolotin <dbolotin@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      |  1 -
 drivers/net/ethernet/qlogic/qede/qede_main.c | 46 ++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 695d645d9ba9..8857da1208d7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -533,7 +533,6 @@ u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
-void qede_tx_log_print(struct qede_dev *edev, struct qede_fastpath *fp);
 int qede_alloc_rx_buffer(struct qede_rx_queue *rxq, bool allow_lazy);
 int qede_free_tx_pkt(struct qede_dev *edev,
 		     struct qede_tx_queue *txq, int *len);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index ee7662da6413..f50d9a9b76be 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -539,6 +539,51 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
+static void qede_tx_log_print(struct qede_dev *edev, struct qede_tx_queue *txq)
+{
+	DP_NOTICE(edev,
+		  "Txq[%d]: FW cons [host] %04x, SW cons %04x, SW prod %04x [Jiffies %lu]\n",
+		  txq->index, le16_to_cpu(*txq->hw_cons_ptr),
+		  qed_chain_get_cons_idx(&txq->tx_pbl),
+		  qed_chain_get_prod_idx(&txq->tx_pbl),
+		  jiffies);
+}
+
+static void qede_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	struct qede_tx_queue *txq;
+	int cos;
+
+	netif_carrier_off(dev);
+	DP_NOTICE(edev, "TX timeout on queue %u!\n", txqueue);
+
+	if (!(edev->fp_array[txqueue].type & QEDE_FASTPATH_TX))
+		return;
+
+	for_each_cos_in_txq(edev, cos) {
+		txq = &edev->fp_array[txqueue].txq[cos];
+
+		if (qed_chain_get_cons_idx(&txq->tx_pbl) !=
+		    qed_chain_get_prod_idx(&txq->tx_pbl))
+			qede_tx_log_print(edev, txq);
+	}
+
+	if (IS_VF(edev))
+		return;
+
+	if (test_and_set_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags) ||
+	    edev->state == QEDE_STATE_RECOVERY) {
+		DP_INFO(edev,
+			"Avoid handling a Tx timeout while another HW error is being handled\n");
+		return;
+	}
+
+	set_bit(QEDE_ERR_GET_DBG_INFO, &edev->err_flags);
+	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+}
+
 static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 {
 	struct qede_dev *edev = netdev_priv(ndev);
@@ -626,6 +671,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = qede_change_mtu,
 	.ndo_do_ioctl = qede_ioctl,
+	.ndo_tx_timeout = qede_tx_timeout,
 #ifdef CONFIG_QED_SRIOV
 	.ndo_set_vf_mac = qede_set_vf_mac,
 	.ndo_set_vf_vlan = qede_set_vf_vlan,
-- 
cgit v1.2.3


From 3e99c2111026244326deee5fcaf8ea744627214b Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:25 +0300
Subject: net: qed: introduce critical fan failure handler

Fan failure is sent by firmware, driver reacts on this error with
newly introduced notification path. It will collect dump and shut down
the device to prevent physical breakage

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_mcp.c | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 21d53b00c2e6..ab042b835797 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12761,7 +12761,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_GET_FCOE_STATS,
 	MFW_DRV_MSG_GET_ISCSI_STATS,
 	MFW_DRV_MSG_GET_RDMA_STATS,
-	MFW_DRV_MSG_BW_UPDATE10,
+	MFW_DRV_MSG_FAILURE_DETECTED,
 	MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
 	MFW_DRV_MSG_BW_UPDATE11,
 	MFW_DRV_MSG_RESERVED,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index db7cf120527a..d5be2d2046c6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1706,6 +1706,17 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		    &resp, &param);
 }
 
+static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn,
+				       struct qed_ptt *p_ptt)
+{
+	/* A single notification should be sent to upper driver in CMT mode */
+	if (p_hwfn != QED_LEADING_HWFN(p_hwfn->cdev))
+		return;
+
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_FAN_FAIL,
+			  "Fan failure was detected on the network interface card and it's going to be shut down.\n");
+}
+
 void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct public_func shmem_info;
@@ -1852,6 +1863,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_S_TAG_UPDATE:
 			qed_mcp_update_stag(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_FAILURE_DETECTED:
+			qed_mcp_handle_fan_failure(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_TLV_REQ:
 			qed_mfw_tlv_req(p_hwfn);
 			break;
-- 
cgit v1.2.3


From ebf64bf4df6331fc612927aae904c310947a02f8 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Thu, 14 May 2020 12:57:26 +0300
Subject: net: qed: introduce critical hardware error handler

MCP may signal driver about generic critical failure.
Driver has to collect mdump information (get_retain),
it pushes that to logs and triggers generic notification on
"hardware attention" event.

Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h |  28 +++++++-
 drivers/net/ethernet/qlogic/qed/qed_mcp.c | 113 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_mcp.h |  13 ++++
 3 files changed, 153 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index ab042b835797..f00460d00cab 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12400,6 +12400,13 @@ struct load_rsp_stc {
 #define LOAD_RSP_FLAGS0_DRV_EXISTS      (0x1 << 0)
 };
 
+struct mdump_retain_data_stc {
+	u32 valid;
+	u32 epoch;
+	u32 pf;
+	u32 status;
+};
+
 union drv_union_data {
 	u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
 	struct mcp_mac wol_mac;
@@ -12488,6 +12495,8 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
 #define DRV_MSG_CODE_RESOURCE_CMD		0x00230000
+/* Send crash dump commands with param[3:0] - opcode */
+#define DRV_MSG_CODE_MDUMP_CMD			0x00250000
 #define DRV_MSG_CODE_GET_TLV_DONE		0x002f0000
 #define DRV_MSG_CODE_GET_ENGINE_CONFIG		0x00370000
 #define DRV_MSG_CODE_GET_PPFID_BITMAP		0x43000000
@@ -12519,6 +12528,21 @@ struct public_drv_mb {
 
 #define RESOURCE_DUMP				0
 
+/* DRV_MSG_CODE_MDUMP_CMD parameters */
+#define MDUMP_DRV_PARAM_OPCODE_MASK             0x0000000f
+#define DRV_MSG_CODE_MDUMP_ACK                  0x01
+#define DRV_MSG_CODE_MDUMP_SET_VALUES           0x02
+#define DRV_MSG_CODE_MDUMP_TRIGGER              0x03
+#define DRV_MSG_CODE_MDUMP_GET_CONFIG           0x04
+#define DRV_MSG_CODE_MDUMP_SET_ENABLE           0x05
+#define DRV_MSG_CODE_MDUMP_CLEAR_LOGS           0x06
+#define DRV_MSG_CODE_MDUMP_GET_RETAIN           0x07
+#define DRV_MSG_CODE_MDUMP_CLR_RETAIN           0x08
+
+#define DRV_MSG_CODE_HW_DUMP_TRIGGER            0x0a
+#define DRV_MSG_CODE_MDUMP_GEN_MDUMP2           0x0b
+#define DRV_MSG_CODE_MDUMP_FREE_MDUMP2          0x0c
+
 #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL	0x002b0000
 #define DRV_MSG_CODE_OS_WOL			0x002e0000
 
@@ -12697,6 +12721,8 @@ struct public_drv_mb {
 #define FW_MSG_CODE_DEBUG_NOT_ENABLED		0xb00a0000
 #define FW_MSG_CODE_DEBUG_DATA_SEND_OK		0xb00b0000
 
+#define FW_MSG_CODE_MDUMP_INVALID_CMD		0x00030000
+
 	u32 fw_mb_param;
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
@@ -12763,7 +12789,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_GET_RDMA_STATS,
 	MFW_DRV_MSG_FAILURE_DETECTED,
 	MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
-	MFW_DRV_MSG_BW_UPDATE11,
+	MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED,
 	MFW_DRV_MSG_RESERVED,
 	MFW_DRV_MSG_GET_TLV_REQ,
 	MFW_DRV_MSG_OEM_CFG_UPDATE,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index d5be2d2046c6..9624616806e7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1717,6 +1717,116 @@ static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn,
 			  "Fan failure was detected on the network interface card and it's going to be shut down.\n");
 }
 
+struct qed_mdump_cmd_params {
+	u32 cmd;
+	void *p_data_src;
+	u8 data_src_size;
+	void *p_data_dst;
+	u8 data_dst_size;
+	u32 mcp_resp;
+};
+
+static int
+qed_mcp_mdump_cmd(struct qed_hwfn *p_hwfn,
+		  struct qed_ptt *p_ptt,
+		  struct qed_mdump_cmd_params *p_mdump_cmd_params)
+{
+	struct qed_mcp_mb_params mb_params;
+	int rc;
+
+	memset(&mb_params, 0, sizeof(mb_params));
+	mb_params.cmd = DRV_MSG_CODE_MDUMP_CMD;
+	mb_params.param = p_mdump_cmd_params->cmd;
+	mb_params.p_data_src = p_mdump_cmd_params->p_data_src;
+	mb_params.data_src_size = p_mdump_cmd_params->data_src_size;
+	mb_params.p_data_dst = p_mdump_cmd_params->p_data_dst;
+	mb_params.data_dst_size = p_mdump_cmd_params->data_dst_size;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	p_mdump_cmd_params->mcp_resp = mb_params.mcp_resp;
+
+	if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_MDUMP_INVALID_CMD) {
+		DP_INFO(p_hwfn,
+			"The mdump sub command is unsupported by the MFW [mdump_cmd 0x%x]\n",
+			p_mdump_cmd_params->cmd);
+		rc = -EOPNOTSUPP;
+	} else if (p_mdump_cmd_params->mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The mdump command is not supported by the MFW\n");
+		rc = -EOPNOTSUPP;
+	}
+
+	return rc;
+}
+
+static int qed_mcp_mdump_ack(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_ACK;
+
+	return qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+}
+
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain)
+{
+	struct qed_mdump_cmd_params mdump_cmd_params;
+	int rc;
+
+	memset(&mdump_cmd_params, 0, sizeof(mdump_cmd_params));
+	mdump_cmd_params.cmd = DRV_MSG_CODE_MDUMP_GET_RETAIN;
+	mdump_cmd_params.p_data_dst = p_mdump_retain;
+	mdump_cmd_params.data_dst_size = sizeof(*p_mdump_retain);
+
+	rc = qed_mcp_mdump_cmd(p_hwfn, p_ptt, &mdump_cmd_params);
+	if (rc)
+		return rc;
+
+	if (mdump_cmd_params.mcp_resp != FW_MSG_CODE_OK) {
+		DP_INFO(p_hwfn,
+			"Failed to get the mdump retained data [mcp_resp 0x%x]\n",
+			mdump_cmd_params.mcp_resp);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void qed_mcp_handle_critical_error(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt)
+{
+	struct mdump_retain_data_stc mdump_retain;
+	int rc;
+
+	/* In CMT mode - no need for more than a single acknowledgment to the
+	 * MFW, and no more than a single notification to the upper driver.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(p_hwfn->cdev))
+		return;
+
+	rc = qed_mcp_mdump_get_retain(p_hwfn, p_ptt, &mdump_retain);
+	if (rc == 0 && mdump_retain.valid)
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device [epoch 0x%08x, pf 0x%x, status 0x%08x]\n",
+			  mdump_retain.epoch,
+			  mdump_retain.pf, mdump_retain.status);
+	else
+		DP_NOTICE(p_hwfn,
+			  "The MFW notified that a critical error occurred in the device\n");
+
+	DP_NOTICE(p_hwfn,
+		  "Acknowledging the notification to not allow the MFW crash dump [driver debug data collection is preferable]\n");
+	qed_mcp_mdump_ack(p_hwfn, p_ptt);
+
+	qed_hw_err_notify(p_hwfn, p_ptt, QED_HW_ERR_HW_ATTN, NULL);
+}
+
 void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct public_func shmem_info;
@@ -1866,6 +1976,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_FAILURE_DETECTED:
 			qed_mcp_handle_fan_failure(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_CRITICAL_ERROR_OCCURRED:
+			qed_mcp_handle_critical_error(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_TLV_REQ:
 			qed_mfw_tlv_req(p_hwfn);
 			break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index bc248418a5f5..5750b4c5ef63 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -1016,6 +1016,19 @@ int __qed_configure_pf_min_bandwidth(struct qed_hwfn *p_hwfn,
 int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u32 mask_parities);
 
+/* @brief - Gets the mdump retained data from the MFW.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_mdump_retain
+ *
+ * @param return 0 upon success.
+ */
+int
+qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn,
+			 struct qed_ptt *p_ptt,
+			 struct mdump_retain_data_stc *p_mdump_retain);
+
 /**
  * @brief - Sets the MFW's max value for the given resource
  *
-- 
cgit v1.2.3


From ec008fa2a9e5686081053750893de5f407a8d076 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Wed, 13 May 2020 09:26:14 -0400
Subject: ethernet: ti: am65-cpts: add routines to support taprio offload

TAPRIO/EST offload support in CPSW2G requires EST scheduler
function enabled in CPTS. So this patch add a function to
set cycle time for EST scheduler.  It also add a function for
getting time in ns of PHC clock for taprio qdisc configuration.
Mostly to verify if timer update is needed or to get actual
state of oper/admin schedule.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpts.c | 48 +++++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/am65-cpts.h | 24 +++++++++++++++++++
 2 files changed, 72 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index 51c94b2a77b1..c59a289e428c 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -450,6 +450,19 @@ static int am65_cpts_ptp_gettimex(struct ptp_clock_info *ptp,
 	return 0;
 }
 
+u64 am65_cpts_ns_gettime(struct am65_cpts *cpts)
+{
+	u64 ns;
+
+	/* reuse ptp_clk_lock as it serialize ts push */
+	mutex_lock(&cpts->ptp_clk_lock);
+	ns = am65_cpts_gettime(cpts, NULL);
+	mutex_unlock(&cpts->ptp_clk_lock);
+
+	return ns;
+}
+EXPORT_SYMBOL_GPL(am65_cpts_ns_gettime);
+
 static int am65_cpts_ptp_settime(struct ptp_clock_info *ptp,
 				 const struct timespec64 *ts)
 {
@@ -494,6 +507,41 @@ static int am65_cpts_extts_enable(struct am65_cpts *cpts, u32 index, int on)
 	return 0;
 }
 
+int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx,
+			  struct am65_cpts_estf_cfg *cfg)
+{
+	u64 cycles;
+	u32 val;
+
+	cycles = cfg->ns_period * cpts->refclk_freq;
+	cycles = DIV_ROUND_UP(cycles, NSEC_PER_SEC);
+	if (cycles > U32_MAX)
+		return -EINVAL;
+
+	/* according to TRM should be zeroed */
+	am65_cpts_write32(cpts, 0, estf[idx].length);
+
+	val = upper_32_bits(cfg->ns_start);
+	am65_cpts_write32(cpts, val, estf[idx].comp_hi);
+	val = lower_32_bits(cfg->ns_start);
+	am65_cpts_write32(cpts, val, estf[idx].comp_lo);
+	val = lower_32_bits(cycles);
+	am65_cpts_write32(cpts, val, estf[idx].length);
+
+	dev_dbg(cpts->dev, "%s: ESTF:%u enabled\n", __func__, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(am65_cpts_estf_enable);
+
+void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx)
+{
+	am65_cpts_write32(cpts, 0, estf[idx].length);
+
+	dev_dbg(cpts->dev, "%s: ESTF:%u disabled\n", __func__, idx);
+}
+EXPORT_SYMBOL_GPL(am65_cpts_estf_disable);
+
 static void am65_cpts_perout_enable_hw(struct am65_cpts *cpts,
 				       struct ptp_perout_request *req, int on)
 {
diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h
index 0b55dc12ba48..98c1960b20b9 100644
--- a/drivers/net/ethernet/ti/am65-cpts.h
+++ b/drivers/net/ethernet/ti/am65-cpts.h
@@ -12,6 +12,11 @@
 
 struct am65_cpts;
 
+struct am65_cpts_estf_cfg {
+	u64 ns_period;
+	u64 ns_start;
+};
+
 #if IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)
 struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs,
 				   struct device_node *node);
@@ -19,6 +24,10 @@ int am65_cpts_phc_index(struct am65_cpts *cpts);
 void am65_cpts_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
 void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb);
 void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en);
+u64 am65_cpts_ns_gettime(struct am65_cpts *cpts);
+int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx,
+			  struct am65_cpts_estf_cfg *cfg);
+void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx);
 #else
 static inline struct am65_cpts *am65_cpts_create(struct device *dev,
 						 void __iomem *regs,
@@ -45,6 +54,21 @@ static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts,
 static inline void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
 {
 }
+
+static s64 am65_cpts_ns_gettime(struct am65_cpts *cpts)
+{
+	return 0;
+}
+
+static int am65_cpts_estf_enable(struct am65_cpts *cpts,
+				 int idx, struct am65_cpts_estf_cfg *cfg)
+{
+	return 0;
+}
+
+static void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx)
+{
+}
 #endif
 
 #endif /* K3_CPTS_H_ */
-- 
cgit v1.2.3


From 8127224c2708aa1558e2be7bbd1b7e9b07860de6 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Wed, 13 May 2020 09:26:15 -0400
Subject: ethernet: ti: am65-cpsw-qos: add TAPRIO offload support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined
in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018)
configuration. EST allows express queue traffic to be scheduled
(placed) on the wire at specific repeatable time intervals. In
Linux kernel, EST configuration is done through tc command and
the taprio scheduler in the net core implements a software only
scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration,
user indicate "flag 2" in the command which is then parsed by
taprio scheduler in net core and indicate that the command is to
be offloaded to h/w. taprio then offloads the command to the
driver by calling ndo_setup_tc() ndo ops. This patch implements
ndo_setup_tc() to offload EST configuration to CPSW h/w.

Currently driver supports only SetGateStates operation. EST
operates on a repeating time interval generated by the CPTS EST
function generator. Each Ethernet port has a global EST fetch
RAM that can be configured as 2 buffers, each of 64 locations
or one large buffer of 128 locations. In 2 buffer configuration,
a ping pong mechanism is used to hold the active schedule (oper)
in one buffer and new (admin) command in the other. Each 22-bit
fetch command consists of a 14-bit fetch count (14 MSB’s) and an
8-bit priority fetch allow (8 LSB’s) that will be applied for the
fetch count time in wireside clocks. Driver process each of the
sched-entry in the offload command and update the fetch RAM.
Driver configures duration in sched-entry into the fetch count
and Gate mask into the priority fetch bits of the RAM. Then
configures the CPTS EST function generator to activate the
schedule. Currently driver supports only 2 buffer configuration
which means driver supports a max cycle time of ~8 msec.

CPSW supports a configurable number of priority queues (up to 8)
and needs to be switched to this mode from the default round
robin mode before EST can be offloaded. User configures
these through ethtool commands (-L for changing number of
queues and --set-priv-flags to disable round robin mode).
Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag
is set. The flag is common for all ports, and so can't be just
overridden by taprio configuration w/o user involvement.
Command fails if pf_p0_rx_ptype_rrobin is already set in the
driver.

Scheds (commands) configuration depends on interface speed so
driver translates the duration to the fetch count based on
link speed. Each schedule can be constructed with several
command entries in fetch RAM  depending on interval. For example
if each sched has timer interval < ~130us on 1000 Mb link then
each sched consumes one command and have 1:1 mapping. When
Ethernet link goes down, driver purge the configuration if link
is down for more than 1 second.

The patch allows to update the timer and scheds memory only if it's
really needed, and skip cases required the user to stop timer by
configuring only shceds memory.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/Kconfig             |   9 +
 drivers/net/ethernet/ti/Makefile            |   2 +-
 drivers/net/ethernet/ti/am65-cpsw-ethtool.c |  12 +-
 drivers/net/ethernet/ti/am65-cpsw-nuss.c    |   9 +
 drivers/net/ethernet/ti/am65-cpsw-nuss.h    |   5 +
 drivers/net/ethernet/ti/am65-cpsw-qos.c     | 626 ++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/am65-cpsw-qos.h     |  29 ++
 7 files changed, 689 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/ti/am65-cpsw-qos.c
 create mode 100644 drivers/net/ethernet/ti/am65-cpsw-qos.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 988e907e3322..4d4852f00ff7 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -123,6 +123,15 @@ config TI_K3_AM65_CPTS
 	  protocol, Ethernet Enhanced Scheduled Traffic Operations (CPTS_ESTFn)
 	  and PCIe Subsystem Precision Time Measurement (PTM).
 
+config TI_AM65_CPSW_TAS
+	bool "Enable TAS offload in AM65 CPSW"
+	depends on TI_K3_AM65_CPSW_NUSS && NET_SCH_TAPRIO && TI_K3_AM65_CPTS
+	help
+	  Say y here to support Time Aware Shaper(TAS) offload in AM65 CPSW.
+	  AM65 CPSW hardware supports Enhanced Scheduled Traffic (EST)
+	  defined in IEEE 802.1Q 2018. The EST scheduler runs on CPTS and the
+	  TAS/EST schedule is updated in the Fetch RAM memory of the CPSW.
+
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
 	select TI_DAVINCI_MDIO
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index bf86067f9b4c..be95512d80b5 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -25,5 +25,5 @@ obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o
 keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o
 
 obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
-ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o
+ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o am65-cpsw-qos.o
 obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index 23661a6ed426..8c4690f3ebcb 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -730,9 +730,17 @@ static u32 am65_cpsw_get_ethtool_priv_flags(struct net_device *ndev)
 static int am65_cpsw_set_ethtool_priv_flags(struct net_device *ndev, u32 flags)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	int rrobin;
 
-	common->pf_p0_rx_ptype_rrobin =
-			!!(flags & AM65_CPSW_PRIV_P0_RX_PTYPE_RROBIN);
+	rrobin = !!(flags & AM65_CPSW_PRIV_P0_RX_PTYPE_RROBIN);
+
+	if (common->est_enabled && rrobin) {
+		netdev_err(ndev,
+			   "p0-rx-ptype-rrobin flag conflicts with QOS\n");
+		return -EINVAL;
+	}
+
+	common->pf_p0_rx_ptype_rrobin = rrobin;
 	am65_cpsw_nuss_set_p0_ptype(common);
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 8cdbb2b9b13a..4a8229864ae4 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -37,12 +37,14 @@
 #define AM65_CPSW_XGMII_BASE	0x2100
 #define AM65_CPSW_CPSW_NU_BASE	0x20000
 #define AM65_CPSW_NU_PORTS_BASE	0x1000
+#define AM65_CPSW_NU_FRAM_BASE	0x12000
 #define AM65_CPSW_NU_STATS_BASE	0x1a000
 #define AM65_CPSW_NU_ALE_BASE	0x1e000
 #define AM65_CPSW_NU_CPTS_BASE	0x1d000
 
 #define AM65_CPSW_NU_PORTS_OFFSET	0x1000
 #define AM65_CPSW_NU_STATS_PORT_OFFSET	0x200
+#define AM65_CPSW_NU_FRAM_PORT_OFFSET	0x200
 
 #define AM65_CPSW_MAX_PORTS	8
 
@@ -188,9 +190,11 @@ void am65_cpsw_nuss_adjust_link(struct net_device *ndev)
 		cpsw_ale_control_set(common->ale, port->port_id,
 				     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
 
+		am65_cpsw_qos_link_up(ndev, phy->speed);
 		netif_tx_wake_all_queues(ndev);
 	} else {
 		int tmo;
+
 		/* disable forwarding */
 		cpsw_ale_control_set(common->ale, port->port_id,
 				     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
@@ -204,6 +208,7 @@ void am65_cpsw_nuss_adjust_link(struct net_device *ndev)
 
 		cpsw_sl_ctl_reset(port->slave.mac_sl);
 
+		am65_cpsw_qos_link_down(ndev);
 		netif_tx_stop_all_queues(ndev);
 	}
 
@@ -1378,6 +1383,7 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = {
 	.ndo_vlan_rx_kill_vid	= am65_cpsw_nuss_ndo_slave_kill_vid,
 	.ndo_do_ioctl		= am65_cpsw_nuss_ndo_slave_ioctl,
 	.ndo_set_features	= am65_cpsw_nuss_ndo_slave_set_features,
+	.ndo_setup_tc           = am65_cpsw_qos_ndo_setup_tc,
 };
 
 static void am65_cpsw_nuss_slave_disable_unused(struct am65_cpsw_port *port)
@@ -1739,6 +1745,9 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		port->stat_base = common->cpsw_base + AM65_CPSW_NU_STATS_BASE +
 				  (AM65_CPSW_NU_STATS_PORT_OFFSET * port_id);
 		port->name = of_get_property(port_np, "label", NULL);
+		port->fetch_ram_base =
+				common->cpsw_base + AM65_CPSW_NU_FRAM_BASE +
+				(AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1));
 
 		port->disabled = !of_device_is_available(port_np);
 		if (port->disabled)
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 8a6382188cb5..9faf4fb1409b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -9,7 +9,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/phy.h>
 #include <linux/platform_device.h>
+#include "am65-cpsw-qos.h"
 
 struct am65_cpts;
 
@@ -38,10 +40,12 @@ struct am65_cpsw_port {
 	u32				port_id;
 	void __iomem			*port_base;
 	void __iomem			*stat_base;
+	void __iomem			*fetch_ram_base;
 	bool				disabled;
 	struct am65_cpsw_slave_data	slave;
 	bool				tx_ts_enabled;
 	bool				rx_ts_enabled;
+	struct am65_cpsw_qos		qos;
 };
 
 struct am65_cpsw_host {
@@ -104,6 +108,7 @@ struct am65_cpsw_common {
 	u32			cpsw_ver;
 	bool			pf_p0_rx_ptype_rrobin;
 	struct am65_cpts	*cpts;
+	int			est_enabled;
 };
 
 struct am65_cpsw_ndev_stats {
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c
new file mode 100644
index 000000000000..32eac04468bb
--- /dev/null
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Texas Instruments K3 AM65 Ethernet QoS submodule
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * quality of service module includes:
+ * Enhanced Scheduler Traffic (EST - P802.1Qbv/D2.2)
+ */
+
+#include <linux/pm_runtime.h>
+#include <linux/time.h>
+
+#include "am65-cpsw-nuss.h"
+#include "am65-cpsw-qos.h"
+#include "am65-cpts.h"
+
+#define AM65_CPSW_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_CTL			0x004
+#define AM65_CPSW_PN_REG_FIFO_STATUS		0x050
+#define AM65_CPSW_PN_REG_EST_CTL		0x060
+
+/* AM65_CPSW_REG_CTL register fields */
+#define AM65_CPSW_CTL_EST_EN			BIT(18)
+
+/* AM65_CPSW_PN_REG_CTL register fields */
+#define AM65_CPSW_PN_CTL_EST_PORT_EN		BIT(17)
+
+/* AM65_CPSW_PN_REG_EST_CTL register fields */
+#define AM65_CPSW_PN_EST_ONEBUF			BIT(0)
+#define AM65_CPSW_PN_EST_BUFSEL			BIT(1)
+#define AM65_CPSW_PN_EST_TS_EN			BIT(2)
+#define AM65_CPSW_PN_EST_TS_FIRST		BIT(3)
+#define AM65_CPSW_PN_EST_ONEPRI			BIT(4)
+#define AM65_CPSW_PN_EST_TS_PRI_MSK		GENMASK(7, 5)
+
+/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
+#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK	GENMASK(7, 0)
+#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK	GENMASK(15, 8)
+#define AM65_CPSW_PN_FST_EST_CNT_ERR		BIT(16)
+#define AM65_CPSW_PN_FST_EST_ADD_ERR		BIT(17)
+#define AM65_CPSW_PN_FST_EST_BUFACT		BIT(18)
+
+/* EST FETCH COMMAND RAM */
+#define AM65_CPSW_FETCH_RAM_CMD_NUM		0x80
+#define AM65_CPSW_FETCH_CNT_MSK			GENMASK(21, 8)
+#define AM65_CPSW_FETCH_CNT_MAX			(AM65_CPSW_FETCH_CNT_MSK >> 8)
+#define AM65_CPSW_FETCH_CNT_OFFSET		8
+#define AM65_CPSW_FETCH_ALLOW_MSK		GENMASK(7, 0)
+#define AM65_CPSW_FETCH_ALLOW_MAX		AM65_CPSW_FETCH_ALLOW_MSK
+
+enum timer_act {
+	TACT_PROG,		/* need program timer */
+	TACT_NEED_STOP,		/* need stop first */
+	TACT_SKIP_PROG,		/* just buffer can be updated */
+};
+
+static int am65_cpsw_port_est_enabled(struct am65_cpsw_port *port)
+{
+	return port->qos.est_oper || port->qos.est_admin;
+}
+
+static void am65_cpsw_est_enable(struct am65_cpsw_common *common, int enable)
+{
+	u32 val;
+
+	val = readl(common->cpsw_base + AM65_CPSW_REG_CTL);
+
+	if (enable)
+		val |= AM65_CPSW_CTL_EST_EN;
+	else
+		val &= ~AM65_CPSW_CTL_EST_EN;
+
+	writel(val, common->cpsw_base + AM65_CPSW_REG_CTL);
+	common->est_enabled = enable;
+}
+
+static void am65_cpsw_port_est_enable(struct am65_cpsw_port *port, int enable)
+{
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_CTL);
+	if (enable)
+		val |= AM65_CPSW_PN_CTL_EST_PORT_EN;
+	else
+		val &= ~AM65_CPSW_PN_CTL_EST_PORT_EN;
+
+	writel(val, port->port_base + AM65_CPSW_PN_REG_CTL);
+}
+
+/* target new EST RAM buffer, actual toggle happens after cycle completion */
+static void am65_cpsw_port_est_assign_buf_num(struct net_device *ndev,
+					      int buf_num)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_EST_CTL);
+	if (buf_num)
+		val |= AM65_CPSW_PN_EST_BUFSEL;
+	else
+		val &= ~AM65_CPSW_PN_EST_BUFSEL;
+
+	writel(val, port->port_base + AM65_CPSW_PN_REG_EST_CTL);
+}
+
+/* am65_cpsw_port_est_is_swapped() - Indicate if h/w is transitioned
+ * admin -> oper or not
+ *
+ * Return true if already transitioned. i.e oper is equal to admin and buf
+ * numbers match (est_oper->buf match with est_admin->buf).
+ * false if before transition. i.e oper is not equal to admin, (i.e a
+ * previous admin command is waiting to be transitioned to oper state
+ * and est_oper->buf not match with est_oper->buf).
+ */
+static int am65_cpsw_port_est_is_swapped(struct net_device *ndev, int *oper,
+					 int *admin)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_FIFO_STATUS);
+	*oper = !!(val & AM65_CPSW_PN_FST_EST_BUFACT);
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_EST_CTL);
+	*admin = !!(val & AM65_CPSW_PN_EST_BUFSEL);
+
+	return *admin == *oper;
+}
+
+/* am65_cpsw_port_est_get_free_buf_num() - Get free buffer number for
+ * Admin to program the new schedule.
+ *
+ * Logic as follows:-
+ * If oper is same as admin, return the other buffer (!oper) as the admin
+ * buffer.  If oper is not the same, driver let the current oper to continue
+ * as it is in the process of transitioning from admin -> oper. So keep the
+ * oper by selecting the same oper buffer by writing to EST_BUFSEL bit in
+ * EST CTL register. In the second iteration they will match and code returns.
+ * The actual buffer to write command is selected later before it is ready
+ * to update the schedule.
+ */
+static int am65_cpsw_port_est_get_free_buf_num(struct net_device *ndev)
+{
+	int oper, admin;
+	int roll = 2;
+
+	while (roll--) {
+		if (am65_cpsw_port_est_is_swapped(ndev, &oper, &admin))
+			return !oper;
+
+		/* admin is not set, so hinder transition as it's not allowed
+		 * to touch memory in-flight, by targeting same oper buf.
+		 */
+		am65_cpsw_port_est_assign_buf_num(ndev, oper);
+
+		dev_info(&ndev->dev,
+			 "Prev. EST admin cycle is in transit %d -> %d\n",
+			 oper, admin);
+	}
+
+	return admin;
+}
+
+static void am65_cpsw_admin_to_oper(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	if (port->qos.est_oper)
+		devm_kfree(&ndev->dev, port->qos.est_oper);
+
+	port->qos.est_oper = port->qos.est_admin;
+	port->qos.est_admin = NULL;
+}
+
+static void am65_cpsw_port_est_get_buf_num(struct net_device *ndev,
+					   struct am65_cpsw_est *est_new)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	u32 val;
+
+	val = readl(port->port_base + AM65_CPSW_PN_REG_EST_CTL);
+	val &= ~AM65_CPSW_PN_EST_ONEBUF;
+	writel(val, port->port_base + AM65_CPSW_PN_REG_EST_CTL);
+
+	est_new->buf = am65_cpsw_port_est_get_free_buf_num(ndev);
+
+	/* rolled buf num means changed buf while configuring */
+	if (port->qos.est_oper && port->qos.est_admin &&
+	    est_new->buf == port->qos.est_oper->buf)
+		am65_cpsw_admin_to_oper(ndev);
+}
+
+static void am65_cpsw_est_set(struct net_device *ndev, int enable)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_common *common = port->common;
+	int common_enable = 0;
+	int i;
+
+	am65_cpsw_port_est_enable(port, enable);
+
+	for (i = 0; i < common->port_num; i++)
+		common_enable |= am65_cpsw_port_est_enabled(&common->ports[i]);
+
+	common_enable |= enable;
+	am65_cpsw_est_enable(common, common_enable);
+}
+
+/* This update is supposed to be used in any routine before getting real state
+ * of admin -> oper transition, particularly it's supposed to be used in some
+ * generic routine for providing real state to Taprio Qdisc.
+ */
+static void am65_cpsw_est_update_state(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	int oper, admin;
+
+	if (!port->qos.est_admin)
+		return;
+
+	if (!am65_cpsw_port_est_is_swapped(ndev, &oper, &admin))
+		return;
+
+	am65_cpsw_admin_to_oper(ndev);
+}
+
+/* Fetch command count it's number of bytes in Gigabit mode or nibbles in
+ * 10/100Mb mode. So, having speed and time in ns, recalculate ns to number of
+ * bytes/nibbles that can be sent while transmission on given speed.
+ */
+static int am65_est_cmd_ns_to_cnt(u64 ns, int link_speed)
+{
+	u64 temp;
+
+	temp = ns * link_speed;
+	if (link_speed < SPEED_1000)
+		temp <<= 1;
+
+	return DIV_ROUND_UP(temp, 8 * 1000);
+}
+
+static void __iomem *am65_cpsw_est_set_sched_cmds(void __iomem *addr,
+						  int fetch_cnt,
+						  int fetch_allow)
+{
+	u32 prio_mask, cmd_fetch_cnt, cmd;
+
+	do {
+		if (fetch_cnt > AM65_CPSW_FETCH_CNT_MAX) {
+			fetch_cnt -= AM65_CPSW_FETCH_CNT_MAX;
+			cmd_fetch_cnt = AM65_CPSW_FETCH_CNT_MAX;
+		} else {
+			cmd_fetch_cnt = fetch_cnt;
+			/* fetch count can't be less than 16? */
+			if (cmd_fetch_cnt && cmd_fetch_cnt < 16)
+				cmd_fetch_cnt = 16;
+
+			fetch_cnt = 0;
+		}
+
+		prio_mask = fetch_allow & AM65_CPSW_FETCH_ALLOW_MSK;
+		cmd = (cmd_fetch_cnt << AM65_CPSW_FETCH_CNT_OFFSET) | prio_mask;
+
+		writel(cmd, addr);
+		addr += 4;
+	} while (fetch_cnt);
+
+	return addr;
+}
+
+static int am65_cpsw_est_calc_cmd_num(struct net_device *ndev,
+				      struct tc_taprio_qopt_offload *taprio,
+				      int link_speed)
+{
+	int i, cmd_cnt, cmd_sum = 0;
+	u32 fetch_cnt;
+
+	for (i = 0; i < taprio->num_entries; i++) {
+		if (taprio->entries[i].command != TC_TAPRIO_CMD_SET_GATES) {
+			dev_err(&ndev->dev, "Only SET command is supported");
+			return -EINVAL;
+		}
+
+		fetch_cnt = am65_est_cmd_ns_to_cnt(taprio->entries[i].interval,
+						   link_speed);
+
+		cmd_cnt = DIV_ROUND_UP(fetch_cnt, AM65_CPSW_FETCH_CNT_MAX);
+		if (!cmd_cnt)
+			cmd_cnt++;
+
+		cmd_sum += cmd_cnt;
+
+		if (!fetch_cnt)
+			break;
+	}
+
+	return cmd_sum;
+}
+
+static int am65_cpsw_est_check_scheds(struct net_device *ndev,
+				      struct am65_cpsw_est *est_new)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	int cmd_num;
+
+	cmd_num = am65_cpsw_est_calc_cmd_num(ndev, &est_new->taprio,
+					     port->qos.link_speed);
+	if (cmd_num < 0)
+		return cmd_num;
+
+	if (cmd_num > AM65_CPSW_FETCH_RAM_CMD_NUM / 2) {
+		dev_err(&ndev->dev, "No fetch RAM");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void am65_cpsw_est_set_sched_list(struct net_device *ndev,
+					 struct am65_cpsw_est *est_new)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	u32 fetch_cnt, fetch_allow, all_fetch_allow = 0;
+	void __iomem *ram_addr, *max_ram_addr;
+	struct tc_taprio_sched_entry *entry;
+	int i, ram_size;
+
+	ram_addr = port->fetch_ram_base;
+	ram_size = AM65_CPSW_FETCH_RAM_CMD_NUM * 2;
+	ram_addr += est_new->buf * ram_size;
+
+	max_ram_addr = ram_size + ram_addr;
+	for (i = 0; i < est_new->taprio.num_entries; i++) {
+		entry = &est_new->taprio.entries[i];
+
+		fetch_cnt = am65_est_cmd_ns_to_cnt(entry->interval,
+						   port->qos.link_speed);
+		fetch_allow = entry->gate_mask;
+		if (fetch_allow > AM65_CPSW_FETCH_ALLOW_MAX)
+			dev_dbg(&ndev->dev, "fetch_allow > 8 bits: %d\n",
+				fetch_allow);
+
+		ram_addr = am65_cpsw_est_set_sched_cmds(ram_addr, fetch_cnt,
+							fetch_allow);
+
+		if (!fetch_cnt && i < est_new->taprio.num_entries - 1) {
+			dev_info(&ndev->dev,
+				 "next scheds after %d have no impact", i + 1);
+			break;
+		}
+
+		all_fetch_allow |= fetch_allow;
+	}
+
+	/* end cmd, enabling non-timed queues for potential over cycle time */
+	if (ram_addr < max_ram_addr)
+		writel(~all_fetch_allow & AM65_CPSW_FETCH_ALLOW_MSK, ram_addr);
+}
+
+/**
+ * Enable ESTf periodic output, set cycle start time and interval.
+ */
+static int am65_cpsw_timer_set(struct net_device *ndev,
+			       struct am65_cpsw_est *est_new)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_common *common = port->common;
+	struct am65_cpts *cpts = common->cpts;
+	struct am65_cpts_estf_cfg cfg;
+
+	cfg.ns_period = est_new->taprio.cycle_time;
+	cfg.ns_start = est_new->taprio.base_time;
+
+	return am65_cpts_estf_enable(cpts, port->port_id - 1, &cfg);
+}
+
+static void am65_cpsw_timer_stop(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpts *cpts = port->common->cpts;
+
+	am65_cpts_estf_disable(cpts, port->port_id - 1);
+}
+
+static enum timer_act am65_cpsw_timer_act(struct net_device *ndev,
+					  struct am65_cpsw_est *est_new)
+{
+	struct tc_taprio_qopt_offload *taprio_oper, *taprio_new;
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpts *cpts = port->common->cpts;
+	u64 cur_time;
+	s64 diff;
+
+	if (!port->qos.est_oper)
+		return TACT_PROG;
+
+	taprio_new = &est_new->taprio;
+	taprio_oper = &port->qos.est_oper->taprio;
+
+	if (taprio_new->cycle_time != taprio_oper->cycle_time)
+		return TACT_NEED_STOP;
+
+	/* in order to avoid timer reset get base_time form oper taprio */
+	if (!taprio_new->base_time && taprio_oper)
+		taprio_new->base_time = taprio_oper->base_time;
+
+	if (taprio_new->base_time == taprio_oper->base_time)
+		return TACT_SKIP_PROG;
+
+	/* base times are cycle synchronized */
+	diff = taprio_new->base_time - taprio_oper->base_time;
+	diff = diff < 0 ? -diff : diff;
+	if (diff % taprio_new->cycle_time)
+		return TACT_NEED_STOP;
+
+	cur_time = am65_cpts_ns_gettime(cpts);
+	if (taprio_new->base_time <= cur_time + taprio_new->cycle_time)
+		return TACT_SKIP_PROG;
+
+	/* TODO: Admin schedule at future time is not currently supported */
+	return TACT_NEED_STOP;
+}
+
+static void am65_cpsw_stop_est(struct net_device *ndev)
+{
+	am65_cpsw_est_set(ndev, 0);
+	am65_cpsw_timer_stop(ndev);
+}
+
+static void am65_cpsw_purge_est(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	am65_cpsw_stop_est(ndev);
+
+	if (port->qos.est_admin)
+		devm_kfree(&ndev->dev, port->qos.est_admin);
+
+	if (port->qos.est_oper)
+		devm_kfree(&ndev->dev, port->qos.est_oper);
+
+	port->qos.est_oper = NULL;
+	port->qos.est_admin = NULL;
+}
+
+static int am65_cpsw_configure_taprio(struct net_device *ndev,
+				      struct am65_cpsw_est *est_new)
+{
+	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpts *cpts = common->cpts;
+	int ret = 0, tact = TACT_PROG;
+
+	am65_cpsw_est_update_state(ndev);
+
+	if (!est_new->taprio.enable) {
+		am65_cpsw_stop_est(ndev);
+		return ret;
+	}
+
+	ret = am65_cpsw_est_check_scheds(ndev, est_new);
+	if (ret < 0)
+		return ret;
+
+	tact = am65_cpsw_timer_act(ndev, est_new);
+	if (tact == TACT_NEED_STOP) {
+		dev_err(&ndev->dev,
+			"Can't toggle estf timer, stop taprio first");
+		return -EINVAL;
+	}
+
+	if (tact == TACT_PROG)
+		am65_cpsw_timer_stop(ndev);
+
+	if (!est_new->taprio.base_time)
+		est_new->taprio.base_time = am65_cpts_ns_gettime(cpts);
+
+	am65_cpsw_port_est_get_buf_num(ndev, est_new);
+	am65_cpsw_est_set_sched_list(ndev, est_new);
+	am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf);
+
+	am65_cpsw_est_set(ndev, est_new->taprio.enable);
+
+	if (tact == TACT_PROG) {
+		ret = am65_cpsw_timer_set(ndev, est_new);
+		if (ret) {
+			dev_err(&ndev->dev, "Failed to set cycle time");
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+static void am65_cpsw_cp_taprio(struct tc_taprio_qopt_offload *from,
+				struct tc_taprio_qopt_offload *to)
+{
+	int i;
+
+	*to = *from;
+	for (i = 0; i < from->num_entries; i++)
+		to->entries[i] = from->entries[i];
+}
+
+static int am65_cpsw_set_taprio(struct net_device *ndev, void *type_data)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct tc_taprio_qopt_offload *taprio = type_data;
+	struct am65_cpsw_est *est_new;
+	size_t size;
+	int ret = 0;
+
+	if (taprio->cycle_time_extension) {
+		dev_err(&ndev->dev, "Failed to set cycle time extension");
+		return -EOPNOTSUPP;
+	}
+
+	size = sizeof(struct tc_taprio_sched_entry) * taprio->num_entries +
+	       sizeof(struct am65_cpsw_est);
+
+	est_new = devm_kzalloc(&ndev->dev, size, GFP_KERNEL);
+	if (!est_new)
+		return -ENOMEM;
+
+	am65_cpsw_cp_taprio(taprio, &est_new->taprio);
+	ret = am65_cpsw_configure_taprio(ndev, est_new);
+	if (!ret) {
+		if (taprio->enable) {
+			if (port->qos.est_admin)
+				devm_kfree(&ndev->dev, port->qos.est_admin);
+
+			port->qos.est_admin = est_new;
+		} else {
+			devm_kfree(&ndev->dev, est_new);
+			am65_cpsw_purge_est(ndev);
+		}
+	} else {
+		devm_kfree(&ndev->dev, est_new);
+	}
+
+	return ret;
+}
+
+static void am65_cpsw_est_link_up(struct net_device *ndev, int link_speed)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	ktime_t cur_time;
+	s64 delta;
+
+	port->qos.link_speed = link_speed;
+	if (!am65_cpsw_port_est_enabled(port))
+		return;
+
+	if (port->qos.link_down_time) {
+		cur_time = ktime_get();
+		delta = ktime_us_delta(cur_time, port->qos.link_down_time);
+		if (delta > USEC_PER_SEC) {
+			dev_err(&ndev->dev,
+				"Link has been lost too long, stopping TAS");
+			goto purge_est;
+		}
+	}
+
+	return;
+
+purge_est:
+	am65_cpsw_purge_est(ndev);
+}
+
+static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_common *common = port->common;
+
+	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
+		return -ENODEV;
+
+	if (!netif_running(ndev)) {
+		dev_err(&ndev->dev, "interface is down, link speed unknown\n");
+		return -ENETDOWN;
+	}
+
+	if (common->pf_p0_rx_ptype_rrobin) {
+		dev_err(&ndev->dev,
+			"p0-rx-ptype-rrobin flag conflicts with taprio qdisc\n");
+		return -EINVAL;
+	}
+
+	if (port->qos.link_speed == SPEED_UNKNOWN)
+		return -ENOLINK;
+
+	return am65_cpsw_set_taprio(ndev, type_data);
+}
+
+int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			       void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return am65_cpsw_setup_taprio(ndev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
+		return;
+
+	am65_cpsw_est_link_up(ndev, link_speed);
+	port->qos.link_down_time = 0;
+}
+
+void am65_cpsw_qos_link_down(struct net_device *ndev)
+{
+	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+
+	if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS))
+		return;
+
+	if (!port->qos.link_down_time)
+		port->qos.link_down_time = ktime_get();
+
+	port->qos.link_speed = SPEED_UNKNOWN;
+}
diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.h b/drivers/net/ethernet/ti/am65-cpsw-qos.h
new file mode 100644
index 000000000000..e8f1b6b59e93
--- /dev/null
+++ b/drivers/net/ethernet/ti/am65-cpsw-qos.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+#ifndef AM65_CPSW_QOS_H_
+#define AM65_CPSW_QOS_H_
+
+#include <linux/netdevice.h>
+#include <net/pkt_sched.h>
+
+struct am65_cpsw_est {
+	int buf;
+	/* has to be the last one */
+	struct tc_taprio_qopt_offload taprio;
+};
+
+struct am65_cpsw_qos {
+	struct am65_cpsw_est *est_admin;
+	struct am65_cpsw_est *est_oper;
+	ktime_t link_down_time;
+	int link_speed;
+};
+
+int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			       void *type_data);
+void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
+void am65_cpsw_qos_link_down(struct net_device *ndev);
+
+#endif /* AM65_CPSW_QOS_H_ */
-- 
cgit v1.2.3


From bcab67822d77142c31f69656dd24226f23acc82e Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Wed, 13 May 2020 22:37:33 +0000
Subject: hinic: add set_ringparam ethtool_ops support

support to change TX/RX queue depth with ethtool -G

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_dev.h     |  2 +
 drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 78 +++++++++++++++++++++--
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c  | 11 ++--
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h  |  2 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_io.c   |  4 +-
 drivers/net/ethernet/huawei/hinic/hinic_hw_io.h   |  3 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c   |  1 +
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h   |  3 +
 drivers/net/ethernet/huawei/hinic/hinic_main.c    |  9 ++-
 drivers/net/ethernet/huawei/hinic/hinic_port.c    |  2 +-
 drivers/net/ethernet/huawei/hinic/hinic_port.h    |  4 ++
 11 files changed, 104 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index a621ebbf7610..48b40be3e84d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -69,6 +69,8 @@ struct hinic_dev {
 
 	struct hinic_txq                *txqs;
 	struct hinic_rxq                *rxqs;
+	u16				sq_depth;
+	u16				rq_depth;
 
 	struct hinic_txq_stats          tx_stats;
 	struct hinic_rxq_stats          rx_stats;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index b426eeced069..ace18d258049 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -538,12 +538,81 @@ static void hinic_get_drvinfo(struct net_device *netdev,
 static void hinic_get_ringparam(struct net_device *netdev,
 				struct ethtool_ringparam *ring)
 {
-	ring->rx_max_pending = HINIC_RQ_DEPTH;
-	ring->tx_max_pending = HINIC_SQ_DEPTH;
-	ring->rx_pending = HINIC_RQ_DEPTH;
-	ring->tx_pending = HINIC_SQ_DEPTH;
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+
+	ring->rx_max_pending = HINIC_MAX_QUEUE_DEPTH;
+	ring->tx_max_pending = HINIC_MAX_QUEUE_DEPTH;
+	ring->rx_pending = nic_dev->rq_depth;
+	ring->tx_pending = nic_dev->sq_depth;
 }
 
+static int check_ringparam_valid(struct hinic_dev *nic_dev,
+				 struct ethtool_ringparam *ring)
+{
+	if (ring->rx_jumbo_pending || ring->rx_mini_pending) {
+		netif_err(nic_dev, drv, nic_dev->netdev,
+			  "Unsupported rx_jumbo_pending/rx_mini_pending\n");
+		return -EINVAL;
+	}
+
+	if (ring->tx_pending > HINIC_MAX_QUEUE_DEPTH ||
+	    ring->tx_pending < HINIC_MIN_QUEUE_DEPTH ||
+	    ring->rx_pending > HINIC_MAX_QUEUE_DEPTH ||
+	    ring->rx_pending < HINIC_MIN_QUEUE_DEPTH) {
+		netif_err(nic_dev, drv, nic_dev->netdev,
+			  "Queue depth out of range [%d-%d]\n",
+			  HINIC_MIN_QUEUE_DEPTH, HINIC_MAX_QUEUE_DEPTH);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hinic_set_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *ring)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	u16 new_sq_depth, new_rq_depth;
+	int err;
+
+	err = check_ringparam_valid(nic_dev, ring);
+	if (err)
+		return err;
+
+	new_sq_depth = (u16)(1U << (u16)ilog2(ring->tx_pending));
+	new_rq_depth = (u16)(1U << (u16)ilog2(ring->rx_pending));
+
+	if (new_sq_depth == nic_dev->sq_depth &&
+	    new_rq_depth == nic_dev->rq_depth)
+		return 0;
+
+	netif_info(nic_dev, drv, netdev,
+		   "Change Tx/Rx ring depth from %d/%d to %d/%d\n",
+		   nic_dev->sq_depth, nic_dev->rq_depth,
+		   new_sq_depth, new_rq_depth);
+
+	nic_dev->sq_depth = new_sq_depth;
+	nic_dev->rq_depth = new_rq_depth;
+
+	if (netif_running(netdev)) {
+		netif_info(nic_dev, drv, netdev, "Restarting netdev\n");
+		err = hinic_close(netdev);
+		if (err) {
+			netif_err(nic_dev, drv, netdev,
+				  "Failed to close netdev\n");
+			return -EFAULT;
+		}
+
+		err = hinic_open(netdev);
+		if (err) {
+			netif_err(nic_dev, drv, netdev,
+				  "Failed to open netdev\n");
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
 static void hinic_get_channels(struct net_device *netdev,
 			       struct ethtool_channels *channels)
 {
@@ -1148,6 +1217,7 @@ static const struct ethtool_ops hinic_ethtool_ops = {
 	.get_drvinfo = hinic_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = hinic_get_ringparam,
+	.set_ringparam = hinic_set_ringparam,
 	.get_channels = hinic_get_channels,
 	.get_rxnfc = hinic_get_rxnfc,
 	.set_rxnfc = hinic_set_rxnfc,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 2879b0445eba..0245da02efbb 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -269,8 +269,8 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
  *
  * Return 0 - Success, negative - Failure
  **/
-static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth,
-			 unsigned int sq_depth)
+static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int sq_depth,
+			 unsigned int rq_depth)
 {
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct hinic_cmd_hw_ioctxt hw_ioctxt;
@@ -435,7 +435,7 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
  *
  * Return 0 - Success, negative - Failure
  **/
-int hinic_hwdev_ifup(struct hinic_hwdev *hwdev)
+int hinic_hwdev_ifup(struct hinic_hwdev *hwdev, u16 sq_depth, u16 rq_depth)
 {
 	struct hinic_func_to_io *func_to_io = &hwdev->func_to_io;
 	struct hinic_cap *nic_cap = &hwdev->nic_cap;
@@ -458,6 +458,9 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev)
 
 	ceq_msix_entries = &hwdev->msix_entries[num_aeqs];
 	func_to_io->hwdev = hwdev;
+	func_to_io->sq_depth = sq_depth;
+	func_to_io->rq_depth = rq_depth;
+
 	err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs,
 			    ceq_msix_entries);
 	if (err) {
@@ -482,7 +485,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev)
 		hinic_db_state_set(hwif, HINIC_DB_ENABLE);
 	}
 
-	err = set_hw_ioctxt(hwdev, HINIC_SQ_DEPTH, HINIC_RQ_DEPTH);
+	err = set_hw_ioctxt(hwdev, sq_depth, rq_depth);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to set HW IO ctxt\n");
 		goto err_hw_ioctxt;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index ce57914bef72..71ea7e46dbbc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -347,7 +347,7 @@ int hinic_hilink_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_hilink_cmd cmd,
 			 void *buf_in, u16 in_size, void *buf_out,
 			 u16 *out_size);
 
-int hinic_hwdev_ifup(struct hinic_hwdev *hwdev);
+int hinic_hwdev_ifup(struct hinic_hwdev *hwdev, u16 sq_depth, u16 rq_depth);
 
 void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index a4581c988a63..3e3fa742e476 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -282,7 +282,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io,
 
 	err = hinic_wq_allocate(&func_to_io->wqs, &func_to_io->sq_wq[q_id],
 				HINIC_SQ_WQEBB_SIZE, HINIC_SQ_PAGE_SIZE,
-				HINIC_SQ_DEPTH, HINIC_SQ_WQE_MAX_SIZE);
+				func_to_io->sq_depth, HINIC_SQ_WQE_MAX_SIZE);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to allocate WQ for SQ\n");
 		return err;
@@ -290,7 +290,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io,
 
 	err = hinic_wq_allocate(&func_to_io->wqs, &func_to_io->rq_wq[q_id],
 				HINIC_RQ_WQEBB_SIZE, HINIC_RQ_PAGE_SIZE,
-				HINIC_RQ_DEPTH, HINIC_RQ_WQE_SIZE);
+				func_to_io->rq_depth, HINIC_RQ_WQE_SIZE);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to allocate WQ for RQ\n");
 		goto err_rq_alloc;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
index 28c0594f636d..214f162f7579 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
@@ -60,6 +60,9 @@ struct hinic_func_to_io {
 	struct hinic_qp         *qps;
 	u16                     max_qps;
 
+	u16			sq_depth;
+	u16			rq_depth;
+
 	void __iomem            **sq_db;
 	void __iomem            *db_base;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index 20c5c8ea452e..fcf7bfe4aa47 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -643,6 +643,7 @@ void hinic_sq_write_db(struct hinic_sq *sq, u16 prod_idx, unsigned int wqe_size,
 
 	/* increment prod_idx to the next */
 	prod_idx += ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	prod_idx = SQ_MASKED_IDX(sq, prod_idx);
 
 	wmb();  /* Write all before the doorbell */
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index c30d092e48d5..ca3e2d060284 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -44,6 +44,9 @@
 #define HINIC_SQ_DEPTH                          SZ_4K
 #define HINIC_RQ_DEPTH                          SZ_4K
 
+#define HINIC_MAX_QUEUE_DEPTH			SZ_4K
+#define HINIC_MIN_QUEUE_DEPTH			128
+
 /* In any change to HINIC_RX_BUF_SZ, HINIC_RX_BUF_SZ_IDX must be changed */
 #define HINIC_RX_BUF_SZ                         2048
 #define HINIC_RX_BUF_SZ_IDX			HINIC_RX_BUF_SZ_2048_IDX
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 3d6569d7bac8..e3ff119fe341 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -372,14 +372,15 @@ static void hinic_enable_rss(struct hinic_dev *nic_dev)
 		netif_err(nic_dev, drv, netdev, "Failed to init rss\n");
 }
 
-static int hinic_open(struct net_device *netdev)
+int hinic_open(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	enum hinic_port_link_state link_state;
 	int err, ret;
 
 	if (!(nic_dev->flags & HINIC_INTF_UP)) {
-		err = hinic_hwdev_ifup(nic_dev->hwdev);
+		err = hinic_hwdev_ifup(nic_dev->hwdev, nic_dev->sq_depth,
+				       nic_dev->rq_depth);
 		if (err) {
 			netif_err(nic_dev, drv, netdev,
 				  "Failed - HW interface up\n");
@@ -483,7 +484,7 @@ err_create_txqs:
 	return err;
 }
 
-static int hinic_close(struct net_device *netdev)
+int hinic_close(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
@@ -1038,6 +1039,8 @@ static int nic_dev_init(struct pci_dev *pdev)
 	nic_dev->rxqs = NULL;
 	nic_dev->tx_weight = tx_weight;
 	nic_dev->rx_weight = rx_weight;
+	nic_dev->sq_depth = HINIC_SQ_DEPTH;
+	nic_dev->rq_depth = HINIC_RQ_DEPTH;
 	nic_dev->sriov_info.hwdev = hwdev;
 	nic_dev->sriov_info.pdev = pdev;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 2edb6127f9fb..175c0ee00038 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -473,7 +473,7 @@ int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs)
 
 	rq_num.func_id = HINIC_HWIF_FUNC_IDX(hwif);
 	rq_num.num_rqs = num_rqs;
-	rq_num.rq_depth = ilog2(HINIC_SQ_DEPTH);
+	rq_num.rq_depth = ilog2(nic_dev->rq_depth);
 
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RQ_IQ_MAP,
 				 &rq_num, sizeof(rq_num),
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 5f34308abd2b..661c6322dc15 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -736,4 +736,8 @@ int hinic_get_hw_pause_info(struct hinic_hwdev *hwdev,
 int hinic_set_hw_pause_info(struct hinic_hwdev *hwdev,
 			    struct hinic_pause_config *pause_info);
 
+int hinic_open(struct net_device *netdev);
+
+int hinic_close(struct net_device *netdev);
+
 #endif
-- 
cgit v1.2.3


From aa443b3f8f3affdc2ea6508ecb20706eee3f67bf Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 14 May 2020 23:39:34 +0200
Subject: r8169: remove not needed checks in rtl8169_set_eee

After 9de5d235b60a ("net: phy: fix aneg restart in phy_ethtool_set_eee")
we don't need the check for aneg being enabled any longer, and as
discussed with Russell configuring the EEE advertisement should be
supported even if we're in a half-duplex mode currently.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b4e49c446bd0..a2e778417144 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1919,12 +1919,6 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data)
 		goto out;
 	}
 
-	if (dev->phydev->autoneg == AUTONEG_DISABLE ||
-	    dev->phydev->duplex != DUPLEX_FULL) {
-		ret = -EPROTONOSUPPORT;
-		goto out;
-	}
-
 	ret = phy_ethtool_set_eee(tp->phydev, data);
 
 	if (!ret)
-- 
cgit v1.2.3


From 9b65d2ffe853e4cf81585eaf60ce00237b277dc0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 14 May 2020 23:44:07 +0200
Subject: r8169: don't include linux/moduleparam.h

93882c6f210a ("r8169: switch from netif_xxx message functions to
netdev_xxx") removed the last module parameter from the driver,
therefore there's no need any longer to include linux/moduleparam.h.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a2e778417144..d926583b407f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
-- 
cgit v1.2.3


From 63fe91ab3d1c5c0b4497b993b8eeaa54f6688d53 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:49:07 +0200
Subject: bnxt: Add XDP frame size to driver

This driver uses full PAGE_SIZE pages when XDP is enabled.

In case of XDP uses driver uses __bnxt_alloc_rx_page which does full
page DMA-map. Thus, xdp_adjust_tail grow is DMA compliant for XDP_TX
action that does DMA-sync.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Cc: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Link: https://lore.kernel.org/bpf/158945334769.97035.13437970179897613984.stgit@firesoul
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c6f6f2033880..5e3b4a3b69ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -138,6 +138,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = *data_ptr + *len;
 	xdp.rxq = &rxr->xdp_rxq;
+	xdp.frame_sz = PAGE_SIZE; /* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
 	orig_data = xdp.data;
 
 	rcu_read_lock();
-- 
cgit v1.2.3


From 983e43451830742fa93f83656ccbdcb865ea4259 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:49:12 +0200
Subject: sfc: Add XDP frame size

This driver uses RX page-split when possible. It was recently fixed
in commit 86e85bf6981c ("sfc: fix XDP-redirect in this driver") to
add needed tailroom for XDP-redirect.

After the fix efx->rx_page_buf_step is the frame size, with enough
head and tail-room for XDP-redirect.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/158945335278.97035.14611425333184621652.stgit@firesoul
---
 drivers/net/ethernet/sfc/rx.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 260352d97d9d..68c47a8c71df 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -308,6 +308,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + rx_buf->len;
 	xdp.rxq = &rx_queue->xdp_rxq_info;
+	xdp.frame_sz = efx->rx_page_buf_step;
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 494f44d54e25dd79af0ed6734c2d6be0aa0b6d94 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:49:17 +0200
Subject: mvneta: Add XDP frame size to driver

This marvell driver mvneta uses PAGE_SIZE frames, which makes it
really easy to convert.  Driver updates rxq and now frame_sz
once per NAPI call.

This driver takes advantage of page_pool PP_FLAG_DMA_SYNC_DEV that
can help reduce the number of cache-lines that need to be flushed
when doing DMA sync for_device. Due to xdp_adjust_tail can grow the
area accessible to the by the CPU (can possibly write into), then max
sync length *after* bpf_prog_run_xdp() needs to be taken into account.

For XDP_TX action the driver is smart and does DMA-sync. When growing
tail this is still safe, because page_pool have DMA-mapped the entire
page size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Cc: thomas.petazzoni@bootlin.com
Link: https://lore.kernel.org/bpf/158945335786.97035.12714388304493736747.stgit@firesoul
---
 drivers/net/ethernet/marvell/mvneta.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e0e9e56830c0..41d2a0eac5fa 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2148,12 +2148,17 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	       struct bpf_prog *prog, struct xdp_buff *xdp,
 	       struct mvneta_stats *stats)
 {
-	unsigned int len;
+	unsigned int len, sync;
+	struct page *page;
 	u32 ret, act;
 
 	len = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
 	act = bpf_prog_run_xdp(prog, xdp);
 
+	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+	sync = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
+	sync = max(sync, len);
+
 	switch (act) {
 	case XDP_PASS:
 		stats->xdp_pass++;
@@ -2164,9 +2169,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		err = xdp_do_redirect(pp->dev, xdp, prog);
 		if (unlikely(err)) {
 			ret = MVNETA_XDP_DROPPED;
-			page_pool_put_page(rxq->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
 		} else {
 			ret = MVNETA_XDP_REDIR;
 			stats->xdp_redirect++;
@@ -2175,10 +2179,10 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	}
 	case XDP_TX:
 		ret = mvneta_xdp_xmit_back(pp, xdp);
-		if (ret != MVNETA_XDP_TX)
-			page_pool_put_page(rxq->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+		if (ret != MVNETA_XDP_TX) {
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
+		}
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2187,8 +2191,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		trace_xdp_exception(pp->dev, prog, act);
 		/* fall through */
 	case XDP_DROP:
-		page_pool_put_page(rxq->page_pool,
-				   virt_to_head_page(xdp->data), len, true);
+		page = virt_to_head_page(xdp->data);
+		page_pool_put_page(rxq->page_pool, page, sync, true);
 		ret = MVNETA_XDP_DROPPED;
 		stats->xdp_drop++;
 		break;
@@ -2320,6 +2324,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(pp->xdp_prog);
 	xdp_buf.rxq = &rxq->xdp_rxq;
+	xdp_buf.frame_sz = PAGE_SIZE;
 
 	/* Fairness NAPI loop */
 	while (rx_proc < budget && rx_proc < rx_todo) {
-- 
cgit v1.2.3


From 495de55f70199bd7ea09079c484283e58bf75c82 Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Thu, 14 May 2020 12:49:23 +0200
Subject: net: netsec: Add support for XDP frame size

This driver takes advantage of page_pool PP_FLAG_DMA_SYNC_DEV that
can help reduce the number of cache-lines that need to be flushed
when doing DMA sync for_device. Due to xdp_adjust_tail can grow the
area accessible to the by the CPU (can possibly write into), then max
sync length *after* bpf_prog_run_xdp() needs to be taken into account.

For XDP_TX action the driver is smart and does DMA-sync. When growing
tail this is still safe, because page_pool have DMA-mapped the entire
page size.

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/bpf/158945336295.97035.15034759661036971024.stgit@firesoul
---
 drivers/net/ethernet/socionext/netsec.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index a5a0fb60193a..e1f4be4b3d69 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -884,23 +884,28 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 			  struct xdp_buff *xdp)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	unsigned int len = xdp->data_end - xdp->data;
+	unsigned int sync, len = xdp->data_end - xdp->data;
 	u32 ret = NETSEC_XDP_PASS;
+	struct page *page;
 	int err;
 	u32 act;
 
 	act = bpf_prog_run_xdp(prog, xdp);
 
+	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+	sync = xdp->data_end - xdp->data_hard_start - NETSEC_RXBUF_HEADROOM;
+	sync = max(sync, len);
+
 	switch (act) {
 	case XDP_PASS:
 		ret = NETSEC_XDP_PASS;
 		break;
 	case XDP_TX:
 		ret = netsec_xdp_xmit_back(priv, xdp);
-		if (ret != NETSEC_XDP_TX)
-			page_pool_put_page(dring->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+		if (ret != NETSEC_XDP_TX) {
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(dring->page_pool, page, sync, true);
+		}
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(priv->ndev, xdp, prog);
@@ -908,9 +913,8 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 			ret = NETSEC_XDP_REDIR;
 		} else {
 			ret = NETSEC_XDP_CONSUMED;
-			page_pool_put_page(dring->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(dring->page_pool, page, sync, true);
 		}
 		break;
 	default:
@@ -921,8 +925,8 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
 		/* fall through -- handle aborts by dropping packet */
 	case XDP_DROP:
 		ret = NETSEC_XDP_CONSUMED;
-		page_pool_put_page(dring->page_pool,
-				   virt_to_head_page(xdp->data), len, true);
+		page = virt_to_head_page(xdp->data);
+		page_pool_put_page(dring->page_pool, page, sync, true);
 		break;
 	}
 
@@ -936,10 +940,14 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_rx_pkt_info rx_info;
 	enum dma_data_direction dma_dir;
 	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
 	u16 xdp_xmit = 0;
 	u32 xdp_act = 0;
 	int done = 0;
 
+	xdp.rxq = &dring->xdp_rxq;
+	xdp.frame_sz = PAGE_SIZE;
+
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(priv->xdp_prog);
 	dma_dir = page_pool_get_dma_dir(dring->page_pool);
@@ -953,7 +961,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct sk_buff *skb = NULL;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
-		struct xdp_buff xdp;
 		void *buf_addr;
 
 		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
@@ -1002,7 +1009,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		xdp.data = desc->addr + NETSEC_RXBUF_HEADROOM;
 		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + pkt_len;
-		xdp.rxq = &dring->xdp_rxq;
 
 		if (xdp_prog) {
 			xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);
-- 
cgit v1.2.3


From 4a9b052a590d6217237502efde7d598156966080 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:49:53 +0200
Subject: dpaa2-eth: Add XDP frame size

The dpaa2-eth driver reserve some headroom used for hardware and
software annotation area in RX/TX buffers. Thus, xdp.data_hard_start
doesn't start at page boundary.

When XDP is configured the area reserved via dpaa2_fd_get_offset(fd) is
448 bytes of which XDP have reserved 256 bytes. As frame_sz is
calculated as an offset from xdp_buff.data_hard_start, an adjust from
the full PAGE_SIZE == DPAA2_ETH_RX_BUF_RAW_SIZE.

When doing XDP_REDIRECT, the driver doesn't need this reserved headroom
any-longer and allows xdp_do_redirect() to use it. This is an advantage
for the drivers own ndo-xdp_xmit, as it uses part of this headroom for
itself.  Patch also adjust frame_sz in this case.

The driver cannot support XDP data_meta, because it uses the headroom
just before xdp.data for struct dpaa2_eth_swa (DPAA2_ETH_SWA_SIZE=64),
when transmitting the packet. When transmitting a xdp_frame in
dpaa2_eth_xdp_xmit_frame (call via ndo_xdp_xmit) is uses this area to
store a pointer to xdp_frame and dma_size, which is used in TX
completion (free_tx_fd) to return frame via xdp_return_frame().

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Link: https://lore.kernel.org/bpf/158945339348.97035.8562488847066908856.stgit@firesoul
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 0f3e842a4fd6..8c8d95aa1dfd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -331,6 +331,9 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.rxq = &ch->xdp_rxq;
 
+	xdp.frame_sz = DPAA2_ETH_RX_BUF_RAW_SIZE -
+		(dpaa2_fd_get_offset(fd) - XDP_PACKET_HEADROOM);
+
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
 	/* xdp.data pointer may have changed */
@@ -366,7 +369,11 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		dma_unmap_page(priv->net_dev->dev.parent, addr,
 			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
 		ch->buf_count--;
+
+		/* Allow redirect use of full headroom */
 		xdp.data_hard_start = vaddr;
+		xdp.frame_sz = DPAA2_ETH_RX_BUF_RAW_SIZE;
+
 		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
 		if (unlikely(err))
 			ch->stats.xdp_drop++;
-- 
cgit v1.2.3


From bc1c5745d77963a4f4684c78cc2b3323900af68b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:03 +0200
Subject: qlogic/qede: Add XDP frame size to driver

The driver qede uses a full page, when XDP is enabled. The drivers value
in rx_buf_seg_size (struct qede_rx_queue) will be PAGE_SIZE when an
XDP bpf_prog is attached.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Ariel Elior <aelior@marvell.com>
Cc: GR-everest-linux-l2@marvell.com
Link: https://lore.kernel.org/bpf/158945340366.97035.7764939691580349618.stgit@firesoul
---
 drivers/net/ethernet/qlogic/qede/qede_fp.c   | 1 +
 drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index c6c20776b474..7598ebe0962a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1066,6 +1066,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 	xdp.rxq = &rxq->xdp_rxq;
+	xdp.frame_sz = rxq->rx_buf_seg_size; /* PAGE_SIZE when XDP enabled */
 
 	/* Queues always have a full reset currently, so for the time
 	 * being until there's atomic program replace just mark read
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index f50d9a9b76be..b2d154258b07 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1476,7 +1476,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 	if (rxq->rx_buf_size + size > PAGE_SIZE)
 		rxq->rx_buf_size = PAGE_SIZE - size;
 
-	/* Segment size to spilt a page in multiple equal parts ,
+	/* Segment size to split a page in multiple equal parts,
 	 * unless XDP is used in which case we'd use the entire page.
 	 */
 	if (!edev->xdp_prog) {
-- 
cgit v1.2.3


From c88c35181d6ab83e439855681032653ef8728045 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:08 +0200
Subject: net: ethernet: ti: Add XDP frame size to driver cpsw

The driver code cpsw.c and cpsw_new.c both use page_pool
with default order-0 pages or their RX-pages.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/bpf/158945340875.97035.752144756428532878.stgit@firesoul
---
 drivers/net/ethernet/ti/cpsw.c     | 1 +
 drivers/net/ethernet/ti/cpsw_new.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 09f98fa2fb4e..ce0645ada6e7 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -406,6 +406,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 
 		xdp.data_hard_start = pa;
 		xdp.rxq = &priv->xdp_rxq[ch];
+		xdp.frame_sz = PAGE_SIZE;
 
 		port = priv->emac_port + cpsw->data.dual_emac;
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, port);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index dce49311d3d3..1247d35d42ef 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -348,6 +348,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 
 		xdp.data_hard_start = pa;
 		xdp.rxq = &priv->xdp_rxq[ch];
+		xdp.frame_sz = PAGE_SIZE;
 
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port);
 		if (ret != CPSW_XDP_PASS)
-- 
cgit v1.2.3


From 08fc1cfd2d250be853d33d6505ae11ff52b83b74 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:13 +0200
Subject: ena: Add XDP frame size to amazon NIC driver

Frame size ENA_PAGE_SIZE is limited to 16K on systems with larger
PAGE_SIZE than 16K. Change ENA_XDP_MAX_MTU to also take into account
the reserved tailroom.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Sameeh Jubran <sameehj@amazon.com>
Cc: Arthur Kiyanovski <akiyano@amazon.com>
Link: https://lore.kernel.org/bpf/158945341384.97035.907403694833419456.stgit@firesoul
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 +
 drivers/net/ethernet/amazon/ena/ena_netdev.h | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 2818965427e9..85b87ed02dd5 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1606,6 +1606,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 		  "%s qid %d\n", __func__, rx_ring->qid);
 	res_budget = budget;
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.frame_sz = ENA_PAGE_SIZE;
 
 	do {
 		xdp_verdict = XDP_PASS;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 7df67bf09b93..680099afcccf 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -151,8 +151,9 @@
  * The buffer size we share with the device is defined to be ENA_PAGE_SIZE
  */
 
-#define ENA_XDP_MAX_MTU (ENA_PAGE_SIZE - ETH_HLEN - ETH_FCS_LEN - \
-				VLAN_HLEN - XDP_PACKET_HEADROOM)
+#define ENA_XDP_MAX_MTU (ENA_PAGE_SIZE - ETH_HLEN - ETH_FCS_LEN -	\
+			 VLAN_HLEN - XDP_PACKET_HEADROOM -		\
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
 #define ENA_IS_XDP_INDEX(adapter, index) (((index) >= (adapter)->xdp_first_ring) && \
 	((index) < (adapter)->xdp_first_ring + (adapter)->xdp_num_queues))
-- 
cgit v1.2.3


From d201ea9ebc519fb34ad9ef1f49ab2ab31f5111ea Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:18 +0200
Subject: mlx4: Add XDP frame size and adjust max XDP MTU

The mlx4 drivers size of memory backing the RX packet is stored in
frag_stride. For XDP mode this will be PAGE_SIZE (normally 4096).
For normal mode frag_stride is 2048.

Also adjust MLX4_EN_MAX_XDP_MTU to take tailroom into account.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Link: https://lore.kernel.org/bpf/158945341893.97035.2688142527052329942.stgit@firesoul
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 43dcbd8214c6..5bd3cd37d50f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -51,7 +51,8 @@
 #include "en_port.h"
 
 #define MLX4_EN_MAX_XDP_MTU ((int)(PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) - \
-				   XDP_PACKET_HEADROOM))
+				XDP_PACKET_HEADROOM -			    \
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info))))
 
 int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 787139219813..8a10285b0e10 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -683,6 +683,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(ring->xdp_prog);
 	xdp.rxq = &ring->xdp_rxq;
+	xdp.frame_sz = priv->frag_info[0].frag_stride;
 	doorbell_pending = 0;
 
 	/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
-- 
cgit v1.2.3


From c8145b263dd85f9e589c7c7ba531423d82ca96ae Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:24 +0200
Subject: net: thunderx: Add XDP frame size

To help reviewers these are the defines related to RCV_FRAG_LEN

 #define DMA_BUFFER_LEN	1536 /* In multiples of 128bytes */
 #define RCV_FRAG_LEN	(SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Sunil Goutham <sgoutham@marvell.com>
Cc: Robert Richter <rrichter@marvell.com>
Link: https://lore.kernel.org/bpf/158945342402.97035.12649844447148990032.stgit@firesoul
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index b4b33368698f..2ba0ce115e63 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -552,6 +552,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + len;
 	xdp.rxq = &rq->xdp_rxq;
+	xdp.frame_sz = RCV_FRAG_LEN + XDP_PACKET_HEADROOM;
 	orig_data = xdp.data;
 
 	rcu_read_lock();
-- 
cgit v1.2.3


From fa6540b8efd8944f8627c2f304114663ef4aadc4 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:29 +0200
Subject: nfp: Add XDP frame size to netronome driver

The netronome nfp driver use PAGE_SIZE when xdp_prog is set, but
xdp.data_hard_start begins at offset NFP_NET_RX_BUF_HEADROOM.
Thus, adjust for this when setting xdp.frame_sz, as it counts
from data_hard_start.

When doing XDP_TX this driver is smart and instead of a full DMA-map
does a DMA-sync on with packet length. As xdp_adjust_tail can now
grow packet length, add checks to make sure that grow size is within
the DMA-mapped size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/bpf/158945342911.97035.11214251236208648808.stgit@firesoul
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 9bfb3b077bc1..0e0cc3d58bdc 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1741,10 +1741,15 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
 		   struct nfp_net_rx_buf *rxbuf, unsigned int dma_off,
 		   unsigned int pkt_len, bool *completed)
 {
+	unsigned int dma_map_sz = dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA;
 	struct nfp_net_tx_buf *txbuf;
 	struct nfp_net_tx_desc *txd;
 	int wr_idx;
 
+	/* Reject if xdp_adjust_tail grow packet beyond DMA area */
+	if (pkt_len + dma_off > dma_map_sz)
+		return false;
+
 	if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
 		if (!*completed) {
 			nfp_net_xdp_complete(tx_ring);
@@ -1817,6 +1822,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(dp->xdp_prog);
 	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
+	xdp.frame_sz = PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM;
 	xdp.rxq = &rx_ring->xdp_rxq;
 	tx_ring = r_vec->xdp_ring;
 
-- 
cgit v1.2.3


From 88eb0ee17b2ece64fcf6689a4557a5c2e7a89c4b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:49 +0200
Subject: ixgbe: Fix XDP redirect on archs with PAGE_SIZE above 4K

The ixgbe driver have another memory model when compiled on archs with
PAGE_SIZE above 4096 bytes. In this mode it doesn't split the page in
two halves, but instead increment rx_buffer->page_offset by truesize of
packet (which include headroom and tailroom for skb_shared_info).

This is done correctly in ixgbe_build_skb(), but in ixgbe_rx_buffer_flip
which is currently only called on XDP_TX and XDP_REDIRECT, it forgets
to add the tailroom for skb_shared_info. This breaks XDP_REDIRECT, for
veth and cpumap.  Fix by adding size of skb_shared_info tailroom.

Maintainers notice: This fix have been queued to Jeff.

Fixes: 6453073987ba ("ixgbe: add initial support for xdp redirect")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Link: https://lore.kernel.org/bpf/158945344946.97035.17031588499266605743.stgit@firesoul
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 718931d951bc..ea6834bae04c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2254,7 +2254,8 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
 	rx_buffer->page_offset ^= truesize;
 #else
 	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
-				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
 				SKB_DATA_ALIGN(size);
 
 	rx_buffer->page_offset += truesize;
-- 
cgit v1.2.3


From cf02512899805d6f3d48c0cf1825148f5d24fe71 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:54 +0200
Subject: ixgbe: Add XDP frame size to driver

This driver uses different memory models depending on PAGE_SIZE at
compile time. For PAGE_SIZE 4K it uses page splitting, meaning for
normal MTU frame size is 2048 bytes (and headroom 192 bytes). For
larger MTUs the driver still use page splitting, by allocating
order-1 pages (8192 bytes) for RX frames. For PAGE_SIZE larger than
4K, driver instead advance its rx_buffer->page_offset with the frame
size "truesize".

For XDP frame size calculations, this mean that in PAGE_SIZE larger
than 4K mode the frame_sz change on a per packet basis. For the page
split 4K PAGE_SIZE mode, xdp.frame_sz is more constant and can be
updated once outside the main NAPI loop.

The default setting in the driver uses build_skb(), which provides
the necessary headroom and tailroom for XDP-redirect in RX-frame
(in both modes).

There is one complication, which is legacy-rx mode (configurable via
ethtool priv-flags). There are zero headroom in this mode, which is a
requirement for XDP-redirect to work. The conversion to xdp_frame
(convert_to_xdp_frame) will detect this insufficient space, and
xdp_do_redirect() call will fail. This is deemed acceptable, as it
allows other XDP actions to still work in legacy-mode. In
legacy-mode + larger PAGE_SIZE due to lacking tailroom, we also
accept that xdp_adjust_tail shrink doesn't work.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Link: https://lore.kernel.org/bpf/158945345455.97035.14334355929030628741.stgit@firesoul
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 34 ++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ea6834bae04c..eab5934b04f5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2244,20 +2244,30 @@ xdp_out:
 	return ERR_PTR(-result);
 }
 
+static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring,
+					    unsigned int size)
+{
+	unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+	truesize = ixgbe_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+	truesize = ring_uses_build_skb(rx_ring) ?
+		SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		SKB_DATA_ALIGN(size);
+#endif
+	return truesize;
+}
+
 static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
 				 struct ixgbe_rx_buffer *rx_buffer,
 				 unsigned int size)
 {
+	unsigned int truesize = ixgbe_rx_frame_truesize(rx_ring, size);
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
-
 	rx_buffer->page_offset ^= truesize;
 #else
-	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
-				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
-				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
-				SKB_DATA_ALIGN(size);
-
 	rx_buffer->page_offset += truesize;
 #endif
 }
@@ -2291,6 +2301,11 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 
 	xdp.rxq = &rx_ring->xdp_rxq;
 
+	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+#if (PAGE_SIZE < 8192)
+	xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0);
+#endif
+
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
 		struct ixgbe_rx_buffer *rx_buffer;
@@ -2324,7 +2339,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			xdp.data_hard_start = xdp.data -
 					      ixgbe_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
-
+#if (PAGE_SIZE > 4096)
+			/* At larger PAGE_SIZE, frame_sz depend on len size */
+			xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size);
+#endif
 			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-- 
cgit v1.2.3


From 81f3c6283cff03efae139a85851602a4c1c6bd72 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:50:59 +0200
Subject: ixgbevf: Add XDP frame size to VF driver

This patch mirrors the changes to ixgbe in previous patch.

This VF driver doesn't support XDP_REDIRECT, but correct tailroom is
still necessary for BPF-helper xdp_adjust_tail.  In legacy-mode +
larger PAGE_SIZE, due to lacking tailroom, we accept that
xdp_adjust_tail shrink doesn't work.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Link: https://lore.kernel.org/bpf/158945345984.97035.13518286183248025173.stgit@firesoul
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 34 ++++++++++++++++++-----
 1 file changed, 27 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 4622c4ea2e46..a39e2cb384dd 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1095,19 +1095,31 @@ xdp_out:
 	return ERR_PTR(-result);
 }
 
+static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring,
+					      unsigned int size)
+{
+	unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+	truesize = ixgbevf_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+	truesize = ring_uses_build_skb(rx_ring) ?
+		SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		SKB_DATA_ALIGN(size);
+#endif
+	return truesize;
+}
+
 static void ixgbevf_rx_buffer_flip(struct ixgbevf_ring *rx_ring,
 				   struct ixgbevf_rx_buffer *rx_buffer,
 				   unsigned int size)
 {
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2;
+	unsigned int truesize = ixgbevf_rx_frame_truesize(rx_ring, size);
 
+#if (PAGE_SIZE < 8192)
 	rx_buffer->page_offset ^= truesize;
 #else
-	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
-				SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) :
-				SKB_DATA_ALIGN(size);
-
 	rx_buffer->page_offset += truesize;
 #endif
 }
@@ -1125,6 +1137,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 
 	xdp.rxq = &rx_ring->xdp_rxq;
 
+	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+#if (PAGE_SIZE < 8192)
+	xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, 0);
+#endif
+
 	while (likely(total_rx_packets < budget)) {
 		struct ixgbevf_rx_buffer *rx_buffer;
 		union ixgbe_adv_rx_desc *rx_desc;
@@ -1157,7 +1174,10 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 			xdp.data_hard_start = xdp.data -
 					      ixgbevf_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
-
+#if (PAGE_SIZE > 4096)
+			/* At larger PAGE_SIZE, frame_sz depend on len size */
+			xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size);
+#endif
 			skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp);
 		}
 
-- 
cgit v1.2.3


From 24104024ce0553ae7738bb1ea5e6e3ed6619160d Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:51:04 +0200
Subject: i40e: Add XDP frame size to driver

This driver uses different memory models depending on PAGE_SIZE at
compile time. For PAGE_SIZE 4K it uses page splitting, meaning for
normal MTU frame size is 2048 bytes (and headroom 192 bytes). For
larger MTUs the driver still use page splitting, by allocating
order-1 pages (8192 bytes) for RX frames. For PAGE_SIZE larger than
4K, driver instead advance its rx_buffer->page_offset with the frame
size "truesize".

For XDP frame size calculations, this mean that in PAGE_SIZE larger
than 4K mode the frame_sz change on a per packet basis. For the page
split 4K PAGE_SIZE mode, xdp.frame_sz is more constant and can be
updated once outside the main NAPI loop.

The default setting in the driver uses build_skb(), which provides
the necessary headroom and tailroom for XDP-redirect in RX-frame
(in both modes).

There is one complication, which is legacy-rx mode (configurable via
ethtool priv-flags). There are zero headroom in this mode, which is a
requirement for XDP-redirect to work. The conversion to xdp_frame
(convert_to_xdp_frame) will detect this insufficient space, and
xdp_do_redirect() call will fail. This is deemed acceptable, as it
allows other XDP actions to still work in legacy-mode. In
legacy-mode + larger PAGE_SIZE due to lacking tailroom, we also
accept that xdp_adjust_tail shrink doesn't work.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Link: https://lore.kernel.org/bpf/158945346494.97035.12809400414566061815.stgit@firesoul
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 30 ++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b8496037ef7f..a3772beffe02 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1507,6 +1507,22 @@ static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
 	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
 }
 
+static unsigned int i40e_rx_frame_truesize(struct i40e_ring *rx_ring,
+					   unsigned int size)
+{
+	unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+	truesize = i40e_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+	truesize = i40e_rx_offset(rx_ring) ?
+		SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		SKB_DATA_ALIGN(size);
+#endif
+	return truesize;
+}
+
 /**
  * i40e_alloc_mapped_page - recycle or make a new page
  * @rx_ring: ring to use
@@ -2246,13 +2262,11 @@ static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring,
 				struct i40e_rx_buffer *rx_buffer,
 				unsigned int size)
 {
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+	unsigned int truesize = i40e_rx_frame_truesize(rx_ring, size);
 
+#if (PAGE_SIZE < 8192)
 	rx_buffer->page_offset ^= truesize;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(i40e_rx_offset(rx_ring) + size);
-
 	rx_buffer->page_offset += truesize;
 #endif
 }
@@ -2335,6 +2349,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 	struct xdp_buff xdp;
 
+#if (PAGE_SIZE < 8192)
+	xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, 0);
+#endif
 	xdp.rxq = &rx_ring->xdp_rxq;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
@@ -2389,7 +2406,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 			xdp.data_hard_start = xdp.data -
 					      i40e_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
-
+#if (PAGE_SIZE > 4096)
+			/* At larger PAGE_SIZE, frame_sz depend on len size */
+			xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size);
+#endif
 			skb = i40e_run_xdp(rx_ring, &xdp);
 		}
 
-- 
cgit v1.2.3


From d4ecdbf7aa2fa4feac09befb04cdaf44e6dc938b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:51:10 +0200
Subject: ice: Add XDP frame size to driver

This driver uses different memory models depending on PAGE_SIZE at
compile time. For PAGE_SIZE 4K it uses page splitting, meaning for
normal MTU frame size is 2048 bytes (and headroom 192 bytes). For
larger MTUs the driver still use page splitting, by allocating
order-1 pages (8192 bytes) for RX frames. For PAGE_SIZE larger than
4K, driver instead advance its rx_buffer->page_offset with the frame
size "truesize".

For XDP frame size calculations, this mean that in PAGE_SIZE larger
than 4K mode the frame_sz change on a per packet basis. For the page
split 4K PAGE_SIZE mode, xdp.frame_sz is more constant and can be
updated once outside the main NAPI loop.

The default setting in the driver uses build_skb(), which provides
the necessary headroom and tailroom for XDP-redirect in RX-frame
(in both modes).

There is one complication, which is legacy-rx mode (configurable via
ethtool priv-flags). There are zero headroom in this mode, which is a
requirement for XDP-redirect to work. The conversion to xdp_frame
(convert_to_xdp_frame) will detect this insufficient space, and
xdp_do_redirect() call will fail. This is deemed acceptable, as it
allows other XDP actions to still work in legacy-mode. In
legacy-mode + larger PAGE_SIZE due to lacking tailroom, we also
accept that xdp_adjust_tail shrink doesn't work.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Link: https://lore.kernel.org/bpf/158945347002.97035.328088795813704587.stgit@firesoul
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 34 +++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index f67e8362958c..69b21b436f9a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -423,6 +423,22 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
 	return 0;
 }
 
+static unsigned int ice_rx_frame_truesize(struct ice_ring *rx_ring,
+					  unsigned int size)
+{
+	unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+	truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+	truesize = ice_rx_offset(rx_ring) ?
+		SKB_DATA_ALIGN(ice_rx_offset(rx_ring) + size) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		SKB_DATA_ALIGN(size);
+#endif
+	return truesize;
+}
+
 /**
  * ice_run_xdp - Executes an XDP program on initialized xdp_buff
  * @rx_ring: Rx ring
@@ -991,6 +1007,10 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 	bool failure;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
+	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+#if (PAGE_SIZE < 8192)
+	xdp.frame_sz = ice_rx_frame_truesize(rx_ring, 0);
+#endif
 
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
@@ -1038,6 +1058,10 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		xdp.data_hard_start = xdp.data - ice_rx_offset(rx_ring);
 		xdp.data_meta = xdp.data;
 		xdp.data_end = xdp.data + size;
+#if (PAGE_SIZE > 4096)
+		/* At larger PAGE_SIZE, frame_sz depend on len size */
+		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
+#endif
 
 		rcu_read_lock();
 		xdp_prog = READ_ONCE(rx_ring->xdp_prog);
@@ -1051,16 +1075,8 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		if (!xdp_res)
 			goto construct_skb;
 		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			unsigned int truesize;
-
-#if (PAGE_SIZE < 8192)
-			truesize = ice_rx_pg_size(rx_ring) / 2;
-#else
-			truesize = SKB_DATA_ALIGN(ice_rx_offset(rx_ring) +
-						  size);
-#endif
 			xdp_xmit |= xdp_res;
-			ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+			ice_rx_buf_adjust_pg_offset(rx_buf, xdp.frame_sz);
 		} else {
 			rx_buf->pagecnt_bias++;
 		}
-- 
cgit v1.2.3


From 2a637c5b1aaf3b21418fadffad7e56ff27cee6f7 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:51:15 +0200
Subject: xdp: For Intel AF_XDP drivers add XDP frame_sz
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Intel drivers implement native AF_XDP zerocopy in separate C-files,
that have its own invocation of bpf_prog_run_xdp(). The setup of
xdp_buff is also handled in separately from normal code path.

This patch update XDP frame_sz for AF_XDP zerocopy drivers i40e, ice
and ixgbe, as the code changes needed are very similar.  Introduce a
helper function xsk_umem_xdp_frame_sz() for calculating frame size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/158945347511.97035.8536753731329475655.stgit@firesoul
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c   |  2 ++
 drivers/net/ethernet/intel/ice/ice_xsk.c     |  2 ++
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c |  2 ++
 include/net/xdp_sock.h                       | 11 +++++++++++
 4 files changed, 17 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 0b7d29192b2c..2b9184aead5f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -531,12 +531,14 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_res, xdp_xmit = 0;
 	bool failure = false;
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		struct i40e_rx_buffer *bi;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8279db15e870..23e5515d4527 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -840,11 +840,13 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
+	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_xmit = 0;
 	bool failure = false;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 74b540ebb3dc..a656ee9a1fae 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -431,12 +431,14 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct ixgbe_adapter *adapter = q_vector->adapter;
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
+	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_res, xdp_xmit = 0;
 	bool failure = false;
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
+	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 67191ccaab85..abd72de25fa4 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -236,6 +236,12 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
 	else
 		return address + offset;
 }
+
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return umem->chunk_size_nohr + umem->headroom;
+}
+
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -366,6 +372,11 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
 	return 0;
 }
 
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return 0;
+}
+
 static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From d628ee4fef1dbd6f2fa11e3548322c7839319537 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 14 May 2020 12:51:20 +0200
Subject: mlx5: Rx queue setup time determine frame_sz for XDP

The mlx5 driver have multiple memory models, which are also changed
according to whether a XDP bpf_prog is attached.

The 'rx_striding_rq' setting is adjusted via ethtool priv-flags e.g.:
 # ethtool --set-priv-flags mlx5p2 rx_striding_rq off

On the general case with 4K page_size and regular MTU packet, then
the frame_sz is 2048 and 4096 when XDP is enabled, in both modes.

The info on the given frame size is stored differently depending on the
RQ-mode and encoded in a union in struct mlx5e_rq union wqe/mpwqe.
In rx striding mode rq->mpwqe.log_stride_sz is either 11 or 12, which
corresponds to 2048 or 4096 (MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ).
In non-striding mode (MLX5_WQ_TYPE_CYCLIC) the frag_stride is stored
in rq->wqe.info.arr[0].frag_stride, for the first fragment, which is
what the XDP case cares about.

To reduce effect on fast-path, this patch determine the frame_sz at
setup time, to avoid determining the memory model runtime. Variable
is named frame0_sz to make it clear that this is only the frame
size of the first fragment.

This mlx5 driver does a DMA-sync on XDP_TX action, but grow is safe
as it have done a DMA-map on the entire PAGE_SIZE. The driver also
already does a XDP length check against sq->hw_mtu on the possible
XDP xmit paths mlx5e_xmit_xdp_frame() + mlx5e_xmit_xdp_frame_mpwqe().

V3+4: Change variable name first_frame_sz to frame0_sz

V2: Fix that frag_size need to be recalc before creating SKB.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Link: https://lore.kernel.org/bpf/158945348021.97035.12295039384250022883.stgit@firesoul
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 2 ++
 4 files changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3bd64c63865b..26911b15f8fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -625,6 +625,7 @@ struct mlx5e_rq {
 	struct {
 		u16            umem_headroom;
 		u16            headroom;
+		u32            frame0_sz;
 		u8             map_dir;   /* dma map direction */
 	} buff;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c4a7fb4ecd14..761c8979bd41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -137,6 +137,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 	if (xsk)
 		xdp.handle = di->xsk.handle;
 	xdp.rxq = &rq->xdp_rxq;
+	xdp.frame_sz = rq->buff.frame0_sz;
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 	if (xsk) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0a9dfc31de3e..0e4ca08ddca9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -462,6 +462,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		rq->mpwqe.num_strides =
 			BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 
+		rq->buff.frame0_sz = (1 << rq->mpwqe.log_stride_sz);
+
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
@@ -485,6 +487,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags;
 
 		rq->wqe.info = rqp->frags_info;
+		rq->buff.frame0_sz = rq->wqe.info.arr[0].frag_stride;
+
 		rq->wqe.frags =
 			kvzalloc_node(array_size(sizeof(*rq->wqe.frags),
 					(wq_sz << rq->wqe.info.log_num_frags)),
@@ -522,6 +526,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	}
 
 	if (xsk) {
+		rq->buff.frame0_sz = xsk_umem_xdp_frame_sz(umem);
+
 		err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames);
 		if (unlikely(err)) {
 			mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 779600bebcca..821f94beda7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1070,6 +1070,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
 
+	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
 	if (unlikely(!skb))
 		return NULL;
@@ -1371,6 +1372,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
+	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32);
 	if (unlikely(!skb))
 		return NULL;
-- 
cgit v1.2.3


From 4f1d97262d58e0f493d03de4938bce736ac3cf3d Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Fri, 15 May 2020 22:41:03 +0530
Subject: cxgb4: improve credits recovery in TC-MQPRIO Tx path

Request credit update for every half credits consumed, including
the current request. Also, avoid re-trying to post packets when there
are no credits left. The credit update reply via interrupt will
eventually restore the credits and will invoke the Tx path again.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 40 +++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 6516c45864b3..1359158652b7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2091,10 +2091,9 @@ static inline u8 ethofld_calc_tx_flits(struct adapter *adap,
 	return flits + nsgl;
 }
 
-static inline void *write_eo_wr(struct adapter *adap,
-				struct sge_eosw_txq *eosw_txq,
-				struct sk_buff *skb, struct fw_eth_tx_eo_wr *wr,
-				u32 hdr_len, u32 wrlen)
+static void *write_eo_wr(struct adapter *adap, struct sge_eosw_txq *eosw_txq,
+			 struct sk_buff *skb, struct fw_eth_tx_eo_wr *wr,
+			 u32 hdr_len, u32 wrlen)
 {
 	const struct skb_shared_info *ssi = skb_shinfo(skb);
 	struct cpl_tx_pkt_core *cpl;
@@ -2113,7 +2112,8 @@ static inline void *write_eo_wr(struct adapter *adap,
 	immd_len += hdr_len;
 
 	if (!eosw_txq->ncompl ||
-	    eosw_txq->last_compl >= adap->params.ofldq_wr_cred / 2) {
+	    (eosw_txq->last_compl + wrlen16) >=
+	    (adap->params.ofldq_wr_cred / 2)) {
 		compl = true;
 		eosw_txq->ncompl++;
 		eosw_txq->last_compl = 0;
@@ -2153,8 +2153,8 @@ static inline void *write_eo_wr(struct adapter *adap,
 	return cpl;
 }
 
-static void ethofld_hard_xmit(struct net_device *dev,
-			      struct sge_eosw_txq *eosw_txq)
+static int ethofld_hard_xmit(struct net_device *dev,
+			     struct sge_eosw_txq *eosw_txq)
 {
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
@@ -2167,8 +2167,8 @@ static void ethofld_hard_xmit(struct net_device *dev,
 	bool skip_eotx_wr = false;
 	struct tx_sw_desc *d;
 	struct sk_buff *skb;
+	int left, ret = 0;
 	u8 flits, ndesc;
-	int left;
 
 	eohw_txq = &adap->sge.eohw_txq[eosw_txq->hwqid];
 	spin_lock(&eohw_txq->lock);
@@ -2198,11 +2198,19 @@ static void ethofld_hard_xmit(struct net_device *dev,
 	wrlen = flits * 8;
 	wrlen16 = DIV_ROUND_UP(wrlen, 16);
 
-	/* If there are no CPL credits, then wait for credits
-	 * to come back and retry again
+	left = txq_avail(&eohw_txq->q) - ndesc;
+
+	/* If there are no descriptors left in hardware queues or no
+	 * CPL credits left in software queues, then wait for them
+	 * to come back and retry again. Note that we always request
+	 * for credits update via interrupt for every half credits
+	 * consumed. So, the interrupt will eventually restore the
+	 * credits and invoke the Tx path again.
 	 */
-	if (unlikely(wrlen16 > eosw_txq->cred))
+	if (unlikely(left < 0 || wrlen16 > eosw_txq->cred)) {
+		ret = -ENOMEM;
 		goto out_unlock;
+	}
 
 	if (unlikely(skip_eotx_wr)) {
 		start = (u64 *)wr;
@@ -2231,7 +2239,8 @@ write_wr_headers:
 	sgl = (u64 *)inline_tx_skb_header(skb, &eohw_txq->q, (void *)start,
 					  hdr_len);
 	if (data_len) {
-		if (unlikely(cxgb4_map_skb(adap->pdev_dev, skb, d->addr))) {
+		ret = cxgb4_map_skb(adap->pdev_dev, skb, d->addr);
+		if (unlikely(ret)) {
 			memset(d->addr, 0, sizeof(d->addr));
 			eohw_txq->mapping_err++;
 			goto out_unlock;
@@ -2277,12 +2286,13 @@ write_wr_headers:
 
 out_unlock:
 	spin_unlock(&eohw_txq->lock);
+	return ret;
 }
 
 static void ethofld_xmit(struct net_device *dev, struct sge_eosw_txq *eosw_txq)
 {
 	struct sk_buff *skb;
-	int pktcount;
+	int pktcount, ret;
 
 	switch (eosw_txq->state) {
 	case CXGB4_EO_STATE_ACTIVE:
@@ -2307,7 +2317,9 @@ static void ethofld_xmit(struct net_device *dev, struct sge_eosw_txq *eosw_txq)
 			continue;
 		}
 
-		ethofld_hard_xmit(dev, eosw_txq);
+		ret = ethofld_hard_xmit(dev, eosw_txq);
+		if (ret)
+			break;
 	}
 }
 
-- 
cgit v1.2.3


From 4bccfc036abbdf510de808925c646c8c49e0309e Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Fri, 15 May 2020 22:41:04 +0530
Subject: cxgb4: tune burst buffer size for TC-MQPRIO offload

For each traffic class, firmware handles up to 4 * MTU amount of data
per burst cycle. Under heavy load, this small buffer size is a
bottleneck when buffering large TSO packets in <= 1500 MTU case.
Increase the burst buffer size to 8 * MTU when supported.

Also, keep the driver's traffic class configuration API similar to
the firmware API counterpart.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h         | 30 ++++++++++++----------
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    |  2 +-
 .../net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c   |  7 +++++
 drivers/net/ethernet/chelsio/cxgb4/sched.c         |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c         |  8 +++---
 5 files changed, 31 insertions(+), 19 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 30d25a37fc3b..fc1405a8ed74 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1125,19 +1125,20 @@ struct adapter {
  * programmed with various parameters.
  */
 struct ch_sched_params {
-	s8   type;                     /* packet or flow */
+	u8   type;                     /* packet or flow */
 	union {
 		struct {
-			s8   level;    /* scheduler hierarchy level */
-			s8   mode;     /* per-class or per-flow */
-			s8   rateunit; /* bit or packet rate */
-			s8   ratemode; /* %port relative or kbps absolute */
-			s8   channel;  /* scheduler channel [0..N] */
-			s8   class;    /* scheduler class [0..N] */
-			s32  minrate;  /* minimum rate */
-			s32  maxrate;  /* maximum rate */
-			s16  weight;   /* percent weight */
-			s16  pktsize;  /* average packet size */
+			u8   level;    /* scheduler hierarchy level */
+			u8   mode;     /* per-class or per-flow */
+			u8   rateunit; /* bit or packet rate */
+			u8   ratemode; /* %port relative or kbps absolute */
+			u8   channel;  /* scheduler channel [0..N] */
+			u8   class;    /* scheduler class [0..N] */
+			u32  minrate;  /* minimum rate */
+			u32  maxrate;  /* maximum rate */
+			u16  weight;   /* percent weight */
+			u16  pktsize;  /* average packet size */
+			u16  burstsize;  /* burst buffer size */
 		} params;
 	} u;
 };
@@ -1952,9 +1953,10 @@ int t4_sge_ctxt_rd(struct adapter *adap, unsigned int mbox, unsigned int cid,
 		   enum ctxt_type ctype, u32 *data);
 int t4_sge_ctxt_rd_bd(struct adapter *adap, unsigned int cid,
 		      enum ctxt_type ctype, u32 *data);
-int t4_sched_params(struct adapter *adapter, int type, int level, int mode,
-		    int rateunit, int ratemode, int channel, int class,
-		    int minrate, int maxrate, int weight, int pktsize);
+int t4_sched_params(struct adapter *adapter, u8 type, u8 level, u8 mode,
+		    u8 rateunit, u8 ratemode, u8 channel, u8 class,
+		    u32 minrate, u32 maxrate, u16 weight, u16 pktsize,
+		    u16 burstsize);
 void t4_sge_decode_idma_state(struct adapter *adapter, int state);
 void t4_idma_monitor_init(struct adapter *adapter,
 			  struct sge_idma_monitor_state *idma);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a70018f067aa..196451f8006f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3021,7 +3021,7 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf,
 			      SCHED_CLASS_RATEUNIT_BITS,
 			      SCHED_CLASS_RATEMODE_ABS,
 			      pi->tx_chan, class_id, 0,
-			      max_tx_rate * 1000, 0, pktsize);
+			      max_tx_rate * 1000, 0, pktsize, 0);
 	if (ret) {
 		dev_err(adap->pdev_dev, "Err %d for Traffic Class config\n",
 			ret);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index e6af4906d674..56079c9937db 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -342,6 +342,13 @@ static int cxgb4_mqprio_alloc_tc(struct net_device *dev,
 		p.u.params.minrate = div_u64(mqprio->min_rate[i] * 8, 1000);
 		p.u.params.maxrate = div_u64(mqprio->max_rate[i] * 8, 1000);
 
+		/* Request larger burst buffer for smaller MTU, so
+		 * that hardware can work on more data per burst
+		 * cycle.
+		 */
+		if (dev->mtu <= ETH_DATA_LEN)
+			p.u.params.burstsize = 8 * dev->mtu;
+
 		e = cxgb4_sched_class_alloc(dev, &p);
 		if (!e) {
 			ret = -ENOMEM;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index cebe1412d960..fde93c50cfec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -57,7 +57,8 @@ static int t4_sched_class_fw_cmd(struct port_info *pi,
 				      p->u.params.ratemode,
 				      p->u.params.channel, e->idx,
 				      p->u.params.minrate, p->u.params.maxrate,
-				      p->u.params.weight, p->u.params.pktsize);
+				      p->u.params.weight, p->u.params.pktsize,
+				      p->u.params.burstsize);
 		break;
 	default:
 		err = -ENOTSUPP;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 2a3480fc1d91..1c8068c02728 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -10361,9 +10361,10 @@ int t4_sge_ctxt_rd_bd(struct adapter *adap, unsigned int cid,
 	return ret;
 }
 
-int t4_sched_params(struct adapter *adapter, int type, int level, int mode,
-		    int rateunit, int ratemode, int channel, int class,
-		    int minrate, int maxrate, int weight, int pktsize)
+int t4_sched_params(struct adapter *adapter, u8 type, u8 level, u8 mode,
+		    u8 rateunit, u8 ratemode, u8 channel, u8 class,
+		    u32 minrate, u32 maxrate, u16 weight, u16 pktsize,
+		    u16 burstsize)
 {
 	struct fw_sched_cmd cmd;
 
@@ -10385,6 +10386,7 @@ int t4_sched_params(struct adapter *adapter, int type, int level, int mode,
 	cmd.u.params.max = cpu_to_be32(maxrate);
 	cmd.u.params.weight = cpu_to_be16(weight);
 	cmd.u.params.pktsize = cpu_to_be16(pktsize);
+	cmd.u.params.burstsize = cpu_to_be16(burstsize);
 
 	return t4_wr_mbox_meat(adapter, adapter->mbox, &cmd, sizeof(cmd),
 			       NULL, 1);
-- 
cgit v1.2.3


From 5148e5950c675a26ab1f5eb4b291e9bd986116c9 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Fri, 15 May 2020 22:41:05 +0530
Subject: cxgb4: add EOTID tracking and software context dump

Rework and add support for dumping EOTID software context used by
TC-MQPRIO. Also track number of EOTIDs in use.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 144 +++++++++++++++++----
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    |   1 +
 .../net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c   |  10 ++
 .../net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h   |   1 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h     |   5 +
 5 files changed, 133 insertions(+), 28 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index ebed99f3d4cf..7818c392da50 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -49,6 +49,7 @@
 #include "cudbg_lib_common.h"
 #include "cudbg_entity.h"
 #include "cudbg_lib.h"
+#include "cxgb4_tc_mqprio.h"
 
 /* generic seq_file support for showing a table of size rows x width. */
 static void *seq_tab_get_idx(struct seq_tab *tb, loff_t pos)
@@ -2657,32 +2658,19 @@ static int sge_qinfo_uld_ciq_entries(const struct adapter *adap, int uld)
 
 static int sge_qinfo_show(struct seq_file *seq, void *v)
 {
-	int eth_entries, ctrl_entries, eo_entries = 0;
+	int eth_entries, ctrl_entries, eohw_entries = 0, eosw_entries = 0;
 	int uld_rxq_entries[CXGB4_ULD_MAX] = { 0 };
 	int uld_ciq_entries[CXGB4_ULD_MAX] = { 0 };
 	int uld_txq_entries[CXGB4_TX_MAX] = { 0 };
 	const struct sge_uld_txq_info *utxq_info;
 	const struct sge_uld_rxq_info *urxq_info;
+	struct cxgb4_tc_port_mqprio *port_mqprio;
 	struct adapter *adap = seq->private;
-	int i, n, r = (uintptr_t)v - 1;
+	int i, j, n, r = (uintptr_t)v - 1;
 	struct sge *s = &adap->sge;
 
 	eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
 	ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
-	if (adap->sge.eohw_txq)
-		eo_entries = DIV_ROUND_UP(adap->sge.eoqsets, 4);
-
-	mutex_lock(&uld_mutex);
-	if (s->uld_txq_info)
-		for (i = 0; i < ARRAY_SIZE(uld_txq_entries); i++)
-			uld_txq_entries[i] = sge_qinfo_uld_txq_entries(adap, i);
-
-	if (s->uld_rxq_info) {
-		for (i = 0; i < ARRAY_SIZE(uld_rxq_entries); i++) {
-			uld_rxq_entries[i] = sge_qinfo_uld_rxq_entries(adap, i);
-			uld_ciq_entries[i] = sge_qinfo_uld_ciq_entries(adap, i);
-		}
-	}
 
 	if (r)
 		seq_putc(seq, '\n');
@@ -2759,11 +2747,21 @@ do { \
 		RL("FLLow:", fl.low);
 		RL("FLStarving:", fl.starving);
 
-		goto unlock;
+		goto out;
 	}
 
 	r -= eth_entries;
-	if (r < eo_entries) {
+	if (!adap->tc_mqprio)
+		goto skip_mqprio;
+
+	mutex_lock(&adap->tc_mqprio->mqprio_mutex);
+	if (!refcount_read(&adap->tc_mqprio->refcnt)) {
+		mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
+		goto skip_mqprio;
+	}
+
+	eohw_entries = DIV_ROUND_UP(adap->sge.eoqsets, 4);
+	if (r < eohw_entries) {
 		int base_qset = r * 4;
 		const struct sge_ofld_rxq *rx = &s->eohw_rxq[base_qset];
 		const struct sge_eohw_txq *tx = &s->eohw_txq[base_qset];
@@ -2808,10 +2806,71 @@ do { \
 		RL("FLLow:", fl.low);
 		RL("FLStarving:", fl.starving);
 
-		goto unlock;
+		mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
+		goto out;
+	}
+
+	r -= eohw_entries;
+	for (j = 0; j < adap->params.nports; j++) {
+		int entries;
+		u8 tc;
+
+		port_mqprio = &adap->tc_mqprio->port_mqprio[j];
+		entries = 0;
+		for (tc = 0; tc < port_mqprio->mqprio.qopt.num_tc; tc++)
+			entries += port_mqprio->mqprio.qopt.count[tc];
+
+		if (!entries)
+			continue;
+
+		eosw_entries = DIV_ROUND_UP(entries, 4);
+		if (r < eosw_entries) {
+			const struct sge_eosw_txq *tx;
+
+			n = min(4, entries - 4 * r);
+			tx = &port_mqprio->eosw_txq[4 * r];
+
+			S("QType:", "EOSW-TXQ");
+			S("Interface:",
+			  adap->port[j] ? adap->port[j]->name : "N/A");
+			T("EOTID:", hwtid);
+			T("HWQID:", hwqid);
+			T("State:", state);
+			T("Size:", ndesc);
+			T("In-Use:", inuse);
+			T("Credits:", cred);
+			T("Compl:", ncompl);
+			T("Last-Compl:", last_compl);
+			T("PIDX:", pidx);
+			T("Last-PIDX:", last_pidx);
+			T("CIDX:", cidx);
+			T("Last-CIDX:", last_cidx);
+			T("FLOWC-IDX:", flowc_idx);
+
+			mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
+			goto out;
+		}
+
+		r -= eosw_entries;
+	}
+	mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
+
+skip_mqprio:
+	if (!is_uld(adap))
+		goto skip_uld;
+
+	mutex_lock(&uld_mutex);
+	if (s->uld_txq_info)
+		for (i = 0; i < ARRAY_SIZE(uld_txq_entries); i++)
+			uld_txq_entries[i] = sge_qinfo_uld_txq_entries(adap, i);
+
+	if (s->uld_rxq_info) {
+		for (i = 0; i < ARRAY_SIZE(uld_rxq_entries); i++) {
+			uld_rxq_entries[i] = sge_qinfo_uld_rxq_entries(adap, i);
+			uld_ciq_entries[i] = sge_qinfo_uld_ciq_entries(adap, i);
+		}
 	}
 
-	r -= eo_entries;
 	if (r < uld_txq_entries[CXGB4_TX_OFLD]) {
 		const struct sge_uld_txq *tx;
 
@@ -2994,6 +3053,9 @@ do { \
 	}
 
 	r -= uld_txq_entries[CXGB4_TX_CRYPTO];
+	mutex_unlock(&uld_mutex);
+
+skip_uld:
 	if (r < ctrl_entries) {
 		const struct sge_ctrl_txq *tx = &s->ctrlq[r * 4];
 
@@ -3008,7 +3070,7 @@ do { \
 		TL("TxQFull:", q.stops);
 		TL("TxQRestarts:", q.restarts);
 
-		goto unlock;
+		goto out;
 	}
 
 	r -= ctrl_entries;
@@ -3026,11 +3088,9 @@ do { \
 		seq_printf(seq, "%-12s %16u\n", "Intr pktcnt:",
 			   s->counter_val[evtq->pktcnt_idx]);
 
-		goto unlock;
+		goto out;
 	}
 
-unlock:
-	mutex_unlock(&uld_mutex);
 #undef R
 #undef RL
 #undef T
@@ -3039,13 +3099,38 @@ unlock:
 #undef R3
 #undef T3
 #undef S3
+out:
+	return 0;
+
+unlock:
+	mutex_unlock(&uld_mutex);
 	return 0;
 }
 
 static int sge_queue_entries(const struct adapter *adap)
 {
-	int tot_uld_entries = 0;
-	int i;
+	int i, tot_uld_entries = 0, eohw_entries = 0, eosw_entries = 0;
+
+	if (adap->tc_mqprio) {
+		struct cxgb4_tc_port_mqprio *port_mqprio;
+		u8 tc;
+
+		mutex_lock(&adap->tc_mqprio->mqprio_mutex);
+		if (adap->sge.eohw_txq)
+			eohw_entries = DIV_ROUND_UP(adap->sge.eoqsets, 4);
+
+		for (i = 0; i < adap->params.nports; i++) {
+			u32 entries = 0;
+
+			port_mqprio = &adap->tc_mqprio->port_mqprio[i];
+			for (tc = 0; tc < port_mqprio->mqprio.qopt.num_tc; tc++)
+				entries += port_mqprio->mqprio.qopt.count[tc];
+
+			if (entries)
+				eosw_entries += DIV_ROUND_UP(entries, 4);
+		}
+		mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
+	}
 
 	if (!is_uld(adap))
 		goto lld_only;
@@ -3062,8 +3147,7 @@ static int sge_queue_entries(const struct adapter *adap)
 
 lld_only:
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
-	       (adap->sge.eohw_txq ? DIV_ROUND_UP(adap->sge.eoqsets, 4) : 0) +
-	       tot_uld_entries +
+	       eohw_entries + eosw_entries + tot_uld_entries +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
 }
 
@@ -3244,6 +3328,10 @@ static int tid_info_show(struct seq_file *seq, void *v)
 	if (t->nhpftids)
 		seq_printf(seq, "HPFTID range: %u..%u\n", t->hpftid_base,
 			   t->hpftid_base + t->nhpftids - 1);
+	if (t->neotids)
+		seq_printf(seq, "EOTID range: %u..%u, in use: %u\n",
+			   t->eotid_base, t->eotid_base + t->neotids - 1,
+			   atomic_read(&t->eotids_in_use));
 	if (t->ntids)
 		seq_printf(seq, "HW TID usage: %u IP users, %u IPv6 users\n",
 			   t4_read_reg(adap, LE_DB_ACT_CNT_IPV4_A),
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 196451f8006f..d05c2371d8c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1579,6 +1579,7 @@ static int tid_init(struct tid_info *t)
 	atomic_set(&t->tids_in_use, 0);
 	atomic_set(&t->conns_in_use, 0);
 	atomic_set(&t->hash_tids_in_use, 0);
+	atomic_set(&t->eotids_in_use, 0);
 
 	/* Setup the free list for atid_tab and clear the stid bitmap. */
 	if (natids) {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index 56079c9937db..ae7123a9de8e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -574,6 +574,7 @@ static void cxgb4_mqprio_disable_offload(struct net_device *dev)
 int cxgb4_setup_tc_mqprio(struct net_device *dev,
 			  struct tc_mqprio_qopt_offload *mqprio)
 {
+	struct adapter *adap = netdev2adap(dev);
 	bool needs_bring_up = false;
 	int ret;
 
@@ -581,6 +582,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	if (ret)
 		return ret;
 
+	mutex_lock(&adap->tc_mqprio->mqprio_mutex);
+
 	/* To configure tc params, the current allocated EOTIDs must
 	 * be freed up. However, they can't be freed up if there's
 	 * traffic running on the interface. So, ensure interface is
@@ -616,6 +619,7 @@ out:
 	if (needs_bring_up)
 		cxgb_open(dev);
 
+	mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
 	return ret;
 }
 
@@ -628,6 +632,7 @@ void cxgb4_mqprio_stop_offload(struct adapter *adap)
 	if (!adap->tc_mqprio || !adap->tc_mqprio->port_mqprio)
 		return;
 
+	mutex_lock(&adap->tc_mqprio->mqprio_mutex);
 	for_each_port(adap, i) {
 		dev = adap->port[i];
 		if (!dev)
@@ -639,6 +644,7 @@ void cxgb4_mqprio_stop_offload(struct adapter *adap)
 
 		cxgb4_mqprio_disable_offload(dev);
 	}
+	mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
 }
 
 int cxgb4_init_tc_mqprio(struct adapter *adap)
@@ -660,6 +666,8 @@ int cxgb4_init_tc_mqprio(struct adapter *adap)
 		goto out_free_mqprio;
 	}
 
+	mutex_init(&tc_mqprio->mqprio_mutex);
+
 	tc_mqprio->port_mqprio = tc_port_mqprio;
 	for (i = 0; i < adap->params.nports; i++) {
 		port_mqprio = &tc_mqprio->port_mqprio[i];
@@ -694,6 +702,7 @@ void cxgb4_cleanup_tc_mqprio(struct adapter *adap)
 	u8 i;
 
 	if (adap->tc_mqprio) {
+		mutex_lock(&adap->tc_mqprio->mqprio_mutex);
 		if (adap->tc_mqprio->port_mqprio) {
 			for (i = 0; i < adap->params.nports; i++) {
 				struct net_device *dev = adap->port[i];
@@ -705,6 +714,7 @@ void cxgb4_cleanup_tc_mqprio(struct adapter *adap)
 			}
 			kfree(adap->tc_mqprio->port_mqprio);
 		}
+		mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
 		kfree(adap->tc_mqprio);
 	}
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
index ff8794132b22..be96f1dc0372 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
@@ -33,6 +33,7 @@ struct cxgb4_tc_port_mqprio {
 
 struct cxgb4_tc_mqprio {
 	refcount_t refcnt; /* Refcount for adapter-wide resources */
+	struct mutex mqprio_mutex; /* Lock for accessing MQPRIO info */
 	struct cxgb4_tc_port_mqprio *port_mqprio; /* Per port MQPRIO info */
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index be831317520a..16796785eea3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -147,6 +147,9 @@ struct tid_info {
 	/* TIDs in the HASH */
 	atomic_t hash_tids_in_use;
 	atomic_t conns_in_use;
+	/* ETHOFLD TIDs used for rate limiting */
+	atomic_t eotids_in_use;
+
 	/* lock for setting/clearing filter bitmap */
 	spinlock_t ftid_lock;
 
@@ -221,12 +224,14 @@ static inline void cxgb4_alloc_eotid(struct tid_info *t, u32 eotid, void *data)
 {
 	set_bit(eotid, t->eotid_bmap);
 	t->eotid_tab[eotid].data = data;
+	atomic_inc(&t->eotids_in_use);
 }
 
 static inline void cxgb4_free_eotid(struct tid_info *t, u32 eotid)
 {
 	clear_bit(eotid, t->eotid_bmap);
 	t->eotid_tab[eotid].data = NULL;
+	atomic_dec(&t->eotids_in_use);
 }
 
 int cxgb4_alloc_atid(struct tid_info *t, void *data);
-- 
cgit v1.2.3


From 2726cd4a29280c20ea983be285a6aefe75b205a4 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 3 May 2020 10:15:58 +0300
Subject: net/mlx5: Dedicate fw page to the requesting function

The cited patch assumes that all chuncks in a fw page belong to the same
function, thus the driver must dedicate fw page to the requesting
function, which is actually what was intedned in the original fw pages
allocator design, hence the fwp->func_id !

Up until the cited patch everything worked ok, but now "relase all pages"
is broken on systems with page_size > 4k.

Fix this by dedicating fw page to the requesting function id via adding a
func_id parameter to alloc_4k() function.

Fixes: c6168161f693 ("net/mlx5: Add support for release all pages event")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 8ce78f42dfc0..84f6356edbf8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -156,15 +156,21 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	return err;
 }
 
-static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
+static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id)
 {
-	struct fw_page *fp;
+	struct fw_page *fp = NULL;
+	struct fw_page *iter;
 	unsigned n;
 
-	if (list_empty(&dev->priv.free_list))
+	list_for_each_entry(iter, &dev->priv.free_list, list) {
+		if (iter->func_id != func_id)
+			continue;
+		fp = iter;
+	}
+
+	if (list_empty(&dev->priv.free_list) || !fp)
 		return -ENOMEM;
 
-	fp = list_entry(dev->priv.free_list.next, struct fw_page, list);
 	n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask));
 	if (n >= MLX5_NUM_4K_IN_PAGE) {
 		mlx5_core_warn(dev, "alloc 4k bug\n");
@@ -295,7 +301,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 
 	for (i = 0; i < npages; i++) {
 retry:
-		err = alloc_4k(dev, &addr);
+		err = alloc_4k(dev, &addr, func_id);
 		if (err) {
 			if (err == -ENOMEM)
 				err = alloc_system_page(dev, func_id);
-- 
cgit v1.2.3


From e7f860e2106a4c288d98308c59545ddd350e4739 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 3 May 2020 11:01:39 +0300
Subject: net/mlx5: Fix a bug of releasing wrong chunks on > 4K page size
 systems

On systems with page size larger than 4K, a fwp object has few 4K chunks.
Fix a bug in fwp free flow where the chunk address was dropped and
fwp->addr was used instead (first chunk address). This caused a wrong
update of fwp->bitmask which later can cause errors in re-alloc fwp
chunk flow.

In order to fix this it, re-factor the release flow:
- Free 4k: Releases a specific 4k chunk inside the fwp, defined by
  starting address.
- Free fwp: Unconditionally release the whole fwp and its resources.
Free addr will call free fwp if all chunks were released, in order to do
code sharing.

In addition, fix npages to count for all released chunks correctly.

Fixes: c6168161f693 ("net/mlx5: Add support for release all pages event")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 44 +++++++++++-----------
 1 file changed, 22 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 84f6356edbf8..5ddd18639a1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -188,35 +188,35 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id)
 
 #define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
 
-static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp)
+static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
+		     bool in_free_list)
 {
-	int n = (fwp->addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
-
-	fwp->free_count++;
-	set_bit(n, &fwp->bitmask);
-	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
-		rb_erase(&fwp->rb_node, &dev->priv.page_root);
-		if (fwp->free_count != 1)
-			list_del(&fwp->list);
-		dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
-			       PAGE_SIZE, DMA_BIDIRECTIONAL);
-		__free_page(fwp->page);
-		kfree(fwp);
-	} else if (fwp->free_count == 1) {
-		list_add(&fwp->list, &dev->priv.free_list);
-	}
+	rb_erase(&fwp->rb_node, &dev->priv.page_root);
+	if (in_free_list)
+		list_del(&fwp->list);
+	dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
+		       PAGE_SIZE, DMA_BIDIRECTIONAL);
+	__free_page(fwp->page);
+	kfree(fwp);
 }
 
-static void free_addr(struct mlx5_core_dev *dev, u64 addr)
+static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 {
 	struct fw_page *fwp;
+	int n;
 
 	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
 	if (!fwp) {
 		mlx5_core_warn_rl(dev, "page not found\n");
 		return;
 	}
-	free_fwp(dev, fwp);
+	n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
+	fwp->free_count++;
+	set_bit(n, &fwp->bitmask);
+	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE)
+		free_fwp(dev, fwp, fwp->free_count != 1);
+	else if (fwp->free_count == 1)
+		list_add(&fwp->list, &dev->priv.free_list);
 }
 
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
@@ -340,7 +340,7 @@ retry:
 
 out_4k:
 	for (i--; i >= 0; i--)
-		free_addr(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
 out_free:
 	kvfree(in);
 	if (notify_fail)
@@ -361,8 +361,8 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 		p = rb_next(p);
 		if (fwp->func_id != func_id)
 			continue;
-		free_fwp(dev, fwp);
-		npages++;
+		npages += (MLX5_NUM_4K_IN_PAGE - fwp->free_count);
+		free_fwp(dev, fwp, fwp->free_count);
 	}
 
 	dev->priv.fw_pages -= npages;
@@ -446,7 +446,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	}
 
 	for (i = 0; i < num_claimed; i++)
-		free_addr(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
 
 	if (nclaimed)
 		*nclaimed = num_claimed;
-- 
cgit v1.2.3


From 4162f58b476b248d0718f3d6aad2e57da2b08a63 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 1 May 2020 10:20:01 -0500
Subject: net/mlx5: Have single error unwinding path

Having multiple error unwinding path are error prone.
Lets have just one error unwinding path.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 742ba012c234..2e128068a48c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1217,10 +1217,9 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 		mlx5_register_device(dev);
 
 	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
-out:
-	mutex_unlock(&dev->intf_state_mutex);
 
-	return err;
+	mutex_unlock(&dev->intf_state_mutex);
+	return 0;
 
 err_devlink_reg:
 	mlx5_unload(dev);
@@ -1230,8 +1229,8 @@ err_load:
 function_teardown:
 	mlx5_function_teardown(dev, boot);
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+out:
 	mutex_unlock(&dev->intf_state_mutex);
-
 	return err;
 }
 
-- 
cgit v1.2.3


From 41798df9bfca5aae080a66252ae1709867e28757 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 1 May 2020 09:42:45 -0500
Subject: net/mlx5: Drain wq first during PCI device removal

mlx5_unload_one() is done with cleanup = true only once.

So instead of doing health wq drain inside the if(), directly do
during PCI device removal.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 2e128068a48c..d6a8128f667a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1236,10 +1236,8 @@ out:
 
 void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
-	if (cleanup) {
+	if (cleanup)
 		mlx5_unregister_device(dev);
-		mlx5_drain_health_wq(dev);
-	}
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
@@ -1382,6 +1380,7 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
 
+	mlx5_drain_health_wq(dev);
 	mlx5_unload_one(dev, true);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);
-- 
cgit v1.2.3


From 49c0355d301b4e0e01e0f19ddbb023bd7d0ee48c Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Thu, 7 May 2020 12:01:39 +0300
Subject: net/mlx5: Wait for inactive autogroups

Currently, if one thread tries to add an entry to an autogrouped table
with no free matching group, while another thread is in the process of
creating a new matching autogroup, it doesn't wait for the new group
creation, and creates an unnecessary new autogroup.

Instead of skipping inactive, wait on the write lock of those groups.

Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2da45e9b9b6d..52af6023a4b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1755,11 +1755,13 @@ skip_search:
 	list_for_each_entry(iter, match_head, list) {
 		g = iter->g;
 
-		if (!g->node.active)
-			continue;
-
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
+		if (!g->node.active) {
+			up_write_ref_node(&g->node, false);
+			continue;
+		}
+
 		err = insert_fte(g, fte);
 		if (err) {
 			up_write_ref_node(&g->node, false);
-- 
cgit v1.2.3


From 90bf1c8dbdc52d08a18c9c1fb2b847999159e3a2 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 7 May 2020 14:13:33 +0300
Subject: net/mlx5: Move internal timer read function to clock library

Move mlx5_read_internal_timer() into lib/clock.c file as it is being
used there. As such, make this function a static one.

In addition, rearrange headers include to support function move.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h        |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 21 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c      | 20 --------------------
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h |  3 ---
 4 files changed, 21 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 26911b15f8fe..195162b9b245 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -36,7 +36,6 @@
 #include <linux/etherdevice.h>
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
-#include <linux/ptp_clock_kernel.h>
 #include <linux/crash_dump.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/qp.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 43f97601b500..ef0706d15a5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -32,6 +32,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/highmem.h>
+#include <linux/ptp_clock_kernel.h>
 #include <rdma/mlx5-abi.h>
 #include "lib/eq.h"
 #include "en.h"
@@ -66,6 +67,26 @@ enum {
 	MLX5_MTPPS_FS_ENH_OUT_PER_ADJ		= BIT(0x7),
 };
 
+static u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
+				    struct ptp_system_timestamp *sts)
+{
+	u32 timer_h, timer_h1, timer_l;
+
+	timer_h = ioread32be(&dev->iseg->internal_timer_h);
+	ptp_read_system_prets(sts);
+	timer_l = ioread32be(&dev->iseg->internal_timer_l);
+	ptp_read_system_postts(sts);
+	timer_h1 = ioread32be(&dev->iseg->internal_timer_h);
+	if (timer_h != timer_h1) {
+		/* wrap around */
+		ptp_read_system_prets(sts);
+		timer_l = ioread32be(&dev->iseg->internal_timer_l);
+		ptp_read_system_postts(sts);
+	}
+
+	return (u64)timer_l | (u64)timer_h1 << 32;
+}
+
 static u64 read_internal_timer(const struct cyclecounter *cc)
 {
 	struct mlx5_clock *clock = container_of(cc, struct mlx5_clock, cycles);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d6a8128f667a..4d2e1e982460 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -672,26 +672,6 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 	return mlx5_cmd_exec_in(dev, disable_hca, in);
 }
 
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
-			     struct ptp_system_timestamp *sts)
-{
-	u32 timer_h, timer_h1, timer_l;
-
-	timer_h = ioread32be(&dev->iseg->internal_timer_h);
-	ptp_read_system_prets(sts);
-	timer_l = ioread32be(&dev->iseg->internal_timer_l);
-	ptp_read_system_postts(sts);
-	timer_h1 = ioread32be(&dev->iseg->internal_timer_h);
-	if (timer_h != timer_h1) {
-		/* wrap around */
-		ptp_read_system_prets(sts);
-		timer_l = ioread32be(&dev->iseg->internal_timer_l);
-		ptp_read_system_postts(sts);
-	}
-
-	return (u64)timer_l | (u64)timer_h1 << 32;
-}
-
 static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 {
 	u32 query_out[MLX5_ST_SZ_DW(query_issi_out)] = {};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index a8fb43a85d1d..fc1649dac11b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -38,7 +38,6 @@
 #include <linux/sched.h>
 #include <linux/if_link.h>
 #include <linux/firmware.h>
-#include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/driver.h>
@@ -141,8 +140,6 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages);
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
-			     struct ptp_system_timestamp *sts);
 
 void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
 void mlx5_cmd_flush(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From 9102d836d296fbc94517736d2dd1131ad6b01740 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 12 Apr 2020 15:39:15 +0300
Subject: net/mlx5e: CT: Fix offload with CT action after CT NAT action

It could be a chain of rules will do action CT again after CT NAT
Before this fix matching will break as we get into the CT table
after NAT changes and not CT NAT.
Fix this by adding pre ct and pre ct nat tables to skip ct/ct_nat
tables and go straight to post_ct table if ct/nat was already done.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 308 +++++++++++++++++++--
 1 file changed, 286 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 5568ded97e0b..98263f00ee43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -24,6 +24,7 @@
 #define MLX5_CT_ZONE_MASK GENMASK(MLX5_CT_ZONE_BITS - 1, 0)
 #define MLX5_CT_STATE_ESTABLISHED_BIT BIT(1)
 #define MLX5_CT_STATE_TRK_BIT BIT(2)
+#define MLX5_CT_STATE_NAT_BIT BIT(3)
 
 #define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen * 8)
 #define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0)
@@ -61,6 +62,15 @@ struct mlx5_ct_zone_rule {
 	bool nat;
 };
 
+struct mlx5_tc_ct_pre {
+	struct mlx5_flow_table *fdb;
+	struct mlx5_flow_group *flow_grp;
+	struct mlx5_flow_group *miss_grp;
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5_flow_handle *miss_rule;
+	struct mlx5_modify_hdr *modify_hdr;
+};
+
 struct mlx5_ct_ft {
 	struct rhash_head node;
 	u16 zone;
@@ -68,6 +78,8 @@ struct mlx5_ct_ft {
 	struct nf_flowtable *nf_ft;
 	struct mlx5_tc_ct_priv *ct_priv;
 	struct rhashtable ct_entries_ht;
+	struct mlx5_tc_ct_pre pre_ct;
+	struct mlx5_tc_ct_pre pre_ct_nat;
 };
 
 struct mlx5_ct_entry {
@@ -426,6 +438,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	struct mlx5_eswitch *esw = ct_priv->esw;
 	struct mlx5_modify_hdr *mod_hdr;
 	struct flow_action_entry *meta;
+	u16 ct_state = 0;
 	int err;
 
 	meta = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
@@ -444,11 +457,13 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 						  &mod_acts);
 		if (err)
 			goto err_mapping;
+
+		ct_state |= MLX5_CT_STATE_NAT_BIT;
 	}
 
+	ct_state |= MLX5_CT_STATE_ESTABLISHED_BIT | MLX5_CT_STATE_TRK_BIT;
 	err = mlx5_tc_ct_entry_set_registers(ct_priv, &mod_acts,
-					     (MLX5_CT_STATE_ESTABLISHED_BIT |
-					      MLX5_CT_STATE_TRK_BIT),
+					     ct_state,
 					     meta->ct_metadata.mark,
 					     meta->ct_metadata.labels[0],
 					     tupleid);
@@ -791,6 +806,238 @@ mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
+				  struct mlx5_tc_ct_pre *pre_ct,
+				  bool nat)
+{
+	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
+	struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {};
+	struct mlx5_core_dev *dev = ct_priv->esw->dev;
+	struct mlx5_flow_table *fdb = pre_ct->fdb;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_modify_hdr *mod_hdr;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	u32 ctstate;
+	u16 zone;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	zone = ct_ft->zone & MLX5_CT_ZONE_MASK;
+	err = mlx5e_tc_match_to_reg_set(dev, &pre_mod_acts, ZONE_TO_REG, zone);
+	if (err) {
+		ct_dbg("Failed to set zone register mapping");
+		goto err_mapping;
+	}
+
+	mod_hdr = mlx5_modify_header_alloc(dev,
+					   MLX5_FLOW_NAMESPACE_FDB,
+					   pre_mod_acts.num_actions,
+					   pre_mod_acts.actions);
+
+	if (IS_ERR(mod_hdr)) {
+		err = PTR_ERR(mod_hdr);
+		ct_dbg("Failed to create pre ct mod hdr");
+		goto err_mapping;
+	}
+	pre_ct->modify_hdr = mod_hdr;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+	flow_act.modify_hdr = mod_hdr;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+
+	/* add flow rule */
+	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG,
+				    zone, MLX5_CT_ZONE_MASK);
+	ctstate = MLX5_CT_STATE_TRK_BIT;
+	if (nat)
+		ctstate |= MLX5_CT_STATE_NAT_BIT;
+	mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, ctstate, ctstate);
+
+	dest.ft = ct_priv->post_ct;
+	rule = mlx5_add_flow_rules(fdb, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		ct_dbg("Failed to add pre ct flow rule zone %d", zone);
+		goto err_flow_rule;
+	}
+	pre_ct->flow_rule = rule;
+
+	/* add miss rule */
+	memset(spec, 0, sizeof(*spec));
+	dest.ft = nat ? ct_priv->ct_nat : ct_priv->ct;
+	rule = mlx5_add_flow_rules(fdb, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		ct_dbg("Failed to add pre ct miss rule zone %d", zone);
+		goto err_miss_rule;
+	}
+	pre_ct->miss_rule = rule;
+
+	dealloc_mod_hdr_actions(&pre_mod_acts);
+	kvfree(spec);
+	return 0;
+
+err_miss_rule:
+	mlx5_del_flow_rules(pre_ct->flow_rule);
+err_flow_rule:
+	mlx5_modify_header_dealloc(dev, pre_ct->modify_hdr);
+err_mapping:
+	dealloc_mod_hdr_actions(&pre_mod_acts);
+	kvfree(spec);
+	return err;
+}
+
+static void
+tc_ct_pre_ct_del_rules(struct mlx5_ct_ft *ct_ft,
+		       struct mlx5_tc_ct_pre *pre_ct)
+{
+	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
+	struct mlx5_core_dev *dev = ct_priv->esw->dev;
+
+	mlx5_del_flow_rules(pre_ct->flow_rule);
+	mlx5_del_flow_rules(pre_ct->miss_rule);
+	mlx5_modify_header_dealloc(dev, pre_ct->modify_hdr);
+}
+
+static int
+mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
+			struct mlx5_tc_ct_pre *pre_ct,
+			bool nat)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
+	struct mlx5_core_dev *dev = ct_priv->esw->dev;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *g;
+	u32 metadata_reg_c_2_mask;
+	u32 *flow_group_in;
+	void *misc;
+	int err;
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!ns) {
+		err = -EOPNOTSUPP;
+		ct_dbg("Failed to get FDB flow namespace");
+		return err;
+	}
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED;
+	ft_attr.prio = FDB_TC_OFFLOAD;
+	ft_attr.max_fte = 2;
+	ft_attr.level = 1;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		ct_dbg("Failed to create pre ct table");
+		goto out_free;
+	}
+	pre_ct->fdb = ft;
+
+	/* create flow group */
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS_2);
+
+	misc = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+			    match_criteria.misc_parameters_2);
+
+	metadata_reg_c_2_mask = MLX5_CT_ZONE_MASK;
+	metadata_reg_c_2_mask |= (MLX5_CT_STATE_TRK_BIT << 16);
+	if (nat)
+		metadata_reg_c_2_mask |= (MLX5_CT_STATE_NAT_BIT << 16);
+
+	MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_2,
+		 metadata_reg_c_2_mask);
+
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		ct_dbg("Failed to create pre ct group");
+		goto err_flow_grp;
+	}
+	pre_ct->flow_grp = g;
+
+	/* create miss group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		ct_dbg("Failed to create pre ct miss group");
+		goto err_miss_grp;
+	}
+	pre_ct->miss_grp = g;
+
+	err = tc_ct_pre_ct_add_rules(ct_ft, pre_ct, nat);
+	if (err)
+		goto err_add_rules;
+
+	kvfree(flow_group_in);
+	return 0;
+
+err_add_rules:
+	mlx5_destroy_flow_group(pre_ct->miss_grp);
+err_miss_grp:
+	mlx5_destroy_flow_group(pre_ct->flow_grp);
+err_flow_grp:
+	mlx5_destroy_flow_table(ft);
+out_free:
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void
+mlx5_tc_ct_free_pre_ct(struct mlx5_ct_ft *ct_ft,
+		       struct mlx5_tc_ct_pre *pre_ct)
+{
+	tc_ct_pre_ct_del_rules(ct_ft, pre_ct);
+	mlx5_destroy_flow_group(pre_ct->miss_grp);
+	mlx5_destroy_flow_group(pre_ct->flow_grp);
+	mlx5_destroy_flow_table(pre_ct->fdb);
+}
+
+static int
+mlx5_tc_ct_alloc_pre_ct_tables(struct mlx5_ct_ft *ft)
+{
+	int err;
+
+	err = mlx5_tc_ct_alloc_pre_ct(ft, &ft->pre_ct, false);
+	if (err)
+		return err;
+
+	err = mlx5_tc_ct_alloc_pre_ct(ft, &ft->pre_ct_nat, true);
+	if (err)
+		goto err_pre_ct_nat;
+
+	return 0;
+
+err_pre_ct_nat:
+	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct);
+	return err;
+}
+
+static void
+mlx5_tc_ct_free_pre_ct_tables(struct mlx5_ct_ft *ft)
+{
+	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct_nat);
+	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct);
+}
+
 static struct mlx5_ct_ft *
 mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
 		     struct nf_flowtable *nf_ft)
@@ -813,6 +1060,10 @@ mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
 	ft->ct_priv = ct_priv;
 	refcount_set(&ft->refcount, 1);
 
+	err = mlx5_tc_ct_alloc_pre_ct_tables(ft);
+	if (err)
+		goto err_alloc_pre_ct;
+
 	err = rhashtable_init(&ft->ct_entries_ht, &cts_ht_params);
 	if (err)
 		goto err_init;
@@ -834,6 +1085,8 @@ err_add_cb:
 err_insert:
 	rhashtable_destroy(&ft->ct_entries_ht);
 err_init:
+	mlx5_tc_ct_free_pre_ct_tables(ft);
+err_alloc_pre_ct:
 	kfree(ft);
 	return ERR_PTR(err);
 }
@@ -859,21 +1112,40 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
 	rhashtable_free_and_destroy(&ft->ct_entries_ht,
 				    mlx5_tc_ct_flush_ft_entry,
 				    ct_priv);
+	mlx5_tc_ct_free_pre_ct_tables(ft);
 	kfree(ft);
 }
 
 /* We translate the tc filter with CT action to the following HW model:
  *
- * +-------------------+      +--------------------+    +--------------+
- * + pre_ct (tc chain) +----->+ CT (nat or no nat) +--->+ post_ct      +----->
- * + original match    +  |   + tuple + zone match + |  + fte_id match +  |
- * +-------------------+  |   +--------------------+ |  +--------------+  |
- *                        v                          v                    v
- *                       set chain miss mapping  set mark             original
- *                       set fte_id              set label            filter
- *                       set zone                set established      actions
- *                       set tunnel_id           do nat (if needed)
- *                       do decap
+ * +---------------------+
+ * + fdb prio (tc chain) +
+ * + original match      +
+ * +---------------------+
+ *      | set chain miss mapping
+ *      | set fte_id
+ *      | set tunnel_id
+ *      | do decap
+ *      v
+ * +---------------------+
+ * + pre_ct/pre_ct_nat   +  if matches     +---------------------+
+ * + zone+nat match      +---------------->+ post_ct (see below) +
+ * +---------------------+  set zone       +---------------------+
+ *      | set zone
+ *      v
+ * +--------------------+
+ * + CT (nat or no nat) +
+ * + tuple + zone match +
+ * +--------------------+
+ *      | set mark
+ *      | set label
+ *      | set established
+ *      | do nat (if needed)
+ *      v
+ * +--------------+
+ * + post_ct      + original filter actions
+ * + fte_id match +------------------------>
+ * +--------------+
  */
 static int
 __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
@@ -888,7 +1160,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	struct mlx5_flow_spec *post_ct_spec = NULL;
 	struct mlx5_eswitch *esw = ct_priv->esw;
 	struct mlx5_esw_flow_attr *pre_ct_attr;
-	struct  mlx5_modify_hdr *mod_hdr;
+	struct mlx5_modify_hdr *mod_hdr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_ct_flow *ct_flow;
 	int chain_mapping = 0, err;
@@ -951,14 +1223,6 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 		goto err_mapping;
 	}
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, &pre_mod_acts, ZONE_TO_REG,
-					attr->ct_attr.zone &
-					MLX5_CT_ZONE_MASK);
-	if (err) {
-		ct_dbg("Failed to set zone register mapping");
-		goto err_mapping;
-	}
-
 	err = mlx5e_tc_match_to_reg_set(esw->dev, &pre_mod_acts,
 					FTEID_TO_REG, fte_id);
 	if (err) {
@@ -1018,7 +1282,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 
 	/* Change original rule point to ct table */
 	pre_ct_attr->dest_chain = 0;
-	pre_ct_attr->dest_ft = nat ? ct_priv->ct_nat : ct_priv->ct;
+	pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.fdb : ft->pre_ct.fdb;
 	ct_flow->pre_ct_rule = mlx5_eswitch_add_offloaded_rule(esw,
 							       orig_spec,
 							       pre_ct_attr);
-- 
cgit v1.2.3


From 80639b199c9ca87444da218ba0e7511946452dd4 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Sun, 3 May 2020 13:01:37 +0300
Subject: net/mlx5e: IPoIB, Enable loopback packets for IPoIB interfaces

Enable loopback of unicast and multicast traffic for IPoIB enhanced
mode.
This will allow interfaces with the same pkey to communicate between
them e.g cloned interfaces that located in different namespaces.

Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h               |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c        | 13 ++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c          |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c      |  7 ++++++-
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h      |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c |  2 +-
 7 files changed, 24 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 195162b9b245..ac385ac93fe5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1082,7 +1082,8 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
+		       bool enable_mc_lb);
 
 /* common netdev helpers */
 void mlx5e_create_q_counters(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index af3228b3f303..1e42c7ae621b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -141,10 +141,12 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	memset(res, 0, sizeof(*res));
 }
 
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
+		       bool enable_mc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
+	u8 lb_flags = 0;
 	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
@@ -158,8 +160,13 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 	}
 
 	if (enable_uc_lb)
-		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST);
+		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+
+	if (enable_mc_lb)
+		lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+	if (lb_flags)
+		MLX5_SET(modify_tir_in, in, ctx.self_lb_block, lb_flags);
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e4ca08ddca9..65e2b364443e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5275,7 +5275,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_refresh_tirs(priv, false);
+	return mlx5e_refresh_tirs(priv, false, false);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index bbff8d8ded76..46790216ce86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -234,7 +234,7 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 			return err;
 	}
 
-	err = mlx5e_refresh_tirs(priv, true);
+	err = mlx5e_refresh_tirs(priv, true, false);
 	if (err)
 		goto out;
 
@@ -263,7 +263,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 		mlx5_nic_vport_update_local_lb(priv->mdev, false);
 
 	dev_remove_pack(&lbtp->pt);
-	mlx5e_refresh_tirs(priv, false);
+	mlx5e_refresh_tirs(priv, false, false);
 }
 
 #define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 035bd21e5d4e..7db70b6ccc07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -262,6 +262,11 @@ void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn)
 	mlx5_cmd_exec_in(mdev, destroy_qp, in);
 }
 
+int mlx5i_update_nic_rx(struct mlx5e_priv *priv)
+{
+	return mlx5e_refresh_tirs(priv, true, true);
+}
+
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
 {
 	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
@@ -456,7 +461,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.cleanup_rx	   = mlx5i_cleanup_rx,
 	.enable		   = NULL, /* mlx5i_enable */
 	.disable	   = NULL, /* mlx5i_disable */
-	.update_rx	   = mlx5e_update_nic_rx,
+	.update_rx	   = mlx5i_update_nic_rx,
 	.update_stats	   = NULL, /* mlx5i_update_stats */
 	.update_carrier    = NULL, /* no HW update in IB link */
 	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index c4aa47018c0e..79071a15c4ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -92,6 +92,8 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
 	       void *ppriv);
 void mlx5i_cleanup(struct mlx5e_priv *priv);
 
+int mlx5i_update_nic_rx(struct mlx5e_priv *priv);
+
 /* Get child interface nic profile */
 const struct mlx5e_profile *mlx5i_pkey_get_profile(void);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index b9af37ad40bf..f70367018862 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -347,7 +347,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.cleanup_rx	   = mlx5i_pkey_cleanup_rx,
 	.enable		   = NULL,
 	.disable	   = NULL,
-	.update_rx	   = mlx5e_update_nic_rx,
+	.update_rx	   = mlx5i_update_nic_rx,
 	.update_stats	   = NULL,
 	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
 	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
-- 
cgit v1.2.3


From 8b46d424a743ddfef8056d5167f13ee7ebd1dcad Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Mon, 4 May 2020 11:46:25 +0300
Subject: net/mlx5e: IPoIB, Drop multicast packets that this interface sent

After enabled loopback packets for IPoIB, we need to drop these packets
that this HCA has replicated and came back to the same interface that
sent them.

Fixes: 4c6c615e3f30 ("net/mlx5e: IPoIB, Add PKEY child interface nic profile")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 821f94beda7a..a514685fb560 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1489,6 +1489,7 @@ out:
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
 
+#define MLX5_IB_GRH_SGID_OFFSET 8
 #define MLX5_IB_GRH_DGID_OFFSET 24
 #define MLX5_GID_SIZE           16
 
@@ -1502,6 +1503,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
 	char *pseudo_header;
+	u32 flags_rqpn;
 	u32 qpn;
 	u8 *dgid;
 	u8 g;
@@ -1523,7 +1525,8 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	tstamp = &priv->tstamp;
 	stats = &priv->channel_stats[rq->ix].rq;
 
-	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
+	flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
+	g = (flags_rqpn >> 28) & 3;
 	dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
 	if ((!g) || dgid[0] != 0xff)
 		skb->pkt_type = PACKET_HOST;
@@ -1532,9 +1535,15 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	else
 		skb->pkt_type = PACKET_MULTICAST;
 
-	/* TODO: IB/ipoib: Allow mcast packets from other VFs
-	 * 68996a6e760e5c74654723eeb57bf65628ae87f4
+	/* Drop packets that this interface sent, ie multicast packets
+	 * that the HCA has replicated.
 	 */
+	if (g && (qpn == (flags_rqpn & 0xffffff)) &&
+	    (memcmp(netdev->dev_addr + 4, skb->data + MLX5_IB_GRH_SGID_OFFSET,
+		    MLX5_GID_SIZE) == 0)) {
+		skb->dev = NULL;
+		return;
+	}
 
 	skb_pull(skb, MLX5_IB_GRH_BYTES);
 
-- 
cgit v1.2.3


From 5ffb4d858b7051720f20bcbb92dce0b433e60d88 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 30 Mar 2020 16:28:34 +0300
Subject: net/mlx5e: Calculate SQ stop room in a robust way

Currently, different formulas are used to estimate the space that may be
taken by WQEs in the SQ during a single packet transmit. This space is
called stop room, and it's checked in the end of packet transmit to find
out if the next packet could overflow the SQ. If it could, the driver
tells the kernel to stop sending next packets.

Many factors affect the stop room:

1. Padding with NOPs to avoid WQEs spanning over page boundaries.

2. Enabled and disabled offloads (TLS, upcoming MPWQE).

3. The maximum size of a WQE.

The padding is performed before every WQE if it doesn't fit the current
page.

The current formula assumes that only one padding will be required per
packet, and it doesn't take into account that the WQEs posted during the
transmission of a single packet might exceed the page size in very rare
circumstances. For example, to hit this condition with 4096-byte pages,
TLS offload will have to interrupt an almost-full MPWQE session, be in
the resync flow and try to transmit a near to maximum amount of data.

To avoid SQ overflows in such rare cases after MPWQE is added, this
patch introduces a more robust formula to estimate the stop room. The
new formula uses the fact that a WQE of size X will not require more
than X-1 WQEBBs of padding. More exact estimations are possible, but
they result in much more complex and error-prone code for little gain.

Before this patch, the TLS stop room included space for both INNOVA and
ConnectX TLS offloads that couldn't run at the same time anyway, so this
patch accounts only for the active one.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h  | 40 ++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |  4 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h   |  2 --
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.c    | 13 +++++++
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.h    | 12 +++----
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 14 ++++++++
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.h |  7 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 28 ++++++++++-----
 8 files changed, 84 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index dce2bbbf9109..bfd3e1161bc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -6,25 +6,6 @@
 
 #include "en.h"
 
-#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1)
-#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
-			    MLX5E_SQ_NOPS_ROOM)
-
-#ifndef CONFIG_MLX5_EN_TLS
-#define MLX5E_SQ_TLS_ROOM (0)
-#else
-/* TLS offload requires additional stop_room for:
- *  - a resync SKB.
- * kTLS offload requires fixed additional stop_room for:
- * - a static params WQE, and a progress params WQE.
- * The additional MTU-depending room for the resync DUMP WQEs
- * will be calculated and added in runtime.
- */
-#define MLX5E_SQ_TLS_ROOM  \
-	(MLX5_SEND_WQE_MAX_WQEBBS + \
-	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS)
-#endif
-
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
 
 enum mlx5e_icosq_wqe_type {
@@ -331,4 +312,25 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 	}
 }
 
+static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size)
+{
+	BUILD_BUG_ON(PAGE_SIZE / MLX5_SEND_WQE_BB < MLX5_SEND_WQE_MAX_WQEBBS);
+
+	/* A WQE must not cross the page boundary, hence two conditions:
+	 * 1. Its size must not exceed the page size.
+	 * 2. If the WQE size is X, and the space remaining in a page is less
+	 *    than X, this space needs to be padded with NOPs. So, one WQE of
+	 *    size X may require up to X-1 WQEBBs of padding, which makes the
+	 *    stop room of X-1 + X.
+	 * WQE size is also limited by the hardware limit.
+	 */
+
+	if (__builtin_constant_p(wqe_size))
+		BUILD_BUG_ON(wqe_size > MLX5_SEND_WQE_MAX_WQEBBS);
+	else
+		WARN_ON_ONCE(wqe_size > MLX5_SEND_WQE_MAX_WQEBBS);
+
+	return wqe_size * 2 - 1;
+}
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 761c8979bd41..42202d19245c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -257,8 +257,10 @@ enum {
 static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
 {
 	if (unlikely(!sq->mpwqe.wqe)) {
+		const u16 stop_room = mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+
 		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-						     MLX5E_XDPSQ_STOP_ROOM))) {
+						     stop_room))) {
 			/* SQ is full, ring doorbell */
 			mlx5e_xmit_xdp_doorbell(sq);
 			sq->stats->full++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e2e01f064c1e..be64eb68f4e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -40,8 +40,6 @@
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
-#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM)
-
 #define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
 #define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
 	DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index 46725cd743a3..417a2d9dd248 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -4,6 +4,19 @@
 #include "en.h"
 #include "en_accel/ktls.h"
 
+u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq)
+{
+	u16 num_dumps, stop_room = 0;
+
+	num_dumps = mlx5e_ktls_dumps_num_wqes(sq, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE);
+
+	stop_room += mlx5e_stop_room_for_wqe(MLX5E_KTLS_STATIC_WQEBBS);
+	stop_room += mlx5e_stop_room_for_wqe(MLX5E_KTLS_PROGRESS_WQEBBS);
+	stop_room += num_dumps * mlx5e_stop_room_for_wqe(MLX5E_KTLS_DUMP_WQEBBS);
+
+	return stop_room;
+}
+
 static int mlx5e_ktls_create_tis(struct mlx5_core_dev *mdev, u32 *tisn)
 {
 	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index dabbc5f226ce..c6180892cfcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -102,15 +102,16 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
+u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq);
+
 static inline u8
-mlx5e_ktls_dumps_num_wqebbs(struct mlx5e_txqsq *sq, unsigned int nfrags,
-			    unsigned int sync_len)
+mlx5e_ktls_dumps_num_wqes(struct mlx5e_txqsq *sq, unsigned int nfrags,
+			  unsigned int sync_len)
 {
 	/* Given the MTU and sync_len, calculates an upper bound for the
-	 * number of WQEBBs needed for the TX resync DUMP WQEs of a record.
+	 * number of DUMP WQEs needed for the TX resync of a record.
 	 */
-	return MLX5E_KTLS_DUMP_WQEBBS *
-		(nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu));
+	return nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu);
 }
 #else
 
@@ -122,7 +123,6 @@ static inline void
 mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 				      struct mlx5e_tx_wqe_info *wi,
 				      u32 *dma_fifo_cc) {}
-
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index fba561ffe1d4..c27e9a609d51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -240,3 +240,17 @@ void mlx5e_tls_cleanup(struct mlx5e_priv *priv)
 	kfree(tls);
 	priv->tls = NULL;
 }
+
+u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+
+	if (!mlx5_accel_is_tls_device(mdev))
+		return 0;
+
+	if (MLX5_CAP_GEN(mdev, tls_tx))
+		return mlx5e_ktls_get_stop_room(sq);
+
+	/* Resync SKB. */
+	return mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 9015f3f7792d..9219bdb2786e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -94,6 +94,8 @@ int mlx5e_tls_get_count(struct mlx5e_priv *priv);
 int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data);
 int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data);
 
+u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq);
+
 #else
 
 static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
@@ -108,6 +110,11 @@ static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; }
 static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; }
 static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; }
 
+static inline u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 65e2b364443e..75f178a43822 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1122,6 +1122,22 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	return 0;
 }
 
+static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size)
+{
+	int sq_size = 1 << log_sq_size;
+
+	sq->stop_room  = mlx5e_tls_get_stop_room(sq);
+	sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+
+	if (WARN_ON(sq->stop_room >= sq_size)) {
+		netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n",
+			   sq->stop_room, sq_size);
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
 static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
@@ -1146,20 +1162,16 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
-	sq->stop_room = MLX5E_SQ_STOP_ROOM;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
 	if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
 		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
-#ifdef CONFIG_MLX5_EN_TLS
-	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
+	if (mlx5_accel_is_tls_device(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
-		sq->stop_room += MLX5E_SQ_TLS_ROOM +
-			mlx5e_ktls_dumps_num_wqebbs(sq, MAX_SKB_FRAGS,
-						    TLS_MAX_PAYLOAD_SIZE);
-	}
-#endif
+	err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size);
+	if (err)
+		return err;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
-- 
cgit v1.2.3


From 3f3ab178c71b12295b5950792b72d2198f0e77c7 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 23 Oct 2019 15:00:52 +0300
Subject: net/mlx5e: Take DCBNL-related definitions into dedicated files

Take DCBNL-related definitions out of the common en.h header,
Use a dedicated header file for exposing them.
Some need not to be exposed, use them locally in the .c file.
Use stubs to eliminate use of CONFIG_MLX5_CORE_EN_DCB in the
generic control flows.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 50 +-------------------
 drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h | 54 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 28 ++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 16 +------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  9 +---
 5 files changed, 84 insertions(+), 73 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ac385ac93fe5..81fd53569463 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
+#include "en/dcbnl.h"
 #include "en/fs.h"
 #include "lib/hv_vhca.h"
 
@@ -68,8 +69,6 @@ struct page_pool;
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
 
-#define MLX5E_MAX_PRIORITY      8
-#define MLX5E_MAX_DSCP          64
 #define MLX5E_MAX_NUM_TC	8
 
 #define MLX5_RX_HEADROOM NET_SKB_PAD
@@ -242,10 +241,6 @@ enum mlx5e_priv_flag {
 
 #define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-#define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#endif
-
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
@@ -270,42 +265,6 @@ struct mlx5e_params {
 	int hard_mtu;
 };
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-struct mlx5e_cee_config {
-	/* bw pct for priority group */
-	u8                         pg_bw_pct[CEE_DCBX_MAX_PGS];
-	u8                         prio_to_pg_map[CEE_DCBX_MAX_PRIO];
-	bool                       pfc_setting[CEE_DCBX_MAX_PRIO];
-	bool                       pfc_enable;
-};
-
-enum {
-	MLX5_DCB_CHG_RESET,
-	MLX5_DCB_NO_CHG,
-	MLX5_DCB_CHG_NO_RESET,
-};
-
-struct mlx5e_dcbx {
-	enum mlx5_dcbx_oper_mode   mode;
-	struct mlx5e_cee_config    cee_cfg; /* pending configuration */
-	u8                         dscp_app_cnt;
-
-	/* The only setting that cannot be read from FW */
-	u8                         tc_tsa[IEEE_8021QAZ_MAX_TCS];
-	u8                         cap;
-
-	/* Buffer configuration */
-	bool                       manual_buffer;
-	u32                        cable_len;
-	u32                        xoff;
-};
-
-struct mlx5e_dcbx_dp {
-	u8                         dscp2prio[MLX5E_MAX_DSCP];
-	u8                         trust_state;
-};
-#endif
-
 enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_RECOVERING,
@@ -1068,13 +1027,6 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
-int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets);
-void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv);
-void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
-void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
-#endif
 
 int mlx5e_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir,
 		     u32 *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
new file mode 100644
index 000000000000..7be6b2d36b60
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __MLX5E_DCBNL_H__
+#define __MLX5E_DCBNL_H__
+
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+
+#define MLX5E_MAX_PRIORITY (8)
+
+struct mlx5e_cee_config {
+	/* bw pct for priority group */
+	u8                         pg_bw_pct[CEE_DCBX_MAX_PGS];
+	u8                         prio_to_pg_map[CEE_DCBX_MAX_PRIO];
+	bool                       pfc_setting[CEE_DCBX_MAX_PRIO];
+	bool                       pfc_enable;
+};
+
+struct mlx5e_dcbx {
+	enum mlx5_dcbx_oper_mode   mode;
+	struct mlx5e_cee_config    cee_cfg; /* pending configuration */
+	u8                         dscp_app_cnt;
+
+	/* The only setting that cannot be read from FW */
+	u8                         tc_tsa[IEEE_8021QAZ_MAX_TCS];
+	u8                         cap;
+
+	/* Buffer configuration */
+	bool                       manual_buffer;
+	u32                        cable_len;
+	u32                        xoff;
+};
+
+#define MLX5E_MAX_DSCP (64)
+
+struct mlx5e_dcbx_dp {
+	u8                         dscp2prio[MLX5E_MAX_DSCP];
+	u8                         trust_state;
+};
+
+void mlx5e_dcbnl_build_netdev(struct net_device *netdev);
+void mlx5e_dcbnl_build_rep_netdev(struct net_device *netdev);
+void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv);
+void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
+void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
+#else
+static inline void mlx5e_dcbnl_build_netdev(struct net_device *netdev) {}
+static inline void mlx5e_dcbnl_build_rep_netdev(struct net_device *netdev) {}
+static inline void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) {}
+static inline void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv) {}
+static inline void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) {}
+#endif
+
+#endif /* __MLX5E_DCBNL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 47874d34156b..ec7b332d74c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -35,6 +35,8 @@
 #include "en/port.h"
 #include "en/port_buffer.h"
 
+#define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
+
 #define MLX5E_100MB (100000)
 #define MLX5E_1GB   (1000000)
 
@@ -49,6 +51,12 @@ enum {
 	MLX5E_LOWEST_PRIO_GROUP   = 0,
 };
 
+enum {
+	MLX5_DCB_CHG_RESET,
+	MLX5_DCB_NO_CHG,
+	MLX5_DCB_CHG_NO_RESET,
+};
+
 #define MLX5_DSCP_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, qcam_reg)  && \
 				   MLX5_CAP_QCAM_REG(mdev, qpts) && \
 				   MLX5_CAP_QCAM_REG(mdev, qpdpm))
@@ -238,7 +246,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
  *   Report both group #0 and #1 as ETS type.
  *     All the tcs in group #0 will be reported with 0% BW.
  */
-int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
+static int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS];
@@ -1009,6 +1017,24 @@ const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = {
 	.setpfcstate    = mlx5e_dcbnl_setpfcstate,
 };
 
+void mlx5e_dcbnl_build_netdev(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (MLX5_CAP_GEN(mdev, vport_group_manager) && MLX5_CAP_GEN(mdev, qos))
+		netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+}
+
+void mlx5e_dcbnl_build_rep_netdev(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (MLX5_CAP_GEN(mdev, qos))
+		netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+}
+
 static void mlx5e_dcbnl_query_dcbx_mode(struct mlx5e_priv *priv,
 					enum mlx5_dcbx_oper_mode *mode)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 75f178a43822..07823abe5557 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -66,7 +66,6 @@
 #include "en/devlink.h"
 #include "lib/mlx5.h"
 
-
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
 	bool striding_rq_umr = MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -4927,10 +4926,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-	if (MLX5_CAP_GEN(mdev, vport_group_manager) && MLX5_CAP_GEN(mdev, qos))
-		netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
-#endif
+	mlx5e_dcbnl_build_netdev(netdev);
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
@@ -5218,9 +5214,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
-#endif
 	return 0;
 }
 
@@ -5247,9 +5241,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5e_hv_vhca_stats_create(priv);
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_init_app(priv);
-#endif
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
@@ -5264,10 +5256,8 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	if (priv->netdev->reg_state == NETREG_REGISTERED)
 		mlx5e_dcbnl_delete_app(priv);
-#endif
 
 	rtnl_lock();
 	if (netif_running(priv->netdev))
@@ -5564,9 +5554,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 
 	mlx5e_devlink_port_type_eth_set(priv);
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_init_app(priv);
-#endif
 	return priv;
 
 err_devlink_port_unregister:
@@ -5589,9 +5577,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 	}
 #endif
 	priv = vpriv;
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
-#endif
 	unregister_netdev(priv->netdev);
 	mlx5e_devlink_port_unregister(priv);
 	mlx5e_detach(mdev, vpriv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 1eac7a53d56f..52351c105627 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1544,10 +1544,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 		/* we want a persistent mac for the uplink rep */
 		mlx5_query_mac_address(mdev, netdev->dev_addr);
 		netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops;
-#ifdef CONFIG_MLX5_CORE_EN_DCB
-		if (MLX5_CAP_GEN(mdev, qos))
-			netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
-#endif
+		mlx5e_dcbnl_build_rep_netdev(netdev);
 	} else {
 		netdev->netdev_ops = &mlx5e_netdev_ops_rep;
 		eth_hw_addr_random(netdev);
@@ -1929,10 +1926,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
 	mlx5e_dcbnl_init_app(priv);
-#endif
 }
 
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
@@ -1940,9 +1935,7 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
-#ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
-#endif
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
 	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
 	mlx5_lag_remove(mdev);
-- 
cgit v1.2.3


From 2ea46dc6864261e94441e4d141058fc538d0de6b Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Fri, 15 May 2020 15:33:18 -0700
Subject: ethernet: ti: am65-cpts: Add missing inline qualifier to stub
 functions

When building with Clang:

In file included from drivers/net/ethernet/ti/am65-cpsw-ethtool.c:15:
drivers/net/ethernet/ti/am65-cpts.h:58:12: warning: unused function
'am65_cpts_ns_gettime' [-Wunused-function]
static s64 am65_cpts_ns_gettime(struct am65_cpts *cpts)
           ^
drivers/net/ethernet/ti/am65-cpts.h:63:12: warning: unused function
'am65_cpts_estf_enable' [-Wunused-function]
static int am65_cpts_estf_enable(struct am65_cpts *cpts,
           ^
drivers/net/ethernet/ti/am65-cpts.h:69:13: warning: unused function
'am65_cpts_estf_disable' [-Wunused-function]
static void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx)
            ^
3 warnings generated.

These functions need to be marked as inline, which adds __maybe_unused,
to avoid these warnings, which is the pattern for stub functions.

Fixes: ec008fa2a9e5 ("ethernet: ti: am65-cpts: add routines to support taprio offload")
Link: https://github.com/ClangBuiltLinux/linux/issues/1026
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpts.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h
index 98c1960b20b9..cf9fbc28fd03 100644
--- a/drivers/net/ethernet/ti/am65-cpts.h
+++ b/drivers/net/ethernet/ti/am65-cpts.h
@@ -55,18 +55,18 @@ static inline void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en)
 {
 }
 
-static s64 am65_cpts_ns_gettime(struct am65_cpts *cpts)
+static inline s64 am65_cpts_ns_gettime(struct am65_cpts *cpts)
 {
 	return 0;
 }
 
-static int am65_cpts_estf_enable(struct am65_cpts *cpts,
-				 int idx, struct am65_cpts_estf_cfg *cfg)
+static inline int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx,
+					struct am65_cpts_estf_cfg *cfg)
 {
 	return 0;
 }
 
-static void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx)
+static inline void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx)
 {
 }
 #endif
-- 
cgit v1.2.3


From 74a1c059168ba1388aa475847c05a02f5f971a46 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Wed, 13 May 2020 16:55:46 +0300
Subject: dpaa2-eth: add bulking to XDP_TX

Add driver level bulking to the XDP_TX action.

An array of frame descriptors is held for each Tx frame queue and
populated accordingly when the action returned by the XDP program is
XDP_TX. The frames will be actually enqueued only when the array is
filled. At the end of the NAPI cycle a flush on the queued frames is
performed in order to enqueue the remaining FDs.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 68 ++++++++++++++++--------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |  1 +
 2 files changed, 46 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 5fbaa51b38bc..fe3806d54630 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -273,13 +273,43 @@ static int dpaa2_eth_xdp_flush(struct dpaa2_eth_priv *priv,
 	return total_enqueued;
 }
 
-static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
-		       void *buf_start, u16 queue_id)
+static void xdp_tx_flush(struct dpaa2_eth_priv *priv,
+			 struct dpaa2_eth_channel *ch,
+			 struct dpaa2_eth_fq *fq)
+{
+	struct rtnl_link_stats64 *percpu_stats;
+	struct dpaa2_fd *fds;
+	int enqueued, i;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+
+	// enqueue the array of XDP_TX frames
+	enqueued = dpaa2_eth_xdp_flush(priv, fq, &fq->xdp_tx_fds);
+
+	/* update statistics */
+	percpu_stats->tx_packets += enqueued;
+	fds = fq->xdp_tx_fds.fds;
+	for (i = 0; i < enqueued; i++) {
+		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]);
+		ch->stats.xdp_tx++;
+	}
+	for (i = enqueued; i < fq->xdp_tx_fds.num; i++) {
+		xdp_release_buf(priv, ch, dpaa2_fd_get_addr(&fds[i]));
+		percpu_stats->tx_errors++;
+		ch->stats.xdp_tx_err++;
+	}
+	fq->xdp_tx_fds.num = 0;
+}
+
+static void xdp_enqueue(struct dpaa2_eth_priv *priv,
+			struct dpaa2_eth_channel *ch,
+			struct dpaa2_fd *fd,
+			void *buf_start, u16 queue_id)
 {
-	struct dpaa2_eth_fq *fq;
 	struct dpaa2_faead *faead;
+	struct dpaa2_fd *dest_fd;
+	struct dpaa2_eth_fq *fq;
 	u32 ctrl, frc;
-	int i, err;
 
 	/* Mark the egress frame hardware annotation area as valid */
 	frc = dpaa2_fd_get_frc(fd);
@@ -296,13 +326,13 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 	faead->conf_fqid = 0;
 
 	fq = &priv->fq[queue_id];
-	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = priv->enqueue(priv, fq, fd, 0, 1, NULL);
-		if (err != -EBUSY)
-			break;
-	}
+	dest_fd = &fq->xdp_tx_fds.fds[fq->xdp_tx_fds.num++];
+	memcpy(dest_fd, fd, sizeof(*dest_fd));
 
-	return err;
+	if (fq->xdp_tx_fds.num < DEV_MAP_BULK_SIZE)
+		return;
+
+	xdp_tx_flush(priv, ch, fq);
 }
 
 static u32 run_xdp(struct dpaa2_eth_priv *priv,
@@ -311,14 +341,11 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		   struct dpaa2_fd *fd, void *vaddr)
 {
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
-	struct rtnl_link_stats64 *percpu_stats;
 	struct bpf_prog *xdp_prog;
 	struct xdp_buff xdp;
 	u32 xdp_act = XDP_PASS;
 	int err;
 
-	percpu_stats = this_cpu_ptr(priv->percpu_stats);
-
 	rcu_read_lock();
 
 	xdp_prog = READ_ONCE(ch->xdp.prog);
@@ -344,16 +371,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		err = xdp_enqueue(priv, fd, vaddr, rx_fq->flowid);
-		if (err) {
-			xdp_release_buf(priv, ch, addr);
-			percpu_stats->tx_errors++;
-			ch->stats.xdp_tx_err++;
-		} else {
-			percpu_stats->tx_packets++;
-			percpu_stats->tx_bytes += dpaa2_fd_get_len(fd);
-			ch->stats.xdp_tx++;
-		}
+		xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(xdp_act);
@@ -1175,6 +1193,7 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	int store_cleaned, work_done;
 	struct list_head rx_list;
 	int retries = 0;
+	u16 flowid;
 	int err;
 
 	ch = container_of(napi, struct dpaa2_eth_channel, napi);
@@ -1197,6 +1216,7 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 			break;
 		if (fq->type == DPAA2_RX_FQ) {
 			rx_cleaned += store_cleaned;
+			flowid = fq->flowid;
 		} else {
 			txconf_cleaned += store_cleaned;
 			/* We have a single Tx conf FQ on this channel */
@@ -1239,6 +1259,8 @@ out:
 
 	if (ch->xdp.res & XDP_REDIRECT)
 		xdp_do_flush_map();
+	else if (rx_cleaned && ch->xdp.res & XDP_TX)
+		xdp_tx_flush(priv, ch, &priv->fq[flowid]);
 
 	return work_done;
 }
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 42f0a7a80afa..0581fbf1f98c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -334,6 +334,7 @@ struct dpaa2_eth_fq {
 	struct dpaa2_eth_fq_stats stats;
 
 	struct dpaa2_eth_xdp_fds xdp_redirect_fds;
+	struct dpaa2_eth_xdp_fds xdp_tx_fds;
 };
 
 struct dpaa2_eth_ch_xdp {
-- 
cgit v1.2.3


From 4df6ff2a99920254ce8c2a3c418ddabc69ff16fe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 15 May 2020 12:49:01 -0700
Subject: nfp: don't check lack of RX/TX channels

Core will now perform this check.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index a5aa3219d112..6eb9fb9a1814 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -1438,8 +1438,7 @@ static int nfp_net_set_channels(struct net_device *netdev,
 	unsigned int total_rx, total_tx;
 
 	/* Reject unsupported */
-	if (!channel->combined_count ||
-	    channel->other_count != NFP_NET_NON_Q_VECTORS ||
+	if (channel->other_count != NFP_NET_NON_Q_VECTORS ||
 	    (channel->rx_count && channel->tx_count))
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 13f15b59ad70549545272cc8f0bf4d68a8ef9c14 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 17 May 2020 00:05:08 +0200
Subject: r8169: remove remaining call to mdiobus_unregister

After having switched to devm_mdiobus_register() also this remaining
call to mdiobus_unregister() can be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 97a7e27fff16..e35820c72264 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4990,7 +4990,6 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
-	mdiobus_unregister(tp->phydev->mdio.bus);
 
 	rtl_release_firmware(tp);
 
-- 
cgit v1.2.3


From 85d4ec592510520a2beb11c7f35748fd09ffe089 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 17 May 2020 01:43:05 +0300
Subject: mlxsw: spectrum_trap: Move struct definition out of header file

'struct mlxsw_sp_trap_policer_item' is only used in one file, so move it
there.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 6 ++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h | 6 ------
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index fbf714d027d8..634e695b89fa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -12,6 +12,12 @@
 #include "spectrum.h"
 #include "spectrum_trap.h"
 
+struct mlxsw_sp_trap_policer_item {
+	u16 hw_id;
+	u32 id;
+	struct list_head list; /* Member of policer_item_list */
+};
+
 /* All driver-specific traps must be documented in
  * Documentation/networking/devlink/mlxsw.rst
  */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
index 8c54897ba173..8a11a2b973f8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
@@ -15,10 +15,4 @@ struct mlxsw_sp_trap {
 	unsigned long policers_usage[]; /* Usage bitmap */
 };
 
-struct mlxsw_sp_trap_policer_item {
-	u16 hw_id;
-	u32 id;
-	struct list_head list; /* Member of policer_item_list */
-};
-
 #endif
-- 
cgit v1.2.3


From cc678f4dbc576f75e0465b21a18f8460858b07b7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 17 May 2020 01:43:06 +0300
Subject: mlxsw: spectrum_trap: Store all trap policer data in one array

Instead of maintaining an array of policers and a linked list, only
maintain an array.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 148 ++++++++++++---------
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.h    |   3 +-
 2 files changed, 89 insertions(+), 62 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 634e695b89fa..7b2ddc49a04d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -13,9 +13,8 @@
 #include "spectrum_trap.h"
 
 struct mlxsw_sp_trap_policer_item {
+	struct devlink_trap_policer policer;
 	u16 hw_id;
-	u32 id;
-	struct list_head list; /* Member of policer_item_list */
 };
 
 /* All driver-specific traps must be documented in
@@ -182,8 +181,11 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
 			     1 << MLXSW_REG_QPCR_LOWEST_CBS)
 
 /* Ordered by policer identifier */
-static const struct devlink_trap_policer mlxsw_sp_trap_policers_arr[] = {
-	MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 128),
+static const struct mlxsw_sp_trap_policer_item
+mlxsw_sp_trap_policer_items_arr[] = {
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 128),
+	},
 };
 
 static const struct devlink_trap_group mlxsw_sp_trap_groups_arr[] = {
@@ -319,12 +321,12 @@ static const u16 mlxsw_sp_listener_devlink_map[] = {
 static struct mlxsw_sp_trap_policer_item *
 mlxsw_sp_trap_policer_item_lookup(struct mlxsw_sp *mlxsw_sp, u32 id)
 {
-	struct mlxsw_sp_trap_policer_item *policer_item;
 	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
 
-	list_for_each_entry(policer_item, &trap->policer_item_list, list) {
-		if (policer_item->id == id)
-			return policer_item;
+	for (i = 0; i < trap->policers_count; i++) {
+		if (trap->policer_items_arr[i].policer.id == id)
+			return &trap->policer_items_arr[i];
 	}
 
 	return NULL;
@@ -352,72 +354,102 @@ static int mlxsw_sp_trap_dummy_group_init(struct mlxsw_sp *mlxsw_sp)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl);
 }
 
-static int mlxsw_sp_trap_policers_init(struct mlxsw_sp *mlxsw_sp)
+static int mlxsw_sp_trap_policer_items_arr_init(struct mlxsw_sp *mlxsw_sp)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	size_t elem_size = sizeof(struct mlxsw_sp_trap_policer_item);
+	u64 arr_size = ARRAY_SIZE(mlxsw_sp_trap_policer_items_arr);
 	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
 	u64 free_policers = 0;
-	u32 last_id = 0;
-	int err, i;
+	u32 last_id;
+	int i;
 
 	for_each_clear_bit(i, trap->policers_usage, trap->max_policers)
 		free_policers++;
 
-	if (ARRAY_SIZE(mlxsw_sp_trap_policers_arr) > free_policers) {
+	if (arr_size > free_policers) {
 		dev_err(mlxsw_sp->bus_info->dev, "Exceeded number of supported packet trap policers\n");
 		return -ENOBUFS;
 	}
 
-	trap->policers_arr = kcalloc(free_policers,
-				     sizeof(struct devlink_trap_policer),
-				     GFP_KERNEL);
-	if (!trap->policers_arr)
+	trap->policer_items_arr = kcalloc(free_policers, elem_size, GFP_KERNEL);
+	if (!trap->policer_items_arr)
 		return -ENOMEM;
 
 	trap->policers_count = free_policers;
 
-	for (i = 0; i < free_policers; i++) {
-		const struct devlink_trap_policer *policer;
-
-		if (i < ARRAY_SIZE(mlxsw_sp_trap_policers_arr)) {
-			policer = &mlxsw_sp_trap_policers_arr[i];
-			trap->policers_arr[i] = *policer;
-			last_id = policer->id;
-		} else {
-			/* Use parameters set for first policer and override
-			 * relevant ones.
-			 */
-			policer = &mlxsw_sp_trap_policers_arr[0];
-			trap->policers_arr[i] = *policer;
-			trap->policers_arr[i].id = ++last_id;
-			trap->policers_arr[i].init_rate = 1;
-			trap->policers_arr[i].init_burst = 16;
-		}
+	/* Initialize policer items array with pre-defined policers. */
+	memcpy(trap->policer_items_arr, mlxsw_sp_trap_policer_items_arr,
+	       elem_size * arr_size);
+
+	/* Initialize policer items array with the rest of the available
+	 * policers.
+	 */
+	last_id = mlxsw_sp_trap_policer_items_arr[arr_size - 1].policer.id;
+	for (i = arr_size; i < trap->policers_count; i++) {
+		const struct mlxsw_sp_trap_policer_item *policer_item;
+
+		/* Use parameters set for first policer and override
+		 * relevant ones.
+		 */
+		policer_item = &mlxsw_sp_trap_policer_items_arr[0];
+		trap->policer_items_arr[i] = *policer_item;
+		trap->policer_items_arr[i].policer.id = ++last_id;
+		trap->policer_items_arr[i].policer.init_rate = 1;
+		trap->policer_items_arr[i].policer.init_burst = 16;
 	}
 
-	INIT_LIST_HEAD(&trap->policer_item_list);
+	return 0;
+}
+
+static void mlxsw_sp_trap_policer_items_arr_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	kfree(mlxsw_sp->trap->policer_items_arr);
+}
+
+static int mlxsw_sp_trap_policers_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	const struct mlxsw_sp_trap_policer_item *policer_item;
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int err, i;
 
-	err = devlink_trap_policers_register(devlink, trap->policers_arr,
-					     trap->policers_count);
+	err = mlxsw_sp_trap_policer_items_arr_init(mlxsw_sp);
 	if (err)
-		goto err_trap_policers_register;
+		return err;
+
+	for (i = 0; i < trap->policers_count; i++) {
+		policer_item = &trap->policer_items_arr[i];
+		err = devlink_trap_policers_register(devlink,
+						     &policer_item->policer, 1);
+		if (err)
+			goto err_trap_policer_register;
+	}
 
 	return 0;
 
-err_trap_policers_register:
-	kfree(trap->policers_arr);
+err_trap_policer_register:
+	for (i--; i >= 0; i--) {
+		policer_item = &trap->policer_items_arr[i];
+		devlink_trap_policers_unregister(devlink,
+						 &policer_item->policer, 1);
+	}
+	mlxsw_sp_trap_policer_items_arr_fini(mlxsw_sp);
 	return err;
 }
 
 static void mlxsw_sp_trap_policers_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	const struct mlxsw_sp_trap_policer_item *policer_item;
 	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
 
-	devlink_trap_policers_unregister(devlink, trap->policers_arr,
-					 trap->policers_count);
-	WARN_ON(!list_empty(&trap->policer_item_list));
-	kfree(trap->policers_arr);
+	for (i = trap->policers_count - 1; i >= 0; i--) {
+		policer_item = &trap->policer_items_arr[i];
+		devlink_trap_policers_unregister(devlink,
+						 &policer_item->policer, 1);
+	}
+	mlxsw_sp_trap_policer_items_arr_fini(mlxsw_sp);
 }
 
 int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
@@ -608,10 +640,10 @@ int mlxsw_sp_trap_group_set(struct mlxsw_core *mlxsw_core,
 	return __mlxsw_sp_trap_group_init(mlxsw_core, group, policer_id);
 }
 
-static struct mlxsw_sp_trap_policer_item *
-mlxsw_sp_trap_policer_item_init(struct mlxsw_sp *mlxsw_sp, u32 id)
+static int
+mlxsw_sp_trap_policer_item_init(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_trap_policer_item *policer_item)
 {
-	struct mlxsw_sp_trap_policer_item *policer_item;
 	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
 	u16 hw_id;
 
@@ -621,27 +653,19 @@ mlxsw_sp_trap_policer_item_init(struct mlxsw_sp *mlxsw_sp, u32 id)
 	 */
 	hw_id = find_first_zero_bit(trap->policers_usage, trap->max_policers);
 	if (WARN_ON(hw_id == trap->max_policers))
-		return ERR_PTR(-ENOBUFS);
-
-	policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL);
-	if (!policer_item)
-		return ERR_PTR(-ENOMEM);
+		return -ENOBUFS;
 
 	__set_bit(hw_id, trap->policers_usage);
 	policer_item->hw_id = hw_id;
-	policer_item->id = id;
-	list_add_tail(&policer_item->list, &trap->policer_item_list);
 
-	return policer_item;
+	return 0;
 }
 
 static void
 mlxsw_sp_trap_policer_item_fini(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_trap_policer_item *policer_item)
 {
-	list_del(&policer_item->list);
 	__clear_bit(policer_item->hw_id, mlxsw_sp->trap->policers_usage);
-	kfree(policer_item);
 }
 
 static int mlxsw_sp_trap_policer_bs(u64 burst, u8 *p_burst_size,
@@ -684,9 +708,13 @@ int mlxsw_sp_trap_policer_init(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp_trap_policer_item *policer_item;
 	int err;
 
-	policer_item = mlxsw_sp_trap_policer_item_init(mlxsw_sp, policer->id);
-	if (IS_ERR(policer_item))
-		return PTR_ERR(policer_item);
+	policer_item = mlxsw_sp_trap_policer_item_lookup(mlxsw_sp, policer->id);
+	if (WARN_ON(!policer_item))
+		return -EINVAL;
+
+	err = mlxsw_sp_trap_policer_item_init(mlxsw_sp, policer_item);
+	if (err)
+		return err;
 
 	err = __mlxsw_sp_trap_policer_set(mlxsw_sp, policer_item->hw_id,
 					  policer->init_rate,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
index 8a11a2b973f8..8be8482d82ac 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
@@ -8,9 +8,8 @@
 #include <net/devlink.h>
 
 struct mlxsw_sp_trap {
-	struct devlink_trap_policer *policers_arr; /* Registered policers */
+	struct mlxsw_sp_trap_policer_item *policer_items_arr;
 	u64 policers_count; /* Number of registered policers */
-	struct list_head policer_item_list;
 	u64 max_policers;
 	unsigned long policers_usage[]; /* Usage bitmap */
 };
-- 
cgit v1.2.3


From b14a40dbdea5d0c4decc463dfd2b5dd8e4b11e46 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 17 May 2020 01:43:07 +0300
Subject: mlxsw: spectrum_trap: Store all trap group data in one array

Use one array to store all the information about all the trap groups
instead of hard coding it in code. This will be used in future patches
to disable certain functionality (e.g., policer binding) on a trap group
basis.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 147 +++++++++++++++------
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.h    |   4 +
 2 files changed, 110 insertions(+), 41 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 7b2ddc49a04d..f87135ee69ee 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -17,6 +17,13 @@ struct mlxsw_sp_trap_policer_item {
 	u16 hw_id;
 };
 
+struct mlxsw_sp_trap_group_item {
+	struct devlink_trap_group group;
+	u16 hw_group_id;
+	u8 priority;
+	u8 tc;
+};
+
 /* All driver-specific traps must be documented in
  * Documentation/networking/devlink/mlxsw.rst
  */
@@ -188,11 +195,31 @@ mlxsw_sp_trap_policer_items_arr[] = {
 	},
 };
 
-static const struct devlink_trap_group mlxsw_sp_trap_groups_arr[] = {
-	DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 1),
-	DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 1),
-	DEVLINK_TRAP_GROUP_GENERIC(TUNNEL_DROPS, 1),
-	DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 1),
+static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 1),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
+		.priority = 0,
+		.tc = 1,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 1),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
+		.priority = 0,
+		.tc = 1,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(TUNNEL_DROPS, 1),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
+		.priority = 0,
+		.tc = 1,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 1),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
+		.priority = 0,
+		.tc = 1,
+	},
 };
 
 static const struct devlink_trap mlxsw_sp_traps_arr[] = {
@@ -332,6 +359,20 @@ mlxsw_sp_trap_policer_item_lookup(struct mlxsw_sp *mlxsw_sp, u32 id)
 	return NULL;
 }
 
+static struct mlxsw_sp_trap_group_item *
+mlxsw_sp_trap_group_item_lookup(struct mlxsw_sp *mlxsw_sp, u16 id)
+{
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
+
+	for (i = 0; i < trap->groups_count; i++) {
+		if (trap->group_items_arr[i].group.id == id)
+			return &trap->group_items_arr[i];
+	}
+
+	return NULL;
+}
+
 static int mlxsw_sp_trap_cpu_policers_set(struct mlxsw_sp *mlxsw_sp)
 {
 	char qpcr_pl[MLXSW_REG_QPCR_LEN];
@@ -452,9 +493,57 @@ static void mlxsw_sp_trap_policers_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp_trap_policer_items_arr_fini(mlxsw_sp);
 }
 
+static int mlxsw_sp_trap_groups_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	const struct mlxsw_sp_trap_group_item *group_item;
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int err, i;
+
+	trap->group_items_arr = kmemdup(mlxsw_sp_trap_group_items_arr,
+					sizeof(mlxsw_sp_trap_group_items_arr),
+					GFP_KERNEL);
+	if (!trap->group_items_arr)
+		return -ENOMEM;
+
+	trap->groups_count = ARRAY_SIZE(mlxsw_sp_trap_group_items_arr);
+
+	for (i = 0; i < trap->groups_count; i++) {
+		group_item = &trap->group_items_arr[i];
+		err = devlink_trap_groups_register(devlink, &group_item->group,
+						   1);
+		if (err)
+			goto err_trap_group_register;
+	}
+
+	return 0;
+
+err_trap_group_register:
+	for (i--; i >= 0; i--) {
+		group_item = &trap->group_items_arr[i];
+		devlink_trap_groups_unregister(devlink, &group_item->group, 1);
+	}
+	kfree(trap->group_items_arr);
+	return err;
+}
+
+static void mlxsw_sp_trap_groups_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
+
+	for (i = trap->groups_count - 1; i >= 0; i--) {
+		const struct mlxsw_sp_trap_group_item *group_item;
+
+		group_item = &trap->group_items_arr[i];
+		devlink_trap_groups_unregister(devlink, &group_item->group, 1);
+	}
+	kfree(trap->group_items_arr);
+}
+
 int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
 {
-	size_t groups_count = ARRAY_SIZE(mlxsw_sp_trap_groups_arr);
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 	int err;
 
@@ -474,10 +563,9 @@ int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		return err;
 
-	err = devlink_trap_groups_register(devlink, mlxsw_sp_trap_groups_arr,
-					   groups_count);
+	err = mlxsw_sp_trap_groups_init(mlxsw_sp);
 	if (err)
-		goto err_trap_groups_register;
+		goto err_trap_groups_init;
 
 	err = devlink_traps_register(devlink, mlxsw_sp_traps_arr,
 				     ARRAY_SIZE(mlxsw_sp_traps_arr), mlxsw_sp);
@@ -487,22 +575,19 @@ int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 
 err_traps_register:
-	devlink_trap_groups_unregister(devlink, mlxsw_sp_trap_groups_arr,
-				       groups_count);
-err_trap_groups_register:
+	mlxsw_sp_trap_groups_fini(mlxsw_sp);
+err_trap_groups_init:
 	mlxsw_sp_trap_policers_fini(mlxsw_sp);
 	return err;
 }
 
 void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp)
 {
-	size_t groups_count = ARRAY_SIZE(mlxsw_sp_trap_groups_arr);
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 
 	devlink_traps_unregister(devlink, mlxsw_sp_traps_arr,
 				 ARRAY_SIZE(mlxsw_sp_traps_arr));
-	devlink_trap_groups_unregister(devlink, mlxsw_sp_trap_groups_arr,
-				       groups_count);
+	mlxsw_sp_trap_groups_fini(mlxsw_sp);
 	mlxsw_sp_trap_policers_fini(mlxsw_sp);
 }
 
@@ -582,33 +667,12 @@ __mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core,
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	u16 hw_policer_id = MLXSW_REG_HTGT_INVALID_POLICER;
+	const struct mlxsw_sp_trap_group_item *group_item;
 	char htgt_pl[MLXSW_REG_HTGT_LEN];
-	u8 priority, tc, group_id;
-
-	switch (group->id) {
-	case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS:
-		group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS;
-		priority = 0;
-		tc = 1;
-		break;
-	case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS:
-		group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS;
-		priority = 0;
-		tc = 1;
-		break;
-	case DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS:
-		group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS;
-		priority = 0;
-		tc = 1;
-		break;
-	case DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS:
-		group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS;
-		priority = 0;
-		tc = 1;
-		break;
-	default:
+
+	group_item = mlxsw_sp_trap_group_item_lookup(mlxsw_sp, group->id);
+	if (WARN_ON(!group_item))
 		return -EINVAL;
-	}
 
 	if (policer_id) {
 		struct mlxsw_sp_trap_policer_item *policer_item;
@@ -620,7 +684,8 @@ __mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core,
 		hw_policer_id = policer_item->hw_id;
 	}
 
-	mlxsw_reg_htgt_pack(htgt_pl, group_id, hw_policer_id, priority, tc);
+	mlxsw_reg_htgt_pack(htgt_pl, group_item->hw_group_id, hw_policer_id,
+			    group_item->priority, group_item->tc);
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
index 8be8482d82ac..1280f8bc617a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
@@ -10,6 +10,10 @@
 struct mlxsw_sp_trap {
 	struct mlxsw_sp_trap_policer_item *policer_items_arr;
 	u64 policers_count; /* Number of registered policers */
+
+	struct mlxsw_sp_trap_group_item *group_items_arr;
+	u64 groups_count; /* Number of registered groups */
+
 	u64 max_policers;
 	unsigned long policers_usage[]; /* Usage bitmap */
 };
-- 
cgit v1.2.3


From 200b7cca0ba170d8a7e1bd228f0fb1f885de02c0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 17 May 2020 01:43:08 +0300
Subject: mlxsw: spectrum_trap: Store all trap data in one array

Each trap registered with devlink is mapped to one or more Rx listeners.
These listeners allow the switch driver (e.g., mlxsw_spectrum) to
register a function that is called when a packet is received (trapped)
for a specific reason.

Currently, three arrays are used to describe the mapping between the
logical devlink traps and the Rx listeners.

Instead, get rid of these arrays and store all the information in one
array that is easier to validate and extend with more per-trap
information.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 466 ++++++++++++++-------
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.h    |   3 +
 2 files changed, 326 insertions(+), 143 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index f87135ee69ee..3a13b17cd1b8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -24,6 +24,13 @@ struct mlxsw_sp_trap_group_item {
 	u8 tc;
 };
 
+#define MLXSW_SP_TRAP_LISTENERS_MAX 3
+
+struct mlxsw_sp_trap_item {
+	struct devlink_trap trap;
+	struct mlxsw_listener listeners_arr[MLXSW_SP_TRAP_LISTENERS_MAX];
+};
+
 /* All driver-specific traps must be documented in
  * Documentation/networking/devlink/mlxsw.rst
  */
@@ -222,125 +229,221 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 	},
 };
 
-static const struct devlink_trap mlxsw_sp_traps_arr[] = {
-	MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS),
-	MLXSW_SP_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(NON_IP_PACKET, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(UC_DIP_MC_DMAC, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(DIP_LB, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(SIP_MC, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(SIP_LB, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(CORRUPTED_IP_HDR, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(IPV4_SIP_BC, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_RESERVED_SCOPE, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(MTU_ERROR, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(RPF, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(REJECT_ROUTE, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(IPV4_LPM_UNICAST_MISS, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(IPV6_LPM_UNICAST_MISS, L3_DROPS),
-	MLXSW_SP_TRAP_DRIVER_DROP(IRIF_DISABLED, L3_DROPS),
-	MLXSW_SP_TRAP_DRIVER_DROP(ERIF_DISABLED, L3_DROPS),
-	MLXSW_SP_TRAP_DROP(NON_ROUTABLE, L3_DROPS),
-	MLXSW_SP_TRAP_EXCEPTION(DECAP_ERROR, TUNNEL_DROPS),
-	MLXSW_SP_TRAP_DROP(OVERLAY_SMAC_MC, TUNNEL_DROPS),
-	MLXSW_SP_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS,
-			       DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE),
-	MLXSW_SP_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS,
-			       DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE),
-};
-
-static const struct mlxsw_listener mlxsw_sp_listeners_arr[] = {
-	MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_SWITCH_STP, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_UC, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_MC_NULL, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_LB, L2_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ROUTER2, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_NON_IP_PACKET, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_UC_DIP_MC_DMAC, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_DIP_LB, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_MC, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_LB, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_CORRUPTED_IP_HDR, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ING_ROUTER_IPV4_SIP_BC, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_RESERVED_SCOPE, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DISCARDS),
-	MLXSW_SP_RXL_EXCEPTION(MTUERROR, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(TTLERROR, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(RPF, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(RTR_INGRESS1, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV4, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_DISCARDS, TRAP_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM4, L3_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6, L3_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_DISCARD(ROUTER_IRIF_EN, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(ROUTER_ERIF_EN, L3_DISCARDS),
-	MLXSW_SP_RXL_DISCARD(NON_ROUTABLE, L3_DISCARDS),
-	MLXSW_SP_RXL_EXCEPTION(DECAP_ECN0, TUNNEL_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(IPIP_DECAP_ERROR, TUNNEL_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_EXCEPTION(DISCARD_DEC_PKT, TUNNEL_DISCARDS,
-			       TRAP_EXCEPTION_TO_CPU),
-	MLXSW_SP_RXL_DISCARD(OVERLAY_SMAC_MC, TUNNEL_DISCARDS),
-	MLXSW_SP_RXL_ACL_DISCARD(INGRESS_ACL, ACL_DISCARDS, DUMMY),
-	MLXSW_SP_RXL_ACL_DISCARD(EGRESS_ACL, ACL_DISCARDS, DUMMY),
-};
-
-/* Mapping between hardware trap and devlink trap. Multiple hardware traps can
- * be mapped to the same devlink trap. Order is according to
- * 'mlxsw_sp_listeners_arr'.
- */
-static const u16 mlxsw_sp_listener_devlink_map[] = {
-	DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
-	DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH,
-	DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER,
-	DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER,
-	DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST,
-	DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST,
-	DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER,
-	DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE,
-	DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET,
-	DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC,
-	DEVLINK_TRAP_GENERIC_ID_DIP_LB,
-	DEVLINK_TRAP_GENERIC_ID_SIP_MC,
-	DEVLINK_TRAP_GENERIC_ID_SIP_LB,
-	DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR,
-	DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC,
-	DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE,
-	DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE,
-	DEVLINK_TRAP_GENERIC_ID_MTU_ERROR,
-	DEVLINK_TRAP_GENERIC_ID_TTL_ERROR,
-	DEVLINK_TRAP_GENERIC_ID_RPF,
-	DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE,
-	DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
-	DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
-	DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH,
-	DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS,
-	DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS,
-	DEVLINK_MLXSW_TRAP_ID_IRIF_DISABLED,
-	DEVLINK_MLXSW_TRAP_ID_ERIF_DISABLED,
-	DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE,
-	DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
-	DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
-	DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR,
-	DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC,
-	DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP,
-	DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP,
+static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
+	{
+		.trap = MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW,
+					     L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_SWITCH_STP, L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_UC, L2_DISCARDS),
+			MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_MC_NULL, L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_LB, L2_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ROUTER2, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(NON_IP_PACKET, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_NON_IP_PACKET,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(UC_DIP_MC_DMAC, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_UC_DIP_MC_DMAC,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(DIP_LB, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_DIP_LB, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(SIP_MC, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_MC, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(SIP_LB, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_LB, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(CORRUPTED_IP_HDR, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_CORRUPTED_IP_HDR,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(IPV4_SIP_BC, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ING_ROUTER_IPV4_SIP_BC,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_RESERVED_SCOPE,
+					   L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_RESERVED_SCOPE,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE,
+					   L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE,
+					     L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(MTU_ERROR, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(MTUERROR, L3_DISCARDS,
+					       TRAP_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(TTLERROR, L3_DISCARDS,
+					       TRAP_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(RPF, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(RPF, L3_DISCARDS, TRAP_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(REJECT_ROUTE, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(RTR_INGRESS1, L3_DISCARDS,
+					       TRAP_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV4, L3_DISCARDS,
+					       TRAP_TO_CPU),
+			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_DISCARDS,
+					       TRAP_TO_CPU),
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(IPV4_LPM_UNICAST_MISS,
+						L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM4, L3_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(IPV6_LPM_UNICAST_MISS,
+						L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6, L3_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DRIVER_DROP(IRIF_DISABLED, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ROUTER_IRIF_EN, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DRIVER_DROP(ERIF_DISABLED, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(ROUTER_ERIF_EN, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(NON_ROUTABLE, L3_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(NON_ROUTABLE, L3_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_EXCEPTION(DECAP_ERROR, TUNNEL_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_EXCEPTION(DECAP_ECN0, TUNNEL_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+			MLXSW_SP_RXL_EXCEPTION(IPIP_DECAP_ERROR,
+					       TUNNEL_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_DEC_PKT, TUNNEL_DISCARDS,
+					       TRAP_EXCEPTION_TO_CPU),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP(OVERLAY_SMAC_MC, TUNNEL_DROPS),
+		.listeners_arr = {
+			MLXSW_SP_RXL_DISCARD(OVERLAY_SMAC_MC, TUNNEL_DISCARDS),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP,
+					       ACL_DROPS,
+					       DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE),
+		.listeners_arr = {
+			MLXSW_SP_RXL_ACL_DISCARD(INGRESS_ACL, ACL_DISCARDS,
+						 DUMMY),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP,
+					       ACL_DROPS,
+					       DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE),
+		.listeners_arr = {
+			MLXSW_SP_RXL_ACL_DISCARD(EGRESS_ACL, ACL_DISCARDS,
+						 DUMMY),
+		},
+	},
 };
 
 #define MLXSW_SP_THIN_POLICER_ID	(MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1)
@@ -373,6 +476,20 @@ mlxsw_sp_trap_group_item_lookup(struct mlxsw_sp *mlxsw_sp, u16 id)
 	return NULL;
 }
 
+static struct mlxsw_sp_trap_item *
+mlxsw_sp_trap_item_lookup(struct mlxsw_sp *mlxsw_sp, u16 id)
+{
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
+
+	for (i = 0; i < trap->traps_count; i++) {
+		if (trap->trap_items_arr[i].trap.id == id)
+			return &trap->trap_items_arr[i];
+	}
+
+	return NULL;
+}
+
 static int mlxsw_sp_trap_cpu_policers_set(struct mlxsw_sp *mlxsw_sp)
 {
 	char qpcr_pl[MLXSW_REG_QPCR_LEN];
@@ -542,9 +659,63 @@ static void mlxsw_sp_trap_groups_fini(struct mlxsw_sp *mlxsw_sp)
 	kfree(trap->group_items_arr);
 }
 
-int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
+static bool
+mlxsw_sp_trap_listener_is_valid(const struct mlxsw_listener *listener)
+{
+	return listener->trap_id != 0;
+}
+
+static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	const struct mlxsw_sp_trap_item *trap_item;
+	int err, i;
+
+	trap->trap_items_arr = kmemdup(mlxsw_sp_trap_items_arr,
+				       sizeof(mlxsw_sp_trap_items_arr),
+				       GFP_KERNEL);
+	if (!trap->trap_items_arr)
+		return -ENOMEM;
+
+	trap->traps_count = ARRAY_SIZE(mlxsw_sp_trap_items_arr);
+
+	for (i = 0; i < trap->traps_count; i++) {
+		trap_item = &trap->trap_items_arr[i];
+		err = devlink_traps_register(devlink, &trap_item->trap, 1,
+					     mlxsw_sp);
+		if (err)
+			goto err_trap_register;
+	}
+
+	return 0;
+
+err_trap_register:
+	for (i--; i >= 0; i--) {
+		trap_item = &trap->trap_items_arr[i];
+		devlink_traps_unregister(devlink, &trap_item->trap, 1);
+	}
+	kfree(trap->trap_items_arr);
+	return err;
+}
+
+static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
+	int i;
+
+	for (i = trap->traps_count - 1; i >= 0; i--) {
+		const struct mlxsw_sp_trap_item *trap_item;
+
+		trap_item = &trap->trap_items_arr[i];
+		devlink_traps_unregister(devlink, &trap_item->trap, 1);
+	}
+	kfree(trap->trap_items_arr);
+}
+
+int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
+{
 	int err;
 
 	err = mlxsw_sp_trap_cpu_policers_set(mlxsw_sp);
@@ -555,10 +726,6 @@ int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		return err;
 
-	if (WARN_ON(ARRAY_SIZE(mlxsw_sp_listener_devlink_map) !=
-		    ARRAY_SIZE(mlxsw_sp_listeners_arr)))
-		return -EINVAL;
-
 	err = mlxsw_sp_trap_policers_init(mlxsw_sp);
 	if (err)
 		return err;
@@ -567,14 +734,13 @@ int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		goto err_trap_groups_init;
 
-	err = devlink_traps_register(devlink, mlxsw_sp_traps_arr,
-				     ARRAY_SIZE(mlxsw_sp_traps_arr), mlxsw_sp);
+	err = mlxsw_sp_traps_init(mlxsw_sp);
 	if (err)
-		goto err_traps_register;
+		goto err_traps_init;
 
 	return 0;
 
-err_traps_register:
+err_traps_init:
 	mlxsw_sp_trap_groups_fini(mlxsw_sp);
 err_trap_groups_init:
 	mlxsw_sp_trap_policers_fini(mlxsw_sp);
@@ -583,10 +749,7 @@ err_trap_groups_init:
 
 void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-
-	devlink_traps_unregister(devlink, mlxsw_sp_traps_arr,
-				 ARRAY_SIZE(mlxsw_sp_traps_arr));
+	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_trap_groups_fini(mlxsw_sp);
 	mlxsw_sp_trap_policers_fini(mlxsw_sp);
 }
@@ -594,16 +757,21 @@ void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp)
 int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core,
 		       const struct devlink_trap *trap, void *trap_ctx)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	const struct mlxsw_sp_trap_item *trap_item;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+	trap_item = mlxsw_sp_trap_item_lookup(mlxsw_sp, trap->id);
+	if (WARN_ON(!trap_item))
+		return -EINVAL;
+
+	for (i = 0; i < MLXSW_SP_TRAP_LISTENERS_MAX; i++) {
 		const struct mlxsw_listener *listener;
 		int err;
 
-		if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+		listener = &trap_item->listeners_arr[i];
+		if (!mlxsw_sp_trap_listener_is_valid(listener))
 			continue;
-		listener = &mlxsw_sp_listeners_arr[i];
-
 		err = mlxsw_core_trap_register(mlxsw_core, listener, trap_ctx);
 		if (err)
 			return err;
@@ -615,15 +783,20 @@ int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core,
 void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core,
 			const struct devlink_trap *trap, void *trap_ctx)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	const struct mlxsw_sp_trap_item *trap_item;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+	trap_item = mlxsw_sp_trap_item_lookup(mlxsw_sp, trap->id);
+	if (WARN_ON(!trap_item))
+		return;
+
+	for (i = MLXSW_SP_TRAP_LISTENERS_MAX - 1; i >= 0; i--) {
 		const struct mlxsw_listener *listener;
 
-		if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+		listener = &trap_item->listeners_arr[i];
+		if (!mlxsw_sp_trap_listener_is_valid(listener))
 			continue;
-		listener = &mlxsw_sp_listeners_arr[i];
-
 		mlxsw_core_trap_unregister(mlxsw_core, listener, trap_ctx);
 	}
 }
@@ -632,16 +805,23 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core,
 			     const struct devlink_trap *trap,
 			     enum devlink_trap_action action)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	const struct mlxsw_sp_trap_item *trap_item;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+	trap_item = mlxsw_sp_trap_item_lookup(mlxsw_sp, trap->id);
+	if (WARN_ON(!trap_item))
+		return -EINVAL;
+
+	for (i = 0; i < MLXSW_SP_TRAP_LISTENERS_MAX; i++) {
 		const struct mlxsw_listener *listener;
 		bool enabled;
 		int err;
 
-		if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+		listener = &trap_item->listeners_arr[i];
+		if (!mlxsw_sp_trap_listener_is_valid(listener))
 			continue;
-		listener = &mlxsw_sp_listeners_arr[i];
+
 		switch (action) {
 		case DEVLINK_TRAP_ACTION_DROP:
 			enabled = false;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
index 1280f8bc617a..759146897b3a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
@@ -14,6 +14,9 @@ struct mlxsw_sp_trap {
 	struct mlxsw_sp_trap_group_item *group_items_arr;
 	u64 groups_count; /* Number of registered groups */
 
+	struct mlxsw_sp_trap_item *trap_items_arr;
+	u64 traps_count; /* Number of registered traps */
+
 	u64 max_policers;
 	unsigned long policers_usage[]; /* Usage bitmap */
 };
-- 
cgit v1.2.3


From 356d411c26735bcc62718c4c9181014255dc302d Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Fri, 15 May 2020 15:16:52 -0700
Subject: net/mlx5: Cleanup mlx5_ifc_fte_match_set_misc2_bits

Remove the "metadata_reg_b" field and all uses of this field in code
to match the device specification. As this field is not in use in SW
steering it is safe to remove it.

Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c   | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h | 3 +--
 include/linux/mlx5/mlx5_ifc.h                               | 4 +---
 3 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index c0e3a1e7389d..78c884911ceb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -961,7 +961,6 @@ static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec)
 	spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1);
 	spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0);
 	spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a);
-	spec->metadata_reg_b = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_b);
 }
 
 static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 984783238baa..71fa01ce348a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -554,8 +554,7 @@ struct mlx5dr_match_misc2 {
 	u32 metadata_reg_c_1;			/* metadata_reg_c_1 */
 	u32 metadata_reg_c_0;			/* metadata_reg_c_0 */
 	u32 metadata_reg_a;			/* metadata_reg_a */
-	u32 metadata_reg_b;			/* metadata_reg_b */
-	u8 reserved_auto2[8];
+	u8 reserved_auto2[12];
 };
 
 struct mlx5dr_match_misc3 {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c9dd6e99ad56..fd8da4875ea0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -584,9 +584,7 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 
 	u8         metadata_reg_a[0x20];
 
-	u8         metadata_reg_b[0x20];
-
-	u8         reserved_at_1c0[0x40];
+	u8         reserved_at_1a0[0x60];
 };
 
 struct mlx5_ifc_fte_match_set_misc3_bits {
-- 
cgit v1.2.3


From 555af0c3fa0b632be73c241cc932129af4b70d27 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 15 May 2020 15:16:53 -0700
Subject: net/mlx5: Move iseg access helper routines close to mlx5_core driver

Only mlx5_core driver handles fw initialization check and command
interface revision check.
Hence move them inside the mlx5_core driver where it is used.
This avoid exposing these helpers to all mlx5 drivers.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  |  5 +++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c |  5 +++++
 include/linux/mlx5/driver.h                    | 10 ----------
 3 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 34cba97f7bf4..e6567d5570ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1890,6 +1890,11 @@ static void free_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 			  cmd->alloc_dma);
 }
 
+static u16 cmdif_rev(struct mlx5_core_dev *dev)
+{
+	return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
+}
+
 int mlx5_cmd_init(struct mlx5_core_dev *dev)
 {
 	int size = sizeof(struct mlx5_cmd_prot_block);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 061b69ea9cc4..8a375e3ed5c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -177,6 +177,11 @@ static struct mlx5_profile profile[] = {
 #define FW_PRE_INIT_TIMEOUT_MILI	120000
 #define FW_INIT_WARN_MESSAGE_INTERVAL	20000
 
+static int fw_initializing(struct mlx5_core_dev *dev)
+{
+	return ioread32be(&dev->iseg->initializing) >> 31;
+}
+
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
 			u32 warn_time_mili)
 {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 24e04901f92e..a988eb405aa6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -823,11 +823,6 @@ static inline u16 fw_rev_sub(struct mlx5_core_dev *dev)
 	return ioread32be(&dev->iseg->cmdif_rev_fw_sub) & 0xffff;
 }
 
-static inline u16 cmdif_rev(struct mlx5_core_dev *dev)
-{
-	return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
-}
-
 static inline u32 mlx5_base_mkey(const u32 key)
 {
 	return key & 0xffffff00u;
@@ -1012,11 +1007,6 @@ int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
 			   const u8 *mac, bool vlan, u16 vlan_id, u8 port_num);
 
-static inline int fw_initializing(struct mlx5_core_dev *dev)
-{
-	return ioread32be(&dev->iseg->initializing) >> 31;
-}
-
 static inline u32 mlx5_mkey_to_idx(u32 mkey)
 {
 	return mkey >> 8;
-- 
cgit v1.2.3


From ecf814e0e19b5616048391eac359a50c1e9d5174 Mon Sep 17 00:00:00 2001
From: Michael Guralnik <michaelgur@mellanox.com>
Date: Fri, 15 May 2020 15:16:54 -0700
Subject: net/mlx5: Add support for RDMA TX FT headers modifying

Support adding header modifying actions to the RDMA TX flow table.

Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c                | 5 ++++-
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 4 ++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 69cb7e6e8955..3a0601c2052c 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -404,7 +404,10 @@ static bool mlx5_ib_modify_header_supported(struct mlx5_ib_dev *dev)
 {
 	return MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
 					 max_modify_header_actions) ||
-	       MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, max_modify_header_actions);
+	       MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
+					 max_modify_header_actions) ||
+	       MLX5_CAP_FLOWTABLE_RDMA_TX(dev->mdev,
+					 max_modify_header_actions);
 }
 
 static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_ACTION_CREATE_MODIFY_HEADER)(
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 1a8e826ac86b..465a1076a477 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -781,6 +781,10 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		max_actions = MLX5_CAP_ESW_INGRESS_ACL(dev, max_modify_header_actions);
 		table_type = FS_FT_ESW_INGRESS_ACL;
 		break;
+	case MLX5_FLOW_NAMESPACE_RDMA_TX:
+		max_actions = MLX5_CAP_FLOWTABLE_RDMA_TX(dev, max_modify_header_actions);
+		table_type = FS_FT_RDMA_TX;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 8e8204a4f3e32ffb1804196f2aa252684ee663e8 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 22 Mar 2020 09:58:46 +0200
Subject: igc: Add ECN support for TSO

Align with other Intel drivers and add ECN support for TSO.

Add NETIF_F_TSO_ECN flag

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9d5f8287c704..7556fcdf1fd7 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4838,6 +4838,7 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_SG;
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
+	netdev->features |= NETIF_F_TSO_ECN;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;
-- 
cgit v1.2.3


From 25f06eff7582ae41c7fdaa30a4a2348122f7a907 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 24 Mar 2020 17:38:15 -0700
Subject: igc: Use netdev log helpers in igc_main.c

In igc_main.c we print log messages using both dev_* and netdev_*
helpers, generating inconsistent output. Since this is a network device
driver, we should preferably use netdev_* helpers because they append
the interface name to the message, helping making sense out of the logs.

This patch converts all dev_* calls to netdev_*. There is only two
exceptions:
  1) calls wihtin igc_probe (net_device has not been registered yet)
  2) calls in igc_init_module (module initialization).

It also takes this opportunity to improve some messages.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 111 ++++++++++++++----------------
 1 file changed, 50 insertions(+), 61 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 7556fcdf1fd7..add31dc3881d 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -76,7 +76,7 @@ static void igc_power_down_link(struct igc_adapter *adapter)
 
 void igc_reset(struct igc_adapter *adapter)
 {
-	struct pci_dev *pdev = adapter->pdev;
+	struct net_device *dev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
 	struct igc_fc_info *fc = &hw->fc;
 	u32 pba, hwm;
@@ -103,7 +103,7 @@ void igc_reset(struct igc_adapter *adapter)
 	hw->mac.ops.reset_hw(hw);
 
 	if (hw->mac.ops.init_hw(hw))
-		dev_err(&pdev->dev, "Hardware Error\n");
+		netdev_err(dev, "Error on hardware initialization\n");
 
 	if (!netif_running(adapter->netdev))
 		igc_power_down_link(adapter);
@@ -288,6 +288,7 @@ static void igc_clean_all_tx_rings(struct igc_adapter *adapter)
  */
 int igc_setup_tx_resources(struct igc_ring *tx_ring)
 {
+	struct net_device *ndev = tx_ring->netdev;
 	struct device *dev = tx_ring->dev;
 	int size = 0;
 
@@ -313,8 +314,7 @@ int igc_setup_tx_resources(struct igc_ring *tx_ring)
 
 err:
 	vfree(tx_ring->tx_buffer_info);
-	dev_err(dev,
-		"Unable to allocate memory for the transmit descriptor ring\n");
+	netdev_err(ndev, "Unable to allocate memory for Tx descriptor ring\n");
 	return -ENOMEM;
 }
 
@@ -326,14 +326,13 @@ err:
  */
 static int igc_setup_all_tx_resources(struct igc_adapter *adapter)
 {
-	struct pci_dev *pdev = adapter->pdev;
+	struct net_device *dev = adapter->netdev;
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		err = igc_setup_tx_resources(adapter->tx_ring[i]);
 		if (err) {
-			dev_err(&pdev->dev,
-				"Allocation for Tx Queue %u failed\n", i);
+			netdev_err(dev, "Error on Tx queue %u setup\n", i);
 			for (i--; i >= 0; i--)
 				igc_free_tx_resources(adapter->tx_ring[i]);
 			break;
@@ -444,6 +443,7 @@ static void igc_free_all_rx_resources(struct igc_adapter *adapter)
  */
 int igc_setup_rx_resources(struct igc_ring *rx_ring)
 {
+	struct net_device *ndev = rx_ring->netdev;
 	struct device *dev = rx_ring->dev;
 	int size, desc_len;
 
@@ -473,8 +473,7 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring)
 err:
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
-	dev_err(dev,
-		"Unable to allocate memory for the receive descriptor ring\n");
+	netdev_err(ndev, "Unable to allocate memory for Rx descriptor ring\n");
 	return -ENOMEM;
 }
 
@@ -487,14 +486,13 @@ err:
  */
 static int igc_setup_all_rx_resources(struct igc_adapter *adapter)
 {
-	struct pci_dev *pdev = adapter->pdev;
+	struct net_device *dev = adapter->netdev;
 	int i, err = 0;
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		err = igc_setup_rx_resources(adapter->rx_ring[i]);
 		if (err) {
-			dev_err(&pdev->dev,
-				"Allocation for Rx Queue %u failed\n", i);
+			netdev_err(dev, "Error on Rx queue %u setup\n", i);
 			for (i--; i >= 0; i--)
 				igc_free_rx_resources(adapter->rx_ring[i]);
 			break;
@@ -1196,7 +1194,7 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 
 	return 0;
 dma_error:
-	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	netdev_err(tx_ring->netdev, "TX DMA map failed\n");
 	tx_buffer = &tx_ring->tx_buffer_info[i];
 
 	/* clear dma mappings for failed tx_buffer_info map */
@@ -1459,8 +1457,8 @@ static void igc_rx_checksum(struct igc_ring *ring,
 				      IGC_RXD_STAT_UDPCS))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-	dev_dbg(ring->dev, "cksum success: bits %08X\n",
-		le32_to_cpu(rx_desc->wb.upper.status_error));
+	netdev_dbg(ring->netdev, "cksum success: bits %08X\n",
+		   le32_to_cpu(rx_desc->wb.upper.status_error));
 }
 
 static inline void igc_rx_hash(struct igc_ring *ring,
@@ -2122,27 +2120,27 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		    (adapter->tx_timeout_factor * HZ)) &&
 		    !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) {
 			/* detected Tx unit hang */
-			dev_err(tx_ring->dev,
-				"Detected Tx Unit Hang\n"
-				"  Tx Queue             <%d>\n"
-				"  TDH                  <%x>\n"
-				"  TDT                  <%x>\n"
-				"  next_to_use          <%x>\n"
-				"  next_to_clean        <%x>\n"
-				"buffer_info[next_to_clean]\n"
-				"  time_stamp           <%lx>\n"
-				"  next_to_watch        <%p>\n"
-				"  jiffies              <%lx>\n"
-				"  desc.status          <%x>\n",
-				tx_ring->queue_index,
-				rd32(IGC_TDH(tx_ring->reg_idx)),
-				readl(tx_ring->tail),
-				tx_ring->next_to_use,
-				tx_ring->next_to_clean,
-				tx_buffer->time_stamp,
-				tx_buffer->next_to_watch,
-				jiffies,
-				tx_buffer->next_to_watch->wb.status);
+			netdev_err(tx_ring->netdev,
+				   "Detected Tx Unit Hang\n"
+				   "  Tx Queue             <%d>\n"
+				   "  TDH                  <%x>\n"
+				   "  TDT                  <%x>\n"
+				   "  next_to_use          <%x>\n"
+				   "  next_to_clean        <%x>\n"
+				   "buffer_info[next_to_clean]\n"
+				   "  time_stamp           <%lx>\n"
+				   "  next_to_watch        <%p>\n"
+				   "  jiffies              <%lx>\n"
+				   "  desc.status          <%x>\n",
+				   tx_ring->queue_index,
+				   rd32(IGC_TDH(tx_ring->reg_idx)),
+				   readl(tx_ring->tail),
+				   tx_ring->next_to_use,
+				   tx_ring->next_to_clean,
+				   tx_buffer->time_stamp,
+				   tx_buffer->next_to_watch,
+				   jiffies,
+				   tx_buffer->next_to_watch->wb.status);
 			netif_stop_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 
@@ -3238,14 +3236,14 @@ err_out:
  */
 static int igc_init_interrupt_scheme(struct igc_adapter *adapter, bool msix)
 {
-	struct pci_dev *pdev = adapter->pdev;
+	struct net_device *dev = adapter->netdev;
 	int err = 0;
 
 	igc_set_interrupt_capability(adapter, msix);
 
 	err = igc_alloc_q_vectors(adapter);
 	if (err) {
-		dev_err(&pdev->dev, "Unable to allocate memory for vectors\n");
+		netdev_err(dev, "Unable to allocate memory for vectors\n");
 		goto err_alloc_q_vectors;
 	}
 
@@ -3305,7 +3303,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 
 	/* This call may decrease the number of queues */
 	if (igc_init_interrupt_scheme(adapter, true)) {
-		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}
 
@@ -3648,8 +3646,7 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu)
 	if (netif_running(netdev))
 		igc_down(adapter);
 
-	netdev_dbg(netdev, "changing MTU from %d to %d\n",
-		   netdev->mtu, new_mtu);
+	netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 
 	if (netif_running(netdev))
@@ -4006,8 +4003,7 @@ static void igc_watchdog_task(struct work_struct *work)
 			ctrl = rd32(IGC_CTRL);
 			/* Link status message must follow this format */
 			netdev_info(netdev,
-				    "igc: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
-				    netdev->name,
+				    "NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
 				    adapter->link_speed,
 				    adapter->link_duplex == FULL_DUPLEX ?
 				    "Full" : "Half",
@@ -4045,10 +4041,10 @@ retry_read_status:
 					retry_count--;
 					goto retry_read_status;
 				} else if (!retry_count) {
-					dev_err(&adapter->pdev->dev, "exceed max 2 second\n");
+					netdev_err(netdev, "exceed max 2 second\n");
 				}
 			} else {
-				dev_err(&adapter->pdev->dev, "read 1000Base-T Status Reg\n");
+				netdev_err(netdev, "read 1000Base-T Status Reg\n");
 			}
 no_wait:
 			netif_carrier_on(netdev);
@@ -4064,8 +4060,7 @@ no_wait:
 			adapter->link_duplex = 0;
 
 			/* Links status message must follow this format */
-			netdev_info(netdev, "igc: %s NIC Link is Down\n",
-				    netdev->name);
+			netdev_info(netdev, "NIC Link is Down\n");
 			netif_carrier_off(netdev);
 
 			/* link state has changed, schedule phy info update */
@@ -4283,8 +4278,7 @@ static int igc_request_irq(struct igc_adapter *adapter)
 			  netdev->name, adapter);
 
 	if (err)
-		dev_err(&pdev->dev, "Error %d getting interrupt\n",
-			err);
+		netdev_err(netdev, "Error %d getting interrupt\n", err);
 
 request_done:
 	return err;
@@ -4686,7 +4680,6 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx)
 {
-	struct pci_dev *pdev = adapter->pdev;
 	struct igc_mac_info *mac = &adapter->hw.mac;
 
 	mac->autoneg = 0;
@@ -4731,7 +4724,7 @@ int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx)
 	return 0;
 
 err_inval:
-	dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n");
+	netdev_err(adapter->netdev, "Unsupported Speed/Duplex configuration\n");
 	return -EINVAL;
 }
 
@@ -4877,8 +4870,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 	if (igc_get_flash_presence_i225(hw)) {
 		if (hw->nvm.ops.validate(hw) < 0) {
-			dev_err(&pdev->dev,
-				"The NVM Checksum Is Not Valid\n");
+			dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
 			err = -EIO;
 			goto err_eeprom;
 		}
@@ -5141,8 +5133,7 @@ static int __maybe_unused igc_resume(struct device *dev)
 		return -ENODEV;
 	err = pci_enable_device_mem(pdev);
 	if (err) {
-		dev_err(&pdev->dev,
-			"igc: Cannot enable PCI device from suspend\n");
+		netdev_err(netdev, "Cannot enable PCI device from suspend\n");
 		return err;
 	}
 	pci_set_master(pdev);
@@ -5151,7 +5142,7 @@ static int __maybe_unused igc_resume(struct device *dev)
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
 	if (igc_init_interrupt_scheme(adapter, true)) {
-		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}
 
@@ -5255,8 +5246,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 	pci_ers_result_t result;
 
 	if (pci_enable_device_mem(pdev)) {
-		dev_err(&pdev->dev,
-			"Could not re-enable PCI device after reset.\n");
+		netdev_err(netdev, "Could not re-enable PCI device after reset\n");
 		result = PCI_ERS_RESULT_DISCONNECT;
 	} else {
 		pci_set_master(pdev);
@@ -5295,7 +5285,7 @@ static void igc_io_resume(struct pci_dev *pdev)
 	rtnl_lock();
 	if (netif_running(netdev)) {
 		if (igc_open(netdev)) {
-			dev_err(&pdev->dev, "igc_open failed after reset\n");
+			netdev_err(netdev, "igc_open failed after reset\n");
 			return;
 		}
 	}
@@ -5342,7 +5332,6 @@ static struct pci_driver igc_driver = {
 int igc_reinit_queues(struct igc_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
-	struct pci_dev *pdev = adapter->pdev;
 	int err = 0;
 
 	if (netif_running(netdev))
@@ -5351,7 +5340,7 @@ int igc_reinit_queues(struct igc_adapter *adapter)
 	igc_reset_interrupt_capability(adapter);
 
 	if (igc_init_interrupt_scheme(adapter, true)) {
-		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}
 
-- 
cgit v1.2.3


From f026d8ca2904622298c5387c384dce04f119e87a Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 5 May 2020 17:06:38 +0300
Subject: igc: add support to eeprom, registers and link self-tests

Introduced igc_diag.c and igc_diag.h, these files have the
diagnostics functionality of igc driver. For the time being
these files are being used by ethtool self-test callbacks.
Which mean that eeprom, registers and link self-tests for
ethtool were implemented.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/Makefile      |   2 +-
 drivers/net/ethernet/intel/igc/igc.h         |   4 +
 drivers/net/ethernet/intel/igc/igc_diag.c    | 186 +++++++++++++++++++++++++++
 drivers/net/ethernet/intel/igc/igc_diag.h    |  30 +++++
 drivers/net/ethernet/intel/igc/igc_ethtool.c |  60 +++++++++
 drivers/net/ethernet/intel/igc/igc_main.c    |   4 +-
 drivers/net/ethernet/intel/igc/igc_regs.h    |   2 +
 7 files changed, 285 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/igc/igc_diag.c
 create mode 100644 drivers/net/ethernet/intel/igc/igc_diag.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index 3652f211f351..1c3051db9085 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -8,4 +8,4 @@
 obj-$(CONFIG_IGC) += igc.o
 
 igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
-igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o
+igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 8ddc39482a8e..661dc8875f3f 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -198,6 +198,8 @@ struct igc_adapter {
 	unsigned long link_check_timeout;
 	struct igc_info ei;
 
+	u32 test_icr;
+
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
 	struct work_struct ptp_tx_work;
@@ -215,6 +217,8 @@ struct igc_adapter {
 
 void igc_up(struct igc_adapter *adapter);
 void igc_down(struct igc_adapter *adapter);
+int igc_open(struct net_device *netdev);
+int igc_close(struct net_device *netdev);
 int igc_setup_tx_resources(struct igc_ring *ring);
 int igc_setup_rx_resources(struct igc_ring *ring);
 void igc_free_tx_resources(struct igc_ring *ring);
diff --git a/drivers/net/ethernet/intel/igc/igc_diag.c b/drivers/net/ethernet/intel/igc/igc_diag.c
new file mode 100644
index 000000000000..cc621970c0cd
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_diag.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2020 Intel Corporation */
+
+#include "igc.h"
+#include "igc_diag.h"
+
+static struct igc_reg_test reg_test[] = {
+	{ IGC_FCAL,	1,	PATTERN_TEST,	0xFFFFFFFF,	0xFFFFFFFF },
+	{ IGC_FCAH,	1,	PATTERN_TEST,	0x0000FFFF,	0xFFFFFFFF },
+	{ IGC_FCT,	1,	PATTERN_TEST,	0x0000FFFF,	0xFFFFFFFF },
+	{ IGC_RDBAH(0), 4,	PATTERN_TEST,	0xFFFFFFFF,	0xFFFFFFFF },
+	{ IGC_RDBAL(0),	4,	PATTERN_TEST,	0xFFFFFF80,	0xFFFFFF80 },
+	{ IGC_RDLEN(0),	4,	PATTERN_TEST,	0x000FFF80,	0x000FFFFF },
+	{ IGC_RDT(0),	4,	PATTERN_TEST,	0x0000FFFF,	0x0000FFFF },
+	{ IGC_FCRTH,	1,	PATTERN_TEST,	0x0003FFF0,	0x0003FFF0 },
+	{ IGC_FCTTV,	1,	PATTERN_TEST,	0x0000FFFF,	0x0000FFFF },
+	{ IGC_TIPG,	1,	PATTERN_TEST,	0x3FFFFFFF,	0x3FFFFFFF },
+	{ IGC_TDBAH(0),	4,	PATTERN_TEST,	0xFFFFFFFF,	0xFFFFFFFF },
+	{ IGC_TDBAL(0),	4,	PATTERN_TEST,	0xFFFFFF80,	0xFFFFFF80 },
+	{ IGC_TDLEN(0),	4,	PATTERN_TEST,	0x000FFF80,	0x000FFFFF },
+	{ IGC_TDT(0),	4,	PATTERN_TEST,	0x0000FFFF,	0x0000FFFF },
+	{ IGC_RCTL,	1,	SET_READ_TEST,	0xFFFFFFFF,	0x00000000 },
+	{ IGC_RCTL,	1,	SET_READ_TEST,	0x04CFB2FE,	0x003FFFFB },
+	{ IGC_RCTL,	1,	SET_READ_TEST,	0x04CFB2FE,	0xFFFFFFFF },
+	{ IGC_TCTL,	1,	SET_READ_TEST,	0xFFFFFFFF,	0x00000000 },
+	{ IGC_RA,	16,	TABLE64_TEST_LO,
+						0xFFFFFFFF,	0xFFFFFFFF },
+	{ IGC_RA,	16,	TABLE64_TEST_HI,
+						0x900FFFFF,	0xFFFFFFFF },
+	{ IGC_MTA,	128,	TABLE32_TEST,
+						0xFFFFFFFF,	0xFFFFFFFF },
+	{ 0, 0, 0, 0}
+};
+
+static bool reg_pattern_test(struct igc_adapter *adapter, u64 *data, int reg,
+			     u32 mask, u32 write)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 pat, val, before;
+	static const u32 test_pattern[] = {
+		0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF
+	};
+
+	for (pat = 0; pat < ARRAY_SIZE(test_pattern); pat++) {
+		before = rd32(reg);
+		wr32(reg, test_pattern[pat] & write);
+		val = rd32(reg);
+		if (val != (test_pattern[pat] & write & mask)) {
+			netdev_err(adapter->netdev,
+				   "pattern test reg %04X failed: got 0x%08X expected 0x%08X",
+				   reg, val, test_pattern[pat] & write & mask);
+			*data = reg;
+			wr32(reg, before);
+			return false;
+		}
+		wr32(reg, before);
+	}
+	return true;
+}
+
+static bool reg_set_and_check(struct igc_adapter *adapter, u64 *data, int reg,
+			      u32 mask, u32 write)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 val, before;
+
+	before = rd32(reg);
+	wr32(reg, write & mask);
+	val = rd32(reg);
+	if ((write & mask) != (val & mask)) {
+		netdev_err(adapter->netdev,
+			   "set/check reg %04X test failed: got 0x%08X expected 0x%08X",
+			   reg, (val & mask), (write & mask));
+		*data = reg;
+		wr32(reg, before);
+		return false;
+	}
+	wr32(reg, before);
+	return true;
+}
+
+bool igc_reg_test(struct igc_adapter *adapter, u64 *data)
+{
+	struct igc_reg_test *test = reg_test;
+	struct igc_hw *hw = &adapter->hw;
+	u32 value, before, after;
+	u32 i, toggle, b = false;
+
+	/* Because the status register is such a special case,
+	 * we handle it separately from the rest of the register
+	 * tests.  Some bits are read-only, some toggle, and some
+	 * are writeable.
+	 */
+	toggle = 0x6800D3;
+	before = rd32(IGC_STATUS);
+	value = before & toggle;
+	wr32(IGC_STATUS, toggle);
+	after = rd32(IGC_STATUS) & toggle;
+	if (value != after) {
+		netdev_err(adapter->netdev,
+			   "failed STATUS register test got: 0x%08X expected: 0x%08X",
+			   after, value);
+		*data = 1;
+		return false;
+	}
+	/* restore previous status */
+	wr32(IGC_STATUS, before);
+
+	/* Perform the remainder of the register test, looping through
+	 * the test table until we either fail or reach the null entry.
+	 */
+	while (test->reg) {
+		for (i = 0; i < test->array_len; i++) {
+			switch (test->test_type) {
+			case PATTERN_TEST:
+				b = reg_pattern_test(adapter, data,
+						     test->reg + (i * 0x40),
+						     test->mask,
+						     test->write);
+				break;
+			case SET_READ_TEST:
+				b = reg_set_and_check(adapter, data,
+						      test->reg + (i * 0x40),
+						      test->mask,
+						      test->write);
+				break;
+			case TABLE64_TEST_LO:
+				b = reg_pattern_test(adapter, data,
+						     test->reg + (i * 8),
+						     test->mask,
+						     test->write);
+				break;
+			case TABLE64_TEST_HI:
+				b = reg_pattern_test(adapter, data,
+						     test->reg + 4 + (i * 8),
+						     test->mask,
+						     test->write);
+				break;
+			case TABLE32_TEST:
+				b = reg_pattern_test(adapter, data,
+						     test->reg + (i * 4),
+						     test->mask,
+						     test->write);
+				break;
+			}
+			if (!b)
+				return false;
+		}
+		test++;
+	}
+	*data = 0;
+	return true;
+}
+
+bool igc_eeprom_test(struct igc_adapter *adapter, u64 *data)
+{
+	struct igc_hw *hw = &adapter->hw;
+
+	*data = 0;
+
+	if (hw->nvm.ops.validate(hw) != IGC_SUCCESS) {
+		*data = 1;
+		return false;
+	}
+
+	return true;
+}
+
+bool igc_link_test(struct igc_adapter *adapter, u64 *data)
+{
+	bool link_up;
+
+	*data = 0;
+
+	/* add delay to give enough time for autonegotioation to finish */
+	if (adapter->hw.mac.autoneg)
+		ssleep(5);
+
+	link_up = igc_has_link(adapter);
+	if (!link_up) {
+		*data = 1;
+		return false;
+	}
+
+	return true;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_diag.h b/drivers/net/ethernet/intel/igc/igc_diag.h
new file mode 100644
index 000000000000..600658e33bec
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_diag.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c)  2020 Intel Corporation */
+
+bool igc_reg_test(struct igc_adapter *adapter, u64 *data);
+bool igc_eeprom_test(struct igc_adapter *adapter, u64 *data);
+bool igc_link_test(struct igc_adapter *adapter, u64 *data);
+
+struct igc_reg_test {
+	u16 reg;
+	u8 array_len;
+	u8 test_type;
+	u32 mask;
+	u32 write;
+};
+
+/* In the hardware, registers are laid out either singly, in arrays
+ * spaced 0x40 bytes apart, or in contiguous tables.  We assume
+ * most tests take place on arrays or single registers (handled
+ * as a single-element array) and special-case the tables.
+ * Table tests are always pattern tests.
+ *
+ * We also make provision for some required setup steps by specifying
+ * registers to be written without any read-back testing.
+ */
+
+#define PATTERN_TEST	1
+#define SET_READ_TEST	2
+#define TABLE32_TEST	3
+#define TABLE64_TEST_LO	4
+#define TABLE64_TEST_HI	5
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 0a8c4a7412a4..9fc250cdf88c 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -6,6 +6,7 @@
 #include <linux/pm_runtime.h>
 
 #include "igc.h"
+#include "igc_diag.h"
 
 /* forward declaration */
 struct igc_stats {
@@ -1896,6 +1897,64 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+static void igc_diag_test(struct net_device *netdev,
+			  struct ethtool_test *eth_test, u64 *data)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	bool if_running = netif_running(netdev);
+
+	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+		netdev_info(adapter->netdev, "offline testing starting");
+		set_bit(__IGC_TESTING, &adapter->state);
+
+		/* Link test performed before hardware reset so autoneg doesn't
+		 * interfere with test result
+		 */
+		if (!igc_link_test(adapter, &data[TEST_LINK]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		if (if_running)
+			igc_close(netdev);
+		else
+			igc_reset(adapter);
+
+		netdev_info(adapter->netdev, "register testing starting");
+		if (!igc_reg_test(adapter, &data[TEST_REG]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		igc_reset(adapter);
+
+		netdev_info(adapter->netdev, "eeprom testing starting");
+		if (!igc_eeprom_test(adapter, &data[TEST_EEP]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		igc_reset(adapter);
+
+		/* loopback and interrupt tests
+		 * will be implemented in the future
+		 */
+		data[TEST_LOOP] = 0;
+		data[TEST_IRQ] = 0;
+
+		clear_bit(__IGC_TESTING, &adapter->state);
+		if (if_running)
+			igc_open(netdev);
+	} else {
+		netdev_info(adapter->netdev, "online testing starting");
+
+		/* register, eeprom, intr and loopback tests not run online */
+		data[TEST_REG] = 0;
+		data[TEST_EEP] = 0;
+		data[TEST_IRQ] = 0;
+		data[TEST_LOOP] = 0;
+
+		if (!igc_link_test(adapter, &data[TEST_LINK]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+	}
+
+	msleep_interruptible(4 * 1000);
+}
+
 static const struct ethtool_ops igc_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
 	.get_drvinfo		= igc_get_drvinfo,
@@ -1933,6 +1992,7 @@ static const struct ethtool_ops igc_ethtool_ops = {
 	.complete		= igc_ethtool_complete,
 	.get_link_ksettings	= igc_get_link_ksettings,
 	.set_link_ksettings	= igc_set_link_ksettings,
+	.self_test		= igc_diag_test,
 };
 
 void igc_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index add31dc3881d..0ae3590a50eb 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4380,7 +4380,7 @@ err_setup_tx:
 	return err;
 }
 
-static int igc_open(struct net_device *netdev)
+int igc_open(struct net_device *netdev)
 {
 	return __igc_open(netdev, false);
 }
@@ -4422,7 +4422,7 @@ static int __igc_close(struct net_device *netdev, bool suspending)
 	return 0;
 }
 
-static int igc_close(struct net_device *netdev)
+int igc_close(struct net_device *netdev)
 {
 	if (netif_device_present(netdev) || netdev->dismantle)
 		return __igc_close(netdev, false);
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 6093cde2351c..633545977a65 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -49,6 +49,7 @@
 #define IGC_FACTPS		0x05B30
 
 /* Interrupt Register Description */
+#define IGC_EICR		0x01580  /* Ext. Interrupt Cause read - W0 */
 #define IGC_EICS		0x01520  /* Ext. Interrupt Cause Set - W0 */
 #define IGC_EIMS		0x01524  /* Ext. Interrupt Mask Set/Read - RW */
 #define IGC_EIMC		0x01528  /* Ext. Interrupt Mask Clear - WO */
@@ -119,6 +120,7 @@
 #define IGC_RLPML		0x05004  /* Rx Long Packet Max Length */
 #define IGC_RFCTL		0x05008  /* Receive Filter Control*/
 #define IGC_MTA			0x05200  /* Multicast Table Array - RW Array */
+#define IGC_RA			0x05400  /* Receive Address - RW Array */
 #define IGC_UTA			0x0A000  /* Unicast Table Array - RW */
 #define IGC_RAL(_n)		(0x05400 + ((_n) * 0x08))
 #define IGC_RAH(_n)		(0x05404 + ((_n) * 0x08))
-- 
cgit v1.2.3


From 95f96a9f2d04b20c26fca405f640acea07cf8b53 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 24 Mar 2020 17:38:16 -0700
Subject: igc: Use netdev log helpers in igc_ethtool.c

In igc_ethtool.c we print log messages using dev_* helpers, generating
inconsistent output with the rest of the driver. Since this is a network
device driver, we should preferably use netdev_* helpers because they
append the interface name to the message, helping making sense the of
the logs.

This patch converts all dev_* calls to netdev_*.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 41 ++++++++++++++--------------
 1 file changed, 21 insertions(+), 20 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 9fc250cdf88c..a05d7abee524 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1155,8 +1155,8 @@ static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
 
 		if ((flags & UDP_RSS_FLAGS) &&
 		    !(adapter->flags & UDP_RSS_FLAGS))
-			dev_err(&adapter->pdev->dev,
-				"enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
+			netdev_err(adapter->netdev,
+				   "Enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
 
 		adapter->flags = flags;
 
@@ -1195,7 +1195,8 @@ static int igc_rxnfc_write_etype_filter(struct igc_adapter *adapter,
 			break;
 	}
 	if (i == MAX_ETYPE_FILTER) {
-		dev_err(&adapter->pdev->dev, "ethtool -N: etype filters are all used.\n");
+		netdev_err(adapter->netdev,
+			   "ethtool -N: etype filters are all used\n");
 		return -EINVAL;
 	}
 
@@ -1236,7 +1237,8 @@ static int igc_rxnfc_write_vlan_prio_filter(struct igc_adapter *adapter,
 	/* check whether this vlan prio is already set */
 	if (vlapqf & IGC_VLAPQF_P_VALID(vlan_priority) &&
 	    queue_index != input->action) {
-		dev_err(&adapter->pdev->dev, "ethtool rxnfc set vlan prio filter failed.\n");
+		netdev_err(adapter->netdev,
+			   "ethtool rxnfc set VLAN prio filter failed\n");
 		return -EEXIST;
 	}
 
@@ -1255,8 +1257,8 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 
 	if (hw->mac.type == igc_i225 &&
 	    !(input->filter.match_flags & ~IGC_FILTER_FLAG_SRC_MAC_ADDR)) {
-		dev_err(&adapter->pdev->dev,
-			"i225 doesn't support flow classification rules specifying only source addresses.\n");
+		netdev_err(adapter->netdev,
+			   "i225 doesn't support flow classification rules specifying only source addresses\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -1404,13 +1406,14 @@ static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
 	 */
 	if (fsp->ring_cookie == RX_CLS_FLOW_DISC ||
 	    fsp->ring_cookie >= adapter->num_rx_queues) {
-		dev_err(&adapter->pdev->dev, "ethtool -N: The specified action is invalid\n");
+		netdev_err(netdev,
+			   "ethtool -N: The specified action is invalid\n");
 		return -EINVAL;
 	}
 
 	/* Don't allow indexes to exist outside of available space */
 	if (fsp->location >= IGC_MAX_RXNFC_FILTERS) {
-		dev_err(&adapter->pdev->dev, "Location out of range\n");
+		netdev_err(netdev, "Location out of range\n");
 		return -EINVAL;
 	}
 
@@ -1458,8 +1461,8 @@ static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
 		if (!memcmp(&input->filter, &rule->filter,
 			    sizeof(input->filter))) {
 			err = -EEXIST;
-			dev_err(&adapter->pdev->dev,
-				"ethtool: this filter is already set\n");
+			netdev_err(netdev,
+				   "ethtool: this filter is already set\n");
 			goto err_out_w_lock;
 		}
 	}
@@ -1832,6 +1835,7 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 				  const struct ethtool_link_ksettings *cmd)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct net_device *dev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
 	u32 advertising;
 
@@ -1839,8 +1843,7 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 	 * cannot be changed
 	 */
 	if (igc_check_reset_block(hw)) {
-		dev_err(&adapter->pdev->dev,
-			"Cannot change link characteristics when reset is active.\n");
+		netdev_err(dev, "Cannot change link characteristics when reset is active\n");
 		return -EINVAL;
 	}
 
@@ -1851,7 +1854,7 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 	if (cmd->base.eth_tp_mdix_ctrl) {
 		if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
 		    cmd->base.autoneg != AUTONEG_ENABLE) {
-			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			netdev_err(dev, "Forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
 			return -EINVAL;
 		}
 	}
@@ -1868,9 +1871,7 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 		if (adapter->fc_autoneg)
 			hw->fc.requested_mode = igc_fc_default;
 	} else {
-		/* calling this overrides forced MDI setting */
-		dev_info(&adapter->pdev->dev,
-			 "Force mode currently not supported\n");
+		netdev_info(dev, "Force mode currently not supported\n");
 	}
 
 	/* MDI-X => 2; MDI => 1; Auto => 3 */
@@ -1904,7 +1905,7 @@ static void igc_diag_test(struct net_device *netdev,
 	bool if_running = netif_running(netdev);
 
 	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
-		netdev_info(adapter->netdev, "offline testing starting");
+		netdev_info(adapter->netdev, "Offline testing starting");
 		set_bit(__IGC_TESTING, &adapter->state);
 
 		/* Link test performed before hardware reset so autoneg doesn't
@@ -1918,13 +1919,13 @@ static void igc_diag_test(struct net_device *netdev,
 		else
 			igc_reset(adapter);
 
-		netdev_info(adapter->netdev, "register testing starting");
+		netdev_info(adapter->netdev, "Register testing starting");
 		if (!igc_reg_test(adapter, &data[TEST_REG]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 
 		igc_reset(adapter);
 
-		netdev_info(adapter->netdev, "eeprom testing starting");
+		netdev_info(adapter->netdev, "EEPROM testing starting");
 		if (!igc_eeprom_test(adapter, &data[TEST_EEP]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
 
@@ -1940,7 +1941,7 @@ static void igc_diag_test(struct net_device *netdev,
 		if (if_running)
 			igc_open(netdev);
 	} else {
-		netdev_info(adapter->netdev, "online testing starting");
+		netdev_info(adapter->netdev, "Online testing starting");
 
 		/* register, eeprom, intr and loopback tests not run online */
 		data[TEST_REG] = 0;
-- 
cgit v1.2.3


From 916a3c650763fbe1e1d37af105a82fee26da45a5 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 24 Mar 2020 17:38:17 -0700
Subject: igc: Use netdev log helpers in igc_ptp.c

In igc_ptp.c we print log messages using dev_* helpers, generating
inconsistent output with the rest of the driver. Since this is a network
device driver, we should preferably use netdev_* helpers because they
append the interface name to the message, helping making sense out of
the logs.

This patch converts all dev_* calls to netdev_*.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ptp.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index f99c514ad0f4..1bf016398b9d 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -466,7 +466,7 @@ void igc_ptp_tx_hang(struct igc_adapter *adapter)
 		 * interrupt
 		 */
 		rd32(IGC_TXSTMPH);
-		dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n");
+		netdev_warn(adapter->netdev, "Clearing Tx timestamp hang\n");
 	}
 }
 
@@ -529,7 +529,7 @@ static void igc_ptp_tx_work(struct work_struct *work)
 		 * interrupt
 		 */
 		rd32(IGC_TXSTMPH);
-		dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n");
+		netdev_warn(adapter->netdev, "Clearing Tx timestamp hang\n");
 		return;
 	}
 
@@ -626,10 +626,9 @@ void igc_ptp_init(struct igc_adapter *adapter)
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
-		dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n");
+		netdev_err(netdev, "ptp_clock_register failed\n");
 	} else if (adapter->ptp_clock) {
-		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
-			 adapter->netdev->name);
+		netdev_info(netdev, "PHC added\n");
 		adapter->ptp_flags |= IGC_PTP_ENABLED;
 	}
 }
@@ -666,8 +665,7 @@ void igc_ptp_stop(struct igc_adapter *adapter)
 
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
-		dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
-			 adapter->netdev->name);
+		netdev_info(adapter->netdev, "PHC removed\n");
 		adapter->ptp_flags &= ~IGC_PTP_ENABLED;
 	}
 }
-- 
cgit v1.2.3


From 5c32bac98c705ce409ac26b5120c14ece8bd9209 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 24 Mar 2020 17:38:18 -0700
Subject: igc: Use netdev log helpers in igc_dump.c

In igc_dump.c we print log messages using dev_* and pr_* helpers,
generating inconsistent output with the rest of the driver. Since this
is a network device driver, we should preferably use netdev_* helpers
because they append the interface name to the message, helping making
sense out of the logs.

This patch converts all dev_* and pr_* calls to netdev_*.

Quick note about igc_rings_dump(): This function is always called with
valid adapter->netdev so there is not need to check it.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_dump.c | 109 +++++++++++++++---------------
 1 file changed, 54 insertions(+), 55 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c
index 657ab50ae296..4ad32d98f77f 100644
--- a/drivers/net/ethernet/intel/igc/igc_dump.c
+++ b/drivers/net/ethernet/intel/igc/igc_dump.c
@@ -47,6 +47,7 @@ static const struct igc_reg_info igc_reg_info_tbl[] = {
 /* igc_regdump - register printout routine */
 static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo)
 {
+	struct net_device *dev = igc_get_hw_dev(hw);
 	int n = 0;
 	char rname[16];
 	u32 regs[8];
@@ -101,13 +102,14 @@ static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo)
 			regs[n] = rd32(IGC_TXDCTL(n));
 		break;
 	default:
-		pr_info("%-15s %08x\n", reginfo->name, rd32(reginfo->ofs));
+		netdev_info(dev, "%-15s %08x\n", reginfo->name,
+			    rd32(reginfo->ofs));
 		return;
 	}
 
 	snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]");
-	pr_info("%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1],
-		regs[2], regs[3]);
+	netdev_info(dev, "%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1],
+		    regs[2], regs[3]);
 }
 
 /* igc_rings_dump - Tx-rings and Rx-rings */
@@ -125,39 +127,34 @@ void igc_rings_dump(struct igc_adapter *adapter)
 	if (!netif_msg_hw(adapter))
 		return;
 
-	/* Print netdevice Info */
-	if (netdev) {
-		dev_info(&adapter->pdev->dev, "Net device Info\n");
-		pr_info("Device Name     state            trans_start\n");
-		pr_info("%-15s %016lX %016lX\n", netdev->name,
-			netdev->state, dev_trans_start(netdev));
-	}
+	netdev_info(netdev, "Device info: state %016lX trans_start %016lX\n",
+		    netdev->state, dev_trans_start(netdev));
 
 	/* Print TX Ring Summary */
-	if (!netdev || !netif_running(netdev))
+	if (!netif_running(netdev))
 		goto exit;
 
-	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
-	pr_info("Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
+	netdev_info(netdev, "TX Rings Summary\n");
+	netdev_info(netdev, "Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
 	for (n = 0; n < adapter->num_tx_queues; n++) {
 		struct igc_tx_buffer *buffer_info;
 
 		tx_ring = adapter->tx_ring[n];
 		buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
 
-		pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n",
-			n, tx_ring->next_to_use, tx_ring->next_to_clean,
-			(u64)dma_unmap_addr(buffer_info, dma),
-			dma_unmap_len(buffer_info, len),
-			buffer_info->next_to_watch,
-			(u64)buffer_info->time_stamp);
+		netdev_info(netdev, "%5d %5X %5X %016llX %04X %p %016llX\n",
+			    n, tx_ring->next_to_use, tx_ring->next_to_clean,
+			    (u64)dma_unmap_addr(buffer_info, dma),
+			    dma_unmap_len(buffer_info, len),
+			    buffer_info->next_to_watch,
+			    (u64)buffer_info->time_stamp);
 	}
 
 	/* Print TX Rings */
 	if (!netif_msg_tx_done(adapter))
 		goto rx_ring_summary;
 
-	dev_info(&adapter->pdev->dev, "TX Rings Dump\n");
+	netdev_info(netdev, "TX Rings Dump\n");
 
 	/* Transmit Descriptor Formats
 	 *
@@ -172,10 +169,11 @@ void igc_rings_dump(struct igc_adapter *adapter)
 
 	for (n = 0; n < adapter->num_tx_queues; n++) {
 		tx_ring = adapter->tx_ring[n];
-		pr_info("------------------------------------\n");
-		pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
-		pr_info("------------------------------------\n");
-		pr_info("T [desc]     [address 63:0  ] [PlPOCIStDDM Ln] [bi->dma       ] leng  ntw timestamp        bi->skb\n");
+		netdev_info(netdev, "------------------------------------\n");
+		netdev_info(netdev, "TX QUEUE INDEX = %d\n",
+			    tx_ring->queue_index);
+		netdev_info(netdev, "------------------------------------\n");
+		netdev_info(netdev, "T [desc]     [address 63:0  ] [PlPOCIStDDM Ln] [bi->dma       ] leng  ntw timestamp        bi->skb\n");
 
 		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
 			const char *next_desc;
@@ -194,14 +192,14 @@ void igc_rings_dump(struct igc_adapter *adapter)
 			else
 				next_desc = "";
 
-			pr_info("T [0x%03X]    %016llX %016llX %016llX %04X  %p %016llX %p%s\n",
-				i, le64_to_cpu(u0->a),
-				le64_to_cpu(u0->b),
-				(u64)dma_unmap_addr(buffer_info, dma),
-				dma_unmap_len(buffer_info, len),
-				buffer_info->next_to_watch,
-				(u64)buffer_info->time_stamp,
-				buffer_info->skb, next_desc);
+			netdev_info(netdev, "T [0x%03X]    %016llX %016llX %016llX %04X  %p %016llX %p%s\n",
+				    i, le64_to_cpu(u0->a),
+				    le64_to_cpu(u0->b),
+				    (u64)dma_unmap_addr(buffer_info, dma),
+				    dma_unmap_len(buffer_info, len),
+				    buffer_info->next_to_watch,
+				    (u64)buffer_info->time_stamp,
+				    buffer_info->skb, next_desc);
 
 			if (netif_msg_pktdata(adapter) && buffer_info->skb)
 				print_hex_dump(KERN_INFO, "",
@@ -214,19 +212,19 @@ void igc_rings_dump(struct igc_adapter *adapter)
 
 	/* Print RX Rings Summary */
 rx_ring_summary:
-	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
-	pr_info("Queue [NTU] [NTC]\n");
+	netdev_info(netdev, "RX Rings Summary\n");
+	netdev_info(netdev, "Queue [NTU] [NTC]\n");
 	for (n = 0; n < adapter->num_rx_queues; n++) {
 		rx_ring = adapter->rx_ring[n];
-		pr_info(" %5d %5X %5X\n",
-			n, rx_ring->next_to_use, rx_ring->next_to_clean);
+		netdev_info(netdev, "%5d %5X %5X\n", n, rx_ring->next_to_use,
+			    rx_ring->next_to_clean);
 	}
 
 	/* Print RX Rings */
 	if (!netif_msg_rx_status(adapter))
 		goto exit;
 
-	dev_info(&adapter->pdev->dev, "RX Rings Dump\n");
+	netdev_info(netdev, "RX Rings Dump\n");
 
 	/* Advanced Receive Descriptor (Read) Format
 	 *    63                                           1        0
@@ -251,11 +249,12 @@ rx_ring_summary:
 
 	for (n = 0; n < adapter->num_rx_queues; n++) {
 		rx_ring = adapter->rx_ring[n];
-		pr_info("------------------------------------\n");
-		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
-		pr_info("------------------------------------\n");
-		pr_info("R  [desc]      [ PktBuf     A0] [  HeadBuf   DD] [bi->dma       ] [bi->skb] <-- Adv Rx Read format\n");
-		pr_info("RWB[desc]      [PcsmIpSHl PtRs] [vl er S cks ln] ---------------- [bi->skb] <-- Adv Rx Write-Back format\n");
+		netdev_info(netdev, "------------------------------------\n");
+		netdev_info(netdev, "RX QUEUE INDEX = %d\n",
+			    rx_ring->queue_index);
+		netdev_info(netdev, "------------------------------------\n");
+		netdev_info(netdev, "R  [desc]      [ PktBuf     A0] [  HeadBuf   DD] [bi->dma       ] [bi->skb] <-- Adv Rx Read format\n");
+		netdev_info(netdev, "RWB[desc]      [PcsmIpSHl PtRs] [vl er S cks ln] ---------------- [bi->skb] <-- Adv Rx Write-Back format\n");
 
 		for (i = 0; i < rx_ring->count; i++) {
 			const char *next_desc;
@@ -275,18 +274,18 @@ rx_ring_summary:
 
 			if (staterr & IGC_RXD_STAT_DD) {
 				/* Descriptor Done */
-				pr_info("%s[0x%03X]     %016llX %016llX ---------------- %s\n",
-					"RWB", i,
-					le64_to_cpu(u0->a),
-					le64_to_cpu(u0->b),
-					next_desc);
+				netdev_info(netdev, "%s[0x%03X]     %016llX %016llX ---------------- %s\n",
+					    "RWB", i,
+					    le64_to_cpu(u0->a),
+					    le64_to_cpu(u0->b),
+					    next_desc);
 			} else {
-				pr_info("%s[0x%03X]     %016llX %016llX %016llX %s\n",
-					"R  ", i,
-					le64_to_cpu(u0->a),
-					le64_to_cpu(u0->b),
-					(u64)buffer_info->dma,
-					next_desc);
+				netdev_info(netdev, "%s[0x%03X]     %016llX %016llX %016llX %s\n",
+					    "R  ", i,
+					    le64_to_cpu(u0->a),
+					    le64_to_cpu(u0->b),
+					    (u64)buffer_info->dma,
+					    next_desc);
 
 				if (netif_msg_pktdata(adapter) &&
 				    buffer_info->dma && buffer_info->page) {
@@ -314,8 +313,8 @@ void igc_regs_dump(struct igc_adapter *adapter)
 	struct igc_reg_info *reginfo;
 
 	/* Print Registers */
-	dev_info(&adapter->pdev->dev, "Register Dump\n");
-	pr_info(" Register Name   Value\n");
+	netdev_info(adapter->netdev, "Register Dump\n");
+	netdev_info(adapter->netdev, "Register Name   Value\n");
 	for (reginfo = (struct igc_reg_info *)igc_reg_info_tbl;
 	     reginfo->name; reginfo++) {
 		igc_regdump(hw, reginfo);
-- 
cgit v1.2.3


From faf82d5bb1589fe4da36fc0e5b1119def97d887a Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 24 Mar 2020 17:38:19 -0700
Subject: igc: Use netdev log helpers in igc_base.c

This patch coverts one pr_debug() call to hw_dbg() in order to keep log
output aligned with the rest of the driver. hw_dbg() is actually a macro
defined in igc_hw.h that expands to netdev_dbg().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_base.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index f7fb18d8d8f5..cc5a6cf531c7 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -26,7 +26,7 @@ static s32 igc_reset_hw_base(struct igc_hw *hw)
 	 */
 	ret_val = igc_disable_pcie_master(hw);
 	if (ret_val)
-		hw_dbg("PCI-E Master disable polling has failed.\n");
+		hw_dbg("PCI-E Master disable polling has failed\n");
 
 	hw_dbg("Masking off all interrupts\n");
 	wr32(IGC_IMC, 0xffffffff);
@@ -177,7 +177,7 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 	 */
 	ret_val = hw->phy.ops.reset(hw);
 	if (ret_val) {
-		hw_dbg("Error resetting the PHY.\n");
+		hw_dbg("Error resetting the PHY\n");
 		goto out;
 	}
 
@@ -367,7 +367,7 @@ void igc_rx_fifo_flush_base(struct igc_hw *hw)
 	}
 
 	if (ms_wait == 10)
-		pr_debug("Queue disable timed out after 10ms\n");
+		hw_dbg("Queue disable timed out after 10ms\n");
 
 	/* Clear RLPML, RCTL.SBP, RFCTL.LEF, and set RCTL.LPE so that all
 	 * incoming packets are rejected.  Set enable and wait 2ms so that
-- 
cgit v1.2.3


From 3494480ad503068d2c14a65e45a37c785a73349f Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 29 Mar 2020 12:01:51 +0300
Subject: igc: Remove unneeded definition

PHY_FORCE_LIMIT definition not in use and could be removed
i225 parts support auto negotiation mechanism

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index af0c03d77a39..54a7941bdb48 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -47,7 +47,6 @@
 /* Loop limit on how long we wait for auto-negotiation to complete */
 #define COPPER_LINK_UP_LIMIT		10
 #define PHY_AUTO_NEG_LIMIT		45
-#define PHY_FORCE_LIMIT			20
 
 /* Number of 100 microseconds we wait for PCI Express master disable */
 #define MASTER_DISABLE_TIMEOUT		800
-- 
cgit v1.2.3


From 5ddb2747ae2e6141edd3b1dd2ed96d4468394cc2 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 29 Mar 2020 14:35:54 +0300
Subject: igc: Remove unneeded register

Flow control status register not applicable for i225 parts
so clean up the unneeded define.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_regs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 633545977a65..5a6110e211fd 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -35,7 +35,6 @@
 #define IGC_FCRTL		0x02160  /* FC Receive Threshold Low - RW */
 #define IGC_FCRTH		0x02168  /* FC Receive Threshold High - RW */
 #define IGC_FCRTV		0x02460  /* FC Refresh Timer Value - RW */
-#define IGC_FCSTS		0x02464  /* FC Status - RO */
 
 /* PCIe Register Description */
 #define IGC_GCR			0x05B00  /* PCIe control- RW */
-- 
cgit v1.2.3


From 0992b49023d0ae3c2786e81821619504c57e7629 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 18 May 2020 22:18:31 +0300
Subject: cxgb4: Use %pM format specifier for MAC addresses

Convert to %pM instead of using custom code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 7818c392da50..c3dd50b45c48 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -1813,12 +1813,8 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 			/* Inner header lookup */
 			if (lookup_type && (lookup_type != DATALKPTYPE_M)) {
 				seq_printf(seq,
-					   "%3u %02x:%02x:%02x:%02x:%02x:%02x "
-					   "%012llx %06x %06x    -    -   %3c"
-					   "      'I'  %4x   "
-					   "%3c   %#x%4u%4d", idx, addr[0],
-					   addr[1], addr[2], addr[3],
-					   addr[4], addr[5],
+					   "%3u %pM %012llx %06x %06x    -    -   %3c      'I'  %4x   %3c   %#x%4u%4d",
+					   idx, addr,
 					   (unsigned long long)mask,
 					   vniy, (vnix | vniy),
 					   dip_hit ? 'Y' : 'N',
@@ -1830,10 +1826,8 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 					   T6_VF_G(cls_lo) : -1);
 			} else {
 				seq_printf(seq,
-					   "%3u %02x:%02x:%02x:%02x:%02x:%02x "
-					   "%012llx    -       -   ",
-					   idx, addr[0], addr[1], addr[2],
-					   addr[3], addr[4], addr[5],
+					   "%3u %pM %012llx    -       -   ",
+					   idx, addr,
 					   (unsigned long long)mask);
 
 				if (vlan_vld)
@@ -1851,10 +1845,8 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 					   T6_VF_G(cls_lo) : -1);
 			}
 		} else
-			seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x "
-				   "%012llx%3c   %#x%4u%4d",
-				   idx, addr[0], addr[1], addr[2], addr[3],
-				   addr[4], addr[5], (unsigned long long)mask,
+			seq_printf(seq, "%3u %pM %012llx%3c   %#x%4u%4d",
+				   idx, addr, (unsigned long long)mask,
 				   (cls_lo & SRAM_VLD_F) ? 'Y' : 'N',
 				   PORTMAP_G(cls_hi),
 				   PF_G(cls_lo),
-- 
cgit v1.2.3


From 35e43c392bf8bb38eb96ddada984bbdfd9e102a0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 18 May 2020 22:21:28 +0300
Subject: net: seeq: Use %pM format specifier for MAC addresses

Convert to %pM instead of using custom code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/seeq/ether3.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index 128ee7cda1ed..65c98837ec45 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -610,12 +610,9 @@ static int ether3_rx(struct net_device *dev, unsigned int maxcnt)
 		ether3_readbuffer(dev, addrs+2, 12);
 
 if (next_ptr < RX_START || next_ptr >= RX_END) {
- int i;
  printk("%s: bad next pointer @%04X: ", dev->name, priv(dev)->rx_head);
  printk("%02X %02X %02X %02X ", next_ptr >> 8, next_ptr & 255, status & 255, status >> 8);
- for (i = 2; i < 14; i++)
-   printk("%02X ", addrs[i]);
- printk("\n");
+ printk("%pM %pM\n", addrs + 2, addrs + 8);
  next_ptr = priv(dev)->rx_head;
  break;
 }
-- 
cgit v1.2.3


From 588c7e5cc04805fae17cac51e77107841b0c62b0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 18 May 2020 22:14:21 +0200
Subject: r8169: make rtl_rx better readable

Avoid the goto from the rx error handling branch into the else branch,
and in general avoid having the main rx work in the else branch.
In addition ensure proper reverse xmas tree order of variables in the
for loop.

No functional change intended.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 99 +++++++++++++++----------------
 1 file changed, 48 insertions(+), 51 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index e35820c72264..e887ee1e308f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4413,15 +4413,17 @@ static inline void rtl8169_rx_csum(struct sk_buff *skb, u32 opts1)
 
 static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget)
 {
-	unsigned int cur_rx, rx_left;
-	unsigned int count;
+	unsigned int cur_rx, rx_left, count;
+	struct device *d = tp_to_dev(tp);
 
 	cur_rx = tp->cur_rx;
 
 	for (rx_left = min(budget, NUM_RX_DESC); rx_left > 0; rx_left--, cur_rx++) {
-		unsigned int entry = cur_rx % NUM_RX_DESC;
-		const void *rx_buf = page_address(tp->Rx_databuff[entry]);
+		unsigned int pkt_size, entry = cur_rx % NUM_RX_DESC;
 		struct RxDesc *desc = tp->RxDescArray + entry;
+		struct sk_buff *skb;
+		const void *rx_buf;
+		dma_addr_t addr;
 		u32 status;
 
 		status = le32_to_cpu(desc->opts1);
@@ -4443,62 +4445,57 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
 				dev->stats.rx_length_errors++;
 			if (status & RxCRC)
 				dev->stats.rx_crc_errors++;
-			if (status & (RxRUNT | RxCRC) && !(status & RxRWT) &&
-			    dev->features & NETIF_F_RXALL) {
-				goto process_pkt;
-			}
-		} else {
-			unsigned int pkt_size;
-			struct sk_buff *skb;
-
-process_pkt:
-			pkt_size = status & GENMASK(13, 0);
-			if (likely(!(dev->features & NETIF_F_RXFCS)))
-				pkt_size -= ETH_FCS_LEN;
-			/*
-			 * The driver does not support incoming fragmented
-			 * frames. They are seen as a symptom of over-mtu
-			 * sized frames.
-			 */
-			if (unlikely(rtl8169_fragmented_frame(status))) {
-				dev->stats.rx_dropped++;
-				dev->stats.rx_length_errors++;
-				goto release_descriptor;
-			}
 
-			skb = napi_alloc_skb(&tp->napi, pkt_size);
-			if (unlikely(!skb)) {
-				dev->stats.rx_dropped++;
+			if (!(dev->features & NETIF_F_RXALL))
 				goto release_descriptor;
-			}
+			else if (status & RxRWT || !(status & (RxRUNT | RxCRC)))
+				goto release_descriptor;
+		}
 
-			dma_sync_single_for_cpu(tp_to_dev(tp),
-						le64_to_cpu(desc->addr),
-						pkt_size, DMA_FROM_DEVICE);
-			prefetch(rx_buf);
-			skb_copy_to_linear_data(skb, rx_buf, pkt_size);
-			skb->tail += pkt_size;
-			skb->len = pkt_size;
+		pkt_size = status & GENMASK(13, 0);
+		if (likely(!(dev->features & NETIF_F_RXFCS)))
+			pkt_size -= ETH_FCS_LEN;
 
-			dma_sync_single_for_device(tp_to_dev(tp),
-						   le64_to_cpu(desc->addr),
-						   pkt_size, DMA_FROM_DEVICE);
+		/* The driver does not support incoming fragmented frames.
+		 * They are seen as a symptom of over-mtu sized frames.
+		 */
+		if (unlikely(rtl8169_fragmented_frame(status))) {
+			dev->stats.rx_dropped++;
+			dev->stats.rx_length_errors++;
+			goto release_descriptor;
+		}
 
-			rtl8169_rx_csum(skb, status);
-			skb->protocol = eth_type_trans(skb, dev);
+		skb = napi_alloc_skb(&tp->napi, pkt_size);
+		if (unlikely(!skb)) {
+			dev->stats.rx_dropped++;
+			goto release_descriptor;
+		}
 
-			rtl8169_rx_vlan_tag(desc, skb);
+		addr = le64_to_cpu(desc->addr);
+		rx_buf = page_address(tp->Rx_databuff[entry]);
 
-			if (skb->pkt_type == PACKET_MULTICAST)
-				dev->stats.multicast++;
+		dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE);
+		prefetch(rx_buf);
+		skb_copy_to_linear_data(skb, rx_buf, pkt_size);
+		skb->tail += pkt_size;
+		skb->len = pkt_size;
+		dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE);
 
-			napi_gro_receive(&tp->napi, skb);
+		rtl8169_rx_csum(skb, status);
+		skb->protocol = eth_type_trans(skb, dev);
+
+		rtl8169_rx_vlan_tag(desc, skb);
+
+		if (skb->pkt_type == PACKET_MULTICAST)
+			dev->stats.multicast++;
+
+		napi_gro_receive(&tp->napi, skb);
+
+		u64_stats_update_begin(&tp->rx_stats.syncp);
+		tp->rx_stats.packets++;
+		tp->rx_stats.bytes += pkt_size;
+		u64_stats_update_end(&tp->rx_stats.syncp);
 
-			u64_stats_update_begin(&tp->rx_stats.syncp);
-			tp->rx_stats.packets++;
-			tp->rx_stats.bytes += pkt_size;
-			u64_stats_update_end(&tp->rx_stats.syncp);
-		}
 release_descriptor:
 		rtl8169_mark_to_asic(desc);
 	}
-- 
cgit v1.2.3


From e2e5fb8d2f7aedb66fea0722f0f712cd37592a5d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 18 May 2020 22:22:09 +0200
Subject: r8169: improve rtl8169_mark_to_asic

Let the compiler decide about inlining, and as confirmed by Eric it's
better to use WRITE_ONCE here to ensure that the descriptor ownership
is transferred to NIC immediately.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index e887ee1e308f..23f1500928cb 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3824,15 +3824,14 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static inline void rtl8169_mark_to_asic(struct RxDesc *desc)
+static void rtl8169_mark_to_asic(struct RxDesc *desc)
 {
 	u32 eor = le32_to_cpu(desc->opts1) & RingEnd;
 
 	desc->opts2 = 0;
 	/* Force memory writes to complete before releasing descriptor */
 	dma_wmb();
-
-	desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE);
+	WRITE_ONCE(desc->opts1, cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE));
 }
 
 static struct page *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
-- 
cgit v1.2.3


From 5cdfe8306631b2224e3f81fc5a1e2721c7a1948b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 18 May 2020 22:47:16 +0200
Subject: r8169: work around an irq coalescing related tx timeout

In [0] a user reported reproducible tx timeouts on RTL8168f except
PktCntrDisable is set and irq coalescing is enabled.
Realtek told me that they are not aware of any related hw issue on
this chip version, therefore root cause is still unknown. It's not
clear whether the issue affects one or more chip versions in general,
or whether issue is specific to reporter's system.
Due to this level of uncertainty, and due to the fact that I'm aware
of this one report only, let's apply the workaround on net-next only.
After this change setting irq coalescing via ethtool can reliably
avoid the issue on the affected system.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=207205

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 23f1500928cb..79817d4ffa47 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1871,6 +1871,15 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 
 	RTL_W16(tp, IntrMitigate, w);
 
+	/* Meaning of PktCntrDisable bit changed from RTL8168e-vl */
+	if (rtl_is_8168evl_up(tp)) {
+		if (!rx_fr && !tx_fr)
+			/* disable packet counter */
+			tp->cp_cmd |= PktCntrDisable;
+		else
+			tp->cp_cmd &= ~PktCntrDisable;
+	}
+
 	tp->cp_cmd = (tp->cp_cmd & ~INTT_MASK) | cp01;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 	rtl_pci_commit(tp);
-- 
cgit v1.2.3


From 472abd3240918278d2da817e064e9b6c8fb4faf2 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 1 Apr 2020 11:43:20 +0300
Subject: igc: Remove PCIe Control register

GCR (PCIe Control) register not in use and should be removed
This patch clean up this register

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_regs.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 5a6110e211fd..0f94285ddc11 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -36,9 +36,6 @@
 #define IGC_FCRTH		0x02168  /* FC Receive Threshold High - RW */
 #define IGC_FCRTV		0x02460  /* FC Refresh Timer Value - RW */
 
-/* PCIe Register Description */
-#define IGC_GCR			0x05B00  /* PCIe control- RW */
-
 /* Semaphore registers */
 #define IGC_SW_FW_SYNC		0x05B5C  /* SW-FW Synchronization - RW */
 #define IGC_SWSM		0x05B50  /* SW Semaphore */
-- 
cgit v1.2.3


From 3c215fb18e700344d96f3bde606b4492c70eaf56 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Wed, 1 Apr 2020 12:16:44 +0300
Subject: igc: remove IGC_REMOVED function

igc driver has leftovers from the previous device that supported
Virtualization. This can be found in the function IGC_REMOVED which
became obsolete, and can be removed.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.h  | 4 ----
 drivers/net/ethernet/intel/igc/igc_main.c | 3 ---
 drivers/net/ethernet/intel/igc/igc_regs.h | 3 +--
 3 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.h b/drivers/net/ethernet/intel/igc/igc_mac.h
index 832cccec87cd..b5963f86defb 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.h
+++ b/drivers/net/ethernet/intel/igc/igc_mac.h
@@ -8,10 +8,6 @@
 #include "igc_phy.h"
 #include "igc_defines.h"
 
-#ifndef IGC_REMOVED
-#define IGC_REMOVED(a) (0)
-#endif /* IGC_REMOVED */
-
 /* forward declaration */
 s32 igc_disable_pcie_master(struct igc_hw *hw);
 s32 igc_check_for_copper_link(struct igc_hw *hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 0ae3590a50eb..125026d053eb 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4659,9 +4659,6 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
 	u32 value = 0;
 
-	if (IGC_REMOVED(hw_addr))
-		return ~value;
-
 	value = readl(&hw_addr[reg]);
 
 	/* reads should not return all F's */
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 0f94285ddc11..f101bfbf52e6 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -275,8 +275,7 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg);
 #define wr32(reg, val) \
 do { \
 	u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
-	if (!IGC_REMOVED(hw_addr)) \
-		writel((val), &hw_addr[(reg)]); \
+	writel((val), &hw_addr[(reg)]); \
 } while (0)
 
 #define rd32(reg) (igc_rd32(hw, reg))
-- 
cgit v1.2.3


From 65b9ee1b928f2b679319c547c52986b8869855df Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 1 Apr 2020 14:38:44 +0300
Subject: igc: Clean up obsolete NVM defines

Packet buffer allocation, reserved word and pointer guard
not applicable for i225 parts.
This patch comes to clean up these obsolete defines

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 54a7941bdb48..0ecc63d423b8 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -163,11 +163,6 @@
 
 /* For checksumming, the sum of all words in the NVM should equal 0xBABA. */
 #define NVM_SUM				0xBABA
-
-#define NVM_PBA_OFFSET_0		8
-#define NVM_PBA_OFFSET_1		9
-#define NVM_RESERVED_WORD		0xFFFF
-#define NVM_PBA_PTR_GUARD		0xFAFA
 #define NVM_WORD_SIZE_BASE_SHIFT	6
 
 /* Collision related configuration parameters */
-- 
cgit v1.2.3


From bbfaa141d211c86441f7e91454e0a306fb5296de Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 3 Apr 2020 11:17:40 -0700
Subject: igc: Rename IGC_VLAPQF macro

This patch renames the IGC_VLAPQF macro to IGC_VLANPQF as well as
related macros so they match the register name and fields described in
the data sheet.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h |  6 +++---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 23 +++++++++++------------
 drivers/net/ethernet/intel/igc/igc_regs.h    |  2 +-
 3 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 0ecc63d423b8..f1bb5414f99f 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -508,9 +508,9 @@
 #define IGC_MAX_MAC_HDR_LEN	127
 #define IGC_MAX_NETWORK_HDR_LEN	511
 
-#define IGC_VLAPQF_QUEUE_SEL(_n, q_idx) ((q_idx) << ((_n) * 4))
-#define IGC_VLAPQF_P_VALID(_n)	(0x1 << (3 + (_n) * 4))
-#define IGC_VLAPQF_QUEUE_MASK	0x03
+#define IGC_VLANPQF_QSEL(_n, q_idx) ((q_idx) << ((_n) * 4))
+#define IGC_VLANPQF_VALID(_n)	(0x1 << (3 + (_n) * 4))
+#define IGC_VLANPQF_QUEUE_MASK	0x03
 
 #define IGC_ADVTXD_MACLEN_SHIFT		9  /* Adv ctxt desc mac len shift */
 #define IGC_ADVTXD_TUCMD_IPV4		0x00000400  /* IP Packet Type:1=IPv4 */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index a05d7abee524..c21971b40cb2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1229,23 +1229,23 @@ static int igc_rxnfc_write_vlan_prio_filter(struct igc_adapter *adapter,
 	u16 queue_index;
 	u32 vlapqf;
 
-	vlapqf = rd32(IGC_VLAPQF);
+	vlapqf = rd32(IGC_VLANPQF);
 	vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK)
 				>> VLAN_PRIO_SHIFT;
-	queue_index = (vlapqf >> (vlan_priority * 4)) & IGC_VLAPQF_QUEUE_MASK;
+	queue_index = (vlapqf >> (vlan_priority * 4)) & IGC_VLANPQF_QUEUE_MASK;
 
-	/* check whether this vlan prio is already set */
-	if (vlapqf & IGC_VLAPQF_P_VALID(vlan_priority) &&
+	/* check whether this VLAN prio is already set */
+	if (vlapqf & IGC_VLANPQF_VALID(vlan_priority) &&
 	    queue_index != input->action) {
 		netdev_err(adapter->netdev,
 			   "ethtool rxnfc set VLAN prio filter failed\n");
 		return -EEXIST;
 	}
 
-	vlapqf |= IGC_VLAPQF_P_VALID(vlan_priority);
-	vlapqf |= IGC_VLAPQF_QUEUE_SEL(vlan_priority, input->action);
+	vlapqf |= IGC_VLANPQF_VALID(vlan_priority);
+	vlapqf |= IGC_VLANPQF_QSEL(vlan_priority, input->action);
 
-	wr32(IGC_VLAPQF, vlapqf);
+	wr32(IGC_VLANPQF, vlapqf);
 
 	return 0;
 }
@@ -1313,12 +1313,11 @@ static void igc_clear_vlan_prio_filter(struct igc_adapter *adapter,
 
 	vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 
-	vlapqf = rd32(IGC_VLAPQF);
-	vlapqf &= ~IGC_VLAPQF_P_VALID(vlan_priority);
-	vlapqf &= ~IGC_VLAPQF_QUEUE_SEL(vlan_priority,
-						IGC_VLAPQF_QUEUE_MASK);
+	vlapqf = rd32(IGC_VLANPQF);
+	vlapqf &= ~IGC_VLANPQF_VALID(vlan_priority);
+	vlapqf &= ~IGC_VLANPQF_QSEL(vlan_priority, IGC_VLANPQF_QUEUE_MASK);
 
-	wr32(IGC_VLAPQF, vlapqf);
+	wr32(IGC_VLANPQF, vlapqf);
 }
 
 int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index f101bfbf52e6..851ff19af703 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -120,7 +120,7 @@
 #define IGC_UTA			0x0A000  /* Unicast Table Array - RW */
 #define IGC_RAL(_n)		(0x05400 + ((_n) * 0x08))
 #define IGC_RAH(_n)		(0x05404 + ((_n) * 0x08))
-#define IGC_VLAPQF		0x055B0  /* VLAN Priority Queue Filter VLAPQF */
+#define IGC_VLANPQF		0x055B0  /* VLAN Priority Queue Filter - RW */
 
 /* Transmit Register Descriptions */
 #define IGC_TCTL		0x00400  /* Tx Control - RW */
-- 
cgit v1.2.3


From fbee4760ec4fc9f885ad0737f7b371cc6b73f573 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 3 Apr 2020 11:17:41 -0700
Subject: igc: Dump VLANPQF register

This patch adds the VLAN Priority Queue Filter Register (VLANPQF) to the
list of registers dumped by igc_get_regs().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index c21971b40cb2..19da9dc8dafb 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -316,6 +316,8 @@ static void igc_get_regs(struct net_device *netdev,
 		regs_buff[172 + i] = rd32(IGC_RAL(i));
 	for (i = 0; i < 16; i++)
 		regs_buff[188 + i] = rd32(IGC_RAH(i));
+
+	regs_buff[204] = rd32(IGC_VLANPQF);
 }
 
 static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
-- 
cgit v1.2.3


From 2e4f1716f31f3486fa454fd3174f3de982b1dcaa Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 3 Apr 2020 11:17:42 -0700
Subject: igc: Return -EOPNOTSUPP when VLAN mask doesn't match

The I225 controller supports Rx queue assignment based on VLAN priority
only. Other Tag Control Information (TCI) are valid, but not supported
by the driver. So this patch changes the returning code from igc_add_
ethtool_nfc_entry() to -EOPNOTSUPP in order to provide more meaningful
information on why the function failed.

It also adds a debug messages to give the user a hint about what went
wrong with the NFC setup.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 19da9dc8dafb..f28f7feb39a5 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1446,7 +1446,8 @@ static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
 
 	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
 		if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
-			err = -EINVAL;
+			netdev_dbg(netdev, "VLAN mask not supported\n");
+			err = -EOPNOTSUPP;
 			goto err_out;
 		}
 		input->filter.vlan_tci = fsp->h_ext.vlan_tci;
-- 
cgit v1.2.3


From e09303d3c4d9d9f71657550d61eb00bc84c13859 Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@netronome.com>
Date: Tue, 19 May 2020 16:15:01 +0200
Subject: nfp: flower: renaming of feature bits

Clean up name aliasing. Some features gets enabled using a slightly
different method, but the bitmap for these were stored in the same
field. Rename their #defines and move the bitmap to a new variable.

Signed-off-by: Louis Peens <louis.peens@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c |  4 ++--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.c   |  4 ++--
 drivers/net/ethernet/netronome/nfp/flower/main.c   | 14 +++++++-------
 drivers/net/ethernet/netronome/nfp/flower/main.h   |  9 ++++++---
 4 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 1c76e1592ca2..ff844e5cc41f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -209,7 +209,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 					    NFP_FL_OUT_FLAGS_USE_TUN);
 		output->port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
 	} else if (netif_is_lag_master(out_dev) &&
-		   priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+		   priv->flower_en_feats & NFP_FL_ENABLE_LAG) {
 		int gid;
 
 		output->flags = cpu_to_be16(tmp_flags);
@@ -956,7 +956,7 @@ nfp_flower_output_action(struct nfp_app *app,
 
 	*a_len += sizeof(struct nfp_fl_output);
 
-	if (priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+	if (priv->flower_en_feats & NFP_FL_ENABLE_LAG) {
 		/* nfp_fl_pre_lag returns -err or size of prelag action added.
 		 * This will be 0 if it is not egressing to a lag dev.
 		 */
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index a595ddb92bff..a050cb898782 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -264,7 +264,7 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 		nfp_flower_cmsg_portmod_rx(app, skb);
 		break;
 	case NFP_FLOWER_CMSG_TYPE_MERGE_HINT:
-		if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE) {
+		if (app_priv->flower_en_feats & NFP_FL_ENABLE_FLOW_MERGE) {
 			nfp_flower_cmsg_merge_hint_rx(app, skb);
 			break;
 		}
@@ -285,7 +285,7 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 		nfp_flower_stats_rlim_reply(app, skb);
 		break;
 	case NFP_FLOWER_CMSG_TYPE_LAG_CONFIG:
-		if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+		if (app_priv->flower_en_feats & NFP_FL_ENABLE_LAG) {
 			skb_stored = nfp_flower_lag_unprocessed_msg(app, skb);
 			break;
 		}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index d8ad9346a26a..62c202307940 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -759,7 +759,7 @@ static int nfp_flower_init(struct nfp_app *app)
 	err = nfp_rtsym_write_le(app->pf->rtbl,
 				 "_abi_flower_balance_sync_enable", 1);
 	if (!err) {
-		app_priv->flower_ext_feats |= NFP_FL_FEATS_LAG;
+		app_priv->flower_ext_feats |= NFP_FL_ENABLE_LAG;
 		nfp_flower_lag_init(&app_priv->nfp_lag);
 	} else if (err == -ENOENT) {
 		nfp_warn(app->cpp, "LAG not supported by FW.\n");
@@ -772,7 +772,7 @@ static int nfp_flower_init(struct nfp_app *app)
 		err = nfp_rtsym_write_le(app->pf->rtbl,
 					 "_abi_flower_merge_hint_enable", 1);
 		if (!err) {
-			app_priv->flower_ext_feats |= NFP_FL_FEATS_FLOW_MERGE;
+			app_priv->flower_ext_feats |= NFP_FL_ENABLE_FLOW_MERGE;
 			nfp_flower_internal_port_init(app_priv);
 		} else if (err == -ENOENT) {
 			nfp_warn(app->cpp, "Flow merge not supported by FW.\n");
@@ -793,7 +793,7 @@ static int nfp_flower_init(struct nfp_app *app)
 	return 0;
 
 err_lag_clean:
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+	if (app_priv->flower_ext_feats & NFP_FL_ENABLE_LAG)
 		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
 err_cleanup_metadata:
 	nfp_flower_metadata_cleanup(app);
@@ -813,10 +813,10 @@ static void nfp_flower_clean(struct nfp_app *app)
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
 		nfp_flower_qos_cleanup(app);
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+	if (app_priv->flower_en_feats & NFP_FL_ENABLE_LAG)
 		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE)
+	if (app_priv->flower_en_feats & NFP_FL_ENABLE_FLOW_MERGE)
 		nfp_flower_internal_port_cleanup(app_priv);
 
 	nfp_flower_metadata_cleanup(app);
@@ -886,7 +886,7 @@ static int nfp_flower_start(struct nfp_app *app)
 	struct nfp_flower_priv *app_priv = app->priv;
 	int err;
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+	if (app_priv->flower_en_feats & NFP_FL_ENABLE_LAG) {
 		err = nfp_flower_lag_reset(&app_priv->nfp_lag);
 		if (err)
 			return err;
@@ -907,7 +907,7 @@ nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
 	struct nfp_flower_priv *app_priv = app->priv;
 	int ret;
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+	if (app_priv->flower_en_feats & NFP_FL_ENABLE_LAG) {
 		ret = nfp_flower_lag_netdev_event(app_priv, netdev, event, ptr);
 		if (ret & NOTIFY_STOP_MASK)
 			return ret;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index d55d0d33bc45..7db3be0b17e9 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -44,8 +44,9 @@ struct nfp_app;
 #define NFP_FL_FEATS_FLOW_MOD		BIT(5)
 #define NFP_FL_FEATS_PRE_TUN_RULES	BIT(6)
 #define NFP_FL_FEATS_IPV6_TUN		BIT(7)
-#define NFP_FL_FEATS_FLOW_MERGE		BIT(30)
-#define NFP_FL_FEATS_LAG		BIT(31)
+
+#define NFP_FL_ENABLE_FLOW_MERGE	BIT(0)
+#define NFP_FL_ENABLE_LAG		BIT(1)
 
 struct nfp_fl_mask_id {
 	struct circ_buf mask_id_free_list;
@@ -145,6 +146,7 @@ struct nfp_fl_internal_ports {
  * @mask_id_seed:	Seed used for mask hash table
  * @flower_version:	HW version of flower
  * @flower_ext_feats:	Bitmap of extra features the HW supports
+ * @flower_en_feats:	Bitmap of features enabled by HW
  * @stats_ids:		List of free stats ids
  * @mask_ids:		List of free mask ids
  * @mask_table:		Hash table used to store masks
@@ -180,6 +182,7 @@ struct nfp_flower_priv {
 	u32 mask_id_seed;
 	u64 flower_version;
 	u64 flower_ext_feats;
+	u8 flower_en_feats;
 	struct nfp_fl_stats_id stats_ids;
 	struct nfp_fl_mask_id mask_ids;
 	DECLARE_HASHTABLE(mask_table, NFP_FLOWER_MASK_HASH_BITS);
@@ -346,7 +349,7 @@ nfp_flower_internal_port_can_offload(struct nfp_app *app,
 {
 	struct nfp_flower_priv *app_priv = app->priv;
 
-	if (!(app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE))
+	if (!(app_priv->flower_en_feats & NFP_FL_ENABLE_FLOW_MERGE))
 		return false;
 	if (!netdev->rtnl_link_ops)
 		return false;
-- 
cgit v1.2.3


From 465957c257f3083785fe8e954724cfac2e5d33e9 Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@netronome.com>
Date: Tue, 19 May 2020 16:15:02 +0200
Subject: nfp: flower: inform firmware of flower features

For backwards compatibility it may be required for the firmware to
disable certain features depending on the features supported by
the host. Combine the host feature bits and firmware feature bits
and write this back to the firmware.

Signed-off-by: Louis Peens <louis.peens@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 106 ++++++++++++++++-------
 drivers/net/ethernet/netronome/nfp/flower/main.h |  11 +++
 2 files changed, 87 insertions(+), 30 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 62c202307940..d054553c75e0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -665,6 +665,77 @@ err_clear_nn:
 	return err;
 }
 
+static void nfp_flower_wait_host_bit(struct nfp_app *app)
+{
+	unsigned long err_at;
+	u64 feat;
+	int err;
+
+	/* Wait for HOST_ACK flag bit to propagate */
+	err_at = jiffies + msecs_to_jiffies(100);
+	do {
+		feat = nfp_rtsym_read_le(app->pf->rtbl,
+					 "_abi_flower_combined_features_global",
+					 &err);
+		if (time_is_before_eq_jiffies(err_at)) {
+			nfp_warn(app->cpp,
+				 "HOST_ACK bit not propagated in FW.\n");
+			break;
+		}
+		usleep_range(1000, 2000);
+	} while (!err && !(feat & NFP_FL_FEATS_HOST_ACK));
+
+	if (err)
+		nfp_warn(app->cpp,
+			 "Could not read global features entry from FW\n");
+}
+
+static int nfp_flower_sync_feature_bits(struct nfp_app *app)
+{
+	struct nfp_flower_priv *app_priv = app->priv;
+	int err;
+
+	/* Tell the firmware of the host supported features. */
+	err = nfp_rtsym_write_le(app->pf->rtbl, "_abi_flower_host_mask",
+				 app_priv->flower_ext_feats |
+				 NFP_FL_FEATS_HOST_ACK);
+	if (!err)
+		nfp_flower_wait_host_bit(app);
+	else if (err != -ENOENT)
+		return err;
+
+	/* Tell the firmware that the driver supports lag. */
+	err = nfp_rtsym_write_le(app->pf->rtbl,
+				 "_abi_flower_balance_sync_enable", 1);
+	if (!err) {
+		app_priv->flower_ext_feats |= NFP_FL_ENABLE_LAG;
+		nfp_flower_lag_init(&app_priv->nfp_lag);
+	} else if (err == -ENOENT) {
+		nfp_warn(app->cpp, "LAG not supported by FW.\n");
+	} else {
+		return err;
+	}
+
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MOD) {
+		/* Tell the firmware that the driver supports flow merging. */
+		err = nfp_rtsym_write_le(app->pf->rtbl,
+					 "_abi_flower_merge_hint_enable", 1);
+		if (!err) {
+			app_priv->flower_ext_feats |= NFP_FL_ENABLE_FLOW_MERGE;
+			nfp_flower_internal_port_init(app_priv);
+		} else if (err == -ENOENT) {
+			nfp_warn(app->cpp,
+				 "Flow merge not supported by FW.\n");
+		} else {
+			return err;
+		}
+	} else {
+		nfp_warn(app->cpp, "Flow mod/merge not supported by FW.\n");
+	}
+
+	return 0;
+}
+
 static int nfp_flower_init(struct nfp_app *app)
 {
 	u64 version, features, ctx_count, num_mems;
@@ -753,35 +824,11 @@ static int nfp_flower_init(struct nfp_app *app)
 	if (err)
 		app_priv->flower_ext_feats = 0;
 	else
-		app_priv->flower_ext_feats = features;
+		app_priv->flower_ext_feats = features & NFP_FL_FEATS_HOST;
 
-	/* Tell the firmware that the driver supports lag. */
-	err = nfp_rtsym_write_le(app->pf->rtbl,
-				 "_abi_flower_balance_sync_enable", 1);
-	if (!err) {
-		app_priv->flower_ext_feats |= NFP_FL_ENABLE_LAG;
-		nfp_flower_lag_init(&app_priv->nfp_lag);
-	} else if (err == -ENOENT) {
-		nfp_warn(app->cpp, "LAG not supported by FW.\n");
-	} else {
-		goto err_cleanup_metadata;
-	}
-
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MOD) {
-		/* Tell the firmware that the driver supports flow merging. */
-		err = nfp_rtsym_write_le(app->pf->rtbl,
-					 "_abi_flower_merge_hint_enable", 1);
-		if (!err) {
-			app_priv->flower_ext_feats |= NFP_FL_ENABLE_FLOW_MERGE;
-			nfp_flower_internal_port_init(app_priv);
-		} else if (err == -ENOENT) {
-			nfp_warn(app->cpp, "Flow merge not supported by FW.\n");
-		} else {
-			goto err_lag_clean;
-		}
-	} else {
-		nfp_warn(app->cpp, "Flow mod/merge not supported by FW.\n");
-	}
+	err = nfp_flower_sync_feature_bits(app);
+	if (err)
+		goto err_cleanup;
 
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
 		nfp_flower_qos_init(app);
@@ -792,10 +839,9 @@ static int nfp_flower_init(struct nfp_app *app)
 
 	return 0;
 
-err_lag_clean:
+err_cleanup:
 	if (app_priv->flower_ext_feats & NFP_FL_ENABLE_LAG)
 		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
-err_cleanup_metadata:
 	nfp_flower_metadata_cleanup(app);
 err_free_app_priv:
 	vfree(app->priv);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 7db3be0b17e9..59abea2a39ad 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -44,10 +44,21 @@ struct nfp_app;
 #define NFP_FL_FEATS_FLOW_MOD		BIT(5)
 #define NFP_FL_FEATS_PRE_TUN_RULES	BIT(6)
 #define NFP_FL_FEATS_IPV6_TUN		BIT(7)
+#define NFP_FL_FEATS_HOST_ACK		BIT(31)
 
 #define NFP_FL_ENABLE_FLOW_MERGE	BIT(0)
 #define NFP_FL_ENABLE_LAG		BIT(1)
 
+#define NFP_FL_FEATS_HOST \
+	(NFP_FL_FEATS_GENEVE | \
+	NFP_FL_NBI_MTU_SETTING | \
+	NFP_FL_FEATS_GENEVE_OPT | \
+	NFP_FL_FEATS_VLAN_PCP | \
+	NFP_FL_FEATS_VF_RLIM | \
+	NFP_FL_FEATS_FLOW_MOD | \
+	NFP_FL_FEATS_PRE_TUN_RULES | \
+	NFP_FL_FEATS_IPV6_TUN)
+
 struct nfp_fl_mask_id {
 	struct circ_buf mask_id_free_list;
 	ktime_t *last_used;
-- 
cgit v1.2.3


From 12ddee68d058792602d017ea940a69fe6969edbe Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Thu, 23 Apr 2020 18:11:19 -0700
Subject: igc: Refactor VLAN priority filtering code

The whole VLAN priority filtering code is implemented in igc_ethtool.c
and mixes logic from ethtool and core parts. This patch refactors it so
core logic is moved to igc_main.c, aligning the VLAN priority filtering
code organization with the MAC address filtering code.

This patch also takes the opportunity to add some log messages to ease
debugging.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  3 ++
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 64 ++++++----------------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 52 ++++++++++++++++++++++
 3 files changed, 68 insertions(+), 51 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 661dc8875f3f..5f1e1d31e832 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -235,6 +235,9 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const s8 queue, const u8 flags);
 int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		       const u8 flags);
+int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
+			     int queue);
+void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio);
 void igc_update_stats(struct igc_adapter *adapter);
 
 /* igc_dump declarations */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index f28f7feb39a5..c5be8b936963 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1223,35 +1223,6 @@ static int igc_rxnfc_write_etype_filter(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_rxnfc_write_vlan_prio_filter(struct igc_adapter *adapter,
-					    struct igc_nfc_filter *input)
-{
-	struct igc_hw *hw = &adapter->hw;
-	u8 vlan_priority;
-	u16 queue_index;
-	u32 vlapqf;
-
-	vlapqf = rd32(IGC_VLANPQF);
-	vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK)
-				>> VLAN_PRIO_SHIFT;
-	queue_index = (vlapqf >> (vlan_priority * 4)) & IGC_VLANPQF_QUEUE_MASK;
-
-	/* check whether this VLAN prio is already set */
-	if (vlapqf & IGC_VLANPQF_VALID(vlan_priority) &&
-	    queue_index != input->action) {
-		netdev_err(adapter->netdev,
-			   "ethtool rxnfc set VLAN prio filter failed\n");
-		return -EEXIST;
-	}
-
-	vlapqf |= IGC_VLANPQF_VALID(vlan_priority);
-	vlapqf |= IGC_VLANPQF_QSEL(vlan_priority, input->action);
-
-	wr32(IGC_VLANPQF, vlapqf);
-
-	return 0;
-}
-
 int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 {
 	struct igc_hw *hw = &adapter->hw;
@@ -1285,10 +1256,15 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 			return err;
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
-		err = igc_rxnfc_write_vlan_prio_filter(adapter, input);
+	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+			   VLAN_PRIO_SHIFT;
+		err = igc_add_vlan_prio_filter(adapter, prio, input->action);
+		if (err)
+			return err;
+	}
 
-	return err;
+	return 0;
 }
 
 static void igc_clear_etype_filter_regs(struct igc_adapter *adapter,
@@ -1306,31 +1282,17 @@ static void igc_clear_etype_filter_regs(struct igc_adapter *adapter,
 	adapter->etype_bitmap[reg_index] = false;
 }
 
-static void igc_clear_vlan_prio_filter(struct igc_adapter *adapter,
-				       u16 vlan_tci)
-{
-	struct igc_hw *hw = &adapter->hw;
-	u8 vlan_priority;
-	u32 vlapqf;
-
-	vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-
-	vlapqf = rd32(IGC_VLANPQF);
-	vlapqf &= ~IGC_VLANPQF_VALID(vlan_priority);
-	vlapqf &= ~IGC_VLANPQF_QSEL(vlan_priority, IGC_VLANPQF_QUEUE_MASK);
-
-	wr32(IGC_VLANPQF, vlapqf);
-}
-
 int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 {
 	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
 		igc_clear_etype_filter_regs(adapter,
 					    input->etype_reg_index);
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
-		igc_clear_vlan_prio_filter(adapter,
-					   ntohs(input->filter.vlan_tci));
+	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+			   VLAN_PRIO_SHIFT;
+		igc_del_vlan_prio_filter(adapter, prio);
+	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
 		igc_del_mac_filter(adapter, input->filter.src_addr,
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 125026d053eb..7e59c0393dbc 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2314,6 +2314,58 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	return 0;
 }
 
+/**
+ * igc_add_vlan_prio_filter() - Add VLAN priority filter
+ * @adapter: Pointer to adapter where the filter should be added
+ * @prio: VLAN priority value
+ * @queue: Queue number which matching frames are assigned to
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
+ */
+int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio, int queue)
+{
+	struct net_device *dev = adapter->netdev;
+	struct igc_hw *hw = &adapter->hw;
+	u32 vlanpqf;
+
+	vlanpqf = rd32(IGC_VLANPQF);
+
+	if (vlanpqf & IGC_VLANPQF_VALID(prio)) {
+		netdev_dbg(dev, "VLAN priority filter already in use\n");
+		return -EEXIST;
+	}
+
+	vlanpqf |= IGC_VLANPQF_QSEL(prio, queue);
+	vlanpqf |= IGC_VLANPQF_VALID(prio);
+
+	wr32(IGC_VLANPQF, vlanpqf);
+
+	netdev_dbg(dev, "Add VLAN priority filter: prio %d queue %d\n",
+		   prio, queue);
+	return 0;
+}
+
+/**
+ * igc_del_vlan_prio_filter() - Delete VLAN priority filter
+ * @adapter: Pointer to adapter where the filter should be deleted from
+ * @prio: VLAN priority value
+ */
+void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 vlanpqf;
+
+	vlanpqf = rd32(IGC_VLANPQF);
+
+	vlanpqf &= ~IGC_VLANPQF_VALID(prio);
+	vlanpqf &= ~IGC_VLANPQF_QSEL(prio, IGC_VLANPQF_QUEUE_MASK);
+
+	wr32(IGC_VLANPQF, vlanpqf);
+
+	netdev_dbg(adapter->netdev, "Delete VLAN priority filter: prio %d\n",
+		   prio);
+}
+
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
-- 
cgit v1.2.3


From 6ad70c7686d4ad14cbea4f9930037cabea0cdb7a Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Mon, 18 May 2020 20:32:13 +0530
Subject: realtek/8139too: use generic power management

compile-tested only

With legacy PM hooks, it was the responsibility
of a driver to manage PCI states and also
device's power state. The generic approach is
to let PCI core handle the work.

PCI core passes "struct device*" as an argument
to the .suspend() and .resume() callbacks. As
these callabcks work with "struct net_device*",
extract it from "struct device*" using
dev_get_drv_data().

Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139too.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 5caeb8368eab..227139d42227 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2603,17 +2603,13 @@ static void rtl8139_set_rx_mode (struct net_device *dev)
 	spin_unlock_irqrestore (&tp->lock, flags);
 }
 
-#ifdef CONFIG_PM
-
-static int rtl8139_suspend (struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused rtl8139_suspend(struct device *device)
 {
-	struct net_device *dev = pci_get_drvdata (pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8139_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
 	unsigned long flags;
 
-	pci_save_state (pdev);
-
 	if (!netif_running (dev))
 		return 0;
 
@@ -2631,38 +2627,30 @@ static int rtl8139_suspend (struct pci_dev *pdev, pm_message_t state)
 
 	spin_unlock_irqrestore (&tp->lock, flags);
 
-	pci_set_power_state (pdev, PCI_D3hot);
-
 	return 0;
 }
 
-
-static int rtl8139_resume (struct pci_dev *pdev)
+static int __maybe_unused rtl8139_resume(struct device *device)
 {
-	struct net_device *dev = pci_get_drvdata (pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 
-	pci_restore_state (pdev);
 	if (!netif_running (dev))
 		return 0;
-	pci_set_power_state (pdev, PCI_D0);
+
 	rtl8139_init_ring (dev);
 	rtl8139_hw_start (dev);
 	netif_device_attach (dev);
 	return 0;
 }
 
-#endif /* CONFIG_PM */
-
+static SIMPLE_DEV_PM_OPS(rtl8139_pm_ops, rtl8139_suspend, rtl8139_resume);
 
 static struct pci_driver rtl8139_pci_driver = {
 	.name		= DRV_NAME,
 	.id_table	= rtl8139_pci_tbl,
 	.probe		= rtl8139_init_one,
 	.remove		= rtl8139_remove_one,
-#ifdef CONFIG_PM
-	.suspend	= rtl8139_suspend,
-	.resume		= rtl8139_resume,
-#endif /* CONFIG_PM */
+	.driver.pm	= &rtl8139_pm_ops,
 };
 
 
-- 
cgit v1.2.3


From a1eae9f677a694c97c232f8c1b3b826ec68a0c11 Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Mon, 18 May 2020 20:32:14 +0530
Subject: realtek/8139cp: use generic power management

compile-tested only

With legacy PM hooks, it was the responsibility
of a driver to manage PCI states and also
device's power state. The generic approach is
to let PCI core handle the work.

The suspend callback enables/disables PCI wake
on the basis of "cp->wol_enabled" variable
which is unknown to PCI core. To utilise its
need, call device_set_wakeup_enable().

Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139cp.c | 25 ++++++++-----------------
 1 file changed, 8 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 60d342f82fb3..e291e6ac40cb 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -2054,10 +2054,9 @@ static void cp_remove_one (struct pci_dev *pdev)
 	free_netdev(dev);
 }
 
-#ifdef CONFIG_PM
-static int cp_suspend (struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused cp_suspend(struct device *device)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
 
@@ -2075,16 +2074,14 @@ static int cp_suspend (struct pci_dev *pdev, pm_message_t state)
 
 	spin_unlock_irqrestore (&cp->lock, flags);
 
-	pci_save_state(pdev);
-	pci_enable_wake(pdev, pci_choose_state(pdev, state), cp->wol_enabled);
-	pci_set_power_state(pdev, pci_choose_state(pdev, state));
+	device_set_wakeup_enable(device, cp->wol_enabled);
 
 	return 0;
 }
 
-static int cp_resume (struct pci_dev *pdev)
+static int __maybe_unused cp_resume(struct device *device)
 {
-	struct net_device *dev = pci_get_drvdata (pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
 
@@ -2093,10 +2090,6 @@ static int cp_resume (struct pci_dev *pdev)
 
 	netif_device_attach (dev);
 
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	pci_enable_wake(pdev, PCI_D0, 0);
-
 	/* FIXME: sh*t may happen if the Rx ring buffer is depleted */
 	cp_init_rings_index (cp);
 	cp_init_hw (cp);
@@ -2111,7 +2104,6 @@ static int cp_resume (struct pci_dev *pdev)
 
 	return 0;
 }
-#endif /* CONFIG_PM */
 
 static const struct pci_device_id cp_pci_tbl[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_REALTEK,     PCI_DEVICE_ID_REALTEK_8139), },
@@ -2120,15 +2112,14 @@ static const struct pci_device_id cp_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, cp_pci_tbl);
 
+static SIMPLE_DEV_PM_OPS(cp_pm_ops, cp_suspend, cp_resume);
+
 static struct pci_driver cp_driver = {
 	.name         = DRV_NAME,
 	.id_table     = cp_pci_tbl,
 	.probe        =	cp_init_one,
 	.remove       = cp_remove_one,
-#ifdef CONFIG_PM
-	.resume       = cp_resume,
-	.suspend      = cp_suspend,
-#endif
+	.driver.pm    = &cp_pm_ops,
 };
 
 module_pci_driver(cp_driver);
-- 
cgit v1.2.3


From 09a2b50a49798611df55f85b0428278d58b089ad Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 7 Apr 2020 14:07:07 -0700
Subject: igc: Remove duplicated IGC_RXPBS macro

This patch remove the IGC_RXPBS macro defined in line 233 since it is
already defined in line 18 with the exactly same value.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_regs.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 851ff19af703..763a24d52865 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -227,8 +227,6 @@
 
 #define IGC_FTQF(_n)	(0x059E0 + (4 * (_n)))  /* 5-tuple Queue Fltr */
 
-#define IGC_RXPBS	0x02404  /* Rx Packet Buffer Size - RW */
-
 /* Transmit Scheduling Registers */
 #define IGC_TQAVCTRL		0x3570
 #define IGC_TXQCTL(_n)		(0x3344 + 0x4 * (_n))
-- 
cgit v1.2.3


From 1664ef3e62271dede7d51056b9ba36697b57d714 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 7 Apr 2020 14:07:08 -0700
Subject: igc: Remove ethertype filter in PTP code

The driver only supports hardware timestamping for all incoming
traffic (HWTSTAMP_FILTER_ALL) which is enabled via Rx Time Sync
Control (TSYNCRXCTL) register already. Therefore, the ethertype
filter set in in igc_ptp_set_timestamp_mode() is useless so this
patch removes it.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  2 +-
 drivers/net/ethernet/intel/igc/igc_defines.h |  3 ---
 drivers/net/ethernet/intel/igc/igc_ptp.c     | 12 ------------
 3 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5f1e1d31e832..e4169fe955d8 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -26,7 +26,7 @@ void igc_set_ethtool_ops(struct net_device *);
 #define MAX_Q_VECTORS			8
 #define MAX_STD_JUMBO_FRAME_SIZE	9216
 
-#define MAX_ETYPE_FILTER		(4 - 1)
+#define MAX_ETYPE_FILTER		4
 #define IGC_RETA_SIZE			128
 
 struct igc_tx_queue_stats {
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index f1bb5414f99f..6909826bc747 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -384,9 +384,6 @@
 
 #define IGC_TSICR_INTERRUPTS	IGC_TSICR_TXTS
 
-/* PTP Queue Filter */
-#define IGC_ETQF_1588		BIT(30)
-
 #define IGC_FTQF_VF_BP		0x00008000
 #define IGC_FTQF_1588_TIME_STAMP	0x08000000
 #define IGC_FTQF_MASK			0xF0000000
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 1bf016398b9d..0d746f8588c8 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -305,7 +305,6 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 	struct igc_hw *hw = &adapter->hw;
 	u32 tsync_rx_cfg = 0;
 	bool is_l4 = false;
-	bool is_l2 = false;
 	u32 regval;
 
 	/* reserved for future extensions */
@@ -346,7 +345,6 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_EVENT_V2;
 		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
-		is_l2 = true;
 		is_l4 = true;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
@@ -370,7 +368,6 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 		tsync_rx_ctl |= IGC_TSYNCRXCTL_TYPE_ALL;
 		tsync_rx_ctl |= IGC_TSYNCRXCTL_RXSYNSIG;
 		config->rx_filter = HWTSTAMP_FILTER_ALL;
-		is_l2 = true;
 		is_l4 = true;
 
 		if (hw->mac.type == igc_i225) {
@@ -405,15 +402,6 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 	/* define which PTP packets are time stamped */
 	wr32(IGC_TSYNCRXCFG, tsync_rx_cfg);
 
-	/* define ethertype filter for timestamped packets */
-	if (is_l2)
-		wr32(IGC_ETQF(3),
-		     (IGC_ETQF_FILTER_ENABLE | /* enable filter */
-		     IGC_ETQF_1588 | /* enable timestamping */
-		     ETH_P_1588)); /* 1588 eth protocol type */
-	else
-		wr32(IGC_ETQF(3), 0);
-
 	/* L4 Queue Filter[3]: filter by destination port and protocol */
 	if (is_l4) {
 		u32 ftqf = (IPPROTO_UDP /* UDP */
-- 
cgit v1.2.3


From b4d48d96eaec9bff4139dcbeb9590869fc765aa9 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 7 Apr 2020 14:07:09 -0700
Subject: igc: Fix MAX_ETYPE_FILTER value

The I225 controller has 8 ethertype filters, not 4. This patch fixes the
MAX_ETYPE_FILTER macro accordingly.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index e4169fe955d8..8389569aea8a 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -26,7 +26,7 @@ void igc_set_ethtool_ops(struct net_device *);
 #define MAX_Q_VECTORS			8
 #define MAX_STD_JUMBO_FRAME_SIZE	9216
 
-#define MAX_ETYPE_FILTER		4
+#define MAX_ETYPE_FILTER		8
 #define IGC_RETA_SIZE			128
 
 struct igc_tx_queue_stats {
-- 
cgit v1.2.3


From aa7ca7266fc49966844ac1f868085a49092b9b5d Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 7 Apr 2020 14:07:10 -0700
Subject: igc: Refactor ethertype filtering code

The whole ethertype filtering code is implemented in igc_ethtool.c and
mixes logic from ethtool and core parts. This patch refactors it so core
logic is moved to igc_main.c, aligning the ethertype filtering code
organization with the rest of the filtering code from the driver (MAC
address and VLAN priority).

Besides moving code to igc_main.c, this patch also does some minor
improvements to the code. Below are some highlights.

In case all filters are already in use and the user tries to add another
filter, we return -ENOSPC instead of -EINVAL so a more meaningful error
code is provided. This also aligns with the behavior implemented in MAC
address filtering code.

With this code refactoring, 'etype_bitmap' array in struct igc_adapter
and 'etype_reg_index' in struct igc_nfc_filter are not needed anymore
and are removed.

Log messages are added to help debugging the ethertype filtering code.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  4 +-
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 67 +++-----------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 93 ++++++++++++++++++++++++++++
 3 files changed, 103 insertions(+), 61 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 8389569aea8a..812e1cd695cf 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -189,7 +189,6 @@ struct igc_adapter {
 
 	/* lock for RX network flow classification filter */
 	spinlock_t nfc_lock;
-	bool etype_bitmap[MAX_ETYPE_FILTER];
 
 	struct igc_mac_addr *mac_table;
 
@@ -238,6 +237,8 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
 			     int queue);
 void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio);
+int igc_add_etype_filter(struct igc_adapter *adapter, u16 etype, int queue);
+int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype);
 void igc_update_stats(struct igc_adapter *adapter);
 
 /* igc_dump declarations */
@@ -466,7 +467,6 @@ struct igc_nfc_filter {
 	struct hlist_node nfc_node;
 	struct igc_nfc_input filter;
 	unsigned long cookie;
-	u16 etype_reg_index;
 	u16 sw_idx;
 	u16 action;
 };
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index c5be8b936963..3cdb88a5eb01 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1183,46 +1183,6 @@ static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_rxnfc_write_etype_filter(struct igc_adapter *adapter,
-					struct igc_nfc_filter *input)
-{
-	struct igc_hw *hw = &adapter->hw;
-	u8 i;
-	u32 etqf;
-	u16 etype;
-
-	/* find an empty etype filter register */
-	for (i = 0; i < MAX_ETYPE_FILTER; ++i) {
-		if (!adapter->etype_bitmap[i])
-			break;
-	}
-	if (i == MAX_ETYPE_FILTER) {
-		netdev_err(adapter->netdev,
-			   "ethtool -N: etype filters are all used\n");
-		return -EINVAL;
-	}
-
-	adapter->etype_bitmap[i] = true;
-
-	etqf = rd32(IGC_ETQF(i));
-	etype = ntohs(input->filter.etype & ETHER_TYPE_FULL_MASK);
-
-	etqf |= IGC_ETQF_FILTER_ENABLE;
-	etqf &= ~IGC_ETQF_ETYPE_MASK;
-	etqf |= (etype & IGC_ETQF_ETYPE_MASK);
-
-	etqf &= ~IGC_ETQF_QUEUE_MASK;
-	etqf |= ((input->action << IGC_ETQF_QUEUE_SHIFT)
-		& IGC_ETQF_QUEUE_MASK);
-	etqf |= IGC_ETQF_QUEUE_ENABLE;
-
-	wr32(IGC_ETQF(i), etqf);
-
-	input->etype_reg_index = i;
-
-	return 0;
-}
-
 int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 {
 	struct igc_hw *hw = &adapter->hw;
@@ -1236,7 +1196,9 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		err = igc_rxnfc_write_etype_filter(adapter, input);
+		u16 etype = ntohs(input->filter.etype);
+
+		err = igc_add_etype_filter(adapter, etype, input->action);
 		if (err)
 			return err;
 	}
@@ -1267,26 +1229,13 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	return 0;
 }
 
-static void igc_clear_etype_filter_regs(struct igc_adapter *adapter,
-					u16 reg_index)
-{
-	struct igc_hw *hw = &adapter->hw;
-	u32 etqf = rd32(IGC_ETQF(reg_index));
-
-	etqf &= ~IGC_ETQF_QUEUE_ENABLE;
-	etqf &= ~IGC_ETQF_QUEUE_MASK;
-	etqf &= ~IGC_ETQF_FILTER_ENABLE;
-
-	wr32(IGC_ETQF(reg_index), etqf);
-
-	adapter->etype_bitmap[reg_index] = false;
-}
-
 int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 {
-	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
-		igc_clear_etype_filter_regs(adapter,
-					    input->etype_reg_index);
+	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		u16 etype = ntohs(input->filter.etype);
+
+		igc_del_etype_filter(adapter, etype);
+	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
 		int prio = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) >>
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 7e59c0393dbc..0df5617eb9d0 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2366,6 +2366,99 @@ void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio)
 		   prio);
 }
 
+static int igc_get_avail_etype_filter_slot(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int i;
+
+	for (i = 0; i < MAX_ETYPE_FILTER; i++) {
+		u32 etqf = rd32(IGC_ETQF(i));
+
+		if (!(etqf & IGC_ETQF_FILTER_ENABLE))
+			return i;
+	}
+
+	return -1;
+}
+
+/**
+ * igc_add_etype_filter() - Add ethertype filter
+ * @adapter: Pointer to adapter where the filter should be added
+ * @etype: Ethertype value
+ * @queue: If non-negative, queue assignment feature is enabled and frames
+ *         matching the filter are enqueued onto 'queue'. Otherwise, queue
+ *         assignment is disabled.
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
+ */
+int igc_add_etype_filter(struct igc_adapter *adapter, u16 etype, int queue)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int index;
+	u32 etqf;
+
+	index = igc_get_avail_etype_filter_slot(adapter);
+	if (index < 0)
+		return -ENOSPC;
+
+	etqf = rd32(IGC_ETQF(index));
+
+	etqf &= ~IGC_ETQF_ETYPE_MASK;
+	etqf |= etype;
+
+	if (queue >= 0) {
+		etqf &= ~IGC_ETQF_QUEUE_MASK;
+		etqf |= (queue << IGC_ETQF_QUEUE_SHIFT);
+		etqf |= IGC_ETQF_QUEUE_ENABLE;
+	}
+
+	etqf |= IGC_ETQF_FILTER_ENABLE;
+
+	wr32(IGC_ETQF(index), etqf);
+
+	netdev_dbg(adapter->netdev, "Add ethertype filter: etype %04x queue %d\n",
+		   etype, queue);
+	return 0;
+}
+
+static int igc_find_etype_filter(struct igc_adapter *adapter, u16 etype)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int i;
+
+	for (i = 0; i < MAX_ETYPE_FILTER; i++) {
+		u32 etqf = rd32(IGC_ETQF(i));
+
+		if ((etqf & IGC_ETQF_ETYPE_MASK) == etype)
+			return i;
+	}
+
+	return -1;
+}
+
+/**
+ * igc_del_etype_filter() - Delete ethertype filter
+ * @adapter: Pointer to adapter where the filter should be deleted from
+ * @etype: Ethertype value
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
+ */
+int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int index;
+
+	index = igc_find_etype_filter(adapter, etype);
+	if (index < 0)
+		return -ENOENT;
+
+	wr32(IGC_ETQF(index), 0);
+
+	netdev_dbg(adapter->netdev, "Delete ethertype filter: etype %04x\n",
+		   etype);
+	return 0;
+}
+
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
-- 
cgit v1.2.3


From 81e330619e45fac4abeb01be1eb88f18c53aad46 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 7 Apr 2020 14:07:11 -0700
Subject: igc: Dump ETQF registers

This patch adds the EType Queue Filter (ETQF) registers to the list of
registers dumped by igc_get_regs().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 3cdb88a5eb01..c6586e2be3a8 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -318,6 +318,9 @@ static void igc_get_regs(struct net_device *netdev,
 		regs_buff[188 + i] = rd32(IGC_RAH(i));
 
 	regs_buff[204] = rd32(IGC_VLANPQF);
+
+	for (i = 0; i < 8; i++)
+		regs_buff[205 + i] = rd32(IGC_ETQF(i));
 }
 
 static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
-- 
cgit v1.2.3


From 551555a7614abda5db60221c012d6c19a7a2d016 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 12 Apr 2020 09:28:29 +0300
Subject: igc: Remove unused IGC_ICS_DRSTA define

Device reset assert for interrupt cause register not in
use for i225 device.
This patch comes to clean up this define.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 6909826bc747..51d8a15e239c 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -244,7 +244,6 @@
 /* Interrupt Cause Set */
 #define IGC_ICS_LSC		IGC_ICR_LSC       /* Link Status Change */
 #define IGC_ICS_RXDMT0		IGC_ICR_RXDMT0    /* rx desc min. threshold */
-#define IGC_ICS_DRSTA		IGC_ICR_DRSTA     /* Device Reset Aserted */
 
 #define IGC_ICR_DOUTSYNC	0x10000000 /* NIC DMA out of sync */
 #define IGC_EITR_CNT_IGNR	0x80000000 /* Don't reset counters on write */
-- 
cgit v1.2.3


From e5264212eb622fbc5704571c8e490c2b5fc718b9 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 12 Apr 2020 17:21:58 +0300
Subject: igc: Remove unused registers

Tx data FIFO Head/Tail, Saved and Packet Count registers
not applicable for i225 LAN controller.
This patch comes to clean up these registers.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_dump.c | 4 ----
 drivers/net/ethernet/intel/igc/igc_regs.h | 5 -----
 2 files changed, 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c
index 4ad32d98f77f..4b9ec7d0b727 100644
--- a/drivers/net/ethernet/intel/igc/igc_dump.c
+++ b/drivers/net/ethernet/intel/igc/igc_dump.c
@@ -35,10 +35,6 @@ static const struct igc_reg_info igc_reg_info_tbl[] = {
 	{IGC_TDH(0), "TDH"},
 	{IGC_TDT(0), "TDT"},
 	{IGC_TXDCTL(0), "TXDCTL"},
-	{IGC_TDFH, "TDFH"},
-	{IGC_TDFT, "TDFT"},
-	{IGC_TDFHS, "TDFHS"},
-	{IGC_TDFPC, "TDFPC"},
 
 	/* List Terminator */
 	{}
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 763a24d52865..61db951f0947 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -17,11 +17,6 @@
 /* Internal Packet Buffer Size Registers */
 #define IGC_RXPBS		0x02404  /* Rx Packet Buffer Size - RW */
 #define IGC_TXPBS		0x03404  /* Tx Packet Buffer Size - RW */
-#define IGC_TDFH		0x03410  /* Tx Data FIFO Head - RW */
-#define IGC_TDFT		0x03418  /* Tx Data FIFO Tail - RW */
-#define IGC_TDFHS		0x03420  /* Tx Data FIFO Head Saved - RW */
-#define IGC_TDFTS		0x03428  /* Tx Data FIFO Tail Saved - RW */
-#define IGC_TDFPC		0x03430  /* Tx Data FIFO Packet Count - RW */
 
 /* NVM  Register Descriptions */
 #define IGC_EERD		0x12014  /* EEprom mode read - RW */
-- 
cgit v1.2.3


From 1c3739cb6e7ac5b5372438bf91b3d0404d18ecf9 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 10 Apr 2020 17:28:31 -0700
Subject: igc: Remove IGC_MAC_STATE_SRC_ADDR flag

MAC address filters based on source address are not currently supported
by the IGC driver. Despite of that, the driver have some dangling code
to handle it, inherited from IGB driver. This patch removes that code to
prepare for a follow up patch that adds proper source MAC address filter
support.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  6 ++----
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 16 ++--------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 27 ++++++++-------------------
 3 files changed, 12 insertions(+), 37 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 812e1cd695cf..885998d3f62e 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -231,9 +231,8 @@ bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
 int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const s8 queue, const u8 flags);
-int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const u8 flags);
+		       const s8 queue);
+int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr);
 int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
 			     int queue);
 void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio);
@@ -479,7 +478,6 @@ struct igc_mac_addr {
 
 #define IGC_MAC_STATE_DEFAULT		0x1
 #define IGC_MAC_STATE_IN_USE		0x2
-#define IGC_MAC_STATE_SRC_ADDR		0x4
 
 #define IGC_MAX_RXNFC_FILTERS		16
 
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index c6586e2be3a8..09d0305a5902 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1208,15 +1208,7 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
 		err = igc_add_mac_filter(adapter, input->filter.dst_addr,
-					 input->action, 0);
-		if (err)
-			return err;
-	}
-
-	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-		err = igc_add_mac_filter(adapter, input->filter.src_addr,
-					 input->action,
-					 IGC_MAC_STATE_SRC_ADDR);
+					 input->action);
 		if (err)
 			return err;
 	}
@@ -1246,12 +1238,8 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 		igc_del_vlan_prio_filter(adapter, prio);
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
-		igc_del_mac_filter(adapter, input->filter.src_addr,
-				   IGC_MAC_STATE_SRC_ADDR);
-
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
-		igc_del_mac_filter(adapter, input->filter.dst_addr, 0);
+		igc_del_mac_filter(adapter, input->filter.dst_addr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 0df5617eb9d0..3242136bb47a 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2184,8 +2184,7 @@ static void igc_nfc_filter_restore(struct igc_adapter *adapter)
 	spin_unlock(&adapter->nfc_lock);
 }
 
-static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-			       u8 flags)
+static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 {
 	int max_entries = adapter->hw.mac.rar_entry_count;
 	struct igc_mac_addr *entry;
@@ -2198,9 +2197,6 @@ static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 			continue;
 		if (!ether_addr_equal(addr, entry->addr))
 			continue;
-		if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
-		    (flags & IGC_MAC_STATE_SRC_ADDR))
-			continue;
 
 		return i;
 	}
@@ -2231,23 +2227,19 @@ static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
  * @queue: If non-negative, queue assignment feature is enabled and frames
  *         matching the filter are enqueued onto 'queue'. Otherwise, queue
  *         assignment is disabled.
- * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source
- *         address
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
 int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const s8 queue, const u8 flags)
+		       const s8 queue)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
 
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
-	if (flags & IGC_MAC_STATE_SRC_ADDR)
-		return -ENOTSUPP;
 
-	index = igc_find_mac_filter(adapter, addr, flags);
+	index = igc_find_mac_filter(adapter, addr);
 	if (index >= 0)
 		goto update_queue_assignment;
 
@@ -2259,7 +2251,7 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 		   index, addr, queue);
 
 	ether_addr_copy(adapter->mac_table[index].addr, addr);
-	adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE | flags;
+	adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE;
 update_queue_assignment:
 	adapter->mac_table[index].queue = queue;
 
@@ -2271,13 +2263,10 @@ update_queue_assignment:
  * igc_del_mac_filter() - Delete MAC address filter
  * @adapter: Pointer to adapter where the filter should be deleted from
  * @addr: MAC address
- * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source
- *         address
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const u8 flags)
+int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 {
 	struct net_device *dev = adapter->netdev;
 	struct igc_mac_addr *entry;
@@ -2286,7 +2275,7 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
-	index = igc_find_mac_filter(adapter, addr, flags);
+	index = igc_find_mac_filter(adapter, addr);
 	if (index < 0)
 		return -ENOENT;
 
@@ -2463,14 +2452,14 @@ static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_add_mac_filter(adapter, addr, -1, 0);
+	return igc_add_mac_filter(adapter, addr, -1);
 }
 
 static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_del_mac_filter(adapter, addr, 0);
+	return igc_del_mac_filter(adapter, addr);
 }
 
 /**
-- 
cgit v1.2.3


From d66358cae25efbd35518d661991fce67af2945e7 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 10 Apr 2020 17:28:32 -0700
Subject: igc: Remove mac_table from igc_adapter

In igc_adapter we keep a sort of shadow copy of RAL and RAH registers.
There is not much benefit in keeping it, at the cost of maintainability,
since adding/removing MAC address filters is not hot path, and we
already keep filters information in adapter->nfc_filter_list for cleanup
and restoration purposes.

So in order to simplify the MAC address filtering code and prepare it
for source address support, this patch removes the mac_table from
igc_adapter.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         | 11 ------
 drivers/net/ethernet/intel/igc/igc_defines.h |  1 +
 drivers/net/ethernet/intel/igc/igc_main.c    | 57 ++++++++++------------------
 3 files changed, 21 insertions(+), 48 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 885998d3f62e..5ce859155396 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -190,8 +190,6 @@ struct igc_adapter {
 	/* lock for RX network flow classification filter */
 	spinlock_t nfc_lock;
 
-	struct igc_mac_addr *mac_table;
-
 	u8 rss_indir_tbl[IGC_RETA_SIZE];
 
 	unsigned long link_check_timeout;
@@ -470,15 +468,6 @@ struct igc_nfc_filter {
 	u16 action;
 };
 
-struct igc_mac_addr {
-	u8 addr[ETH_ALEN];
-	s8 queue;
-	u8 state; /* bitmask */
-};
-
-#define IGC_MAC_STATE_DEFAULT		0x1
-#define IGC_MAC_STATE_IN_USE		0x2
-
 #define IGC_MAX_RXNFC_FILTERS		16
 
 /* igc_desc_unused - calculate if we have unused descriptors */
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 51d8a15e239c..be152a93088a 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -62,6 +62,7 @@
  * (RAR[15]) for our directed address used by controllers with
  * manageability enabled, allowing us room for 15 multicast addresses.
  */
+#define IGC_RAH_RAH_MASK	0x0000FFFF
 #define IGC_RAH_QSEL_MASK	0x000C0000
 #define IGC_RAH_QSEL_SHIFT	18
 #define IGC_RAH_QSEL_ENABLE	BIT(28)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 3242136bb47a..af3092813a06 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -820,17 +820,12 @@ static void igc_clear_mac_filter_hw(struct igc_adapter *adapter, int index)
 /* Set default MAC address for the PF in the first RAR entry */
 static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 {
-	struct igc_mac_addr *mac_table = &adapter->mac_table[0];
 	struct net_device *dev = adapter->netdev;
 	u8 *addr = adapter->hw.mac.addr;
 
 	netdev_dbg(dev, "Set default MAC address filter: address %pM", addr);
 
-	ether_addr_copy(mac_table->addr, addr);
-	mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
-	mac_table->queue = -1;
-
-	igc_set_mac_filter_hw(adapter, 0, addr, mac_table->queue);
+	igc_set_mac_filter_hw(adapter, 0, addr, -1);
 }
 
 /**
@@ -2186,16 +2181,21 @@ static void igc_nfc_filter_restore(struct igc_adapter *adapter)
 
 static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 {
-	int max_entries = adapter->hw.mac.rar_entry_count;
-	struct igc_mac_addr *entry;
+	struct igc_hw *hw = &adapter->hw;
+	int max_entries = hw->mac.rar_entry_count;
+	u32 ral, rah;
 	int i;
 
 	for (i = 0; i < max_entries; i++) {
-		entry = &adapter->mac_table[i];
+		ral = rd32(IGC_RAL(i));
+		rah = rd32(IGC_RAH(i));
 
-		if (!(entry->state & IGC_MAC_STATE_IN_USE))
+		if (!(rah & IGC_RAH_AV))
 			continue;
-		if (!ether_addr_equal(addr, entry->addr))
+		if ((rah & IGC_RAH_RAH_MASK) !=
+		    le16_to_cpup((__le16 *)(addr + 4)))
+			continue;
+		if (ral != le32_to_cpup((__le32 *)(addr)))
 			continue;
 
 		return i;
@@ -2206,14 +2206,15 @@ static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 
 static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
 {
-	int max_entries = adapter->hw.mac.rar_entry_count;
-	struct igc_mac_addr *entry;
+	struct igc_hw *hw = &adapter->hw;
+	int max_entries = hw->mac.rar_entry_count;
+	u32 rah;
 	int i;
 
 	for (i = 0; i < max_entries; i++) {
-		entry = &adapter->mac_table[i];
+		rah = rd32(IGC_RAH(i));
 
-		if (!(entry->state & IGC_MAC_STATE_IN_USE))
+		if (!(rah & IGC_RAH_AV))
 			return i;
 	}
 
@@ -2241,7 +2242,7 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 
 	index = igc_find_mac_filter(adapter, addr);
 	if (index >= 0)
-		goto update_queue_assignment;
+		goto update_filter;
 
 	index = igc_get_avail_mac_filter_slot(adapter);
 	if (index < 0)
@@ -2250,11 +2251,7 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	netdev_dbg(dev, "Add MAC address filter: index %d address %pM queue %d",
 		   index, addr, queue);
 
-	ether_addr_copy(adapter->mac_table[index].addr, addr);
-	adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE;
-update_queue_assignment:
-	adapter->mac_table[index].queue = queue;
-
+update_filter:
 	igc_set_mac_filter_hw(adapter, index, addr, queue);
 	return 0;
 }
@@ -2269,7 +2266,6 @@ update_queue_assignment:
 int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 {
 	struct net_device *dev = adapter->netdev;
-	struct igc_mac_addr *entry;
 	int index;
 
 	if (!is_valid_ether_addr(addr))
@@ -2279,24 +2275,18 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 	if (index < 0)
 		return -ENOENT;
 
-	entry = &adapter->mac_table[index];
-
-	if (entry->state & IGC_MAC_STATE_DEFAULT) {
+	if (index == 0) {
 		/* If this is the default filter, we don't actually delete it.
 		 * We just reset to its default value i.e. disable queue
 		 * assignment.
 		 */
 		netdev_dbg(dev, "Disable default MAC filter queue assignment");
 
-		entry->queue = -1;
-		igc_set_mac_filter_hw(adapter, 0, addr, entry->queue);
+		igc_set_mac_filter_hw(adapter, 0, addr, -1);
 	} else {
 		netdev_dbg(dev, "Delete MAC address filter: index %d address %pM",
 			   index, addr);
 
-		entry->state = 0;
-		entry->queue = -1;
-		memset(entry->addr, 0, ETH_ALEN);
 		igc_clear_mac_filter_hw(adapter, index);
 	}
 
@@ -3404,8 +3394,6 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
 
-	int size = sizeof(struct igc_mac_addr) * hw->mac.rar_entry_count;
-
 	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
 
 	/* set default ring sizes */
@@ -3429,10 +3417,6 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	/* Assume MSI-X interrupts, will be checked during IRQ allocation */
 	adapter->flags |= IGC_FLAG_HAS_MSIX;
 
-	adapter->mac_table = kzalloc(size, GFP_ATOMIC);
-	if (!adapter->mac_table)
-		return -ENOMEM;
-
 	igc_init_queue_configuration(adapter);
 
 	/* This call may decrease the number of queues */
@@ -5135,7 +5119,6 @@ static void igc_remove(struct pci_dev *pdev)
 	pci_iounmap(pdev, adapter->io_addr);
 	pci_release_mem_regions(pdev);
 
-	kfree(adapter->mac_table);
 	free_netdev(netdev);
 
 	pci_disable_pcie_error_reporting(pdev);
-- 
cgit v1.2.3


From 750433d0aa097265432a2b30a8a984604bd76e7f Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 10 Apr 2020 17:28:33 -0700
Subject: igc: Add support for source address filters in core

This patch extends MAC address filter internal APIs igc_add_mac_filter()
and igc_del_mac_filter(), as well as local helpers, to support filters
based on source address.

A new parameters 'type' is added to the APIs to indicate if the filter
type is source or destination. In case it is source type, the RAH
register is configured accordingly in igc_set_mac_filter_hw().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         | 13 ++++++--
 drivers/net/ethernet/intel/igc/igc_defines.h |  2 ++
 drivers/net/ethernet/intel/igc/igc_ethtool.c |  6 ++--
 drivers/net/ethernet/intel/igc/igc_main.c    | 49 +++++++++++++++++++---------
 4 files changed, 49 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 5ce859155396..b501be243536 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -29,6 +29,11 @@ void igc_set_ethtool_ops(struct net_device *);
 #define MAX_ETYPE_FILTER		8
 #define IGC_RETA_SIZE			128
 
+enum igc_mac_filter_type {
+	IGC_MAC_FILTER_TYPE_DST = 0,
+	IGC_MAC_FILTER_TYPE_SRC
+};
+
 struct igc_tx_queue_stats {
 	u64 packets;
 	u64 bytes;
@@ -228,9 +233,11 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
 bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
-int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const s8 queue);
-int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr);
+int igc_add_mac_filter(struct igc_adapter *adapter,
+		       enum igc_mac_filter_type type, const u8 *addr,
+		       int queue);
+int igc_del_mac_filter(struct igc_adapter *adapter,
+		       enum igc_mac_filter_type type, const u8 *addr);
 int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
 			     int queue);
 void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio);
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index be152a93088a..45b567587ca9 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -63,6 +63,8 @@
  * manageability enabled, allowing us room for 15 multicast addresses.
  */
 #define IGC_RAH_RAH_MASK	0x0000FFFF
+#define IGC_RAH_ASEL_MASK	0x00030000
+#define IGC_RAH_ASEL_SRC_ADDR	BIT(16)
 #define IGC_RAH_QSEL_MASK	0x000C0000
 #define IGC_RAH_QSEL_SHIFT	18
 #define IGC_RAH_QSEL_ENABLE	BIT(28)
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 09d0305a5902..6c27046a852d 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1207,7 +1207,8 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
-		err = igc_add_mac_filter(adapter, input->filter.dst_addr,
+		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
+					 input->filter.dst_addr,
 					 input->action);
 		if (err)
 			return err;
@@ -1239,7 +1240,8 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	}
 
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
-		igc_del_mac_filter(adapter, input->filter.dst_addr);
+		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
+				   input->filter.dst_addr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index af3092813a06..398a9307af2b 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -766,12 +766,14 @@ static void igc_setup_tctl(struct igc_adapter *adapter)
  * igc_set_mac_filter_hw() - Set MAC address filter in hardware
  * @adapter: Pointer to adapter where the filter should be set
  * @index: Filter index
- * @addr: Destination MAC address
+ * @type: MAC address filter type (source or destination)
+ * @addr: MAC address
  * @queue: If non-negative, queue assignment feature is enabled and frames
  *         matching the filter are enqueued onto 'queue'. Otherwise, queue
  *         assignment is disabled.
  */
 static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
+				  enum igc_mac_filter_type type,
 				  const u8 *addr, int queue)
 {
 	struct net_device *dev = adapter->netdev;
@@ -784,6 +786,11 @@ static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index,
 	ral = le32_to_cpup((__le32 *)(addr));
 	rah = le16_to_cpup((__le16 *)(addr + 4));
 
+	if (type == IGC_MAC_FILTER_TYPE_SRC) {
+		rah &= ~IGC_RAH_ASEL_MASK;
+		rah |= IGC_RAH_ASEL_SRC_ADDR;
+	}
+
 	if (queue >= 0) {
 		rah &= ~IGC_RAH_QSEL_MASK;
 		rah |= (queue << IGC_RAH_QSEL_SHIFT);
@@ -825,7 +832,7 @@ static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 
 	netdev_dbg(dev, "Set default MAC address filter: address %pM", addr);
 
-	igc_set_mac_filter_hw(adapter, 0, addr, -1);
+	igc_set_mac_filter_hw(adapter, 0, IGC_MAC_FILTER_TYPE_DST, addr, -1);
 }
 
 /**
@@ -2179,7 +2186,8 @@ static void igc_nfc_filter_restore(struct igc_adapter *adapter)
 	spin_unlock(&adapter->nfc_lock);
 }
 
-static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr)
+static int igc_find_mac_filter(struct igc_adapter *adapter,
+			       enum igc_mac_filter_type type, const u8 *addr)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int max_entries = hw->mac.rar_entry_count;
@@ -2192,6 +2200,8 @@ static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 
 		if (!(rah & IGC_RAH_AV))
 			continue;
+		if (!!(rah & IGC_RAH_ASEL_SRC_ADDR) != type)
+			continue;
 		if ((rah & IGC_RAH_RAH_MASK) !=
 		    le16_to_cpup((__le16 *)(addr + 4)))
 			continue;
@@ -2224,6 +2234,7 @@ static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
 /**
  * igc_add_mac_filter() - Add MAC address filter
  * @adapter: Pointer to adapter where the filter should be added
+ * @type: MAC address filter type (source or destination)
  * @addr: MAC address
  * @queue: If non-negative, queue assignment feature is enabled and frames
  *         matching the filter are enqueued onto 'queue'. Otherwise, queue
@@ -2231,8 +2242,9 @@ static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
-		       const s8 queue)
+int igc_add_mac_filter(struct igc_adapter *adapter,
+		       enum igc_mac_filter_type type, const u8 *addr,
+		       int queue)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
@@ -2240,7 +2252,7 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
-	index = igc_find_mac_filter(adapter, addr);
+	index = igc_find_mac_filter(adapter, type, addr);
 	if (index >= 0)
 		goto update_filter;
 
@@ -2248,22 +2260,25 @@ int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr,
 	if (index < 0)
 		return -ENOSPC;
 
-	netdev_dbg(dev, "Add MAC address filter: index %d address %pM queue %d",
-		   index, addr, queue);
+	netdev_dbg(dev, "Add MAC address filter: index %d type %s address %pM queue %d\n",
+		   index, type == IGC_MAC_FILTER_TYPE_DST ? "dst" : "src",
+		   addr, queue);
 
 update_filter:
-	igc_set_mac_filter_hw(adapter, index, addr, queue);
+	igc_set_mac_filter_hw(adapter, index, type, addr, queue);
 	return 0;
 }
 
 /**
  * igc_del_mac_filter() - Delete MAC address filter
  * @adapter: Pointer to adapter where the filter should be deleted from
+ * @type: MAC address filter type (source or destination)
  * @addr: MAC address
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
+int igc_del_mac_filter(struct igc_adapter *adapter,
+		       enum igc_mac_filter_type type, const u8 *addr)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
@@ -2271,7 +2286,7 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
 
-	index = igc_find_mac_filter(adapter, addr);
+	index = igc_find_mac_filter(adapter, type, addr);
 	if (index < 0)
 		return -ENOENT;
 
@@ -2282,10 +2297,12 @@ int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr)
 		 */
 		netdev_dbg(dev, "Disable default MAC filter queue assignment");
 
-		igc_set_mac_filter_hw(adapter, 0, addr, -1);
+		igc_set_mac_filter_hw(adapter, 0, type, addr, -1);
 	} else {
-		netdev_dbg(dev, "Delete MAC address filter: index %d address %pM",
-			   index, addr);
+		netdev_dbg(dev, "Delete MAC address filter: index %d type %s address %pM\n",
+			   index,
+			   type == IGC_MAC_FILTER_TYPE_DST ? "dst" : "src",
+			   addr);
 
 		igc_clear_mac_filter_hw(adapter, index);
 	}
@@ -2442,14 +2459,14 @@ static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_add_mac_filter(adapter, addr, -1);
+	return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, addr, -1);
 }
 
 static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_del_mac_filter(adapter, addr);
+	return igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, addr);
 }
 
 /**
-- 
cgit v1.2.3


From 8eb2449d839079f979eded636dabcd6b815ff28f Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Mon, 13 Apr 2020 09:00:50 -0700
Subject: igc: Enable NFC rules based source MAC address

This patch adds support for Network Flow Classification (NFC) rules
based on source MAC address. Note that the controller doesn't support
rules with both source and destination addresses set, so this special
case is checked in igc_add_ethtool_nfc_entry().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 32 +++++++++++++++++++---------
 1 file changed, 22 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 6c27046a852d..42ecb493c1a2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1188,16 +1188,8 @@ static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
 
 int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 {
-	struct igc_hw *hw = &adapter->hw;
 	int err = -EINVAL;
 
-	if (hw->mac.type == igc_i225 &&
-	    !(input->filter.match_flags & ~IGC_FILTER_FLAG_SRC_MAC_ADDR)) {
-		netdev_err(adapter->netdev,
-			   "i225 doesn't support flow classification rules specifying only source addresses\n");
-		return -EOPNOTSUPP;
-	}
-
 	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
 		u16 etype = ntohs(input->filter.etype);
 
@@ -1206,6 +1198,14 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 			return err;
 	}
 
+	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
+					 input->filter.src_addr,
+					 input->action);
+		if (err)
+			return err;
+	}
+
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
 		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
 					 input->filter.dst_addr,
@@ -1239,6 +1239,10 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 		igc_del_vlan_prio_filter(adapter, prio);
 	}
 
+	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
+				   input->filter.src_addr);
+
 	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
 		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
 				   input->filter.dst_addr);
@@ -1334,20 +1338,28 @@ static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
 		input->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
 	}
 
-	/* Only support matching addresses by the full mask */
+	/* Both source and destination address filters only support the full
+	 * mask.
+	 */
 	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) {
 		input->filter.match_flags |= IGC_FILTER_FLAG_SRC_MAC_ADDR;
 		ether_addr_copy(input->filter.src_addr,
 				fsp->h_u.ether_spec.h_source);
 	}
 
-	/* Only support matching addresses by the full mask */
 	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) {
 		input->filter.match_flags |= IGC_FILTER_FLAG_DST_MAC_ADDR;
 		ether_addr_copy(input->filter.dst_addr,
 				fsp->h_u.ether_spec.h_dest);
 	}
 
+	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
+	    input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		netdev_dbg(netdev, "Filters with both dst and src are not supported\n");
+		err = -EOPNOTSUPP;
+		goto err_out;
+	}
+
 	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
 		if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
 			netdev_dbg(netdev, "VLAN mask not supported\n");
-- 
cgit v1.2.3


From 49ee3c2ab5234757bfb56a0b3a3cb422f427e3a3 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Date: Fri, 17 Apr 2020 09:35:31 -0700
Subject: e1000: Do not perform reset in reset_task if we are already down

We are seeing a deadlock in e1000 down when NAPI is being disabled. Looking
over the kernel function trace of the system it appears that the interface
is being closed and then a reset is hitting which deadlocks the interface
as the NAPI interface is already disabled.

To prevent this from happening I am disabling the reset task when
__E1000_DOWN is already set. In addition code has been added so that we set
the __E1000_DOWN while holding the __E1000_RESET flag in e1000_close in
order to guarantee that the reset task will not run after we have started
the close call.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Tested-by: Maxim Zhukov <mussitantesmortem@gmail.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 05bc6e216bca..d9fa4600f745 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -542,8 +542,13 @@ void e1000_reinit_locked(struct e1000_adapter *adapter)
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
-	e1000_down(adapter);
-	e1000_up(adapter);
+
+	/* only run the task if not already down */
+	if (!test_bit(__E1000_DOWN, &adapter->flags)) {
+		e1000_down(adapter);
+		e1000_up(adapter);
+	}
+
 	clear_bit(__E1000_RESETTING, &adapter->flags);
 }
 
@@ -1433,10 +1438,15 @@ int e1000_close(struct net_device *netdev)
 	struct e1000_hw *hw = &adapter->hw;
 	int count = E1000_CHECK_RESET_COUNT;
 
-	while (test_bit(__E1000_RESETTING, &adapter->flags) && count--)
+	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags) && count--)
 		usleep_range(10000, 20000);
 
-	WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
+	WARN_ON(count < 0);
+
+	/* signal that we're down so that the reset task will no longer run */
+	set_bit(__E1000_DOWN, &adapter->flags);
+	clear_bit(__E1000_RESETTING, &adapter->flags);
+
 	e1000_down(adapter);
 	e1000_power_down_phy(adapter);
 	e1000_free_irq(adapter);
-- 
cgit v1.2.3


From 3b5fc88f78ea5bc6d2da06c6acff8fe6ba0e7e40 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Mon, 20 Apr 2020 14:38:53 +0300
Subject: igc: Remove obsolete circuit breaker registers

Part of circuit breaker registers is obsolete
and not applicable for i225 device.
This patch comes to clean up these registers.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.c  | 4 ----
 drivers/net/ethernet/intel/igc/igc_regs.h | 7 -------
 2 files changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index 12aa6b5fcb5d..89445ab02a98 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -307,12 +307,8 @@ void igc_clear_hw_cntrs_base(struct igc_hw *hw)
 	rd32(IGC_ICTXQMTC);
 	rd32(IGC_ICRXDMTC);
 
-	rd32(IGC_CBTMPC);
-	rd32(IGC_HTDPMC);
-	rd32(IGC_CBRMPC);
 	rd32(IGC_RPTHC);
 	rd32(IGC_HGPTC);
-	rd32(IGC_HTCBDPC);
 	rd32(IGC_HGORCL);
 	rd32(IGC_HGORCH);
 	rd32(IGC_HGOTCL);
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 61db951f0947..f2654f379d88 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -68,13 +68,6 @@
 #define IGC_ICRXDMTC		0x04120  /* Rx Descriptor Min Threshold Count */
 #define IGC_ICRXOC		0x04124  /* Receiver Overrun Count */
 
-#define IGC_CBTMPC		0x0402C  /* Circuit Breaker TX Packet Count */
-#define IGC_HTDPMC		0x0403C  /* Host Transmit Discarded Packets */
-#define IGC_CBRMPC		0x040FC  /* Circuit Breaker RX Packet Count */
-#define IGC_RPTHC		0x04104  /* Rx Packets To Host */
-#define IGC_HGPTC		0x04118  /* Host Good Packets TX Count */
-#define IGC_HTCBDPC		0x04124  /* Host TX Circ.Breaker Drop Count */
-
 /* MSI-X Table Register Descriptions */
 #define IGC_PBACL		0x05B68  /* MSIx PBA Clear - R/W 1 to clear */
 
-- 
cgit v1.2.3


From d1fe569f517e8ee402f5faac28e65c3a72790d0e Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 22 Apr 2020 11:41:55 +0300
Subject: igc: Remove header redirection register

Header redirection missed packet counter not applicable for i225 device.
This patch comes to clean up this register.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_regs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index f2654f379d88..79bd104363ed 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -199,7 +199,6 @@
 #define IGC_HGOTCL	0x04130  /* Host Good Octets Transmit Count Low */
 #define IGC_HGOTCH	0x04134  /* Host Good Octets Transmit Count High */
 #define IGC_LENERRS	0x04138  /* Length Errors Count */
-#define IGC_HRMPC	0x0A018  /* Header Redirection Missed Packet Count */
 
 /* Time sync registers */
 #define IGC_TSICR	0x0B66C  /* Time Sync Interrupt Cause */
-- 
cgit v1.2.3


From 281380a6fd8a202635c484c5ac978c468c006cbd Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 22 Apr 2020 13:46:47 +0300
Subject: igc: Remove per queue good transmited counter register

Per queue good transmitted packet counter not applicable for i225 device.
This patch comes to clean up this register.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_regs.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 79bd104363ed..7f999cfc9b39 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -124,9 +124,6 @@
 #define IGC_MMDAC		13 /* MMD Access Control */
 #define IGC_MMDAAD		14 /* MMD Access Address/Data */
 
-/* Good transmitted packets counter registers */
-#define IGC_PQGPTC(_n)		(0x010014 + (0x100 * (_n)))
-
 /* Statistics Register Descriptions */
 #define IGC_CRCERRS	0x04000  /* CRC Error Count - R/clr */
 #define IGC_ALGNERRC	0x04004  /* Alignment Error Count - R/clr */
-- 
cgit v1.2.3


From 8e34cad1677a45211d5112ea2bab770656139d20 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:05 -0700
Subject: igc: Remove unused field from igc_nfc_filter

The 'cookie' field is not used anywhere in the code so this patch
removes it from struct igc_nfc_filter.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index b501be243536..7c92fc7703be 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -470,7 +470,6 @@ struct igc_nfc_input {
 struct igc_nfc_filter {
 	struct hlist_node nfc_node;
 	struct igc_nfc_input filter;
-	unsigned long cookie;
 	u16 sw_idx;
 	u16 action;
 };
-- 
cgit v1.2.3


From 4d0710c241dddf0db62b4be533347d3acd9e8c96 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:06 -0700
Subject: igc: Get rid of igc_max_channels()

The local function igc_max_channels() is a pointless wrapper around
igc_get_max_rss_queues(). This patch removes it and updates the callers
accordingly. It also does some cleanup on igc_get_max_rss_queues().

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 9 ++-------
 drivers/net/ethernet/intel/igc/igc_main.c    | 7 +------
 2 files changed, 3 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 42ecb493c1a2..9081f36ee1f7 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1508,18 +1508,13 @@ static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
 	return 0;
 }
 
-static unsigned int igc_max_channels(struct igc_adapter *adapter)
-{
-	return igc_get_max_rss_queues(adapter);
-}
-
 static void igc_get_channels(struct net_device *netdev,
 			     struct ethtool_channels *ch)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
 	/* Report maximum channels */
-	ch->max_combined = igc_max_channels(adapter);
+	ch->max_combined = igc_get_max_rss_queues(adapter);
 
 	/* Report info for other vector */
 	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
@@ -1546,7 +1541,7 @@ static int igc_set_channels(struct net_device *netdev,
 		return -EINVAL;
 
 	/* Verify the number of channels doesn't exceed hw limits */
-	max_combined = igc_max_channels(adapter);
+	max_combined = igc_get_max_rss_queues(adapter);
 	if (count > max_combined)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 398a9307af2b..843e8a2aaf24 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2731,12 +2731,7 @@ void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
 
 unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
 {
-	unsigned int max_rss_queues;
-
-	/* Determine the maximum number of RSS queues supported. */
-	max_rss_queues = IGC_MAX_RX_QUEUES;
-
-	return max_rss_queues;
+	return IGC_MAX_RX_QUEUES;
 }
 
 static void igc_init_queue_configuration(struct igc_adapter *adapter)
-- 
cgit v1.2.3


From 8b9c23cdf04f927d591f3fbc3b846d941557e886 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:07 -0700
Subject: igc: Cleanup _get|set_rxnfc ethtool ops

This patch does a trivial change in igc_ethtool_get_rxnfc() and
igc_ethtool_set_rxnfc() to simplify their logic.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 33 +++++++++-------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 9081f36ee1f7..37fb5f0544ad 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1055,31 +1055,23 @@ static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 			 u32 *rule_locs)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
 		cmd->data = adapter->num_rx_queues;
-		ret = 0;
-		break;
+		return 0;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = adapter->nfc_filter_count;
-		ret = 0;
-		break;
+		return 0;
 	case ETHTOOL_GRXCLSRULE:
-		ret = igc_get_ethtool_nfc_entry(adapter, cmd);
-		break;
+		return igc_get_ethtool_nfc_entry(adapter, cmd);
 	case ETHTOOL_GRXCLSRLALL:
-		ret = igc_get_ethtool_nfc_all(adapter, cmd, rule_locs);
-		break;
+		return igc_get_ethtool_nfc_all(adapter, cmd, rule_locs);
 	case ETHTOOL_GRXFH:
-		ret = igc_get_rss_hash_opts(adapter, cmd);
-		break;
+		return igc_get_rss_hash_opts(adapter, cmd);
 	default:
-		break;
+		return -EOPNOTSUPP;
 	}
-
-	return ret;
 }
 
 #define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \
@@ -1418,22 +1410,17 @@ static int igc_del_ethtool_nfc_entry(struct igc_adapter *adapter,
 static int igc_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
-	int ret = -EOPNOTSUPP;
 
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXFH:
-		ret = igc_set_rss_hash_opt(adapter, cmd);
-		break;
+		return igc_set_rss_hash_opt(adapter, cmd);
 	case ETHTOOL_SRXCLSRLINS:
-		ret = igc_add_ethtool_nfc_entry(adapter, cmd);
-		break;
+		return igc_add_ethtool_nfc_entry(adapter, cmd);
 	case ETHTOOL_SRXCLSRLDEL:
-		ret = igc_del_ethtool_nfc_entry(adapter, cmd);
+		return igc_del_ethtool_nfc_entry(adapter, cmd);
 	default:
-		break;
+		return -EOPNOTSUPP;
 	}
-
-	return ret;
 }
 
 void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
-- 
cgit v1.2.3


From 876ea04db7675391baa8011795188e55d154aa4e Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:08 -0700
Subject: igc: Early return in igc_get_ethtool_nfc_entry()

This patch re-writes the second half of igc_ethtool_get_nfc_entry() to
follow the 'return early' pattern seen in other parts of the driver and
removes some duplicate comments.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 58 ++++++++++++++--------------
 1 file changed, 28 insertions(+), 30 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 37fb5f0544ad..f03093d1f863 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -945,38 +945,36 @@ static int igc_get_ethtool_nfc_entry(struct igc_adapter *adapter,
 	if (!rule || fsp->location != rule->sw_idx)
 		return -EINVAL;
 
-	if (rule->filter.match_flags) {
-		fsp->flow_type = ETHER_FLOW;
-		fsp->ring_cookie = rule->action;
-		if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-			fsp->h_u.ether_spec.h_proto = rule->filter.etype;
-			fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
-		}
-		if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-			fsp->flow_type |= FLOW_EXT;
-			fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
-			fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
-		}
-		if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
-			ether_addr_copy(fsp->h_u.ether_spec.h_dest,
-					rule->filter.dst_addr);
-			/* As we only support matching by the full
-			 * mask, return the mask to userspace
-			 */
-			eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
-		}
-		if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-			ether_addr_copy(fsp->h_u.ether_spec.h_source,
-					rule->filter.src_addr);
-			/* As we only support matching by the full
-			 * mask, return the mask to userspace
-			 */
-			eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
-		}
+	if (!rule->filter.match_flags)
+		return -EINVAL;
 
-		return 0;
+	fsp->flow_type = ETHER_FLOW;
+	fsp->ring_cookie = rule->action;
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		fsp->h_u.ether_spec.h_proto = rule->filter.etype;
+		fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
 	}
-	return -EINVAL;
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		fsp->flow_type |= FLOW_EXT;
+		fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
+		fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+		ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+				rule->filter.dst_addr);
+		eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		ether_addr_copy(fsp->h_u.ether_spec.h_source,
+				rule->filter.src_addr);
+		eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
+	}
+
+	return 0;
 }
 
 static int igc_get_ethtool_nfc_all(struct igc_adapter *adapter,
-- 
cgit v1.2.3


From 7df76bd1918188c80ee0bb2e849756d07ce71507 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:09 -0700
Subject: igc: Add 'igc_ethtool_' prefix to functions in igc_ethtool.c

This patch adds the prefix 'igc_ethtool_' to all functions defined in
igc_ethtool.c so they align with the name convention already followed by
other parts of the driver (e.g. igc_tsn, igc_ptp). Also, this avoids
some name clashing with functions added to igc_main.c by upcoming
patches in this series. No functionality is changed by this patch, just
function renaming.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |   3 +-
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 215 ++++++++++++++-------------
 drivers/net/ethernet/intel/igc/igc_main.c    |   2 +-
 3 files changed, 112 insertions(+), 108 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 7c92fc7703be..359ac40908f6 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -16,8 +16,7 @@
 
 #include "igc_hw.h"
 
-/* forward declaration */
-void igc_set_ethtool_ops(struct net_device *);
+void igc_ethtool_set_ops(struct net_device *);
 
 /* Transmit and receive queues */
 #define IGC_MAX_RX_QUEUES		4
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index f03093d1f863..0399ca1d7d0c 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -124,8 +124,8 @@ static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = {
 
 #define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings)
 
-static void igc_get_drvinfo(struct net_device *netdev,
-			    struct ethtool_drvinfo *drvinfo)
+static void igc_ethtool_get_drvinfo(struct net_device *netdev,
+				    struct ethtool_drvinfo *drvinfo)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -139,13 +139,13 @@ static void igc_get_drvinfo(struct net_device *netdev,
 	drvinfo->n_priv_flags = IGC_PRIV_FLAGS_STR_LEN;
 }
 
-static int igc_get_regs_len(struct net_device *netdev)
+static int igc_ethtool_get_regs_len(struct net_device *netdev)
 {
 	return IGC_REGS_LEN * sizeof(u32);
 }
 
-static void igc_get_regs(struct net_device *netdev,
-			 struct ethtool_regs *regs, void *p)
+static void igc_ethtool_get_regs(struct net_device *netdev,
+				 struct ethtool_regs *regs, void *p)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -323,7 +323,8 @@ static void igc_get_regs(struct net_device *netdev,
 		regs_buff[205 + i] = rd32(IGC_ETQF(i));
 }
 
-static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+static void igc_ethtool_get_wol(struct net_device *netdev,
+				struct ethtool_wolinfo *wol)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -354,7 +355,8 @@ static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		wol->wolopts |= WAKE_PHY;
 }
 
-static int igc_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+static int igc_ethtool_set_wol(struct net_device *netdev,
+			       struct ethtool_wolinfo *wol)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -382,21 +384,21 @@ static int igc_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
-static u32 igc_get_msglevel(struct net_device *netdev)
+static u32 igc_ethtool_get_msglevel(struct net_device *netdev)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
 	return adapter->msg_enable;
 }
 
-static void igc_set_msglevel(struct net_device *netdev, u32 data)
+static void igc_ethtool_set_msglevel(struct net_device *netdev, u32 data)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
 	adapter->msg_enable = data;
 }
 
-static int igc_nway_reset(struct net_device *netdev)
+static int igc_ethtool_nway_reset(struct net_device *netdev)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -405,7 +407,7 @@ static int igc_nway_reset(struct net_device *netdev)
 	return 0;
 }
 
-static u32 igc_get_link(struct net_device *netdev)
+static u32 igc_ethtool_get_link(struct net_device *netdev)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_mac_info *mac = &adapter->hw.mac;
@@ -422,15 +424,15 @@ static u32 igc_get_link(struct net_device *netdev)
 	return igc_has_link(adapter);
 }
 
-static int igc_get_eeprom_len(struct net_device *netdev)
+static int igc_ethtool_get_eeprom_len(struct net_device *netdev)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
 	return adapter->hw.nvm.word_size * 2;
 }
 
-static int igc_get_eeprom(struct net_device *netdev,
-			  struct ethtool_eeprom *eeprom, u8 *bytes)
+static int igc_ethtool_get_eeprom(struct net_device *netdev,
+				  struct ethtool_eeprom *eeprom, u8 *bytes)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -476,8 +478,8 @@ static int igc_get_eeprom(struct net_device *netdev,
 	return ret_val;
 }
 
-static int igc_set_eeprom(struct net_device *netdev,
-			  struct ethtool_eeprom *eeprom, u8 *bytes)
+static int igc_ethtool_set_eeprom(struct net_device *netdev,
+				  struct ethtool_eeprom *eeprom, u8 *bytes)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -544,8 +546,8 @@ static int igc_set_eeprom(struct net_device *netdev,
 	return ret_val;
 }
 
-static void igc_get_ringparam(struct net_device *netdev,
-			      struct ethtool_ringparam *ring)
+static void igc_ethtool_get_ringparam(struct net_device *netdev,
+				      struct ethtool_ringparam *ring)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -555,8 +557,8 @@ static void igc_get_ringparam(struct net_device *netdev,
 	ring->tx_pending = adapter->tx_ring_count;
 }
 
-static int igc_set_ringparam(struct net_device *netdev,
-			     struct ethtool_ringparam *ring)
+static int igc_ethtool_set_ringparam(struct net_device *netdev,
+				     struct ethtool_ringparam *ring)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_ring *temp_ring;
@@ -670,8 +672,8 @@ clear_reset:
 	return err;
 }
 
-static void igc_get_pauseparam(struct net_device *netdev,
-			       struct ethtool_pauseparam *pause)
+static void igc_ethtool_get_pauseparam(struct net_device *netdev,
+				       struct ethtool_pauseparam *pause)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -689,8 +691,8 @@ static void igc_get_pauseparam(struct net_device *netdev,
 	}
 }
 
-static int igc_set_pauseparam(struct net_device *netdev,
-			      struct ethtool_pauseparam *pause)
+static int igc_ethtool_set_pauseparam(struct net_device *netdev,
+				      struct ethtool_pauseparam *pause)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -729,7 +731,8 @@ static int igc_set_pauseparam(struct net_device *netdev,
 	return retval;
 }
 
-static void igc_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset,
+				    u8 *data)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	u8 *p = data;
@@ -780,7 +783,7 @@ static void igc_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	}
 }
 
-static int igc_get_sset_count(struct net_device *netdev, int sset)
+static int igc_ethtool_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
 	case ETH_SS_STATS:
@@ -794,7 +797,7 @@ static int igc_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
-static void igc_get_ethtool_stats(struct net_device *netdev,
+static void igc_ethtool_get_stats(struct net_device *netdev,
 				  struct ethtool_stats *stats, u64 *data)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
@@ -850,8 +853,8 @@ static void igc_get_ethtool_stats(struct net_device *netdev,
 	spin_unlock(&adapter->stats64_lock);
 }
 
-static int igc_get_coalesce(struct net_device *netdev,
-			    struct ethtool_coalesce *ec)
+static int igc_ethtool_get_coalesce(struct net_device *netdev,
+				    struct ethtool_coalesce *ec)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -870,8 +873,8 @@ static int igc_get_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static int igc_set_coalesce(struct net_device *netdev,
-			    struct ethtool_coalesce *ec)
+static int igc_ethtool_set_coalesce(struct net_device *netdev,
+				    struct ethtool_coalesce *ec)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -928,7 +931,7 @@ static int igc_set_coalesce(struct net_device *netdev,
 }
 
 #define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
-static int igc_get_ethtool_nfc_entry(struct igc_adapter *adapter,
+static int igc_ethtool_get_nfc_entry(struct igc_adapter *adapter,
 				     struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
@@ -977,7 +980,7 @@ static int igc_get_ethtool_nfc_entry(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_get_ethtool_nfc_all(struct igc_adapter *adapter,
+static int igc_ethtool_get_nfc_all(struct igc_adapter *adapter,
 				   struct ethtool_rxnfc *cmd,
 				   u32 *rule_locs)
 {
@@ -999,8 +1002,8 @@ static int igc_get_ethtool_nfc_all(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_get_rss_hash_opts(struct igc_adapter *adapter,
-				 struct ethtool_rxnfc *cmd)
+static int igc_ethtool_get_rss_hash_opts(struct igc_adapter *adapter,
+					 struct ethtool_rxnfc *cmd)
 {
 	cmd->data = 0;
 
@@ -1049,8 +1052,8 @@ static int igc_get_rss_hash_opts(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
-			 u32 *rule_locs)
+static int igc_ethtool_get_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *cmd, u32 *rule_locs)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
@@ -1062,11 +1065,11 @@ static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		cmd->rule_cnt = adapter->nfc_filter_count;
 		return 0;
 	case ETHTOOL_GRXCLSRULE:
-		return igc_get_ethtool_nfc_entry(adapter, cmd);
+		return igc_ethtool_get_nfc_entry(adapter, cmd);
 	case ETHTOOL_GRXCLSRLALL:
-		return igc_get_ethtool_nfc_all(adapter, cmd, rule_locs);
+		return igc_ethtool_get_nfc_all(adapter, cmd, rule_locs);
 	case ETHTOOL_GRXFH:
-		return igc_get_rss_hash_opts(adapter, cmd);
+		return igc_ethtool_get_rss_hash_opts(adapter, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1074,8 +1077,8 @@ static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 
 #define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \
 		       IGC_FLAG_RSS_FIELD_IPV6_UDP)
-static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
-				struct ethtool_rxnfc *nfc)
+static int igc_ethtool_set_rss_hash_opt(struct igc_adapter *adapter,
+					struct ethtool_rxnfc *nfc)
 {
 	u32 flags = adapter->flags;
 
@@ -1240,7 +1243,7 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	return 0;
 }
 
-static int igc_update_ethtool_nfc_entry(struct igc_adapter *adapter,
+static int igc_ethtool_update_nfc_entry(struct igc_adapter *adapter,
 					struct igc_nfc_filter *input,
 					u16 sw_idx)
 {
@@ -1288,7 +1291,7 @@ static int igc_update_ethtool_nfc_entry(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
+static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
 				     struct ethtool_rxnfc *cmd)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -1379,7 +1382,7 @@ static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
 	if (err)
 		goto err_out_w_lock;
 
-	igc_update_ethtool_nfc_entry(adapter, input, input->sw_idx);
+	igc_ethtool_update_nfc_entry(adapter, input, input->sw_idx);
 
 	spin_unlock(&adapter->nfc_lock);
 	return 0;
@@ -1391,7 +1394,7 @@ err_out:
 	return err;
 }
 
-static int igc_del_ethtool_nfc_entry(struct igc_adapter *adapter,
+static int igc_ethtool_del_nfc_entry(struct igc_adapter *adapter,
 				     struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fsp =
@@ -1399,23 +1402,24 @@ static int igc_del_ethtool_nfc_entry(struct igc_adapter *adapter,
 	int err;
 
 	spin_lock(&adapter->nfc_lock);
-	err = igc_update_ethtool_nfc_entry(adapter, NULL, fsp->location);
+	err = igc_ethtool_update_nfc_entry(adapter, NULL, fsp->location);
 	spin_unlock(&adapter->nfc_lock);
 
 	return err;
 }
 
-static int igc_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+static int igc_ethtool_set_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *cmd)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXFH:
-		return igc_set_rss_hash_opt(adapter, cmd);
+		return igc_ethtool_set_rss_hash_opt(adapter, cmd);
 	case ETHTOOL_SRXCLSRLINS:
-		return igc_add_ethtool_nfc_entry(adapter, cmd);
+		return igc_ethtool_add_nfc_entry(adapter, cmd);
 	case ETHTOOL_SRXCLSRLDEL:
-		return igc_del_ethtool_nfc_entry(adapter, cmd);
+		return igc_ethtool_del_nfc_entry(adapter, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1443,13 +1447,13 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
 	}
 }
 
-static u32 igc_get_rxfh_indir_size(struct net_device *netdev)
+static u32 igc_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 {
 	return IGC_RETA_SIZE;
 }
 
-static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int igc_ethtool_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+				u8 *hfunc)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -1464,8 +1468,8 @@ static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
-static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int igc_ethtool_set_rxfh(struct net_device *netdev, const u32 *indir,
+				const u8 *key, const u8 hfunc)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	u32 num_queues;
@@ -1493,8 +1497,8 @@ static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
 	return 0;
 }
 
-static void igc_get_channels(struct net_device *netdev,
-			     struct ethtool_channels *ch)
+static void igc_ethtool_get_channels(struct net_device *netdev,
+				     struct ethtool_channels *ch)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
@@ -1510,8 +1514,8 @@ static void igc_get_channels(struct net_device *netdev,
 	ch->combined_count = adapter->rss_queues;
 }
 
-static int igc_set_channels(struct net_device *netdev,
-			    struct ethtool_channels *ch)
+static int igc_ethtool_set_channels(struct net_device *netdev,
+				    struct ethtool_channels *ch)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	unsigned int count = ch->combined_count;
@@ -1543,8 +1547,8 @@ static int igc_set_channels(struct net_device *netdev,
 	return 0;
 }
 
-static int igc_get_ts_info(struct net_device *dev,
-			   struct ethtool_ts_info *info)
+static int igc_ethtool_get_ts_info(struct net_device *dev,
+				   struct ethtool_ts_info *info)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
@@ -1576,7 +1580,7 @@ static int igc_get_ts_info(struct net_device *dev,
 	}
 }
 
-static u32 igc_get_priv_flags(struct net_device *netdev)
+static u32 igc_ethtool_get_priv_flags(struct net_device *netdev)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	u32 priv_flags = 0;
@@ -1587,7 +1591,7 @@ static u32 igc_get_priv_flags(struct net_device *netdev)
 	return priv_flags;
 }
 
-static int igc_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+static int igc_ethtool_set_priv_flags(struct net_device *netdev, u32 priv_flags)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	unsigned int flags = adapter->flags;
@@ -1622,8 +1626,8 @@ static void igc_ethtool_complete(struct net_device *netdev)
 	pm_runtime_put(&adapter->pdev->dev);
 }
 
-static int igc_get_link_ksettings(struct net_device *netdev,
-				  struct ethtool_link_ksettings *cmd)
+static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
+					  struct ethtool_link_ksettings *cmd)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
@@ -1729,8 +1733,9 @@ static int igc_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
-static int igc_set_link_ksettings(struct net_device *netdev,
-				  const struct ethtool_link_ksettings *cmd)
+static int
+igc_ethtool_set_link_ksettings(struct net_device *netdev,
+			       const struct ethtool_link_ksettings *cmd)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct net_device *dev = adapter->netdev;
@@ -1796,8 +1801,8 @@ static int igc_set_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
-static void igc_diag_test(struct net_device *netdev,
-			  struct ethtool_test *eth_test, u64 *data)
+static void igc_ethtool_diag_test(struct net_device *netdev,
+				  struct ethtool_test *eth_test, u64 *data)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	bool if_running = netif_running(netdev);
@@ -1856,45 +1861,45 @@ static void igc_diag_test(struct net_device *netdev,
 
 static const struct ethtool_ops igc_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
-	.get_drvinfo		= igc_get_drvinfo,
-	.get_regs_len		= igc_get_regs_len,
-	.get_regs		= igc_get_regs,
-	.get_wol		= igc_get_wol,
-	.set_wol		= igc_set_wol,
-	.get_msglevel		= igc_get_msglevel,
-	.set_msglevel		= igc_set_msglevel,
-	.nway_reset		= igc_nway_reset,
-	.get_link		= igc_get_link,
-	.get_eeprom_len		= igc_get_eeprom_len,
-	.get_eeprom		= igc_get_eeprom,
-	.set_eeprom		= igc_set_eeprom,
-	.get_ringparam		= igc_get_ringparam,
-	.set_ringparam		= igc_set_ringparam,
-	.get_pauseparam		= igc_get_pauseparam,
-	.set_pauseparam		= igc_set_pauseparam,
-	.get_strings		= igc_get_strings,
-	.get_sset_count		= igc_get_sset_count,
-	.get_ethtool_stats	= igc_get_ethtool_stats,
-	.get_coalesce		= igc_get_coalesce,
-	.set_coalesce		= igc_set_coalesce,
-	.get_rxnfc		= igc_get_rxnfc,
-	.set_rxnfc		= igc_set_rxnfc,
-	.get_rxfh_indir_size	= igc_get_rxfh_indir_size,
-	.get_rxfh		= igc_get_rxfh,
-	.set_rxfh		= igc_set_rxfh,
-	.get_ts_info		= igc_get_ts_info,
-	.get_channels		= igc_get_channels,
-	.set_channels		= igc_set_channels,
-	.get_priv_flags		= igc_get_priv_flags,
-	.set_priv_flags		= igc_set_priv_flags,
+	.get_drvinfo		= igc_ethtool_get_drvinfo,
+	.get_regs_len		= igc_ethtool_get_regs_len,
+	.get_regs		= igc_ethtool_get_regs,
+	.get_wol		= igc_ethtool_get_wol,
+	.set_wol		= igc_ethtool_set_wol,
+	.get_msglevel		= igc_ethtool_get_msglevel,
+	.set_msglevel		= igc_ethtool_set_msglevel,
+	.nway_reset		= igc_ethtool_nway_reset,
+	.get_link		= igc_ethtool_get_link,
+	.get_eeprom_len		= igc_ethtool_get_eeprom_len,
+	.get_eeprom		= igc_ethtool_get_eeprom,
+	.set_eeprom		= igc_ethtool_set_eeprom,
+	.get_ringparam		= igc_ethtool_get_ringparam,
+	.set_ringparam		= igc_ethtool_set_ringparam,
+	.get_pauseparam		= igc_ethtool_get_pauseparam,
+	.set_pauseparam		= igc_ethtool_set_pauseparam,
+	.get_strings		= igc_ethtool_get_strings,
+	.get_sset_count		= igc_ethtool_get_sset_count,
+	.get_ethtool_stats	= igc_ethtool_get_stats,
+	.get_coalesce		= igc_ethtool_get_coalesce,
+	.set_coalesce		= igc_ethtool_set_coalesce,
+	.get_rxnfc		= igc_ethtool_get_rxnfc,
+	.set_rxnfc		= igc_ethtool_set_rxnfc,
+	.get_rxfh_indir_size	= igc_ethtool_get_rxfh_indir_size,
+	.get_rxfh		= igc_ethtool_get_rxfh,
+	.set_rxfh		= igc_ethtool_set_rxfh,
+	.get_ts_info		= igc_ethtool_get_ts_info,
+	.get_channels		= igc_ethtool_get_channels,
+	.set_channels		= igc_ethtool_set_channels,
+	.get_priv_flags		= igc_ethtool_get_priv_flags,
+	.set_priv_flags		= igc_ethtool_set_priv_flags,
 	.begin			= igc_ethtool_begin,
 	.complete		= igc_ethtool_complete,
-	.get_link_ksettings	= igc_get_link_ksettings,
-	.set_link_ksettings	= igc_set_link_ksettings,
-	.self_test		= igc_diag_test,
+	.get_link_ksettings	= igc_ethtool_get_link_ksettings,
+	.set_link_ksettings	= igc_ethtool_set_link_ksettings,
+	.self_test		= igc_ethtool_diag_test,
 };
 
-void igc_set_ethtool_ops(struct net_device *netdev)
+void igc_ethtool_set_ops(struct net_device *netdev)
 {
 	netdev->ethtool_ops = &igc_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 843e8a2aaf24..98356652a7d9 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4932,7 +4932,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
-	igc_set_ethtool_ops(netdev);
+	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
 	netdev->mem_start = pci_resource_start(pdev, 0);
-- 
cgit v1.2.3


From 97700bc86d068442ee19ca6d31fc0a600cdbd672 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:10 -0700
Subject: igc: Align terms used in NFC support code

The Network Flow Classification (NFC) support code from IGC driver uses
terms such as 'rule', 'filter', 'entry', 'input' interchangeably when
referring to NFC rules, making it harder to follow the code. This patch
renames IGC's internal APIs, structs, and variables so we stick with the
term 'rule' since this is the term used in ethtool APIs. It also removes
some not applicable comments along the way. No functionality is changed
by this patch.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  29 +++--
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 160 +++++++++++++--------------
 drivers/net/ethernet/intel/igc/igc_main.c    |  42 +++----
 3 files changed, 114 insertions(+), 117 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 359ac40908f6..7124ba254b89 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -187,12 +187,12 @@ struct igc_adapter {
 	u32 rss_queues;
 	u32 rss_indir_tbl_init;
 
-	/* RX network flow classification support */
-	struct hlist_head nfc_filter_list;
-	unsigned int nfc_filter_count;
-
-	/* lock for RX network flow classification filter */
-	spinlock_t nfc_lock;
+	/* Any access to elements in nfc_rule_list is protected by the
+	 * nfc_rule_lock.
+	 */
+	spinlock_t nfc_rule_lock;
+	struct hlist_head nfc_rule_list;
+	unsigned int nfc_rule_count;
 
 	u8 rss_indir_tbl[IGC_RETA_SIZE];
 
@@ -453,7 +453,7 @@ enum igc_filter_match_flags {
 };
 
 /* RX network flow classification data structure */
-struct igc_nfc_input {
+struct igc_nfc_filter {
 	/* Byte layout in order, all values with MSB first:
 	 * match_flags - 1 byte
 	 * etype - 2 bytes
@@ -466,14 +466,14 @@ struct igc_nfc_input {
 	u8 dst_addr[ETH_ALEN];
 };
 
-struct igc_nfc_filter {
+struct igc_nfc_rule {
 	struct hlist_node nfc_node;
-	struct igc_nfc_input filter;
+	struct igc_nfc_filter filter;
 	u16 sw_idx;
 	u16 action;
 };
 
-#define IGC_MAX_RXNFC_FILTERS		16
+#define IGC_MAX_RXNFC_RULES		16
 
 /* igc_desc_unused - calculate if we have unused descriptors */
 static inline u16 igc_desc_unused(const struct igc_ring *ring)
@@ -549,12 +549,11 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
 	return 0;
 }
 
-/* forward declaration */
 void igc_reinit_locked(struct igc_adapter *);
-int igc_add_filter(struct igc_adapter *adapter,
-		   struct igc_nfc_filter *input);
-int igc_erase_filter(struct igc_adapter *adapter,
-		     struct igc_nfc_filter *input);
+int igc_enable_nfc_rule(struct igc_adapter *adapter,
+			const struct igc_nfc_rule *rule);
+int igc_disable_nfc_rule(struct igc_adapter *adapter,
+			 const struct igc_nfc_rule *rule);
 
 void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 0399ca1d7d0c..408f4a9a199f 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -931,16 +931,15 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev,
 }
 
 #define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
-static int igc_ethtool_get_nfc_entry(struct igc_adapter *adapter,
-				     struct ethtool_rxnfc *cmd)
+static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
+				    struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
-	struct igc_nfc_filter *rule = NULL;
+	struct igc_nfc_rule *rule = NULL;
 
-	/* report total rule count */
-	cmd->data = IGC_MAX_RXNFC_FILTERS;
+	cmd->data = IGC_MAX_RXNFC_RULES;
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		if (fsp->location <= rule->sw_idx)
 			break;
 	}
@@ -980,17 +979,16 @@ static int igc_ethtool_get_nfc_entry(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_ethtool_get_nfc_all(struct igc_adapter *adapter,
-				   struct ethtool_rxnfc *cmd,
-				   u32 *rule_locs)
+static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
+				     struct ethtool_rxnfc *cmd,
+				     u32 *rule_locs)
 {
-	struct igc_nfc_filter *rule;
+	struct igc_nfc_rule *rule;
 	int cnt = 0;
 
-	/* report total rule count */
-	cmd->data = IGC_MAX_RXNFC_FILTERS;
+	cmd->data = IGC_MAX_RXNFC_RULES;
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		if (cnt == cmd->rule_cnt)
 			return -EMSGSIZE;
 		rule_locs[cnt] = rule->sw_idx;
@@ -1062,12 +1060,12 @@ static int igc_ethtool_get_rxnfc(struct net_device *dev,
 		cmd->data = adapter->num_rx_queues;
 		return 0;
 	case ETHTOOL_GRXCLSRLCNT:
-		cmd->rule_cnt = adapter->nfc_filter_count;
+		cmd->rule_cnt = adapter->nfc_rule_count;
 		return 0;
 	case ETHTOOL_GRXCLSRULE:
-		return igc_ethtool_get_nfc_entry(adapter, cmd);
+		return igc_ethtool_get_nfc_rule(adapter, cmd);
 	case ETHTOOL_GRXCLSRLALL:
-		return igc_ethtool_get_nfc_all(adapter, cmd, rule_locs);
+		return igc_ethtool_get_nfc_rules(adapter, cmd, rule_locs);
 	case ETHTOOL_GRXFH:
 		return igc_ethtool_get_rss_hash_opts(adapter, cmd);
 	default:
@@ -1179,38 +1177,37 @@ static int igc_ethtool_set_rss_hash_opt(struct igc_adapter *adapter,
 	return 0;
 }
 
-int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+int igc_enable_nfc_rule(struct igc_adapter *adapter,
+			const struct igc_nfc_rule *rule)
 {
 	int err = -EINVAL;
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		u16 etype = ntohs(input->filter.etype);
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		u16 etype = ntohs(rule->filter.etype);
 
-		err = igc_add_etype_filter(adapter, etype, input->action);
+		err = igc_add_etype_filter(adapter, etype, rule->action);
 		if (err)
 			return err;
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
 		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
-					 input->filter.src_addr,
-					 input->action);
+					 rule->filter.src_addr, rule->action);
 		if (err)
 			return err;
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
 		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
-					 input->filter.dst_addr,
-					 input->action);
+					 rule->filter.dst_addr, rule->action);
 		if (err)
 			return err;
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (ntohs(rule->filter.vlan_tci) & VLAN_PRIO_MASK) >>
 			   VLAN_PRIO_SHIFT;
-		err = igc_add_vlan_prio_filter(adapter, prio, input->action);
+		err = igc_add_vlan_prio_filter(adapter, prio, rule->action);
 		if (err)
 			return err;
 	}
@@ -1218,42 +1215,43 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
 	return 0;
 }
 
-int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+int igc_disable_nfc_rule(struct igc_adapter *adapter,
+			 const struct igc_nfc_rule *rule)
 {
-	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		u16 etype = ntohs(input->filter.etype);
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		u16 etype = ntohs(rule->filter.etype);
 
 		igc_del_etype_filter(adapter, etype);
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (ntohs(rule->filter.vlan_tci) & VLAN_PRIO_MASK) >>
 			   VLAN_PRIO_SHIFT;
 		igc_del_vlan_prio_filter(adapter, prio);
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
 		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
-				   input->filter.src_addr);
+				   rule->filter.src_addr);
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
 		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
-				   input->filter.dst_addr);
+				   rule->filter.dst_addr);
 
 	return 0;
 }
 
-static int igc_ethtool_update_nfc_entry(struct igc_adapter *adapter,
-					struct igc_nfc_filter *input,
-					u16 sw_idx)
+static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
+				       struct igc_nfc_rule *input,
+				       u16 sw_idx)
 {
-	struct igc_nfc_filter *rule, *parent;
+	struct igc_nfc_rule *rule, *parent;
 	int err = -EINVAL;
 
 	parent = NULL;
 	rule = NULL;
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		/* hash found, or no matching entry */
 		if (rule->sw_idx >= sw_idx)
 			break;
@@ -1263,11 +1261,11 @@ static int igc_ethtool_update_nfc_entry(struct igc_adapter *adapter,
 	/* if there is an old rule occupying our place remove it */
 	if (rule && rule->sw_idx == sw_idx) {
 		if (!input)
-			err = igc_erase_filter(adapter, rule);
+			err = igc_disable_nfc_rule(adapter, rule);
 
 		hlist_del(&rule->nfc_node);
 		kfree(rule);
-		adapter->nfc_filter_count--;
+		adapter->nfc_rule_count--;
 	}
 
 	/* If no input this was a delete, err should be 0 if a rule was
@@ -1283,21 +1281,21 @@ static int igc_ethtool_update_nfc_entry(struct igc_adapter *adapter,
 	if (parent)
 		hlist_add_behind(&input->nfc_node, &parent->nfc_node);
 	else
-		hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list);
+		hlist_add_head(&input->nfc_node, &adapter->nfc_rule_list);
 
 	/* update counts */
-	adapter->nfc_filter_count++;
+	adapter->nfc_rule_count++;
 
 	return 0;
 }
 
-static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
-				     struct ethtool_rxnfc *cmd)
+static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
+				    struct ethtool_rxnfc *cmd)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct ethtool_rx_flow_spec *fsp =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
-	struct igc_nfc_filter *input, *rule;
+	struct igc_nfc_rule *rule, *tmp;
 	int err = 0;
 
 	if (!(netdev->hw_features & NETIF_F_NTUPLE))
@@ -1314,7 +1312,7 @@ static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
 	}
 
 	/* Don't allow indexes to exist outside of available space */
-	if (fsp->location >= IGC_MAX_RXNFC_FILTERS) {
+	if (fsp->location >= IGC_MAX_RXNFC_RULES) {
 		netdev_err(netdev, "Location out of range\n");
 		return -EINVAL;
 	}
@@ -1322,32 +1320,32 @@ static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
 	if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
 		return -EINVAL;
 
-	input = kzalloc(sizeof(*input), GFP_KERNEL);
-	if (!input)
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
 		return -ENOMEM;
 
 	if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) {
-		input->filter.etype = fsp->h_u.ether_spec.h_proto;
-		input->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
+		rule->filter.etype = fsp->h_u.ether_spec.h_proto;
+		rule->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
 	}
 
 	/* Both source and destination address filters only support the full
 	 * mask.
 	 */
 	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) {
-		input->filter.match_flags |= IGC_FILTER_FLAG_SRC_MAC_ADDR;
-		ether_addr_copy(input->filter.src_addr,
+		rule->filter.match_flags |= IGC_FILTER_FLAG_SRC_MAC_ADDR;
+		ether_addr_copy(rule->filter.src_addr,
 				fsp->h_u.ether_spec.h_source);
 	}
 
 	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) {
-		input->filter.match_flags |= IGC_FILTER_FLAG_DST_MAC_ADDR;
-		ether_addr_copy(input->filter.dst_addr,
+		rule->filter.match_flags |= IGC_FILTER_FLAG_DST_MAC_ADDR;
+		ether_addr_copy(rule->filter.dst_addr,
 				fsp->h_u.ether_spec.h_dest);
 	}
 
-	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
-	    input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
+	    rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
 		netdev_dbg(netdev, "Filters with both dst and src are not supported\n");
 		err = -EOPNOTSUPP;
 		goto err_out;
@@ -1359,18 +1357,18 @@ static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
 			err = -EOPNOTSUPP;
 			goto err_out;
 		}
-		input->filter.vlan_tci = fsp->h_ext.vlan_tci;
-		input->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
+		rule->filter.vlan_tci = fsp->h_ext.vlan_tci;
+		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
 	}
 
-	input->action = fsp->ring_cookie;
-	input->sw_idx = fsp->location;
+	rule->action = fsp->ring_cookie;
+	rule->sw_idx = fsp->location;
 
-	spin_lock(&adapter->nfc_lock);
+	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
-		if (!memcmp(&input->filter, &rule->filter,
-			    sizeof(input->filter))) {
+	hlist_for_each_entry(tmp, &adapter->nfc_rule_list, nfc_node) {
+		if (!memcmp(&rule->filter, &tmp->filter,
+			    sizeof(rule->filter))) {
 			err = -EEXIST;
 			netdev_err(netdev,
 				   "ethtool: this filter is already set\n");
@@ -1378,32 +1376,32 @@ static int igc_ethtool_add_nfc_entry(struct igc_adapter *adapter,
 		}
 	}
 
-	err = igc_add_filter(adapter, input);
+	err = igc_enable_nfc_rule(adapter, rule);
 	if (err)
 		goto err_out_w_lock;
 
-	igc_ethtool_update_nfc_entry(adapter, input, input->sw_idx);
+	igc_ethtool_update_nfc_rule(adapter, rule, rule->sw_idx);
 
-	spin_unlock(&adapter->nfc_lock);
+	spin_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
 err_out_w_lock:
-	spin_unlock(&adapter->nfc_lock);
+	spin_unlock(&adapter->nfc_rule_lock);
 err_out:
-	kfree(input);
+	kfree(rule);
 	return err;
 }
 
-static int igc_ethtool_del_nfc_entry(struct igc_adapter *adapter,
-				     struct ethtool_rxnfc *cmd)
+static int igc_ethtool_del_nfc_rule(struct igc_adapter *adapter,
+				    struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fsp =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
 	int err;
 
-	spin_lock(&adapter->nfc_lock);
-	err = igc_ethtool_update_nfc_entry(adapter, NULL, fsp->location);
-	spin_unlock(&adapter->nfc_lock);
+	spin_lock(&adapter->nfc_rule_lock);
+	err = igc_ethtool_update_nfc_rule(adapter, NULL, fsp->location);
+	spin_unlock(&adapter->nfc_rule_lock);
 
 	return err;
 }
@@ -1417,9 +1415,9 @@ static int igc_ethtool_set_rxnfc(struct net_device *dev,
 	case ETHTOOL_SRXFH:
 		return igc_ethtool_set_rss_hash_opt(adapter, cmd);
 	case ETHTOOL_SRXCLSRLINS:
-		return igc_ethtool_add_nfc_entry(adapter, cmd);
+		return igc_ethtool_add_nfc_rule(adapter, cmd);
 	case ETHTOOL_SRXCLSRLDEL:
-		return igc_ethtool_del_nfc_entry(adapter, cmd);
+		return igc_ethtool_del_nfc_rule(adapter, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 98356652a7d9..f48d6127a220 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2174,16 +2174,16 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 	return !!budget;
 }
 
-static void igc_nfc_filter_restore(struct igc_adapter *adapter)
+static void igc_restore_nfc_rules(struct igc_adapter *adapter)
 {
-	struct igc_nfc_filter *rule;
+	struct igc_nfc_rule *rule;
 
-	spin_lock(&adapter->nfc_lock);
+	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
-		igc_add_filter(adapter, rule);
+	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node)
+		igc_enable_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_lock);
+	spin_unlock(&adapter->nfc_rule_lock);
 }
 
 static int igc_find_mac_filter(struct igc_adapter *adapter,
@@ -2537,7 +2537,7 @@ static void igc_configure(struct igc_adapter *adapter)
 	igc_setup_rctl(adapter);
 
 	igc_set_default_mac_filter(adapter);
-	igc_nfc_filter_restore(adapter);
+	igc_restore_nfc_rules(adapter);
 
 	igc_configure_tx(adapter);
 	igc_configure_rx(adapter);
@@ -3424,7 +3424,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 				VLAN_HLEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
-	spin_lock_init(&adapter->nfc_lock);
+	spin_lock_init(&adapter->nfc_rule_lock);
 	spin_lock_init(&adapter->stats64_lock);
 	/* Assume MSI-X interrupts, will be checked during IRQ allocation */
 	adapter->flags |= IGC_FLAG_HAS_MSIX;
@@ -3651,16 +3651,16 @@ void igc_update_stats(struct igc_adapter *adapter)
 	adapter->stats.mgpdc += rd32(IGC_MGTPDC);
 }
 
-static void igc_nfc_filter_exit(struct igc_adapter *adapter)
+static void igc_nfc_rule_exit(struct igc_adapter *adapter)
 {
-	struct igc_nfc_filter *rule;
+	struct igc_nfc_rule *rule;
 
-	spin_lock(&adapter->nfc_lock);
+	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
-		igc_erase_filter(adapter, rule);
+	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node)
+		igc_disable_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_lock);
+	spin_unlock(&adapter->nfc_rule_lock);
 }
 
 /**
@@ -3681,7 +3681,7 @@ void igc_down(struct igc_adapter *adapter)
 	wr32(IGC_RCTL, rctl & ~IGC_RCTL_EN);
 	/* flush and sleep below */
 
-	igc_nfc_filter_exit(adapter);
+	igc_nfc_rule_exit(adapter);
 
 	/* set trans_start so we don't get spurious watchdogs during reset */
 	netif_trans_update(netdev);
@@ -3833,17 +3833,17 @@ static int igc_set_features(struct net_device *netdev,
 
 	if (!(features & NETIF_F_NTUPLE)) {
 		struct hlist_node *node2;
-		struct igc_nfc_filter *rule;
+		struct igc_nfc_rule *rule;
 
-		spin_lock(&adapter->nfc_lock);
+		spin_lock(&adapter->nfc_rule_lock);
 		hlist_for_each_entry_safe(rule, node2,
-					  &adapter->nfc_filter_list, nfc_node) {
-			igc_erase_filter(adapter, rule);
+					  &adapter->nfc_rule_list, nfc_node) {
+			igc_disable_nfc_rule(adapter, rule);
 			hlist_del(&rule->nfc_node);
 			kfree(rule);
 		}
-		spin_unlock(&adapter->nfc_lock);
-		adapter->nfc_filter_count = 0;
+		spin_unlock(&adapter->nfc_rule_lock);
+		adapter->nfc_rule_count = 0;
 	}
 
 	netdev->features = features;
-- 
cgit v1.2.3


From c983e3271923c96cd5f90de0b580f1b210f7f8b6 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:11 -0700
Subject: igc: Change byte order in struct igc_nfc_filter

Every time we access the 'etype' and 'vlan_tci' fields from struct
igc_nfc_filter to enable or disable filters in hardware we have to
convert them from big endian to host order so it makes more sense to
simply have these fields in host order.

The byte order conversion should take place in igc_ethtool_get_nfc_
rule() and igc_ethtool_add_nfc_rule(), which are called by .get_rxnfc
and .set_rxnfc ethtool ops, since ethtool subsystem is the one who deals
with them in big endian order.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         | 10 ++--------
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 25 +++++++++++--------------
 2 files changed, 13 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 7124ba254b89..fcc6261d7f67 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -452,16 +452,10 @@ enum igc_filter_match_flags {
 	IGC_FILTER_FLAG_DST_MAC_ADDR =	0x8,
 };
 
-/* RX network flow classification data structure */
 struct igc_nfc_filter {
-	/* Byte layout in order, all values with MSB first:
-	 * match_flags - 1 byte
-	 * etype - 2 bytes
-	 * vlan_tci - 2 bytes
-	 */
 	u8 match_flags;
-	__be16 etype;
-	__be16 vlan_tci;
+	u16 etype;
+	u16 vlan_tci;
 	u8 src_addr[ETH_ALEN];
 	u8 dst_addr[ETH_ALEN];
 };
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 408f4a9a199f..66e0760a8f9e 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -954,13 +954,13 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 	fsp->ring_cookie = rule->action;
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		fsp->h_u.ether_spec.h_proto = rule->filter.etype;
+		fsp->h_u.ether_spec.h_proto = htons(rule->filter.etype);
 		fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
 	}
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
 		fsp->flow_type |= FLOW_EXT;
-		fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
+		fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci);
 		fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
 	}
 
@@ -1183,9 +1183,8 @@ int igc_enable_nfc_rule(struct igc_adapter *adapter,
 	int err = -EINVAL;
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		u16 etype = ntohs(rule->filter.etype);
-
-		err = igc_add_etype_filter(adapter, etype, rule->action);
+		err = igc_add_etype_filter(adapter, rule->filter.etype,
+					   rule->action);
 		if (err)
 			return err;
 	}
@@ -1205,8 +1204,9 @@ int igc_enable_nfc_rule(struct igc_adapter *adapter,
 	}
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (ntohs(rule->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
 			   VLAN_PRIO_SHIFT;
+
 		err = igc_add_vlan_prio_filter(adapter, prio, rule->action);
 		if (err)
 			return err;
@@ -1218,14 +1218,11 @@ int igc_enable_nfc_rule(struct igc_adapter *adapter,
 int igc_disable_nfc_rule(struct igc_adapter *adapter,
 			 const struct igc_nfc_rule *rule)
 {
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		u16 etype = ntohs(rule->filter.etype);
-
-		igc_del_etype_filter(adapter, etype);
-	}
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
+		igc_del_etype_filter(adapter, rule->filter.etype);
 
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (ntohs(rule->filter.vlan_tci) & VLAN_PRIO_MASK) >>
+		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
 			   VLAN_PRIO_SHIFT;
 		igc_del_vlan_prio_filter(adapter, prio);
 	}
@@ -1325,7 +1322,7 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 		return -ENOMEM;
 
 	if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) {
-		rule->filter.etype = fsp->h_u.ether_spec.h_proto;
+		rule->filter.etype = ntohs(fsp->h_u.ether_spec.h_proto);
 		rule->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
 	}
 
@@ -1357,7 +1354,7 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 			err = -EOPNOTSUPP;
 			goto err_out;
 		}
-		rule->filter.vlan_tci = fsp->h_ext.vlan_tci;
+		rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci);
 		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
 	}
 
-- 
cgit v1.2.3


From b8204ad878ce7f49870669283de348e458a97ac4 Mon Sep 17 00:00:00 2001
From: Yuval Basson <ybason@marvell.com>
Date: Tue, 19 May 2020 23:51:25 +0300
Subject: qed: changes to ILT to support XRC

First ILT page for TSDM client is allocated for XRC-SRQ's.
For regular SRQ's skip first ILT page that is reserved for
XRC-SRQ's.

Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Yuval Bason <ybason@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_cxt.c  | 60 +++++++++++++++++++++++++-----
 drivers/net/ethernet/qlogic/qed/qed_cxt.h  | 10 ++++-
 drivers/net/ethernet/qlogic/qed/qed_dev.c  |  6 ++-
 drivers/net/ethernet/qlogic/qed/qed_rdma.c |  2 +-
 4 files changed, 64 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 1a636bad717d..7b76667acaba 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -110,6 +110,7 @@ struct src_ent {
 	ALIGNED_TYPE_SIZE(union conn_context, p_hwfn)
 
 #define SRQ_CXT_SIZE (sizeof(struct rdma_srq_context))
+#define XRC_SRQ_CXT_SIZE (sizeof(struct rdma_xrc_srq_context))
 
 #define TYPE0_TASK_CXT_SIZE(p_hwfn) \
 	ALIGNED_TYPE_SIZE(union type0_task_context, p_hwfn)
@@ -293,18 +294,40 @@ static struct qed_tid_seg *qed_cxt_tid_seg_info(struct qed_hwfn *p_hwfn,
 	return NULL;
 }
 
-static void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn, u32 num_srqs)
+static void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn,
+				  u32 num_srqs, u32 num_xrc_srqs)
 {
 	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
 
 	p_mgr->srq_count = num_srqs;
+	p_mgr->xrc_srq_count = num_xrc_srqs;
 }
 
-u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn)
+u32 qed_cxt_get_ilt_page_size(struct qed_hwfn *p_hwfn,
+			      enum ilt_clients ilt_client)
+{
+	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
+	struct qed_ilt_client_cfg *p_cli = &p_mngr->clients[ilt_client];
+
+	return ILT_PAGE_IN_BYTES(p_cli->p_size.val);
+}
+
+static u32 qed_cxt_xrc_srqs_per_page(struct qed_hwfn *p_hwfn)
+{
+	u32 page_size;
+
+	page_size = qed_cxt_get_ilt_page_size(p_hwfn, ILT_CLI_TSDM);
+	return page_size / XRC_SRQ_CXT_SIZE;
+}
+
+u32 qed_cxt_get_total_srq_count(struct qed_hwfn *p_hwfn)
 {
 	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
+	u32 total_srqs;
+
+	total_srqs = p_mgr->srq_count + p_mgr->xrc_srq_count;
 
-	return p_mgr->srq_count;
+	return total_srqs;
 }
 
 /* set the iids count per protocol */
@@ -692,7 +715,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
 	}
 
 	/* TSDM (SRQ CONTEXT) */
-	total = qed_cxt_get_srq_count(p_hwfn);
+	total = qed_cxt_get_total_srq_count(p_hwfn);
 
 	if (total) {
 		p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]);
@@ -1962,11 +1985,9 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 				   struct qed_rdma_pf_params *p_params,
 				   u32 num_tasks)
 {
-	u32 num_cons, num_qps, num_srqs;
+	u32 num_cons, num_qps;
 	enum protocol_type proto;
 
-	num_srqs = min_t(u32, QED_RDMA_MAX_SRQS, p_params->num_srqs);
-
 	if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) {
 		DP_NOTICE(p_hwfn,
 			  "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
@@ -1989,6 +2010,8 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 	}
 
 	if (num_cons && num_tasks) {
+		u32 num_srqs, num_xrc_srqs;
+
 		qed_cxt_set_proto_cid_count(p_hwfn, proto, num_cons, 0);
 
 		/* Deliberatly passing ROCE for tasks id. This is because
@@ -1997,7 +2020,13 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 		qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_ROCE,
 					    QED_CXT_ROCE_TID_SEG, 1,
 					    num_tasks, false);
-		qed_cxt_set_srq_count(p_hwfn, num_srqs);
+
+		num_srqs = min_t(u32, QED_RDMA_MAX_SRQS, p_params->num_srqs);
+
+		/* XRC SRQs populate a single ILT page */
+		num_xrc_srqs = qed_cxt_xrc_srqs_per_page(p_hwfn);
+
+		qed_cxt_set_srq_count(p_hwfn, num_srqs, num_xrc_srqs);
 	} else {
 		DP_INFO(p_hwfn->cdev,
 			"RDMA personality used without setting params!\n");
@@ -2163,10 +2192,17 @@ qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
 		p_blk = &p_cli->pf_blks[CDUC_BLK];
 		break;
 	case QED_ELEM_SRQ:
+		/* The first ILT page is not used for regular SRQs. Skip it. */
+		iid += p_hwfn->p_cxt_mngr->xrc_srq_count;
 		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
 		elem_size = SRQ_CXT_SIZE;
 		p_blk = &p_cli->pf_blks[SRQ_BLK];
 		break;
+	case QED_ELEM_XRC_SRQ:
+		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
+		elem_size = XRC_SRQ_CXT_SIZE;
+		p_blk = &p_cli->pf_blks[SRQ_BLK];
+		break;
 	case QED_ELEM_TASK:
 		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
 		elem_size = TYPE1_TASK_CXT_SIZE(p_hwfn);
@@ -2386,8 +2422,12 @@ int qed_cxt_free_proto_ilt(struct qed_hwfn *p_hwfn, enum protocol_type proto)
 		return rc;
 
 	/* Free TSDM CXT */
-	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_SRQ, 0,
-				    qed_cxt_get_srq_count(p_hwfn));
+	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_XRC_SRQ, 0,
+				    p_hwfn->p_cxt_mngr->xrc_srq_count);
+
+	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_SRQ,
+				    p_hwfn->p_cxt_mngr->xrc_srq_count,
+				    p_hwfn->p_cxt_mngr->srq_count);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index c4e815f6cabd..ce08ae8d8498 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -82,7 +82,8 @@ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn,
 enum qed_cxt_elem_type {
 	QED_ELEM_CXT,
 	QED_ELEM_SRQ,
-	QED_ELEM_TASK
+	QED_ELEM_TASK,
+	QED_ELEM_XRC_SRQ,
 };
 
 u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn,
@@ -235,7 +236,6 @@ u32 qed_cxt_get_proto_tid_count(struct qed_hwfn *p_hwfn,
 				enum protocol_type type);
 u32 qed_cxt_get_proto_cid_start(struct qed_hwfn *p_hwfn,
 				enum protocol_type type);
-u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn);
 int qed_cxt_free_proto_ilt(struct qed_hwfn *p_hwfn, enum protocol_type proto);
 
 #define QED_CTX_WORKING_MEM 0
@@ -358,6 +358,7 @@ struct qed_cxt_mngr {
 
 	/* total number of SRQ's for this hwfn */
 	u32 srq_count;
+	u32 xrc_srq_count;
 
 	/* Maximal number of L2 steering filters */
 	u32 arfs_count;
@@ -372,4 +373,9 @@ u16 qed_get_cdut_num_vf_init_pages(struct qed_hwfn *p_hwfn);
 u16 qed_get_cdut_num_pf_work_pages(struct qed_hwfn *p_hwfn);
 u16 qed_get_cdut_num_vf_work_pages(struct qed_hwfn *p_hwfn);
 
+u32 qed_cxt_get_ilt_page_size(struct qed_hwfn *p_hwfn,
+			      enum ilt_clients ilt_client);
+
+u32 qed_cxt_get_total_srq_count(struct qed_hwfn *p_hwfn);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 6e857468e993..1eebf30fa798 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -2269,6 +2269,7 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		/* EQ */
 		n_eqes = qed_chain_get_capacity(&p_hwfn->p_spq->chain);
 		if (QED_IS_RDMA_PERSONALITY(p_hwfn)) {
+			u32 n_srq = qed_cxt_get_total_srq_count(p_hwfn);
 			enum protocol_type rdma_proto;
 
 			if (QED_IS_ROCE_PERSONALITY(p_hwfn))
@@ -2279,7 +2280,10 @@ int qed_resc_alloc(struct qed_dev *cdev)
 			num_cons = qed_cxt_get_proto_cid_count(p_hwfn,
 							       rdma_proto,
 							       NULL) * 2;
-			n_eqes += num_cons + 2 * MAX_NUM_VFS_BB;
+			/* EQ should be able to get events from all SRQ's
+			 * at the same time
+			 */
+			n_eqes += num_cons + 2 * MAX_NUM_VFS_BB + n_srq;
 		} else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
 			num_cons =
 			    qed_cxt_get_proto_cid_count(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 38b1f402f7ed..415f3f3d2152 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -272,7 +272,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn)
 	}
 
 	/* Allocate bitmap for srqs */
-	p_rdma_info->num_srqs = qed_cxt_get_srq_count(p_hwfn);
+	p_rdma_info->num_srqs = p_hwfn->p_cxt_mngr->srq_count;
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->srq_map,
 				 p_rdma_info->num_srqs, "SRQ");
 	if (rc) {
-- 
cgit v1.2.3


From 7bfb399eca460500f048098bf427c45b40e17cae Mon Sep 17 00:00:00 2001
From: Yuval Basson <ybason@marvell.com>
Date: Tue, 19 May 2020 23:51:26 +0300
Subject: qed: Add XRC to RoCE

Add support for XRC-SRQ's and XRC-QP's for upper layer driver.

We maintain separate bitmaps for resource management for srq and
xrc-srq, However, the range in FW is one, The xrc-srq's are first
and then the srq's follow. Therefore we maintain a srq-id offset.

v2: perform cleanups if XRC bitmpas allocation fail.

Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Yuval Bason <ybason@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_rdma.c | 145 +++++++++++++++++++++++++----
 drivers/net/ethernet/qlogic/qed/qed_rdma.h |  19 ++++
 drivers/net/ethernet/qlogic/qed/qed_roce.c |  29 ++++++
 include/linux/qed/qed_rdma_if.h            |  19 ++++
 4 files changed, 194 insertions(+), 18 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 415f3f3d2152..50985871cd3d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -212,13 +212,22 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn)
 		goto free_rdma_port;
 	}
 
+	/* Allocate bit map for XRC Domains */
+	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->xrcd_map,
+				 QED_RDMA_MAX_XRCDS, "XRCD");
+	if (rc) {
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Failed to allocate xrcd_map,rc = %d\n", rc);
+		goto free_pd_map;
+	}
+
 	/* Allocate DPI bitmap */
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->dpi_map,
 				 p_hwfn->dpi_count, "DPI");
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate DPI bitmap, rc = %d\n", rc);
-		goto free_pd_map;
+		goto free_xrcd_map;
 	}
 
 	/* Allocate bitmap for cq's. The maximum number of CQs is bound to
@@ -271,6 +280,19 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn)
 		goto free_cid_map;
 	}
 
+	/* The first SRQ follows the last XRC SRQ. This means that the
+	 * SRQ IDs start from an offset equals to max_xrc_srqs.
+	 */
+	p_rdma_info->srq_id_offset = p_hwfn->p_cxt_mngr->xrc_srq_count;
+	rc = qed_rdma_bmap_alloc(p_hwfn,
+				 &p_rdma_info->xrc_srq_map,
+				 p_hwfn->p_cxt_mngr->xrc_srq_count, "XRC SRQ");
+	if (rc) {
+		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+			   "Failed to allocate xrc srq bitmap, rc = %d\n", rc);
+		goto free_real_cid_map;
+	}
+
 	/* Allocate bitmap for srqs */
 	p_rdma_info->num_srqs = p_hwfn->p_cxt_mngr->srq_count;
 	rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->srq_map,
@@ -278,7 +300,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn)
 	if (rc) {
 		DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
 			   "Failed to allocate srq bitmap, rc = %d\n", rc);
-		goto free_real_cid_map;
+		goto free_xrc_srq_map;
 	}
 
 	if (QED_IS_IWARP_PERSONALITY(p_hwfn))
@@ -292,6 +314,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn)
 
 free_srq_map:
 	kfree(p_rdma_info->srq_map.bitmap);
+free_xrc_srq_map:
+	kfree(p_rdma_info->xrc_srq_map.bitmap);
 free_real_cid_map:
 	kfree(p_rdma_info->real_cid_map.bitmap);
 free_cid_map:
@@ -304,6 +328,8 @@ free_cq_map:
 	kfree(p_rdma_info->cq_map.bitmap);
 free_dpi_map:
 	kfree(p_rdma_info->dpi_map.bitmap);
+free_xrcd_map:
+	kfree(p_rdma_info->xrcd_map.bitmap);
 free_pd_map:
 	kfree(p_rdma_info->pd_map.bitmap);
 free_rdma_port:
@@ -377,6 +403,7 @@ static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
 	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tid_map, 1);
 	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->srq_map, 1);
 	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, 1);
+	qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->xrc_srq_map, 1);
 
 	kfree(p_rdma_info->port);
 	kfree(p_rdma_info->dev);
@@ -612,7 +639,10 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn,
 	p_params_header->cnq_start_offset = (u8)RESC_START(p_hwfn,
 							   QED_RDMA_CNQ_RAM);
 	p_params_header->num_cnqs = params->desired_cnq;
-
+	p_params_header->first_reg_srq_id =
+	    cpu_to_le16(p_hwfn->p_rdma_info->srq_id_offset);
+	p_params_header->reg_srq_base_addr =
+	    cpu_to_le32(qed_cxt_get_ilt_page_size(p_hwfn, ILT_CLI_TSDM));
 	if (params->cq_mode == QED_RDMA_CQ_MODE_16_BITS)
 		p_params_header->cq_ring_mode = 1;
 	else
@@ -983,6 +1013,41 @@ static void qed_rdma_free_pd(void *rdma_cxt, u16 pd)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
+static int qed_rdma_alloc_xrcd(void *rdma_cxt, u16 *xrcd_id)
+{
+	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
+	u32 returned_id;
+	int rc;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Alloc XRCD\n");
+
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	rc = qed_rdma_bmap_alloc_id(p_hwfn,
+				    &p_hwfn->p_rdma_info->xrcd_map,
+				    &returned_id);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+	if (rc) {
+		DP_NOTICE(p_hwfn, "Failed in allocating xrcd id\n");
+		return rc;
+	}
+
+	*xrcd_id = (u16)returned_id;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Alloc XRCD - done, rc = %d\n", rc);
+	return rc;
+}
+
+static void qed_rdma_free_xrcd(void *rdma_cxt, u16 xrcd_id)
+{
+	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "xrcd_id = %08x\n", xrcd_id);
+
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->xrcd_map, xrcd_id);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
 static enum qed_rdma_toggle_bit
 qed_rdma_toggle_bit_create_resize_cq(struct qed_hwfn *p_hwfn, u16 icid)
 {
@@ -1306,6 +1371,8 @@ qed_rdma_create_qp(void *rdma_cxt,
 	qp->resp_offloaded = false;
 	qp->e2e_flow_control_en = qp->use_srq ? false : true;
 	qp->stats_queue = in_params->stats_queue;
+	qp->qp_type = in_params->qp_type;
+	qp->xrcd_id = in_params->xrcd_id;
 
 	if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
 		rc = qed_iwarp_create_qp(p_hwfn, qp, out_params);
@@ -1418,6 +1485,18 @@ static int qed_rdma_modify_qp(void *rdma_cxt,
 			   qp->cur_state);
 	}
 
+	switch (qp->qp_type) {
+	case QED_RDMA_QP_TYPE_XRC_INI:
+		qp->has_req = 1;
+		break;
+	case QED_RDMA_QP_TYPE_XRC_TGT:
+		qp->has_resp = 1;
+		break;
+	default:
+		qp->has_req = 1;
+		qp->has_resp = 1;
+	}
+
 	if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
 		enum qed_iwarp_qp_state new_state =
 		    qed_roce2iwarp_state(qp->cur_state);
@@ -1657,6 +1736,15 @@ static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev)
 	return QED_AFFIN_HWFN(cdev);
 }
 
+static struct qed_bmap *qed_rdma_get_srq_bmap(struct qed_hwfn *p_hwfn,
+					      bool is_xrc)
+{
+	if (is_xrc)
+		return &p_hwfn->p_rdma_info->xrc_srq_map;
+
+	return &p_hwfn->p_rdma_info->srq_map;
+}
+
 static int qed_rdma_modify_srq(void *rdma_cxt,
 			       struct qed_rdma_modify_srq_in_params *in_params)
 {
@@ -1686,8 +1774,8 @@ static int qed_rdma_modify_srq(void *rdma_cxt,
 	if (rc)
 		return rc;
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "modified SRQ id = %x",
-		   in_params->srq_id);
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "modified SRQ id = %x, is_xrc=%u\n",
+		   in_params->srq_id, in_params->is_xrc);
 
 	return rc;
 }
@@ -1702,6 +1790,7 @@ qed_rdma_destroy_srq(void *rdma_cxt,
 	struct qed_spq_entry *p_ent;
 	struct qed_bmap *bmap;
 	u16 opaque_fid;
+	u16 offset;
 	int rc;
 
 	opaque_fid = p_hwfn->hw_info.opaque_fid;
@@ -1723,14 +1812,16 @@ qed_rdma_destroy_srq(void *rdma_cxt,
 	if (rc)
 		return rc;
 
-	bmap = &p_hwfn->p_rdma_info->srq_map;
+	bmap = qed_rdma_get_srq_bmap(p_hwfn, in_params->is_xrc);
+	offset = (in_params->is_xrc) ? 0 : p_hwfn->p_rdma_info->srq_id_offset;
 
 	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
-	qed_bmap_release_id(p_hwfn, bmap, in_params->srq_id);
+	qed_bmap_release_id(p_hwfn, bmap, in_params->srq_id - offset);
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "SRQ destroyed Id = %x",
-		   in_params->srq_id);
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+		   "XRC/SRQ destroyed Id = %x, is_xrc=%u\n",
+		   in_params->srq_id, in_params->is_xrc);
 
 	return rc;
 }
@@ -1748,24 +1839,26 @@ qed_rdma_create_srq(void *rdma_cxt,
 	u16 opaque_fid, srq_id;
 	struct qed_bmap *bmap;
 	u32 returned_id;
+	u16 offset;
 	int rc;
 
-	bmap = &p_hwfn->p_rdma_info->srq_map;
+	bmap = qed_rdma_get_srq_bmap(p_hwfn, in_params->is_xrc);
 	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
 	rc = qed_rdma_bmap_alloc_id(p_hwfn, bmap, &returned_id);
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 
 	if (rc) {
-		DP_NOTICE(p_hwfn, "failed to allocate srq id\n");
+		DP_NOTICE(p_hwfn,
+			  "failed to allocate xrc/srq id (is_xrc=%u)\n",
+			  in_params->is_xrc);
 		return rc;
 	}
 
-	elem_type = QED_ELEM_SRQ;
+	elem_type = (in_params->is_xrc) ? (QED_ELEM_XRC_SRQ) : (QED_ELEM_SRQ);
 	rc = qed_cxt_dynamic_ilt_alloc(p_hwfn, elem_type, returned_id);
 	if (rc)
 		goto err;
-	/* returned id is no greater than u16 */
-	srq_id = (u16)returned_id;
+
 	opaque_fid = p_hwfn->hw_info.opaque_fid;
 
 	opaque_fid = p_hwfn->hw_info.opaque_fid;
@@ -1782,20 +1875,34 @@ qed_rdma_create_srq(void *rdma_cxt,
 	DMA_REGPAIR_LE(p_ramrod->pbl_base_addr, in_params->pbl_base_addr);
 	p_ramrod->pages_in_srq_pbl = cpu_to_le16(in_params->num_pages);
 	p_ramrod->pd_id = cpu_to_le16(in_params->pd_id);
-	p_ramrod->srq_id.srq_idx = cpu_to_le16(srq_id);
 	p_ramrod->srq_id.opaque_fid = cpu_to_le16(opaque_fid);
 	p_ramrod->page_size = cpu_to_le16(in_params->page_size);
 	DMA_REGPAIR_LE(p_ramrod->producers_addr, in_params->prod_pair_addr);
+	offset = (in_params->is_xrc) ? 0 : p_hwfn->p_rdma_info->srq_id_offset;
+	srq_id = (u16)returned_id + offset;
+	p_ramrod->srq_id.srq_idx = cpu_to_le16(srq_id);
 
+	if (in_params->is_xrc) {
+		SET_FIELD(p_ramrod->flags,
+			  RDMA_SRQ_CREATE_RAMROD_DATA_XRC_FLAG, 1);
+		SET_FIELD(p_ramrod->flags,
+			  RDMA_SRQ_CREATE_RAMROD_DATA_RESERVED_KEY_EN,
+			  in_params->reserved_key_en);
+		p_ramrod->xrc_srq_cq_cid =
+			cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
+				     in_params->cq_cid);
+		p_ramrod->xrc_domain = cpu_to_le16(in_params->xrcd_id);
+	}
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
 	if (rc)
 		goto err;
 
 	out_params->srq_id = srq_id;
 
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
-		   "SRQ created Id = %x\n", out_params->srq_id);
-
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_RDMA,
+		   "XRC/SRQ created Id = %x (is_xrc=%u)\n",
+		   out_params->srq_id, in_params->is_xrc);
 	return rc;
 
 err:
@@ -1961,6 +2068,8 @@ static const struct qed_rdma_ops qed_rdma_ops_pass = {
 	.rdma_cnq_prod_update = &qed_rdma_cnq_prod_update,
 	.rdma_alloc_pd = &qed_rdma_alloc_pd,
 	.rdma_dealloc_pd = &qed_rdma_free_pd,
+	.rdma_alloc_xrcd = &qed_rdma_alloc_xrcd,
+	.rdma_dealloc_xrcd = &qed_rdma_free_xrcd,
 	.rdma_create_cq = &qed_rdma_create_cq,
 	.rdma_destroy_cq = &qed_rdma_destroy_cq,
 	.rdma_create_qp = &qed_rdma_create_qp,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index 3689fe3e5935..5a7ebc764bb6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -63,6 +63,11 @@
 #define QED_RDMA_MAX_CQE_32_BIT             (0x7FFFFFFF - 1)
 #define QED_RDMA_MAX_CQE_16_BIT             (0x7FFF - 1)
 
+/* Up to 2^16 XRC Domains are supported, but the actual number of supported XRC
+ * SRQs is much smaller so there's no need to have that many domains.
+ */
+#define QED_RDMA_MAX_XRCDS      (roundup_pow_of_two(RDMA_MAX_XRC_SRQS))
+
 enum qed_rdma_toggle_bit {
 	QED_RDMA_TOGGLE_BIT_CLEAR = 0,
 	QED_RDMA_TOGGLE_BIT_SET = 1
@@ -81,9 +86,11 @@ struct qed_rdma_info {
 
 	struct qed_bmap cq_map;
 	struct qed_bmap pd_map;
+	struct qed_bmap xrcd_map;
 	struct qed_bmap tid_map;
 	struct qed_bmap qp_map;
 	struct qed_bmap srq_map;
+	struct qed_bmap xrc_srq_map;
 	struct qed_bmap cid_map;
 	struct qed_bmap tcp_cid_map;
 	struct qed_bmap real_cid_map;
@@ -111,6 +118,7 @@ struct qed_rdma_qp {
 	u32 qpid;
 	u16 icid;
 	enum qed_roce_qp_state cur_state;
+	enum qed_rdma_qp_type qp_type;
 	enum qed_iwarp_qp_state iwarp_state;
 	bool use_srq;
 	bool signal_all;
@@ -153,18 +161,21 @@ struct qed_rdma_qp {
 	dma_addr_t orq_phys_addr;
 	u8 orq_num_pages;
 	bool req_offloaded;
+	bool has_req;
 
 	/* responder */
 	u8 max_rd_atomic_resp;
 	u32 rq_psn;
 	u16 rq_cq_id;
 	u16 rq_num_pages;
+	u16 xrcd_id;
 	dma_addr_t rq_pbl_ptr;
 	void *irq;
 	dma_addr_t irq_phys_addr;
 	u8 irq_num_pages;
 	bool resp_offloaded;
 	u32 cq_prod;
+	bool has_resp;
 
 	u8 remote_mac_addr[6];
 	u8 local_mac_addr[6];
@@ -174,6 +185,14 @@ struct qed_rdma_qp {
 	struct qed_iwarp_ep *ep;
 };
 
+static inline bool qed_rdma_is_xrc_qp(struct qed_rdma_qp *qp)
+{
+	if (qp->qp_type == QED_RDMA_QP_TYPE_XRC_TGT ||
+	    qp->qp_type == QED_RDMA_QP_TYPE_XRC_INI)
+		return true;
+
+	return false;
+}
 #if IS_ENABLED(CONFIG_QED_RDMA)
 void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 void qed_rdma_dpm_conf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 475b89903f46..46a4d09eacef 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -254,6 +254,9 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	int rc;
 	u8 tc;
 
+	if (!qp->has_resp)
+		return 0;
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
 	/* Allocate DMA-able memory for IRQ */
@@ -315,6 +318,10 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 		  ROCE_CREATE_QP_RESP_RAMROD_DATA_MIN_RNR_NAK_TIMER,
 		  qp->min_rnr_nak_timer);
 
+	SET_FIELD(p_ramrod->flags,
+		  ROCE_CREATE_QP_RESP_RAMROD_DATA_XRC_FLAG,
+		  qed_rdma_is_xrc_qp(qp));
+
 	p_ramrod->max_ird = qp->max_rd_atomic_resp;
 	p_ramrod->traffic_class = qp->traffic_class_tos;
 	p_ramrod->hop_limit = qp->hop_limit_ttl;
@@ -335,6 +342,7 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
+	p_ramrod->xrc_domain = cpu_to_le16(qp->xrcd_id);
 
 	tc = qed_roce_get_qp_tc(p_hwfn, qp);
 	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
@@ -395,6 +403,9 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	int rc;
 	u8 tc;
 
+	if (!qp->has_req)
+		return 0;
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
 	/* Allocate DMA-able memory for ORQ */
@@ -444,6 +455,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 		  ROCE_CREATE_QP_REQ_RAMROD_DATA_RNR_NAK_CNT,
 		  qp->rnr_retry_cnt);
 
+	SET_FIELD(p_ramrod->flags,
+		  ROCE_CREATE_QP_REQ_RAMROD_DATA_XRC_FLAG,
+		  qed_rdma_is_xrc_qp(qp));
+
 	p_ramrod->max_ord = qp->max_rd_atomic_req;
 	p_ramrod->traffic_class = qp->traffic_class_tos;
 	p_ramrod->hop_limit = qp->hop_limit_ttl;
@@ -517,6 +532,9 @@ static int qed_roce_sp_modify_responder(struct qed_hwfn *p_hwfn,
 	struct qed_spq_entry *p_ent;
 	int rc;
 
+	if (!qp->has_resp)
+		return 0;
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
 	if (move_to_err && !qp->resp_offloaded)
@@ -611,6 +629,9 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
 	struct qed_spq_entry *p_ent;
 	int rc;
 
+	if (!qp->has_req)
+		return 0;
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
 	if (move_to_err && !(qp->req_offloaded))
@@ -705,6 +726,11 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
 	dma_addr_t ramrod_res_phys;
 	int rc;
 
+	if (!qp->has_resp) {
+		*cq_prod = 0;
+		return 0;
+	}
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 	*cq_prod = qp->cq_prod;
 
@@ -785,6 +811,9 @@ static int qed_roce_sp_destroy_qp_requester(struct qed_hwfn *p_hwfn,
 	dma_addr_t ramrod_res_phys;
 	int rc = -ENOMEM;
 
+	if (!qp->has_req)
+		return 0;
+
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
 	if (!qp->req_offloaded)
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index 74efca15fde7..f93edd5750a5 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -53,6 +53,13 @@ enum qed_roce_qp_state {
 	QED_ROCE_QP_STATE_SQE
 };
 
+enum qed_rdma_qp_type {
+	QED_RDMA_QP_TYPE_RC,
+	QED_RDMA_QP_TYPE_XRC_INI,
+	QED_RDMA_QP_TYPE_XRC_TGT,
+	QED_RDMA_QP_TYPE_INVAL = 0xffff,
+};
+
 enum qed_rdma_tid_type {
 	QED_RDMA_TID_REGISTERED_MR,
 	QED_RDMA_TID_FMR,
@@ -291,6 +298,12 @@ struct qed_rdma_create_srq_in_params {
 	u16 num_pages;
 	u16 pd_id;
 	u16 page_size;
+
+	/* XRC related only */
+	bool reserved_key_en;
+	bool is_xrc;
+	u32 cq_cid;
+	u16 xrcd_id;
 };
 
 struct qed_rdma_destroy_cq_in_params {
@@ -319,7 +332,9 @@ struct qed_rdma_create_qp_in_params {
 	u16 rq_num_pages;
 	u64 rq_pbl_ptr;
 	u16 srq_id;
+	u16 xrcd_id;
 	u8 stats_queue;
+	enum qed_rdma_qp_type qp_type;
 };
 
 struct qed_rdma_create_qp_out_params {
@@ -429,11 +444,13 @@ struct qed_rdma_create_srq_out_params {
 
 struct qed_rdma_destroy_srq_in_params {
 	u16 srq_id;
+	bool is_xrc;
 };
 
 struct qed_rdma_modify_srq_in_params {
 	u32 wqe_limit;
 	u16 srq_id;
+	bool is_xrc;
 };
 
 struct qed_rdma_stats_out_params {
@@ -611,6 +628,8 @@ struct qed_rdma_ops {
 	int (*rdma_set_rdma_int)(struct qed_dev *cdev, u16 cnt);
 	int (*rdma_alloc_pd)(void *rdma_cxt, u16 *pd);
 	void (*rdma_dealloc_pd)(void *rdma_cxt, u16 pd);
+	int (*rdma_alloc_xrcd)(void *rdma_cxt, u16 *xrcd);
+	void (*rdma_dealloc_xrcd)(void *rdma_cxt, u16 xrcd);
 	int (*rdma_create_cq)(void *rdma_cxt,
 			      struct qed_rdma_create_cq_in_params *params,
 			      u16 *icid);
-- 
cgit v1.2.3


From a71506a4fda92a39c8ece119876bc7ccde6d3c9d Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 20 May 2020 21:20:51 +0200
Subject: xsk: Move driver interface to xdp_sock_drv.h

Move the AF_XDP zero-copy driver interface to its own include file
called xdp_sock_drv.h. This, hopefully, will make it more clear for
NIC driver implementors to know what functions to use for zero-copy
support.

v4->v5: Fix -Wmissing-prototypes by include header file. (Jakub)

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200520192103.355233-4-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/i40e/i40e_main.c        |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c         |   2 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c           |   2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c       |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h    |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.h    |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.c  |   2 +-
 include/net/xdp_sock.h                             | 214 +-------------------
 include/net/xdp_sock_drv.h                         | 217 +++++++++++++++++++++
 net/ethtool/channels.c                             |   2 +-
 net/ethtool/ioctl.c                                |   2 +-
 net/xdp/xdp_umem.h                                 |   2 +-
 net/xdp/xsk.c                                      |   2 +-
 net/xdp/xsk_queue.c                                |   1 +
 15 files changed, 238 insertions(+), 218 deletions(-)
 create mode 100644 include/net/xdp_sock_drv.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 2a037ec244b9..d6b2db4f2c65 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11,7 +11,7 @@
 #include "i40e_diag.h"
 #include "i40e_xsk.h"
 #include <net/udp_tunnel.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 /* All i40e tracepoints are defined by the include below, which
  * must be included exactly once across the whole kernel with
  * CREATE_TRACE_POINTS defined
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 2b9184aead5f..d8b0be29099a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,7 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 
 #include "i40e.h"
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 23e5515d4527..70e204307a93 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/bpf_trace.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 #include "ice.h"
 #include "ice_base.h"
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index a656ee9a1fae..82e4effae704 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -2,7 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 
 #include "ixgbe.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 761c8979bd41..3507d23f0eb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -31,7 +31,7 @@
  */
 
 #include <linux/bpf_trace.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include "en/xdp.h"
 #include "en/params.h"
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index cab0e93497ae..a8e11adbf426 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -5,7 +5,7 @@
 #define __MLX5_EN_XSK_RX_H__
 
 #include "en.h"
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 /* RX data path */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
index 79b487d89757..39fa0a705856 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
@@ -5,7 +5,7 @@
 #define __MLX5_EN_XSK_TX_H__
 
 #include "en.h"
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 /* TX data path */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
index 4baaa5788320..5e49fdb564b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2019 Mellanox Technologies. */
 
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include "umem.h"
 #include "setup.h"
 #include "en/params.h"
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 8f3f6f5b0dfe..6a986dcbc336 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -15,6 +15,7 @@
 
 struct net_device;
 struct xsk_queue;
+struct xdp_buff;
 
 /* Masks for xdp_umem_page flags.
  * The low 12-bits of the addr will be 0 since this is the page address, so we
@@ -101,27 +102,9 @@ struct xdp_sock {
 	spinlock_t map_list_lock;
 };
 
-struct xdp_buff;
 #ifdef CONFIG_XDP_SOCKETS
-int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
-/* Used from netdev driver */
-bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
-bool xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
-void xsk_umem_release_addr(struct xdp_umem *umem);
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
-struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
-					  struct xdp_umem_fq_reuse *newq);
-void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
 
+int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
 void __xsk_map_flush(void);
 
@@ -153,131 +136,24 @@ static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
 	return xsk_umem_extract_addr(addr) + xsk_umem_extract_offset(addr);
 }
 
-static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
-{
-	unsigned long page_addr;
-
-	addr = xsk_umem_add_offset_to_addr(addr);
-	page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr;
-
-	return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK);
-}
-
-static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
-{
-	addr = xsk_umem_add_offset_to_addr(addr);
-
-	return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK);
-}
-
-/* Reuse-queue aware version of FILL queue helpers */
-static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
-{
-	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
-	if (rq->length >= cnt)
-		return true;
-
-	return xsk_umem_has_addrs(umem, cnt - rq->length);
-}
-
-static inline bool xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
-{
-	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
-	if (!rq->length)
-		return xsk_umem_peek_addr(umem, addr);
-
-	*addr = rq->handles[rq->length - 1];
-	return addr;
-}
-
-static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem)
-{
-	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
-	if (!rq->length)
-		xsk_umem_release_addr(umem);
-	else
-		rq->length--;
-}
-
-static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
-{
-	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
-
-	rq->handles[rq->length++] = addr;
-}
-
-/* Handle the offset appropriately depending on aligned or unaligned mode.
- * For unaligned mode, we store the offset in the upper 16-bits of the address.
- * For aligned mode, we simply add the offset to the address.
- */
-static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
-					 u64 offset)
-{
-	if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG)
-		return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
-	else
-		return address + offset;
-}
-
-static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
-{
-	return umem->chunk_size_nohr;
-}
-
 #else
+
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	return -ENOTSUPP;
 }
 
-static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
-{
-	return false;
-}
-
-static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
-{
-	return NULL;
-}
-
-static inline void xsk_umem_release_addr(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
-{
-}
-
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
-				       struct xdp_desc *desc)
-{
-	return false;
-}
-
-static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
-{
-}
-
-static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
+static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
-	return NULL;
+	return -EOPNOTSUPP;
 }
 
-static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
-	struct xdp_umem *umem,
-	struct xdp_umem_fq_reuse *newq)
-{
-	return NULL;
-}
-static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
+static inline void __xsk_map_flush(void)
 {
 }
 
-static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
-						     u16 queue_id)
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+						     u32 key)
 {
 	return NULL;
 }
@@ -297,80 +173,6 @@ static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
 	return 0;
 }
 
-static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
-{
-	return NULL;
-}
-
-static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
-{
-	return 0;
-}
-
-static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
-{
-	return false;
-}
-
-static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
-{
-	return NULL;
-}
-
-static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
-{
-}
-
-static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
-{
-}
-
-static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
-{
-	return false;
-}
-
-static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
-					 u64 offset)
-{
-	return 0;
-}
-
-static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
-{
-	return 0;
-}
-
-static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void __xsk_map_flush(void)
-{
-}
-
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
-						     u32 key)
-{
-	return NULL;
-}
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
new file mode 100644
index 000000000000..d67f2361937a
--- /dev/null
+++ b/include/net/xdp_sock_drv.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Interface for implementing AF_XDP zero-copy support in drivers.
+ * Copyright(c) 2020 Intel Corporation.
+ */
+
+#ifndef _LINUX_XDP_SOCK_DRV_H
+#define _LINUX_XDP_SOCK_DRV_H
+
+#include <net/xdp_sock.h>
+
+#ifdef CONFIG_XDP_SOCKETS
+
+bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
+bool xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
+void xsk_umem_release_addr(struct xdp_umem *umem);
+void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
+bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
+void xsk_umem_consume_tx_done(struct xdp_umem *umem);
+struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
+struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
+					  struct xdp_umem_fq_reuse *newq);
+void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
+struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
+bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
+{
+	unsigned long page_addr;
+
+	addr = xsk_umem_add_offset_to_addr(addr);
+	page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr;
+
+	return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK);
+}
+
+static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
+{
+	addr = xsk_umem_add_offset_to_addr(addr);
+
+	return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK);
+}
+
+/* Reuse-queue aware version of FILL queue helpers */
+static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
+{
+	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+	if (rq->length >= cnt)
+		return true;
+
+	return xsk_umem_has_addrs(umem, cnt - rq->length);
+}
+
+static inline bool xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
+{
+	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+	if (!rq->length)
+		return xsk_umem_peek_addr(umem, addr);
+
+	*addr = rq->handles[rq->length - 1];
+	return addr;
+}
+
+static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem)
+{
+	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+	if (!rq->length)
+		xsk_umem_release_addr(umem);
+	else
+		rq->length--;
+}
+
+static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
+{
+	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+	rq->handles[rq->length++] = addr;
+}
+
+/* Handle the offset appropriately depending on aligned or unaligned mode.
+ * For unaligned mode, we store the offset in the upper 16-bits of the address.
+ * For aligned mode, we simply add the offset to the address.
+ */
+static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
+					 u64 offset)
+{
+	if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+		return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+	else
+		return address + offset;
+}
+
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return umem->chunk_size_nohr;
+}
+
+#else
+
+static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
+{
+	return false;
+}
+
+static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
+{
+	return NULL;
+}
+
+static inline void xsk_umem_release_addr(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+{
+}
+
+static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
+				       struct xdp_desc *desc)
+{
+	return false;
+}
+
+static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+{
+}
+
+static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
+{
+	return NULL;
+}
+
+static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
+	struct xdp_umem *umem, struct xdp_umem_fq_reuse *newq)
+{
+	return NULL;
+}
+
+static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
+{
+}
+
+static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
+						     u16 queue_id)
+{
+	return NULL;
+}
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
+{
+	return NULL;
+}
+
+static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
+{
+	return 0;
+}
+
+static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
+{
+	return false;
+}
+
+static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
+{
+	return NULL;
+}
+
+static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
+{
+}
+
+static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+{
+	return false;
+}
+
+static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
+					 u64 offset)
+{
+	return 0;
+}
+
+static inline u32 xsk_umem_xdp_frame_sz(struct xdp_umem *umem)
+{
+	return 0;
+}
+
+#endif /* CONFIG_XDP_SOCKETS */
+
+#endif /* _LINUX_XDP_SOCK_DRV_H */
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 389924b65d05..658a8580b464 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 #include "netlink.h"
 #include "common.h"
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 52102ab1709b..74892623bacd 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -24,7 +24,7 @@
 #include <linux/sched/signal.h>
 #include <linux/net.h>
 #include <net/devlink.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/flow_offload.h>
 #include <linux/ethtool_netlink.h>
 #include <generated/utsrelease.h>
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index a63a9fb251f5..32067fe98f65 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -6,7 +6,7 @@
 #ifndef XDP_UMEM_H_
 #define XDP_UMEM_H_
 
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 			u16 queue_id, u16 flags);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 45ffd67b367d..8bda654e82ec 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -22,7 +22,7 @@
 #include <linux/net.h>
 #include <linux/netdevice.h>
 #include <linux/rculist.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 
 #include "xsk_queue.h"
diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
index 57fb81bd593c..554b1ebb4d02 100644
--- a/net/xdp/xsk_queue.c
+++ b/net/xdp/xsk_queue.c
@@ -6,6 +6,7 @@
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/overflow.h>
+#include <net/xdp_sock_drv.h>
 
 #include "xsk_queue.h"
 
-- 
cgit v1.2.3


From e1675f97367bed74d4dcfe08de9ce9b5d6b288c1 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:54 +0200
Subject: i40e: Refactor rx_bi accesses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As a first step to migrate i40e to the new MEM_TYPE_XSK_BUFF_POOL
APIs, code that accesses the rx_bi (SW/shadow ring) is refactored to
use an accessor function.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-7-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 17 +++++++++++------
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 18 ++++++++++++------
 2 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index a3772beffe02..9b9ef951f9ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1195,6 +1195,11 @@ clear_counts:
 	rc->total_packets = 0;
 }
 
+static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->rx_bi[idx];
+}
+
 /**
  * i40e_reuse_rx_page - page flip buffer and store it back on the ring
  * @rx_ring: rx descriptor ring to store buffers on
@@ -1208,7 +1213,7 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	struct i40e_rx_buffer *new_buff;
 	u16 nta = rx_ring->next_to_alloc;
 
-	new_buff = &rx_ring->rx_bi[nta];
+	new_buff = i40e_rx_bi(rx_ring, nta);
 
 	/* update, and store next to alloc */
 	nta++;
@@ -1272,7 +1277,7 @@ struct i40e_rx_buffer *i40e_clean_programming_status(
 	ntc = rx_ring->next_to_clean;
 
 	/* fetch, update, and store next to clean */
-	rx_buffer = &rx_ring->rx_bi[ntc++];
+	rx_buffer = i40e_rx_bi(rx_ring, ntc++);
 	ntc = (ntc < rx_ring->count) ? ntc : 0;
 	rx_ring->next_to_clean = ntc;
 
@@ -1361,7 +1366,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 
 	/* Free all the Rx ring sk_buffs */
 	for (i = 0; i < rx_ring->count; i++) {
-		struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+		struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
 
 		if (!rx_bi->page)
 			continue;
@@ -1592,7 +1597,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		return false;
 
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_bi[ntu];
+	bi = i40e_rx_bi(rx_ring, ntu);
 
 	do {
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
@@ -1614,7 +1619,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		ntu++;
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = I40E_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_bi;
+			bi = i40e_rx_bi(rx_ring, 0);
 			ntu = 0;
 		}
 
@@ -1981,7 +1986,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
 {
 	struct i40e_rx_buffer *rx_buffer;
 
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 	prefetchw(rx_buffer->page);
 
 	/* we are reusing so sync this buffer for CPU use */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index d8b0be29099a..d84ec92f8538 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -9,6 +9,11 @@
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
 
+static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->rx_bi[idx];
+}
+
 /**
  * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
  * @vsi: Current VSI
@@ -321,7 +326,7 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
 	bool ok = true;
 
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_bi[ntu];
+	bi = i40e_rx_bi(rx_ring, ntu);
 	do {
 		if (!alloc(rx_ring, bi)) {
 			ok = false;
@@ -340,7 +345,7 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
 
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = I40E_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_bi;
+			bi = i40e_rx_bi(rx_ring, 0);
 			ntu = 0;
 		}
 
@@ -402,7 +407,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
 {
 	struct i40e_rx_buffer *bi;
 
-	bi = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev,
@@ -424,7 +429,8 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
 static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
 				    struct i40e_rx_buffer *old_bi)
 {
-	struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc];
+	struct i40e_rx_buffer *new_bi = i40e_rx_bi(rx_ring,
+						   rx_ring->next_to_alloc);
 	u16 nta = rx_ring->next_to_alloc;
 
 	/* update, and store next to alloc */
@@ -456,7 +462,7 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
 	mask = rx_ring->xsk_umem->chunk_mask;
 
 	nta = rx_ring->next_to_alloc;
-	bi = &rx_ring->rx_bi[nta];
+	bi = i40e_rx_bi(rx_ring, nta);
 
 	nta++;
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
@@ -826,7 +832,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 	u16 i;
 
 	for (i = 0; i < rx_ring->count; i++) {
-		struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+		struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
 
 		if (!rx_bi->addr)
 			continue;
-- 
cgit v1.2.3


From be1222b585fdc410b8c1dbcc57dd03a00f04eff5 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:55 +0200
Subject: i40e: Separate kernel allocated rx_bi rings from AF_XDP rings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Continuing the path to support MEM_TYPE_XSK_BUFF_POOL, the AF_XDP
zero-copy/sk_buff rx_bi rings are now separate. Functions to properly
allocate the different rings are added as well.

v3->v4: Made i40e_fd_handle_status() static. (kbuild test robot)
v4->v5: Fix kdoc for i40e_clean_programming_status(). (Jakub)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-8-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/i40e/i40e_main.c        |   7 ++
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        | 119 ++++++++-------------
 drivers/net/ethernet/intel/i40e/i40e_txrx.h        |  22 ++--
 drivers/net/ethernet/intel/i40e/i40e_txrx_common.h |  40 +++++--
 drivers/net/ethernet/intel/i40e/i40e_type.h        |   5 +-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c         |  74 +++++++------
 drivers/net/ethernet/intel/i40e/i40e_xsk.h         |   2 +
 7 files changed, 142 insertions(+), 127 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index d6b2db4f2c65..3e1695bb8262 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3260,8 +3260,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (ring->vsi->type == I40E_VSI_MAIN)
 		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
+	kfree(ring->rx_bi);
 	ring->xsk_umem = i40e_xsk_umem(ring);
 	if (ring->xsk_umem) {
+		ret = i40e_alloc_rx_bi_zc(ring);
+		if (ret)
+			return ret;
 		ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
 				   XDP_PACKET_HEADROOM;
 		/* For AF_XDP ZC, we disallow packets to span on
@@ -3280,6 +3284,9 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 			 ring->queue_index);
 
 	} else {
+		ret = i40e_alloc_rx_bi(ring);
+		if (ret)
+			return ret;
 		ring->rx_buf_len = vsi->rx_buf_len;
 		if (ring->vsi->type == I40E_VSI_MAIN) {
 			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9b9ef951f9ce..f613782f2f56 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -521,28 +521,29 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 /**
  * i40e_fd_handle_status - check the Programming Status for FD
  * @rx_ring: the Rx ring for this descriptor
- * @rx_desc: the Rx descriptor for programming Status, not a packet descriptor.
+ * @qword0_raw: qword0
+ * @qword1: qword1 after le_to_cpu
  * @prog_id: the id originally used for programming
  *
  * This is used to verify if the FD programming or invalidation
  * requested by SW to the HW is successful or not and take actions accordingly.
  **/
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
-			   union i40e_rx_desc *rx_desc, u8 prog_id)
+static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				  u64 qword1, u8 prog_id)
 {
 	struct i40e_pf *pf = rx_ring->vsi->back;
 	struct pci_dev *pdev = pf->pdev;
+	struct i40e_32b_rx_wb_qw0 *qw0;
 	u32 fcnt_prog, fcnt_avail;
 	u32 error;
-	u64 qw;
 
-	qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
+	qw0 = (struct i40e_32b_rx_wb_qw0 *)&qword0_raw;
+	error = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
 		I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
 
 	if (error == BIT(I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) {
-		pf->fd_inv = le32_to_cpu(rx_desc->wb.qword0.hi_dword.fd_id);
-		if ((rx_desc->wb.qword0.hi_dword.fd_id != 0) ||
+		pf->fd_inv = le32_to_cpu(qw0->hi_dword.fd_id);
+		if (qw0->hi_dword.fd_id != 0 ||
 		    (I40E_DEBUG_FD & pf->hw.debug_mask))
 			dev_warn(&pdev->dev, "ntuple filter loc = %d, could not be added\n",
 				 pf->fd_inv);
@@ -560,7 +561,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		/* store the current atr filter count */
 		pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
 
-		if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
+		if (qw0->hi_dword.fd_id == 0 &&
 		    test_bit(__I40E_FD_SB_AUTO_DISABLED, pf->state)) {
 			/* These set_bit() calls aren't atomic with the
 			 * test_bit() here, but worse case we potentially
@@ -589,7 +590,7 @@ void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 	} else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) {
 		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pdev->dev, "ntuple filter fd_id = %d, could not be removed\n",
-				 rx_desc->wb.qword0.hi_dword.fd_id);
+				 qw0->hi_dword.fd_id);
 	}
 }
 
@@ -1232,29 +1233,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 }
 
 /**
- * i40e_rx_is_programming_status - check for programming status descriptor
- * @qw: qword representing status_error_len in CPU ordering
- *
- * The value of in the descriptor length field indicate if this
- * is a programming status descriptor for flow director or FCoE
- * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
- * it is a packet descriptor.
- **/
-static inline bool i40e_rx_is_programming_status(u64 qw)
-{
-	/* The Rx filter programming status and SPH bit occupy the same
-	 * spot in the descriptor. Since we don't support packet split we
-	 * can just reuse the bit as an indication that this is a
-	 * programming status descriptor.
-	 */
-	return qw & I40E_RXD_QW1_LENGTH_SPH_MASK;
-}
-
-/**
- * i40e_clean_programming_status - try clean the programming status descriptor
+ * i40e_clean_programming_status - clean the programming status descriptor
  * @rx_ring: the rx ring that has this descriptor
- * @rx_desc: the rx descriptor written back by HW
- * @qw: qword representing status_error_len in CPU ordering
+ * @qword0_raw: qword0
+ * @qword1: qword1 representing status_error_len in CPU ordering
  *
  * Flow director should handle FD_FILTER_STATUS to check its filter programming
  * status being successful or not and take actions accordingly. FCoE should
@@ -1262,34 +1244,16 @@ static inline bool i40e_rx_is_programming_status(u64 qw)
  *
  * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL.
  **/
-struct i40e_rx_buffer *i40e_clean_programming_status(
-	struct i40e_ring *rx_ring,
-	union i40e_rx_desc *rx_desc,
-	u64 qw)
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				   u64 qword1)
 {
-	struct i40e_rx_buffer *rx_buffer;
-	u32 ntc;
 	u8 id;
 
-	if (!i40e_rx_is_programming_status(qw))
-		return NULL;
-
-	ntc = rx_ring->next_to_clean;
-
-	/* fetch, update, and store next to clean */
-	rx_buffer = i40e_rx_bi(rx_ring, ntc++);
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
-
-	id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
+	id = (qword1 & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
 		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
-		i40e_fd_handle_status(rx_ring, rx_desc, id);
-
-	return rx_buffer;
+		i40e_fd_handle_status(rx_ring, qword0_raw, qword1, id);
 }
 
 /**
@@ -1341,13 +1305,25 @@ err:
 	return -ENOMEM;
 }
 
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring)
+{
+	unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count;
+
+	rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL);
+	return rx_ring->rx_bi ? 0 : -ENOMEM;
+}
+
+static void i40e_clear_rx_bi(struct i40e_ring *rx_ring)
+{
+	memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count);
+}
+
 /**
  * i40e_clean_rx_ring - Free Rx buffers
  * @rx_ring: ring to be cleaned
  **/
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	unsigned long bi_size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
@@ -1393,8 +1369,10 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 	}
 
 skip_free:
-	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_bi, 0, bi_size);
+	if (rx_ring->xsk_umem)
+		i40e_clear_rx_bi_zc(rx_ring);
+	else
+		i40e_clear_rx_bi(rx_ring);
 
 	/* Zero out the descriptor ring */
 	memset(rx_ring->desc, 0, rx_ring->size);
@@ -1435,15 +1413,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int err = -ENOMEM;
-	int bi_size;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_bi);
-	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
-	rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
-	if (!rx_ring->rx_bi)
-		goto err;
+	int err;
 
 	u64_stats_init(&rx_ring->syncp);
 
@@ -1456,7 +1426,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	if (!rx_ring->desc) {
 		dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			 rx_ring->size);
-		goto err;
+		return -ENOMEM;
 	}
 
 	rx_ring->next_to_alloc = 0;
@@ -1468,16 +1438,12 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
 				       rx_ring->queue_index);
 		if (err < 0)
-			goto err;
+			return err;
 	}
 
 	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
 
 	return 0;
-err:
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
-	return err;
 }
 
 /**
@@ -2387,9 +2353,12 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc,
-							  qword);
-		if (unlikely(rx_buffer)) {
+		if (i40e_rx_is_programming_status(qword)) {
+			i40e_clean_programming_status(rx_ring,
+						      rx_desc->raw.qword[0],
+						      qword);
+			rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+			i40e_inc_ntc(rx_ring);
 			i40e_reuse_rx_page(rx_ring, rx_buffer);
 			cleaned_count++;
 			continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 36d37f31a287..d343498e8de5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -296,17 +296,15 @@ struct i40e_tx_buffer {
 
 struct i40e_rx_buffer {
 	dma_addr_t dma;
-	union {
-		struct {
-			struct page *page;
-			__u32 page_offset;
-			__u16 pagecnt_bias;
-		};
-		struct {
-			void *addr;
-			u64 handle;
-		};
-	};
+	struct page *page;
+	__u32 page_offset;
+	__u16 pagecnt_bias;
+};
+
+struct i40e_rx_buffer_zc {
+	dma_addr_t dma;
+	void *addr;
+	u64 handle;
 };
 
 struct i40e_queue_stats {
@@ -358,6 +356,7 @@ struct i40e_ring {
 	union {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
+		struct i40e_rx_buffer_zc *rx_bi_zc;
 	};
 	DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
 	u16 queue_index;		/* Queue number of ring */
@@ -495,6 +494,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
 int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		  u32 flags);
+int i40e_alloc_rx_bi(struct i40e_ring *rx_ring);
 
 /**
  * i40e_get_head - Retrieve head from head writeback
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index 8af0e99c6c0d..667c4dc4b39f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -4,13 +4,9 @@
 #ifndef I40E_TXRX_COMMON_
 #define I40E_TXRX_COMMON_
 
-void i40e_fd_handle_status(struct i40e_ring *rx_ring,
-			   union i40e_rx_desc *rx_desc, u8 prog_id);
 int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
-struct i40e_rx_buffer *i40e_clean_programming_status(
-	struct i40e_ring *rx_ring,
-	union i40e_rx_desc *rx_desc,
-	u64 qw);
+void i40e_clean_programming_status(struct i40e_ring *rx_ring, u64 qword0_raw,
+				   u64 qword1);
 void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 			     union i40e_rx_desc *rx_desc, struct sk_buff *skb);
 void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
@@ -84,6 +80,38 @@ static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
 	}
 }
 
+/**
+ * i40e_rx_is_programming_status - check for programming status descriptor
+ * @qword1: qword1 representing status_error_len in CPU ordering
+ *
+ * The value of in the descriptor length field indicate if this
+ * is a programming status descriptor for flow director or FCoE
+ * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise
+ * it is a packet descriptor.
+ **/
+static inline bool i40e_rx_is_programming_status(u64 qword1)
+{
+	/* The Rx filter programming status and SPH bit occupy the same
+	 * spot in the descriptor. Since we don't support packet split we
+	 * can just reuse the bit as an indication that this is a
+	 * programming status descriptor.
+	 */
+	return qword1 & I40E_RXD_QW1_LENGTH_SPH_MASK;
+}
+
+/**
+ * i40e_inc_ntc: Advance the next_to_clean index
+ * @rx_ring: Rx ring
+ **/
+static inline void i40e_inc_ntc(struct i40e_ring *rx_ring)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+	prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
 void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring);
 void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring);
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 6ea2867ff60f..63e098f7cb63 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -689,7 +689,7 @@ union i40e_32byte_rx_desc {
 		__le64  rsvd2;
 	} read;
 	struct {
-		struct {
+		struct i40e_32b_rx_wb_qw0 {
 			struct {
 				union {
 					__le16 mirroring_status;
@@ -727,6 +727,9 @@ union i40e_32byte_rx_desc {
 			} hi_dword;
 		} qword3;
 	} wb;  /* writeback */
+	struct {
+		u64 qword[4];
+	} raw;
 };
 
 enum i40e_rx_desc_status_bits {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index d84ec92f8538..4fca52a30ea4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -9,9 +9,23 @@
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
 
-static struct i40e_rx_buffer *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring)
 {
-	return &rx_ring->rx_bi[idx];
+	unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count;
+
+	rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL);
+	return rx_ring->rx_bi_zc ? 0 : -ENOMEM;
+}
+
+void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
+{
+	memset(rx_ring->rx_bi_zc, 0,
+	       sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
+}
+
+static struct i40e_rx_buffer_zc *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->rx_bi_zc[idx];
 }
 
 /**
@@ -238,7 +252,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 }
 
 /**
- * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer
+ * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer_zc
  * @rx_ring: Rx ring
  * @bi: Rx buffer to populate
  *
@@ -248,7 +262,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
  * Returns true for a successful allocation, false otherwise
  **/
 static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
-				 struct i40e_rx_buffer *bi)
+				 struct i40e_rx_buffer_zc *bi)
 {
 	struct xdp_umem *umem = rx_ring->xsk_umem;
 	void *addr = bi->addr;
@@ -279,7 +293,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
 }
 
 /**
- * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer
+ * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer_zc
  * @rx_ring: Rx ring
  * @bi: Rx buffer to populate
  *
@@ -289,7 +303,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
  * Returns true for a successful allocation, false otherwise
  **/
 static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer *bi)
+				      struct i40e_rx_buffer_zc *bi)
 {
 	struct xdp_umem *umem = rx_ring->xsk_umem;
 	u64 handle, hr;
@@ -318,11 +332,11 @@ static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
 static __always_inline bool
 __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
 			   bool alloc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer *bi))
+				      struct i40e_rx_buffer_zc *bi))
 {
 	u16 ntu = rx_ring->next_to_use;
 	union i40e_rx_desc *rx_desc;
-	struct i40e_rx_buffer *bi;
+	struct i40e_rx_buffer_zc *bi;
 	bool ok = true;
 
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
@@ -402,10 +416,11 @@ static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
  *
  * Returns the received Rx buffer
  **/
-static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
-						    const unsigned int size)
+static struct i40e_rx_buffer_zc *i40e_get_rx_buffer_zc(
+	struct i40e_ring *rx_ring,
+	const unsigned int size)
 {
-	struct i40e_rx_buffer *bi;
+	struct i40e_rx_buffer_zc *bi;
 
 	bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 
@@ -427,10 +442,10 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
  * recycle queue (next_to_alloc).
  **/
 static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
-				    struct i40e_rx_buffer *old_bi)
+				    struct i40e_rx_buffer_zc *old_bi)
 {
-	struct i40e_rx_buffer *new_bi = i40e_rx_bi(rx_ring,
-						   rx_ring->next_to_alloc);
+	struct i40e_rx_buffer_zc *new_bi = i40e_rx_bi(rx_ring,
+						      rx_ring->next_to_alloc);
 	u16 nta = rx_ring->next_to_alloc;
 
 	/* update, and store next to alloc */
@@ -452,7 +467,7 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
  **/
 void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
 {
-	struct i40e_rx_buffer *bi;
+	struct i40e_rx_buffer_zc *bi;
 	struct i40e_ring *rx_ring;
 	u64 hr, mask;
 	u16 nta;
@@ -490,7 +505,7 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
  * Returns the skb, or NULL on failure.
  **/
 static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
-					     struct i40e_rx_buffer *bi,
+					     struct i40e_rx_buffer_zc *bi,
 					     struct xdp_buff *xdp)
 {
 	unsigned int metasize = xdp->data - xdp->data_meta;
@@ -513,19 +528,6 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 	return skb;
 }
 
-/**
- * i40e_inc_ntc: Advance the next_to_clean index
- * @rx_ring: Rx ring
- **/
-static void i40e_inc_ntc(struct i40e_ring *rx_ring)
-{
-	u32 ntc = rx_ring->next_to_clean + 1;
-
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
-}
-
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring
@@ -547,7 +549,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
-		struct i40e_rx_buffer *bi;
+		struct i40e_rx_buffer_zc *bi;
 		union i40e_rx_desc *rx_desc;
 		unsigned int size;
 		u64 qword;
@@ -568,14 +570,18 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		bi = i40e_clean_programming_status(rx_ring, rx_desc,
-						   qword);
-		if (unlikely(bi)) {
+		if (i40e_rx_is_programming_status(qword)) {
+			i40e_clean_programming_status(rx_ring,
+						      rx_desc->raw.qword[0],
+						      qword);
+			bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+			i40e_inc_ntc(rx_ring);
 			i40e_reuse_rx_buffer_zc(rx_ring, bi);
 			cleaned_count++;
 			continue;
 		}
 
+		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
 		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
 		if (!size)
@@ -832,7 +838,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 	u16 i;
 
 	for (i = 0; i < rx_ring->count; i++) {
-		struct i40e_rx_buffer *rx_bi = i40e_rx_bi(rx_ring, i);
+		struct i40e_rx_buffer_zc *rx_bi = i40e_rx_bi(rx_ring, i);
 
 		if (!rx_bi->addr)
 			continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 9ed59c14eb55..f5e292c218ee 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -19,5 +19,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
 bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 			   struct i40e_ring *tx_ring, int napi_budget);
 int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring);
+void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring);
 
 #endif /* _I40E_XSK_H_ */
-- 
cgit v1.2.3


From 3b4f0b66c2b3dceea01bd26efa8c4c6f01b4961f Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:56 +0200
Subject: i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs. The AF_XDP zero-copy rx_bi ring is now simply a struct xdp_buff
pointer.

v4->v5: Fixed "warning: Excess function parameter 'bi' description in
        'i40e_construct_skb_zc'". (Jakub)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-9-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/i40e/i40e_main.c |  19 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h |   9 +-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 353 +++-------------------------
 drivers/net/ethernet/intel/i40e/i40e_xsk.h  |   1 -
 4 files changed, 47 insertions(+), 335 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3e1695bb8262..ea7395b391e5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3266,21 +3266,19 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		ret = i40e_alloc_rx_bi_zc(ring);
 		if (ret)
 			return ret;
-		ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
-				   XDP_PACKET_HEADROOM;
+		ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
 		/* For AF_XDP ZC, we disallow packets to span on
 		 * multiple buffers, thus letting us skip that
 		 * handling in the fast-path.
 		 */
 		chain_len = 1;
-		ring->zca.free = i40e_zca_free;
 		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-						 MEM_TYPE_ZERO_COPY,
-						 &ring->zca);
+						 MEM_TYPE_XSK_BUFF_POOL,
+						 NULL);
 		if (ret)
 			return ret;
 		dev_info(&vsi->back->pdev->dev,
-			 "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
@@ -3351,9 +3349,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
-	ok = ring->xsk_umem ?
-	     i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
-	     !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+	if (ring->xsk_umem) {
+		xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
+		ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
+	} else {
+		ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+	}
 	if (!ok) {
 		/* Log this in case the user has forgotten to give the kernel
 		 * any buffers, even later in the application.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index d343498e8de5..5c255977fd58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -301,12 +301,6 @@ struct i40e_rx_buffer {
 	__u16 pagecnt_bias;
 };
 
-struct i40e_rx_buffer_zc {
-	dma_addr_t dma;
-	void *addr;
-	u64 handle;
-};
-
 struct i40e_queue_stats {
 	u64 packets;
 	u64 bytes;
@@ -356,7 +350,7 @@ struct i40e_ring {
 	union {
 		struct i40e_tx_buffer *tx_bi;
 		struct i40e_rx_buffer *rx_bi;
-		struct i40e_rx_buffer_zc *rx_bi_zc;
+		struct xdp_buff **rx_bi_zc;
 	};
 	DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
 	u16 queue_index;		/* Queue number of ring */
@@ -418,7 +412,6 @@ struct i40e_ring {
 	struct i40e_channel *ch;
 	struct xdp_rxq_info xdp_rxq;
 	struct xdp_umem *xsk_umem;
-	struct zero_copy_allocator zca; /* ZC allocator anchor */
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 4fca52a30ea4..f3953744c505 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -23,68 +23,11 @@ void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
 	       sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
 }
 
-static struct i40e_rx_buffer_zc *i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
 {
 	return &rx_ring->rx_bi_zc[idx];
 }
 
-/**
- * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
- * @vsi: Current VSI
- * @umem: UMEM to DMA map
- *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i, j;
-	dma_addr_t dma;
-
-	dev = &pf->pdev->dev;
-	for (i = 0; i < umem->npgs; i++) {
-		dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
-					 DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
-		if (dma_mapping_error(dev, dma))
-			goto out_unmap;
-
-		umem->pages[i].dma = dma;
-	}
-
-	return 0;
-
-out_unmap:
-	for (j = 0; j < i; j++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
-		umem->pages[i].dma = 0;
-	}
-
-	return -1;
-}
-
-/**
- * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev
- * @vsi: Current VSI
- * @umem: UMEM to DMA map
- **/
-static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
-{
-	struct i40e_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i;
-
-	dev = &pf->pdev->dev;
-
-	for (i = 0; i < umem->npgs; i++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
-
-		umem->pages[i].dma = 0;
-	}
-}
-
 /**
  * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
  * @vsi: Current VSI
@@ -97,7 +40,6 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 				u16 qid)
 {
 	struct net_device *netdev = vsi->netdev;
-	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
 
@@ -111,13 +53,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
-	if (!reuseq)
-		return -ENOMEM;
-
-	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
-	err = i40e_xsk_umem_dma_map(vsi, umem);
+	err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -170,7 +106,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 	}
 
 	clear_bit(qid, vsi->af_xdp_zc_qps);
-	i40e_xsk_umem_dma_unmap(vsi, umem);
+	xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR);
 
 	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
@@ -209,11 +145,9 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
  **/
 static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 {
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	int err, result = I40E_XDP_PASS;
 	struct i40e_ring *xdp_ring;
 	struct bpf_prog *xdp_prog;
-	u64 offset;
 	u32 act;
 
 	rcu_read_lock();
@@ -222,9 +156,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	 */
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	offset = xdp->data - xdp->data_hard_start;
-
-	xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
 
 	switch (act) {
 	case XDP_PASS:
@@ -251,107 +182,26 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	return result;
 }
 
-/**
- * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer_zc
- * @rx_ring: Rx ring
- * @bi: Rx buffer to populate
- *
- * This function allocates an Rx buffer. The buffer can come from fill
- * queue, or via the recycle queue (next_to_alloc).
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
-				 struct i40e_rx_buffer_zc *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	void *addr = bi->addr;
-	u64 handle, hr;
-
-	if (addr) {
-		rx_ring->rx_stats.page_reuse_count++;
-		return true;
-	}
-
-	if (!xsk_umem_peek_addr(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr(umem);
-	return true;
-}
-
-/**
- * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer_zc
- * @rx_ring: Rx ring
- * @bi: Rx buffer to populate
- *
- * This function allocates an Rx buffer. The buffer can come from fill
- * queue, or via the reuse queue.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer_zc *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	u64 handle, hr;
-
-	if (!xsk_umem_peek_addr_rq(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	handle &= rx_ring->xsk_umem->chunk_mask;
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr_rq(umem);
-	return true;
-}
-
-static __always_inline bool
-__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
-			   bool alloc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer_zc *bi))
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 {
 	u16 ntu = rx_ring->next_to_use;
 	union i40e_rx_desc *rx_desc;
-	struct i40e_rx_buffer_zc *bi;
+	struct xdp_buff **bi, *xdp;
+	dma_addr_t dma;
 	bool ok = true;
 
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
 	bi = i40e_rx_bi(rx_ring, ntu);
 	do {
-		if (!alloc(rx_ring, bi)) {
+		xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		if (!xdp) {
 			ok = false;
 			goto no_buffers;
 		}
-
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
-						 rx_ring->rx_buf_len,
-						 DMA_BIDIRECTIONAL);
-
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+		*bi = xdp;
+		dma = xsk_buff_xdp_get_dma(xdp);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
+		rx_desc->read.hdr_addr = 0;
 
 		rx_desc++;
 		bi++;
@@ -363,7 +213,6 @@ __i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
 			ntu = 0;
 		}
 
-		rx_desc->wb.qword1.status_error_len = 0;
 		count--;
 	} while (count);
 
@@ -374,130 +223,9 @@ no_buffers:
 	return ok;
 }
 
-/**
- * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
- * @rx_ring: Rx ring
- * @count: The number of buffers to allocate
- *
- * This function allocates a number of Rx buffers from the reuse queue
- * or fill ring and places them on the Rx ring.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
-{
-	return __i40e_alloc_rx_buffers_zc(rx_ring, count,
-					  i40e_alloc_buffer_slow_zc);
-}
-
-/**
- * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers
- * @rx_ring: Rx ring
- * @count: The number of buffers to allocate
- *
- * This function allocates a number of Rx buffers from the fill ring
- * or the internal recycle mechanism and places them on the Rx ring.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
-{
-	return __i40e_alloc_rx_buffers_zc(rx_ring, count,
-					  i40e_alloc_buffer_zc);
-}
-
-/**
- * i40e_get_rx_buffer_zc - Return the current Rx buffer
- * @rx_ring: Rx ring
- * @size: The size of the rx buffer (read from descriptor)
- *
- * This function returns the current, received Rx buffer, and also
- * does DMA synchronization.  the Rx ring.
- *
- * Returns the received Rx buffer
- **/
-static struct i40e_rx_buffer_zc *i40e_get_rx_buffer_zc(
-	struct i40e_ring *rx_ring,
-	const unsigned int size)
-{
-	struct i40e_rx_buffer_zc *bi;
-
-	bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      bi->dma, 0,
-				      size,
-				      DMA_BIDIRECTIONAL);
-
-	return bi;
-}
-
-/**
- * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer
- * @rx_ring: Rx ring
- * @old_bi: The Rx buffer to recycle
- *
- * This function recycles a finished Rx buffer, and places it on the
- * recycle queue (next_to_alloc).
- **/
-static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
-				    struct i40e_rx_buffer_zc *old_bi)
-{
-	struct i40e_rx_buffer_zc *new_bi = i40e_rx_bi(rx_ring,
-						      rx_ring->next_to_alloc);
-	u16 nta = rx_ring->next_to_alloc;
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_bi->dma = old_bi->dma;
-	new_bi->addr = old_bi->addr;
-	new_bi->handle = old_bi->handle;
-
-	old_bi->addr = NULL;
-}
-
-/**
- * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations
- * @alloc: Zero-copy allocator
- * @handle: Buffer handle
- **/
-void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
-{
-	struct i40e_rx_buffer_zc *bi;
-	struct i40e_ring *rx_ring;
-	u64 hr, mask;
-	u16 nta;
-
-	rx_ring = container_of(alloc, struct i40e_ring, zca);
-	hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
-	mask = rx_ring->xsk_umem->chunk_mask;
-
-	nta = rx_ring->next_to_alloc;
-	bi = i40e_rx_bi(rx_ring, nta);
-
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	handle &= mask;
-
-	bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
-					    rx_ring->xsk_umem->headroom);
-}
-
 /**
  * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
  * @rx_ring: Rx ring
- * @bi: Rx buffer
  * @xdp: xdp_buff
  *
  * This functions allocates a new skb from a zero-copy Rx buffer.
@@ -505,7 +233,6 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
  * Returns the skb, or NULL on failure.
  **/
 static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
-					     struct i40e_rx_buffer_zc *bi,
 					     struct xdp_buff *xdp)
 {
 	unsigned int metasize = xdp->data - xdp->data_meta;
@@ -524,7 +251,7 @@ static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	i40e_reuse_rx_buffer_zc(rx_ring, bi);
+	xsk_buff_free(xdp);
 	return skb;
 }
 
@@ -539,25 +266,20 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_res, xdp_xmit = 0;
 	bool failure = false;
 	struct sk_buff *skb;
-	struct xdp_buff xdp;
-
-	xdp.rxq = &rx_ring->xdp_rxq;
-	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
-		struct i40e_rx_buffer_zc *bi;
 		union i40e_rx_desc *rx_desc;
+		struct xdp_buff **bi;
 		unsigned int size;
 		u64 qword;
 
 		if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
 			failure = failure ||
-				  !i40e_alloc_rx_buffers_fast_zc(rx_ring,
-								 cleaned_count);
+				  !i40e_alloc_rx_buffers_zc(rx_ring,
+							    cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -575,9 +297,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 						      rx_desc->raw.qword[0],
 						      qword);
 			bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-			i40e_inc_ntc(rx_ring);
-			i40e_reuse_rx_buffer_zc(rx_ring, bi);
+			xsk_buff_free(*bi);
+			*bi = NULL;
 			cleaned_count++;
+			i40e_inc_ntc(rx_ring);
 			continue;
 		}
 
@@ -587,22 +310,18 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		bi = i40e_get_rx_buffer_zc(rx_ring, size);
-		xdp.data = bi->addr;
-		xdp.data_meta = xdp.data;
-		xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
-		xdp.data_end = xdp.data + size;
-		xdp.handle = bi->handle;
+		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
+		(*bi)->data_end = (*bi)->data + size;
+		xsk_buff_dma_sync_for_cpu(*bi);
 
-		xdp_res = i40e_run_xdp_zc(rx_ring, &xdp);
+		xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
 		if (xdp_res) {
-			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR))
 				xdp_xmit |= xdp_res;
-				bi->addr = NULL;
-			} else {
-				i40e_reuse_rx_buffer_zc(rx_ring, bi);
-			}
+			else
+				xsk_buff_free(*bi);
 
+			*bi = NULL;
 			total_rx_bytes += size;
 			total_rx_packets++;
 
@@ -618,7 +337,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
 		 * SBP is *not* set in PRT_SBPVSI (default not set).
 		 */
-		skb = i40e_construct_skb_zc(rx_ring, bi, &xdp);
+		skb = i40e_construct_skb_zc(rx_ring, *bi);
+		*bi = NULL;
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
 			break;
@@ -676,10 +396,9 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
 			break;
 
-		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
-		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
-					   DMA_BIDIRECTIONAL);
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+						 desc.len);
 
 		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
 		tx_bi->bytecount = desc.len;
@@ -838,13 +557,13 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 	u16 i;
 
 	for (i = 0; i < rx_ring->count; i++) {
-		struct i40e_rx_buffer_zc *rx_bi = i40e_rx_bi(rx_ring, i);
+		struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, i);
 
-		if (!rx_bi->addr)
+		if (!rx_bi)
 			continue;
 
-		xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
-		rx_bi->addr = NULL;
+		xsk_buff_free(rx_bi);
+		rx_bi = NULL;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index f5e292c218ee..ea919a7d60ec 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -12,7 +12,6 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
 int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
 int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
 			u16 qid);
-void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
 bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
 int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
 
-- 
cgit v1.2.3


From 175fc430670be92c00317b9aada8bf39b47b717e Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:57 +0200
Subject: ice, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs.

v4->v5: Fixed "warning: Excess function parameter 'alloc' description
        in 'ice_alloc_rx_bufs_zc'" and "warning: Excess function
        parameter 'xdp' description in
        'ice_construct_skb_zc'". (Jakub)

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-10-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/ice/ice_base.c |  16 +-
 drivers/net/ethernet/intel/ice/ice_txrx.h |   8 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c  | 376 ++++--------------------------
 drivers/net/ethernet/intel/ice/ice_xsk.h  |  13 +-
 4 files changed, 54 insertions(+), 359 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index a19cd6f5436b..433eb72b1c85 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019, Intel Corporation. */
 
+#include <net/xdp_sock_drv.h>
 #include "ice_base.h"
 #include "ice_dcb_lib.h"
 
@@ -308,24 +309,23 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 		if (ring->xsk_umem) {
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
-			ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
-					   XDP_PACKET_HEADROOM;
+			ring->rx_buf_len =
+				xsk_umem_get_rx_frame_size(ring->xsk_umem);
 			/* For AF_XDP ZC, we disallow packets to span on
 			 * multiple buffers, thus letting us skip that
 			 * handling in the fast-path.
 			 */
 			chain_len = 1;
-			ring->zca.free = ice_zca_free;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_ZERO_COPY,
-							 &ring->zca);
+							 MEM_TYPE_XSK_BUFF_POOL,
+							 NULL);
 			if (err)
 				return err;
+			xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
 
-			dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+			dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
-			ring->zca.free = NULL;
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,
@@ -426,7 +426,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	writel(0, ring->tail);
 
 	err = ring->xsk_umem ?
-	      ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) :
+	      ice_alloc_rx_bufs_zc(ring, ICE_DESC_UNUSED(ring)) :
 	      ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
 	if (err)
 		dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 7ee00a128663..d0fd2173854f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -155,17 +155,16 @@ struct ice_tx_offload_params {
 };
 
 struct ice_rx_buf {
-	struct sk_buff *skb;
-	dma_addr_t dma;
 	union {
 		struct {
+			struct sk_buff *skb;
+			dma_addr_t dma;
 			struct page *page;
 			unsigned int page_offset;
 			u16 pagecnt_bias;
 		};
 		struct {
-			void *addr;
-			u64 handle;
+			struct xdp_buff *xdp;
 		};
 	};
 };
@@ -289,7 +288,6 @@ struct ice_ring {
 	struct rcu_head rcu;		/* to avoid race on free */
 	struct bpf_prog *xdp_prog;
 	struct xdp_umem *xsk_umem;
-	struct zero_copy_allocator zca;
 	/* CL3 - 3rd cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
 	/* CLX - the below items are only accessed infrequently and should be
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 70e204307a93..a73f6c3c70a4 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -279,28 +279,6 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi)
 	return 0;
 }
 
-/**
- * ice_xsk_add_umem - add a UMEM region for XDP sockets
- * @vsi: VSI to which the UMEM will be added
- * @umem: pointer to a requested UMEM region
- * @qid: queue ID
- *
- * Returns 0 on success, negative on error
- */
-static int ice_xsk_add_umem(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
-{
-	int err;
-
-	err = ice_xsk_alloc_umems(vsi);
-	if (err)
-		return err;
-
-	vsi->xsk_umems[qid] = umem;
-	vsi->num_xsk_umems_used++;
-
-	return 0;
-}
-
 /**
  * ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid
  * @vsi: VSI from which the VSI will be removed
@@ -318,65 +296,6 @@ static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid)
 	}
 }
 
-/**
- * ice_xsk_umem_dma_map - DMA map UMEM region for XDP sockets
- * @vsi: VSI to map the UMEM region
- * @umem: UMEM to map
- *
- * Returns 0 on success, negative on error
- */
-static int ice_xsk_umem_dma_map(struct ice_vsi *vsi, struct xdp_umem *umem)
-{
-	struct ice_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i;
-
-	dev = ice_pf_to_dev(pf);
-	for (i = 0; i < umem->npgs; i++) {
-		dma_addr_t dma = dma_map_page_attrs(dev, umem->pgs[i], 0,
-						    PAGE_SIZE,
-						    DMA_BIDIRECTIONAL,
-						    ICE_RX_DMA_ATTR);
-		if (dma_mapping_error(dev, dma)) {
-			dev_dbg(dev, "XSK UMEM DMA mapping error on page num %d\n",
-				i);
-			goto out_unmap;
-		}
-
-		umem->pages[i].dma = dma;
-	}
-
-	return 0;
-
-out_unmap:
-	for (; i > 0; i--) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR);
-		umem->pages[i].dma = 0;
-	}
-
-	return -EFAULT;
-}
-
-/**
- * ice_xsk_umem_dma_unmap - DMA unmap UMEM region for XDP sockets
- * @vsi: VSI from which the UMEM will be unmapped
- * @umem: UMEM to unmap
- */
-static void ice_xsk_umem_dma_unmap(struct ice_vsi *vsi, struct xdp_umem *umem)
-{
-	struct ice_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i;
-
-	dev = ice_pf_to_dev(pf);
-	for (i = 0; i < umem->npgs; i++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, ICE_RX_DMA_ATTR);
-
-		umem->pages[i].dma = 0;
-	}
-}
 
 /**
  * ice_xsk_umem_disable - disable a UMEM region
@@ -391,7 +310,7 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid)
 	    !vsi->xsk_umems[qid])
 		return -EINVAL;
 
-	ice_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]);
+	xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR);
 	ice_xsk_remove_umem(vsi, qid);
 
 	return 0;
@@ -408,7 +327,6 @@ static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid)
 static int
 ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
 {
-	struct xdp_umem_fq_reuse *reuseq;
 	int err;
 
 	if (vsi->type != ICE_VSI_PF)
@@ -419,20 +337,18 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
 	if (qid >= vsi->num_xsk_umems)
 		return -EINVAL;
 
+	err = ice_xsk_alloc_umems(vsi);
+	if (err)
+		return err;
+
 	if (vsi->xsk_umems && vsi->xsk_umems[qid])
 		return -EBUSY;
 
-	reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
-	if (!reuseq)
-		return -ENOMEM;
-
-	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
-	err = ice_xsk_umem_dma_map(vsi, umem);
-	if (err)
-		return err;
+	vsi->xsk_umems[qid] = umem;
+	vsi->num_xsk_umems_used++;
 
-	err = ice_xsk_add_umem(vsi, umem, qid);
+	err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back),
+			       ICE_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -483,138 +399,23 @@ xsk_umem_if_up:
 	return ret;
 }
 
-/**
- * ice_zca_free - Callback for MEM_TYPE_ZERO_COPY allocations
- * @zca: zero-cpoy allocator
- * @handle: Buffer handle
- */
-void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
-{
-	struct ice_rx_buf *rx_buf;
-	struct ice_ring *rx_ring;
-	struct xdp_umem *umem;
-	u64 hr, mask;
-	u16 nta;
-
-	rx_ring = container_of(zca, struct ice_ring, zca);
-	umem = rx_ring->xsk_umem;
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	mask = umem->chunk_mask;
-
-	nta = rx_ring->next_to_alloc;
-	rx_buf = &rx_ring->rx_buf[nta];
-
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	handle &= mask;
-
-	rx_buf->dma = xdp_umem_get_dma(umem, handle);
-	rx_buf->dma += hr;
-
-	rx_buf->addr = xdp_umem_get_data(umem, handle);
-	rx_buf->addr += hr;
-
-	rx_buf->handle = (u64)handle + umem->headroom;
-}
-
-/**
- * ice_alloc_buf_fast_zc - Retrieve buffer address from XDP umem
- * @rx_ring: ring with an xdp_umem bound to it
- * @rx_buf: buffer to which xsk page address will be assigned
- *
- * This function allocates an Rx buffer in the hot path.
- * The buffer can come from fill queue or recycle queue.
- *
- * Returns true if an assignment was successful, false if not.
- */
-static __always_inline bool
-ice_alloc_buf_fast_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	void *addr = rx_buf->addr;
-	u64 handle, hr;
-
-	if (addr) {
-		rx_ring->rx_stats.page_reuse_count++;
-		return true;
-	}
-
-	if (!xsk_umem_peek_addr(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	rx_buf->dma = xdp_umem_get_dma(umem, handle);
-	rx_buf->dma += hr;
-
-	rx_buf->addr = xdp_umem_get_data(umem, handle);
-	rx_buf->addr += hr;
-
-	rx_buf->handle = handle + umem->headroom;
-
-	xsk_umem_release_addr(umem);
-	return true;
-}
-
-/**
- * ice_alloc_buf_slow_zc - Retrieve buffer address from XDP umem
- * @rx_ring: ring with an xdp_umem bound to it
- * @rx_buf: buffer to which xsk page address will be assigned
- *
- * This function allocates an Rx buffer in the slow path.
- * The buffer can come from fill queue or recycle queue.
- *
- * Returns true if an assignment was successful, false if not.
- */
-static __always_inline bool
-ice_alloc_buf_slow_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	u64 handle, headroom;
-
-	if (!xsk_umem_peek_addr_rq(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	handle &= umem->chunk_mask;
-	headroom = umem->headroom + XDP_PACKET_HEADROOM;
-
-	rx_buf->dma = xdp_umem_get_dma(umem, handle);
-	rx_buf->dma += headroom;
-
-	rx_buf->addr = xdp_umem_get_data(umem, handle);
-	rx_buf->addr += headroom;
-
-	rx_buf->handle = handle + umem->headroom;
-
-	xsk_umem_release_addr_rq(umem);
-	return true;
-}
-
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
  * @count: The number of buffers to allocate
- * @alloc: the function pointer to call for allocation
  *
  * This function allocates a number of Rx buffers from the fill ring
  * or the internal recycle mechanism and places them on the Rx ring.
  *
  * Returns false if all allocations were successful, true if any fail.
  */
-static bool
-ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
-		     bool (*alloc)(struct ice_ring *, struct ice_rx_buf *))
+bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 {
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
 	struct ice_rx_buf *rx_buf;
 	bool ret = false;
+	dma_addr_t dma;
 
 	if (!count)
 		return false;
@@ -623,16 +424,14 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
 	rx_buf = &rx_ring->rx_buf[ntu];
 
 	do {
-		if (!alloc(rx_ring, rx_buf)) {
+		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		if (!rx_buf->xdp) {
 			ret = true;
 			break;
 		}
 
-		dma_sync_single_range_for_device(rx_ring->dev, rx_buf->dma, 0,
-						 rx_ring->rx_buf_len,
-						 DMA_BIDIRECTIONAL);
-
-		rx_desc->read.pkt_addr = cpu_to_le64(rx_buf->dma);
+		dma = xsk_buff_xdp_get_dma(rx_buf->xdp);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
 		rx_desc->wb.status_error0 = 0;
 
 		rx_desc++;
@@ -652,32 +451,6 @@ ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count,
 	return ret;
 }
 
-/**
- * ice_alloc_rx_bufs_fast_zc - allocate zero copy bufs in the hot path
- * @rx_ring: Rx ring
- * @count: number of bufs to allocate
- *
- * Returns false on success, true on failure.
- */
-static bool ice_alloc_rx_bufs_fast_zc(struct ice_ring *rx_ring, u16 count)
-{
-	return ice_alloc_rx_bufs_zc(rx_ring, count,
-				    ice_alloc_buf_fast_zc);
-}
-
-/**
- * ice_alloc_rx_bufs_slow_zc - allocate zero copy bufs in the slow path
- * @rx_ring: Rx ring
- * @count: number of bufs to allocate
- *
- * Returns false on success, true on failure.
- */
-bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count)
-{
-	return ice_alloc_rx_bufs_zc(rx_ring, count,
-				    ice_alloc_buf_slow_zc);
-}
-
 /**
  * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring
  * @rx_ring: Rx ring
@@ -691,77 +464,22 @@ static void ice_bump_ntc(struct ice_ring *rx_ring)
 	prefetch(ICE_RX_DESC(rx_ring, ntc));
 }
 
-/**
- * ice_get_rx_buf_zc - Fetch the current Rx buffer
- * @rx_ring: Rx ring
- * @size: size of a buffer
- *
- * This function returns the current, received Rx buffer and does
- * DMA synchronization.
- *
- * Returns a pointer to the received Rx buffer.
- */
-static struct ice_rx_buf *ice_get_rx_buf_zc(struct ice_ring *rx_ring, int size)
-{
-	struct ice_rx_buf *rx_buf;
-
-	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
-
-	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, 0,
-				      size, DMA_BIDIRECTIONAL);
-
-	return rx_buf;
-}
-
-/**
- * ice_reuse_rx_buf_zc - reuse an Rx buffer
- * @rx_ring: Rx ring
- * @old_buf: The buffer to recycle
- *
- * This function recycles a finished Rx buffer, and places it on the recycle
- * queue (next_to_alloc).
- */
-static void
-ice_reuse_rx_buf_zc(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
-{
-	unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
-	u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
-	u16 nta = rx_ring->next_to_alloc;
-	struct ice_rx_buf *new_buf;
-
-	new_buf = &rx_ring->rx_buf[nta++];
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	new_buf->dma = old_buf->dma & mask;
-	new_buf->dma += hr;
-
-	new_buf->addr = (void *)((unsigned long)old_buf->addr & mask);
-	new_buf->addr += hr;
-
-	new_buf->handle = old_buf->handle & mask;
-	new_buf->handle += rx_ring->xsk_umem->headroom;
-
-	old_buf->addr = NULL;
-}
-
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
  * @rx_buf: zero-copy Rx buffer
- * @xdp: XDP buffer
  *
  * This function allocates a new skb from a zero-copy Rx buffer.
  *
  * Returns the skb on success, NULL on failure.
  */
 static struct sk_buff *
-ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
-		     struct xdp_buff *xdp)
+ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int datasize_hard = xdp->data_end -
-				     xdp->data_hard_start;
+	unsigned int metasize = rx_buf->xdp->data - rx_buf->xdp->data_meta;
+	unsigned int datasize = rx_buf->xdp->data_end - rx_buf->xdp->data;
+	unsigned int datasize_hard = rx_buf->xdp->data_end -
+				     rx_buf->xdp->data_hard_start;
 	struct sk_buff *skb;
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
@@ -769,13 +487,13 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+	skb_reserve(skb, rx_buf->xdp->data - rx_buf->xdp->data_hard_start);
+	memcpy(__skb_put(skb, datasize), rx_buf->xdp->data, datasize);
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	ice_reuse_rx_buf_zc(rx_ring, rx_buf);
-
+	xsk_buff_free(rx_buf->xdp);
+	rx_buf->xdp = NULL;
 	return skb;
 }
 
@@ -802,7 +520,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 	}
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	xdp->handle += xdp->data - xdp->data_hard_start;
 	switch (act) {
 	case XDP_PASS:
 		break;
@@ -840,13 +557,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_xmit = 0;
 	bool failure = false;
-	struct xdp_buff xdp;
-
-	xdp.rxq = &rx_ring->xdp_rxq;
-	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
@@ -858,8 +570,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 		u8 rx_ptype;
 
 		if (cleaned_count >= ICE_RX_BUF_WRITE) {
-			failure |= ice_alloc_rx_bufs_fast_zc(rx_ring,
-							     cleaned_count);
+			failure |= ice_alloc_rx_bufs_zc(rx_ring,
+							cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -880,25 +592,19 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		rx_buf = ice_get_rx_buf_zc(rx_ring, size);
-		if (!rx_buf->addr)
-			break;
 
-		xdp.data = rx_buf->addr;
-		xdp.data_meta = xdp.data;
-		xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
-		xdp.data_end = xdp.data + size;
-		xdp.handle = rx_buf->handle;
+		rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
+		rx_buf->xdp->data_end = rx_buf->xdp->data + size;
+		xsk_buff_dma_sync_for_cpu(rx_buf->xdp);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, &xdp);
+		xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp);
 		if (xdp_res) {
-			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
-				rx_buf->addr = NULL;
-			} else {
-				ice_reuse_rx_buf_zc(rx_ring, rx_buf);
-			}
+			else
+				xsk_buff_free(rx_buf->xdp);
 
+			rx_buf->xdp = NULL;
 			total_rx_bytes += size;
 			total_rx_packets++;
 			cleaned_count++;
@@ -908,7 +614,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 		}
 
 		/* XDP_PASS path */
-		skb = ice_construct_skb_zc(rx_ring, rx_buf, &xdp);
+		skb = ice_construct_skb_zc(rx_ring, rx_buf);
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buf_failed++;
 			break;
@@ -979,10 +685,9 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
 			break;
 
-		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
-		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
-					   DMA_BIDIRECTIONAL);
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+						 desc.len);
 
 		tx_buf->bytecount = desc.len;
 
@@ -1165,11 +870,10 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring)
 	for (i = 0; i < rx_ring->count; i++) {
 		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
 
-		if (!rx_buf->addr)
+		if (!rx_buf->xdp)
 			continue;
 
-		xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_buf->handle);
-		rx_buf->addr = NULL;
+		rx_buf->xdp = NULL;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 8a4ba7c6d549..fc1a06b4df36 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -10,11 +10,10 @@ struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS
 int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid);
-void ice_zca_free(struct zero_copy_allocator *zca, unsigned long handle);
 int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget);
 bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_slow_zc(struct ice_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring);
@@ -27,12 +26,6 @@ ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi,
 	return -EOPNOTSUPP;
 }
 
-static inline void
-ice_zca_free(struct zero_copy_allocator __always_unused *zca,
-	     unsigned long __always_unused handle)
-{
-}
-
 static inline int
 ice_clean_rx_irq_zc(struct ice_ring __always_unused *rx_ring,
 		    int __always_unused budget)
@@ -48,8 +41,8 @@ ice_clean_tx_irq_zc(struct ice_ring __always_unused *xdp_ring,
 }
 
 static inline bool
-ice_alloc_rx_bufs_slow_zc(struct ice_ring __always_unused *rx_ring,
-			  u16 __always_unused count)
+ice_alloc_rx_bufs_zc(struct ice_ring __always_unused *rx_ring,
+		     u16 __always_unused count)
 {
 	return false;
 }
-- 
cgit v1.2.3


From 7117132b22538d24728295ffafa183a0a782fe03 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:58 +0200
Subject: ixgbe, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs.

v1->v2: Fixed xdp_buff data_end update. (Björn)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-11-bjorn.topel@gmail.com
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h           |   9 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  15 +-
 .../net/ethernet/intel/ixgbe/ixgbe_txrx_common.h   |   2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c       | 307 ++++-----------------
 4 files changed, 62 insertions(+), 271 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 2833e4f041ce..5ddfc83a1e46 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -224,17 +224,17 @@ struct ixgbe_tx_buffer {
 };
 
 struct ixgbe_rx_buffer {
-	struct sk_buff *skb;
-	dma_addr_t dma;
 	union {
 		struct {
+			struct sk_buff *skb;
+			dma_addr_t dma;
 			struct page *page;
 			__u32 page_offset;
 			__u16 pagecnt_bias;
 		};
 		struct {
-			void *addr;
-			u64 handle;
+			bool discard;
+			struct xdp_buff *xdp;
 		};
 	};
 };
@@ -351,7 +351,6 @@ struct ixgbe_ring {
 	};
 	struct xdp_rxq_info xdp_rxq;
 	struct xdp_umem *xsk_umem;
-	struct zero_copy_allocator zca; /* ZC allocator anchor */
 	u16 ring_idx;		/* {rx,tx,xdp}_ring back reference idx */
 	u16 rx_buf_len;
 } ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index eab5934b04f5..45fc7ce1a543 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -35,7 +35,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/vxlan.h>
 #include <net/mpls.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xfrm.h>
 
 #include "ixgbe.h"
@@ -3745,8 +3745,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 
 	/* configure the packet buffer length */
 	if (rx_ring->xsk_umem) {
-		u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr -
-				  XDP_PACKET_HEADROOM;
+		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem);
 
 		/* If the MAC support setting RXDCTL.RLPML, the
 		 * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
@@ -4093,11 +4092,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 	ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
 	if (ring->xsk_umem) {
-		ring->zca.free = ixgbe_zca_free;
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-						   MEM_TYPE_ZERO_COPY,
-						   &ring->zca));
-
+						   MEM_TYPE_XSK_BUFF_POOL,
+						   NULL));
+		xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
 	} else {
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						   MEM_TYPE_PAGE_SHARED, NULL));
@@ -4153,8 +4151,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	}
 
 	if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) {
-		u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr -
-				  XDP_PACKET_HEADROOM;
+		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
 
 		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
 			    IXGBE_RXDCTL_RLPML_EN);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index 6d01700b46bc..7887ae4aaf4f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -35,7 +35,7 @@ int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
 
 void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
 
-void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
+bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
 int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 			  struct ixgbe_ring *rx_ring,
 			  const int budget);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 82e4effae704..86add9fbd36c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -20,54 +20,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
 	return xdp_get_umem_from_qid(adapter->netdev, qid);
 }
 
-static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter,
-				  struct xdp_umem *umem)
-{
-	struct device *dev = &adapter->pdev->dev;
-	unsigned int i, j;
-	dma_addr_t dma;
-
-	for (i = 0; i < umem->npgs; i++) {
-		dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
-					 DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
-		if (dma_mapping_error(dev, dma))
-			goto out_unmap;
-
-		umem->pages[i].dma = dma;
-	}
-
-	return 0;
-
-out_unmap:
-	for (j = 0; j < i; j++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
-		umem->pages[i].dma = 0;
-	}
-
-	return -1;
-}
-
-static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter,
-				     struct xdp_umem *umem)
-{
-	struct device *dev = &adapter->pdev->dev;
-	unsigned int i;
-
-	for (i = 0; i < umem->npgs; i++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
-
-		umem->pages[i].dma = 0;
-	}
-}
-
 static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 				 struct xdp_umem *umem,
 				 u16 qid)
 {
 	struct net_device *netdev = adapter->netdev;
-	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
 
@@ -78,13 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count);
-	if (!reuseq)
-		return -ENOMEM;
-
-	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
-	err = ixgbe_xsk_umem_dma_map(adapter, umem);
+	err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -124,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 		ixgbe_txrx_ring_disable(adapter, qid);
 
 	clear_bit(qid, adapter->af_xdp_zc_qps);
-	ixgbe_xsk_umem_dma_unmap(adapter, umem);
+	xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR);
 
 	if (if_running)
 		ixgbe_txrx_ring_enable(adapter, qid);
@@ -143,19 +94,14 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 			    struct ixgbe_ring *rx_ring,
 			    struct xdp_buff *xdp)
 {
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
 	struct xdp_frame *xdpf;
-	u64 offset;
 	u32 act;
 
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	offset = xdp->data - xdp->data_hard_start;
-
-	xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
 
 	switch (act) {
 	case XDP_PASS:
@@ -186,140 +132,16 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	return result;
 }
 
-static struct
-ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring,
-					unsigned int size)
-{
-	struct ixgbe_rx_buffer *bi;
-
-	bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      bi->dma, 0,
-				      size,
-				      DMA_BIDIRECTIONAL);
-
-	return bi;
-}
-
-static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
-				     struct ixgbe_rx_buffer *obi)
-{
-	u16 nta = rx_ring->next_to_alloc;
-	struct ixgbe_rx_buffer *nbi;
-
-	nbi = &rx_ring->rx_buffer_info[rx_ring->next_to_alloc];
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	nbi->dma = obi->dma;
-	nbi->addr = obi->addr;
-	nbi->handle = obi->handle;
-
-	obi->addr = NULL;
-	obi->skb = NULL;
-}
-
-void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
-{
-	struct ixgbe_rx_buffer *bi;
-	struct ixgbe_ring *rx_ring;
-	u64 hr, mask;
-	u16 nta;
-
-	rx_ring = container_of(alloc, struct ixgbe_ring, zca);
-	hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
-	mask = rx_ring->xsk_umem->chunk_mask;
-
-	nta = rx_ring->next_to_alloc;
-	bi = rx_ring->rx_buffer_info;
-
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	handle &= mask;
-
-	bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
-					    rx_ring->xsk_umem->headroom);
-}
-
-static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
-				  struct ixgbe_rx_buffer *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	void *addr = bi->addr;
-	u64 handle, hr;
-
-	if (addr)
-		return true;
-
-	if (!xsk_umem_peek_addr(umem, &handle)) {
-		rx_ring->rx_stats.alloc_rx_page_failed++;
-		return false;
-	}
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr(umem);
-	return true;
-}
-
-static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring,
-				       struct ixgbe_rx_buffer *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	u64 handle, hr;
-
-	if (!xsk_umem_peek_addr_rq(umem, &handle)) {
-		rx_ring->rx_stats.alloc_rx_page_failed++;
-		return false;
-	}
-
-	handle &= rx_ring->xsk_umem->chunk_mask;
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr_rq(umem);
-	return true;
-}
-
-static __always_inline bool
-__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
-			    bool alloc(struct ixgbe_ring *rx_ring,
-				       struct ixgbe_rx_buffer *bi))
+bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
 {
 	union ixgbe_adv_rx_desc *rx_desc;
 	struct ixgbe_rx_buffer *bi;
 	u16 i = rx_ring->next_to_use;
+	dma_addr_t dma;
 	bool ok = true;
 
 	/* nothing to do */
-	if (!cleaned_count)
+	if (!count)
 		return true;
 
 	rx_desc = IXGBE_RX_DESC(rx_ring, i);
@@ -327,21 +149,18 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
 	i -= rx_ring->count;
 
 	do {
-		if (!alloc(rx_ring, bi)) {
+		bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		if (!bi->xdp) {
 			ok = false;
 			break;
 		}
 
-		/* sync the buffer for use by the device */
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 rx_ring->rx_buf_len,
-						 DMA_BIDIRECTIONAL);
+		dma = xsk_buff_xdp_get_dma(bi->xdp);
 
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
 
 		rx_desc++;
 		bi++;
@@ -355,17 +174,14 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
 		/* clear the length for the next_to_use descriptor */
 		rx_desc->wb.upper.length = 0;
 
-		cleaned_count--;
-	} while (cleaned_count);
+		count--;
+	} while (count);
 
 	i += rx_ring->count;
 
 	if (rx_ring->next_to_use != i) {
 		rx_ring->next_to_use = i;
 
-		/* update next to alloc since we have filled the ring */
-		rx_ring->next_to_alloc = i;
-
 		/* Force memory writes to complete before letting h/w
 		 * know there are new descriptors to fetch.  (Only
 		 * applicable for weak-ordered memory model archs,
@@ -378,40 +194,27 @@ __ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
 	return ok;
 }
 
-void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
-{
-	__ixgbe_alloc_rx_buffers_zc(rx_ring, count,
-				    ixgbe_alloc_buffer_slow_zc);
-}
-
-static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring,
-					   u16 count)
-{
-	return __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
-					   ixgbe_alloc_buffer_zc);
-}
-
 static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
-					      struct ixgbe_rx_buffer *bi,
-					      struct xdp_buff *xdp)
+					      struct ixgbe_rx_buffer *bi)
 {
-	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
+	unsigned int metasize = bi->xdp->data - bi->xdp->data_meta;
+	unsigned int datasize = bi->xdp->data_end - bi->xdp->data;
 	struct sk_buff *skb;
 
 	/* allocate a skb to store the frags */
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       xdp->data_end - xdp->data_hard_start,
+			       bi->xdp->data_end - bi->xdp->data_hard_start,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+	skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start);
+	memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize);
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-	ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+	xsk_buff_free(bi->xdp);
+	bi->xdp = NULL;
 	return skb;
 }
 
@@ -431,14 +234,9 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct ixgbe_adapter *adapter = q_vector->adapter;
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	unsigned int xdp_res, xdp_xmit = 0;
 	bool failure = false;
 	struct sk_buff *skb;
-	struct xdp_buff xdp;
-
-	xdp.rxq = &rx_ring->xdp_rxq;
-	xdp.frame_sz = xsk_umem_xdp_frame_sz(umem);
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
@@ -448,8 +246,8 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
 			failure = failure ||
-				  !ixgbe_alloc_rx_buffers_fast_zc(rx_ring,
-								 cleaned_count);
+				  !ixgbe_alloc_rx_buffers_zc(rx_ring,
+							     cleaned_count);
 			cleaned_count = 0;
 		}
 
@@ -464,42 +262,40 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		 */
 		dma_rmb();
 
-		bi = ixgbe_get_rx_buffer_zc(rx_ring, size);
+		bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
 
 		if (unlikely(!ixgbe_test_staterr(rx_desc,
 						 IXGBE_RXD_STAT_EOP))) {
 			struct ixgbe_rx_buffer *next_bi;
 
-			ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+			xsk_buff_free(bi->xdp);
+			bi->xdp = NULL;
 			ixgbe_inc_ntc(rx_ring);
 			next_bi =
 			       &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-			next_bi->skb = ERR_PTR(-EINVAL);
+			next_bi->discard = true;
 			continue;
 		}
 
-		if (unlikely(bi->skb)) {
-			ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
+		if (unlikely(bi->discard)) {
+			xsk_buff_free(bi->xdp);
+			bi->xdp = NULL;
+			bi->discard = false;
 			ixgbe_inc_ntc(rx_ring);
 			continue;
 		}
 
-		xdp.data = bi->addr;
-		xdp.data_meta = xdp.data;
-		xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
-		xdp.data_end = xdp.data + size;
-		xdp.handle = bi->handle;
-
-		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp);
+		bi->xdp->data_end = bi->xdp->data + size;
+		xsk_buff_dma_sync_for_cpu(bi->xdp);
+		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);
 
 		if (xdp_res) {
-			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
-				bi->addr = NULL;
-				bi->skb = NULL;
-			} else {
-				ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
-			}
+			else
+				xsk_buff_free(bi->xdp);
+
+			bi->xdp = NULL;
 			total_rx_packets++;
 			total_rx_bytes += size;
 
@@ -509,7 +305,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		}
 
 		/* XDP_PASS path */
-		skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp);
+		skb = ixgbe_construct_skb_zc(rx_ring, bi);
 		if (!skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
 			break;
@@ -561,17 +357,17 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 
 void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
 {
-	u16 i = rx_ring->next_to_clean;
-	struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i];
+	struct ixgbe_rx_buffer *bi;
+	u16 i;
 
-	while (i != rx_ring->next_to_alloc) {
-		xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle);
-		i++;
-		bi++;
-		if (i == rx_ring->count) {
-			i = 0;
-			bi = rx_ring->rx_buffer_info;
-		}
+	for (i = 0; i < rx_ring->count; i++) {
+		bi = &rx_ring->rx_buffer_info[i];
+
+		if (!bi->xdp)
+			continue;
+
+		xsk_buff_free(bi->xdp);
+		bi->xdp = NULL;
 	}
 }
 
@@ -594,10 +390,9 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
 			break;
 
-		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
-
-		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
-					   DMA_BIDIRECTIONAL);
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+						 desc.len);
 
 		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
 		tx_bi->bytecount = desc.len;
-- 
cgit v1.2.3


From 39d6443c8daf9fefcfcf89de7ae87240956a0b84 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Wed, 20 May 2020 21:20:59 +0200
Subject: mlx5, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the new MEM_TYPE_XSK_BUFF_POOL API in lieu of MEM_TYPE_ZERO_COPY in
mlx5e. It allows to drop a lot of code from the driver (which is now
common in AF_XDP core and was related to XSK RX frame allocation, DMA
mapping, etc.) and slightly improve performance (RX +0.8 Mpps, TX +0.4
Mpps).

rfc->v1: Put back the sanity check for XSK params, use XSK API to get
         the total headroom size. (Maxim)

v1->v2: Fix DMA address handling, set XDP metadata to invalid. (Maxim)

v2->v3: Handle frame_sz, use xsk_buff_xdp_get_frame_dma, use xsk_buff
        API for DMA sync on TX, add performance numbers. (Maxim)

v3->v4: Remove unused variable num_xsk_frames. (Jakub)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200520192103.355233-12-bjorn.topel@gmail.com
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   7 +-
 .../net/ethernet/mellanox/mlx5/core/en/params.c    |  13 +--
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |  31 ++----
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.c    | 113 ++++-----------------
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h    |  23 +++--
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c    |   9 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.c  |  49 ++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  25 +----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |  34 ++++++-
 10 files changed, 96 insertions(+), 210 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 26911b15f8fe..0a02b804b2fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -407,10 +407,7 @@ struct mlx5e_dma_info {
 	dma_addr_t addr;
 	union {
 		struct page *page;
-		struct {
-			u64 handle;
-			void *data;
-		} xsk;
+		struct xdp_buff *xsk;
 	};
 };
 
@@ -623,7 +620,6 @@ struct mlx5e_rq {
 		} mpwqe;
 	};
 	struct {
-		u16            umem_headroom;
 		u16            headroom;
 		u32            frame0_sz;
 		u8             map_dir;   /* dma map direction */
@@ -656,7 +652,6 @@ struct mlx5e_rq {
 	struct page_pool      *page_pool;
 
 	/* AF_XDP zero-copy */
-	struct zero_copy_allocator zca;
 	struct xdp_umem       *umem;
 
 	struct work_struct     recover_work;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index eb2e1f2138e4..38e4f19d69f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -12,15 +12,16 @@ static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
 u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params,
 				 struct mlx5e_xsk_param *xsk)
 {
-	u16 headroom = NET_IP_ALIGN;
+	u16 headroom;
 
-	if (mlx5e_rx_is_xdp(params, xsk)) {
+	if (xsk)
+		return xsk->headroom;
+
+	headroom = NET_IP_ALIGN;
+	if (mlx5e_rx_is_xdp(params, xsk))
 		headroom += XDP_PACKET_HEADROOM;
-		if (xsk)
-			headroom += xsk->headroom;
-	} else {
+	else
 		headroom += MLX5_RX_HEADROOM;
-	}
 
 	return headroom;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3507d23f0eb8..a2a194525b15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -71,7 +71,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	xdptxd.data = xdpf->data;
 	xdptxd.len  = xdpf->len;
 
-	if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) {
+	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) {
 		/* The xdp_buff was in the UMEM and was copied into a newly
 		 * allocated page. The UMEM page was returned via the ZCA, and
 		 * this new page has to be mapped at this point and has to be
@@ -119,50 +119,33 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 
 /* returns true if packet was consumed by xdp */
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-		      void *va, u16 *rx_headroom, u32 *len, bool xsk)
+		      u32 *len, struct xdp_buff *xdp)
 {
 	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
-	struct xdp_umem *umem = rq->umem;
-	struct xdp_buff xdp;
 	u32 act;
 	int err;
 
 	if (!prog)
 		return false;
 
-	xdp.data = va + *rx_headroom;
-	xdp_set_data_meta_invalid(&xdp);
-	xdp.data_end = xdp.data + *len;
-	xdp.data_hard_start = va;
-	if (xsk)
-		xdp.handle = di->xsk.handle;
-	xdp.rxq = &rq->xdp_rxq;
-	xdp.frame_sz = rq->buff.frame0_sz;
-
-	act = bpf_prog_run_xdp(prog, &xdp);
-	if (xsk) {
-		u64 off = xdp.data - xdp.data_hard_start;
-
-		xdp.handle = xsk_umem_adjust_offset(umem, xdp.handle, off);
-	}
+	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_PASS:
-		*rx_headroom = xdp.data - xdp.data_hard_start;
-		*len = xdp.data_end - xdp.data;
+		*len = xdp->data_end - xdp->data;
 		return false;
 	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, &xdp)))
+		if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, xdp)))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
 		return true;
 	case XDP_REDIRECT:
 		/* When XDP enabled then page-refcnt==1 here */
-		err = xdp_do_redirect(rq->netdev, &xdp, prog);
+		err = xdp_do_redirect(rq->netdev, xdp, prog);
 		if (unlikely(err))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
 		__set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
-		if (!xsk)
+		if (xdp->rxq->mem.type != MEM_TYPE_XSK_BUFF_POOL)
 			mlx5e_page_dma_unmap(rq, di);
 		rq->stats->xdp_redirect++;
 		return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e2e01f064c1e..2e4e117aeb49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -63,7 +63,7 @@
 struct mlx5e_xsk_param;
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-		      void *va, u16 *rx_headroom, u32 *len, bool xsk);
+		      u32 *len, struct xdp_buff *xdp);
 void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 62fc8a128a8d..a33a1f762c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -3,71 +3,10 @@
 
 #include "rx.h"
 #include "en/xdp.h"
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 /* RX data path */
 
-bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count)
-{
-	/* Check in advance that we have enough frames, instead of allocating
-	 * one-by-one, failing and moving frames to the Reuse Ring.
-	 */
-	return xsk_umem_has_addrs_rq(rq->umem, count);
-}
-
-int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
-			      struct mlx5e_dma_info *dma_info)
-{
-	struct xdp_umem *umem = rq->umem;
-	u64 handle;
-
-	if (!xsk_umem_peek_addr_rq(umem, &handle))
-		return -ENOMEM;
-
-	dma_info->xsk.handle = xsk_umem_adjust_offset(umem, handle,
-						      rq->buff.umem_headroom);
-	dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle);
-
-	/* No need to add headroom to the DMA address. In striding RQ case, we
-	 * just provide pages for UMR, and headroom is counted at the setup
-	 * stage when creating a WQE. In non-striding RQ case, headroom is
-	 * accounted in mlx5e_alloc_rx_wqe.
-	 */
-	dma_info->addr = xdp_umem_get_dma(umem, handle);
-
-	xsk_umem_release_addr_rq(umem);
-
-	dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE,
-				   DMA_BIDIRECTIONAL);
-
-	return 0;
-}
-
-static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle)
-{
-	xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask);
-}
-
-/* XSKRQ uses pages from UMEM, they must not be released. They are returned to
- * the userspace if possible, and if not, this function is called to reuse them
- * in the driver.
- */
-void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
-			    struct mlx5e_dma_info *dma_info)
-{
-	mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle);
-}
-
-/* Return a frame back to the hardware to fill in again. It is used by XDP when
- * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP.
- */
-void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
-{
-	struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca);
-
-	mlx5e_xsk_recycle_frame(rq, handle);
-}
-
 static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
 					       u32 cqe_bcnt)
 {
@@ -90,11 +29,8 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    u32 head_offset,
 						    u32 page_idx)
 {
-	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
-	u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
+	struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
 	u32 cqe_bcnt32 = cqe_bcnt;
-	void *va, *data;
-	u32 frag_size;
 	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
@@ -103,22 +39,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 		return NULL;
 	}
 
-	/* head_offset is not used in this function, because di->xsk.data and
-	 * di->addr point directly to the necessary place. Furthermore, in the
-	 * current implementation, UMR pages are mapped to XSK frames, so
+	/* head_offset is not used in this function, because xdp->data and the
+	 * DMA address point directly to the necessary place. Furthermore, in
+	 * the current implementation, UMR pages are mapped to XSK frames, so
 	 * head_offset should always be 0.
 	 */
 	WARN_ON_ONCE(head_offset);
 
-	va             = di->xsk.data;
-	data           = va + rx_headroom;
-	frag_size      = rq->buff.headroom + cqe_bcnt32;
-
-	dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
-	prefetch(data);
+	xdp->data_end = xdp->data + cqe_bcnt32;
+	xdp_set_data_meta_invalid(xdp);
+	xsk_buff_dma_sync_for_cpu(xdp);
+	prefetch(xdp->data);
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true);
+	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
 	rcu_read_unlock();
 
 	/* Possible flows:
@@ -145,7 +79,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	/* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the
 	 * frame. On SKB allocation failure, NULL is returned.
 	 */
-	return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32);
+	return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt32);
 }
 
 struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
@@ -153,25 +87,20 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
 					      u32 cqe_bcnt)
 {
-	struct mlx5e_dma_info *di = wi->di;
-	u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
-	void *va, *data;
+	struct xdp_buff *xdp = wi->di->xsk;
 	bool consumed;
-	u32 frag_size;
 
-	/* wi->offset is not used in this function, because di->xsk.data and
-	 * di->addr point directly to the necessary place. Furthermore, in the
-	 * current implementation, one page = one packet = one frame, so
+	/* wi->offset is not used in this function, because xdp->data and the
+	 * DMA address point directly to the necessary place. Furthermore, the
+	 * XSK allocator allocates frames per packet, instead of pages, so
 	 * wi->offset should always be 0.
 	 */
 	WARN_ON_ONCE(wi->offset);
 
-	va             = di->xsk.data;
-	data           = va + rx_headroom;
-	frag_size      = rq->buff.headroom + cqe_bcnt;
-
-	dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
-	prefetch(data);
+	xdp->data_end = xdp->data + cqe_bcnt;
+	xdp_set_data_meta_invalid(xdp);
+	xsk_buff_dma_sync_for_cpu(xdp);
+	prefetch(xdp->data);
 
 	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
@@ -179,7 +108,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	}
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true);
+	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
 	rcu_read_unlock();
 
 	if (likely(consumed))
@@ -189,5 +118,5 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	 * will be handled by mlx5e_put_rx_frag.
 	 * On SKB allocation failure, NULL is returned.
 	 */
-	return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt);
+	return mlx5e_xsk_construct_skb(rq, xdp->data, cqe_bcnt);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index a8e11adbf426..d147b2f13b54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -9,12 +9,6 @@
 
 /* RX data path */
 
-bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count);
-int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
-			      struct mlx5e_dma_info *dma_info);
-void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
-			    struct mlx5e_dma_info *dma_info);
-void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle);
 struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 						    struct mlx5e_mpw_info *wi,
 						    u16 cqe_bcnt,
@@ -25,6 +19,23 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
 					      u32 cqe_bcnt);
 
+static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
+					    struct mlx5e_dma_info *dma_info)
+{
+	dma_info->xsk = xsk_buff_alloc(rq->umem);
+	if (!dma_info->xsk)
+		return -ENOMEM;
+
+	/* Store the DMA address without headroom. In striding RQ case, we just
+	 * provide pages for UMR, and headroom is counted at the setup stage
+	 * when creating a WQE. In non-striding RQ case, headroom is accounted
+	 * in mlx5e_alloc_rx_wqe.
+	 */
+	dma_info->addr = xsk_buff_xdp_get_frame_dma(dma_info->xsk);
+
+	return 0;
+}
+
 static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err)
 {
 	if (!xsk_umem_uses_need_wakeup(rq->umem))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 3bcdb5b2fc20..83dce9cdb8c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -5,7 +5,7 @@
 #include "umem.h"
 #include "en/xdp.h"
 #include "en/params.h"
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
@@ -92,12 +92,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			break;
 		}
 
-		xdptxd.dma_addr = xdp_umem_get_dma(umem, desc.addr);
-		xdptxd.data = xdp_umem_get_data(umem, desc.addr);
+		xdptxd.dma_addr = xsk_buff_raw_get_dma(umem, desc.addr);
+		xdptxd.data = xsk_buff_raw_get_data(umem, desc.addr);
 		xdptxd.len = desc.len;
 
-		dma_sync_single_for_device(sq->pdev, xdptxd.dma_addr,
-					   xdptxd.len, DMA_BIDIRECTIONAL);
+		xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len);
 
 		if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) {
 			if (sq->mpwqe.wqe)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
index 5e49fdb564b3..7b17fcd0a56d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
@@ -10,40 +10,14 @@ static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv,
 			      struct xdp_umem *umem)
 {
 	struct device *dev = priv->mdev->device;
-	u32 i;
 
-	for (i = 0; i < umem->npgs; i++) {
-		dma_addr_t dma = dma_map_page(dev, umem->pgs[i], 0, PAGE_SIZE,
-					      DMA_BIDIRECTIONAL);
-
-		if (unlikely(dma_mapping_error(dev, dma)))
-			goto err_unmap;
-		umem->pages[i].dma = dma;
-	}
-
-	return 0;
-
-err_unmap:
-	while (i--) {
-		dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
-		umem->pages[i].dma = 0;
-	}
-
-	return -ENOMEM;
+	return xsk_buff_dma_map(umem, dev, 0);
 }
 
 static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv,
 				 struct xdp_umem *umem)
 {
-	struct device *dev = priv->mdev->device;
-	u32 i;
-
-	for (i = 0; i < umem->npgs; i++) {
-		dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
-		umem->pages[i].dma = 0;
-	}
+	return xsk_buff_dma_unmap(umem, 0);
 }
 
 static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk)
@@ -90,13 +64,14 @@ static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix)
 
 static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem)
 {
-	return umem->headroom <= 0xffff && umem->chunk_size_nohr <= 0xffff;
+	return xsk_umem_get_headroom(umem) <= 0xffff &&
+		xsk_umem_get_chunk_size(umem) <= 0xffff;
 }
 
 void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk)
 {
-	xsk->headroom = umem->headroom;
-	xsk->chunk_size = umem->chunk_size_nohr + umem->headroom;
+	xsk->headroom = xsk_umem_get_headroom(umem);
+	xsk->chunk_size = xsk_umem_get_chunk_size(umem);
 }
 
 static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
@@ -241,18 +216,6 @@ int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid)
 		      mlx5e_xsk_disable_umem(priv, ix);
 }
 
-int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries)
-{
-	struct xdp_umem_fq_reuse *reuseq;
-
-	reuseq = xsk_reuseq_prepare(nentries);
-	if (unlikely(!reuseq))
-		return -ENOMEM;
-	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
-	return 0;
-}
-
 u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk)
 {
 	u16 res = xsk->refcnt ? params->num_channels : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e4ca08ddca9..4041132723a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -38,7 +38,7 @@
 #include <linux/bpf.h>
 #include <linux/if_bridge.h>
 #include <net/page_pool.h>
-#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 #include "eswitch.h"
 #include "en.h"
 #include "en/txrx.h"
@@ -374,7 +374,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
-	u32 num_xsk_frames = 0;
 	u32 rq_xdp_ix;
 	u32 pool_size;
 	int wq_sz;
@@ -414,7 +413,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
-	rq->buff.umem_headroom = xsk ? xsk->headroom : 0;
 	pool_size = 1 << params->log_rq_mtu_frames;
 
 	switch (rq->wq_type) {
@@ -428,10 +426,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-		if (xsk)
-			num_xsk_frames = wq_sz <<
-				mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
-
 		pool_size = MLX5_MPWRQ_PAGES_PER_WQE <<
 			mlx5e_mpwqe_get_log_rq_size(params, xsk);
 
@@ -483,9 +477,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq);
 
-		if (xsk)
-			num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags;
-
 		rq->wqe.info = rqp->frags_info;
 		rq->buff.frame0_sz = rq->wqe.info.arr[0].frag_stride;
 
@@ -526,19 +517,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	}
 
 	if (xsk) {
-		rq->buff.frame0_sz = xsk_umem_xdp_frame_sz(umem);
-
-		err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames);
-		if (unlikely(err)) {
-			mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n",
-				      num_xsk_frames);
-			goto err_free;
-		}
-
-		rq->zca.free = mlx5e_xsk_zca_free;
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
-						 MEM_TYPE_ZERO_COPY,
-						 &rq->zca);
+						 MEM_TYPE_XSK_BUFF_POOL, NULL);
+		xsk_buff_set_rxq_info(rq->umem, &rq->xdp_rxq);
 	} else {
 		/* Create a page_pool and register it with rxq */
 		pp_params.order     = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 821f94beda7a..d7b24e8905f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -300,7 +300,7 @@ static inline void mlx5e_page_release(struct mlx5e_rq *rq,
 		 * put into the Reuse Ring, because there is no way to return
 		 * the page to the userspace when the interface goes down.
 		 */
-		mlx5e_xsk_page_release(rq, dma_info);
+		xsk_buff_free(dma_info->xsk);
 	else
 		mlx5e_page_release_dynamic(rq, dma_info, recycle);
 }
@@ -385,7 +385,11 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
 	if (rq->umem) {
 		int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
 
-		if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired)))
+		/* Check in advance that we have enough frames, instead of
+		 * allocating one-by-one, failing and moving frames to the
+		 * Reuse Ring.
+		 */
+		if (unlikely(!xsk_buff_can_alloc(rq->umem, pages_desired)))
 			return -ENOMEM;
 	}
 
@@ -480,8 +484,11 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	int err;
 	int i;
 
+	/* Check in advance that we have enough frames, instead of allocating
+	 * one-by-one, failing and moving frames to the Reuse Ring.
+	 */
 	if (rq->umem &&
-	    unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) {
+	    unlikely(!xsk_buff_can_alloc(rq->umem, MLX5_MPWRQ_PAGES_PER_WQE))) {
 		err = -ENOMEM;
 		goto err;
 	}
@@ -1044,12 +1051,24 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 	return skb;
 }
 
+static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom,
+				u32 len, struct xdp_buff *xdp)
+{
+	xdp->data_hard_start = va;
+	xdp_set_data_meta_invalid(xdp);
+	xdp->data = va + headroom;
+	xdp->data_end = xdp->data + len;
+	xdp->rxq = &rq->xdp_rxq;
+	xdp->frame_sz = rq->buff.frame0_sz;
+}
+
 struct sk_buff *
 mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			  struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
 	struct mlx5e_dma_info *di = wi->di;
 	u16 rx_headroom = rq->buff.headroom;
+	struct xdp_buff xdp;
 	struct sk_buff *skb;
 	void *va, *data;
 	bool consumed;
@@ -1065,11 +1084,13 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetch(data);
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
+	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp);
+	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp);
 	rcu_read_unlock();
 	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
 
+	rx_headroom = xdp.data - xdp.data_hard_start;
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
 	if (unlikely(!skb))
@@ -1343,6 +1364,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
 	u16 rx_headroom = rq->buff.headroom;
 	u32 cqe_bcnt32 = cqe_bcnt;
+	struct xdp_buff xdp;
 	struct sk_buff *skb;
 	void *va, *data;
 	u32 frag_size;
@@ -1364,7 +1386,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	prefetch(data);
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false);
+	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp);
+	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp);
 	rcu_read_unlock();
 	if (consumed) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
@@ -1372,6 +1395,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
+	rx_headroom = xdp.data - xdp.data_hard_start;
 	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32);
 	if (unlikely(!skb))
-- 
cgit v1.2.3


From f45a645fa6af37abb5484a8d8be779283a38fb53 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 5 May 2020 15:55:37 -0700
Subject: ice: report netlist version in .info_get

The flash memory for the ice hardware contains a block of information
used for link management called the Netlist module.

As this essentially represents another section of firmware, add its
version information to the output of the driver's .info_get handler.

This includes both a version and the first few bytes of a hash of the
module contents.

  fw.netlist -> the version information extracted from the netlist module
  fw.netlist.build-> first 4 bytes of the hash of the contents, similar
                     to fw.mgmt.build

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 Documentation/networking/devlink/ice.rst        | 11 ++++
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 27 ++++++++
 drivers/net/ethernet/intel/ice/ice_devlink.c    | 23 +++++++
 drivers/net/ethernet/intel/ice/ice_nvm.c        | 86 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_type.h       | 11 ++++
 5 files changed, 158 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index 4574352d6ff4..72ea8d295724 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -69,6 +69,17 @@ The ``ice`` driver reports the following versions
       - The version of the DDP package that is active in the device. Note
         that both the name (as reported by ``fw.app.name``) and version are
         required to uniquely identify the package.
+    * - ``fw.netlist``
+      - running
+      - 1.1.2000-6.7.0
+      - The version of the netlist module. This module defines the device's
+        Ethernet capabilities and default settings, and is used by the
+        management firmware as part of managing link and device
+        connectivity.
+    * - ``fw.netlist.build``
+      - running
+      - 0xee16ced7
+      - The first 4 bytes of the hash of the netlist module contents.
 
 Regions
 =======
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 2381b4014ed6..8767a78038e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1264,6 +1264,33 @@ struct ice_aqc_nvm_checksum {
 	u8 rsvd2[12];
 };
 
+/* The result of netlist NVM read comes in a TLV format. The actual data
+ * (netlist header) starts from word offset 1 (byte 2). The FW strips
+ * out the type field from the TLV header so all the netlist fields
+ * should adjust their offset value by 1 word (2 bytes) in order to map
+ * their correct location.
+ */
+#define ICE_AQC_NVM_LINK_TOPO_NETLIST_MOD_ID		0x11B
+#define ICE_AQC_NVM_LINK_TOPO_NETLIST_LEN_OFFSET	1
+#define ICE_AQC_NVM_LINK_TOPO_NETLIST_LEN		2 /* In bytes */
+#define ICE_AQC_NVM_NETLIST_NODE_COUNT_OFFSET		2
+#define ICE_AQC_NVM_NETLIST_NODE_COUNT_LEN		2 /* In bytes */
+#define ICE_AQC_NVM_NETLIST_NODE_COUNT_M		ICE_M(0x3FF, 0)
+#define ICE_AQC_NVM_NETLIST_ID_BLK_START_OFFSET		5
+#define ICE_AQC_NVM_NETLIST_ID_BLK_LEN			0x30 /* In words */
+
+/* netlist ID block field offsets (word offsets) */
+#define ICE_AQC_NVM_NETLIST_ID_BLK_MAJOR_VER_LOW	2
+#define ICE_AQC_NVM_NETLIST_ID_BLK_MAJOR_VER_HIGH	3
+#define ICE_AQC_NVM_NETLIST_ID_BLK_MINOR_VER_LOW	4
+#define ICE_AQC_NVM_NETLIST_ID_BLK_MINOR_VER_HIGH	5
+#define ICE_AQC_NVM_NETLIST_ID_BLK_TYPE_LOW		6
+#define ICE_AQC_NVM_NETLIST_ID_BLK_TYPE_HIGH		7
+#define ICE_AQC_NVM_NETLIST_ID_BLK_REV_LOW		8
+#define ICE_AQC_NVM_NETLIST_ID_BLK_REV_HIGH		9
+#define ICE_AQC_NVM_NETLIST_ID_BLK_SHA_HASH		0xA
+#define ICE_AQC_NVM_NETLIST_ID_BLK_CUST_VER		0x2F
+
 /**
  * Send to PF command (indirect 0x0801) ID is only used by PF
  *
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index c6833944b90a..a73d06e06b5d 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -105,6 +105,27 @@ static int ice_info_ddp_pkg_version(struct ice_pf *pf, char *buf, size_t len)
 	return 0;
 }
 
+static int ice_info_netlist_ver(struct ice_pf *pf, char *buf, size_t len)
+{
+	struct ice_netlist_ver_info *netlist = &pf->hw.netlist_ver;
+
+	/* The netlist version fields are BCD formatted */
+	snprintf(buf, len, "%x.%x.%x-%x.%x.%x", netlist->major, netlist->minor,
+		 netlist->type >> 16, netlist->type & 0xFFFF, netlist->rev,
+		 netlist->cust_ver);
+
+	return 0;
+}
+
+static int ice_info_netlist_build(struct ice_pf *pf, char *buf, size_t len)
+{
+	struct ice_netlist_ver_info *netlist = &pf->hw.netlist_ver;
+
+	snprintf(buf, len, "0x%08x", netlist->hash);
+
+	return 0;
+}
+
 #define fixed(key, getter) { ICE_VERSION_FIXED, key, getter }
 #define running(key, getter) { ICE_VERSION_RUNNING, key, getter }
 
@@ -128,6 +149,8 @@ static const struct ice_devlink_version {
 	running(DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID, ice_info_eetrack),
 	running("fw.app.name", ice_info_ddp_pkg_name),
 	running(DEVLINK_INFO_VERSION_GENERIC_FW_APP, ice_info_ddp_pkg_version),
+	running("fw.netlist", ice_info_netlist_ver),
+	running("fw.netlist.build", ice_info_netlist_build),
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 8beb675d676b..7c2a06892bbb 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -366,6 +366,87 @@ static enum ice_status ice_get_orom_ver_info(struct ice_hw *hw)
 	return 0;
 }
 
+/**
+ * ice_get_netlist_ver_info
+ * @hw: pointer to the HW struct
+ *
+ * Get the netlist version information
+ */
+static enum ice_status ice_get_netlist_ver_info(struct ice_hw *hw)
+{
+	struct ice_netlist_ver_info *ver = &hw->netlist_ver;
+	enum ice_status ret;
+	u32 id_blk_start;
+	__le16 raw_data;
+	u16 data, i;
+	u16 *buff;
+
+	ret = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (ret)
+		return ret;
+	buff = kcalloc(ICE_AQC_NVM_NETLIST_ID_BLK_LEN, sizeof(*buff),
+		       GFP_KERNEL);
+	if (!buff) {
+		ret = ICE_ERR_NO_MEMORY;
+		goto exit_no_mem;
+	}
+
+	/* read module length */
+	ret = ice_aq_read_nvm(hw, ICE_AQC_NVM_LINK_TOPO_NETLIST_MOD_ID,
+			      ICE_AQC_NVM_LINK_TOPO_NETLIST_LEN_OFFSET * 2,
+			      ICE_AQC_NVM_LINK_TOPO_NETLIST_LEN, &raw_data,
+			      false, false, NULL);
+	if (ret)
+		goto exit_error;
+
+	data = le16_to_cpu(raw_data);
+	/* exit if length is = 0 */
+	if (!data)
+		goto exit_error;
+
+	/* read node count */
+	ret = ice_aq_read_nvm(hw, ICE_AQC_NVM_LINK_TOPO_NETLIST_MOD_ID,
+			      ICE_AQC_NVM_NETLIST_NODE_COUNT_OFFSET * 2,
+			      ICE_AQC_NVM_NETLIST_NODE_COUNT_LEN, &raw_data,
+			      false, false, NULL);
+	if (ret)
+		goto exit_error;
+	data = le16_to_cpu(raw_data) & ICE_AQC_NVM_NETLIST_NODE_COUNT_M;
+
+	/* netlist ID block starts from offset 4 + node count * 2 */
+	id_blk_start = ICE_AQC_NVM_NETLIST_ID_BLK_START_OFFSET + data * 2;
+
+	/* read the entire netlist ID block */
+	ret = ice_aq_read_nvm(hw, ICE_AQC_NVM_LINK_TOPO_NETLIST_MOD_ID,
+			      id_blk_start * 2,
+			      ICE_AQC_NVM_NETLIST_ID_BLK_LEN * 2, buff, false,
+			      false, NULL);
+	if (ret)
+		goto exit_error;
+
+	for (i = 0; i < ICE_AQC_NVM_NETLIST_ID_BLK_LEN; i++)
+		buff[i] = le16_to_cpu(((__force __le16 *)buff)[i]);
+
+	ver->major = (buff[ICE_AQC_NVM_NETLIST_ID_BLK_MAJOR_VER_HIGH] << 16) |
+		buff[ICE_AQC_NVM_NETLIST_ID_BLK_MAJOR_VER_LOW];
+	ver->minor = (buff[ICE_AQC_NVM_NETLIST_ID_BLK_MINOR_VER_HIGH] << 16) |
+		buff[ICE_AQC_NVM_NETLIST_ID_BLK_MINOR_VER_LOW];
+	ver->type = (buff[ICE_AQC_NVM_NETLIST_ID_BLK_TYPE_HIGH] << 16) |
+		buff[ICE_AQC_NVM_NETLIST_ID_BLK_TYPE_LOW];
+	ver->rev = (buff[ICE_AQC_NVM_NETLIST_ID_BLK_REV_HIGH] << 16) |
+		buff[ICE_AQC_NVM_NETLIST_ID_BLK_REV_LOW];
+	ver->cust_ver = buff[ICE_AQC_NVM_NETLIST_ID_BLK_CUST_VER];
+	/* Read the left most 4 bytes of SHA */
+	ver->hash = buff[ICE_AQC_NVM_NETLIST_ID_BLK_SHA_HASH + 15] << 16 |
+		buff[ICE_AQC_NVM_NETLIST_ID_BLK_SHA_HASH + 14];
+
+exit_error:
+	kfree(buff);
+exit_no_mem:
+	ice_release_nvm(hw);
+	return ret;
+}
+
 /**
  * ice_discover_flash_size - Discover the available flash size.
  * @hw: pointer to the HW struct
@@ -515,6 +596,11 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
 		return status;
 	}
 
+	/* read the netlist version information */
+	status = ice_get_netlist_ver_info(hw);
+	if (status)
+		ice_debug(hw, ICE_DBG_INIT, "Failed to read netlist info.\n");
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4ce5f92fca4a..35ea5adbb3e5 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -259,6 +259,16 @@ struct ice_nvm_info {
 
 #define ICE_NVM_VER_LEN	32
 
+/* netlist version information */
+struct ice_netlist_ver_info {
+	u32 major;			/* major high/low */
+	u32 minor;			/* minor high/low */
+	u32 type;			/* type high/low */
+	u32 rev;			/* revision high/low */
+	u32 hash;			/* SHA-1 hash word */
+	u16 cust_ver;			/* customer version */
+};
+
 /* Max number of port to queue branches w.r.t topology */
 #define ICE_MAX_TRAFFIC_CLASS 8
 #define ICE_TXSCHED_MAX_BRANCHES ICE_MAX_TRAFFIC_CLASS
@@ -506,6 +516,7 @@ struct ice_hw {
 	struct ice_nvm_info nvm;
 	struct ice_hw_dev_caps dev_caps;	/* device capabilities */
 	struct ice_hw_func_caps func_caps;	/* function capabilities */
+	struct ice_netlist_ver_info netlist_ver; /* netlist version info */
 
 	struct ice_switch_info *switch_info;	/* switch filter lists */
 
-- 
cgit v1.2.3


From a4e82a81f57387803f950cc3d9d112bcc5553a3d Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Wed, 6 May 2020 09:32:30 -0700
Subject: ice: Add support for tunnel offloads

Create a boost TCAM entry for each tunnel port in order to get a tunnel
PTYPE. Update netdev feature flags and implement the appropriate logic to
get and set values for hardware offloads.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h               |   4 +
 drivers/net/ethernet/intel/ice/ice_common.c        |   2 +
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c     | 524 ++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_flex_pipe.h     |   5 +
 drivers/net/ethernet/intel/ice/ice_flex_type.h     |  33 ++
 drivers/net/ethernet/intel/ice/ice_flow.c          |  36 +-
 drivers/net/ethernet/intel/ice/ice_flow.h          |   3 +
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h     |  25 +
 drivers/net/ethernet/intel/ice/ice_main.c          |  94 +++-
 drivers/net/ethernet/intel/ice/ice_protocol_type.h |   1 +
 drivers/net/ethernet/intel/ice/ice_txrx.c          | 126 ++++-
 drivers/net/ethernet/intel/ice/ice_txrx.h          |   3 +
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c      |  21 +-
 drivers/net/ethernet/intel/ice/ice_type.h          |   4 +
 14 files changed, 867 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 5c11448bfbb3..43349eaa02b2 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -37,6 +37,10 @@
 #include <net/devlink.h>
 #include <net/ipv6.h>
 #include <net/xdp_sock.h>
+#include <net/geneve.h>
+#include <net/gre.h>
+#include <net/udp_tunnel.h>
+#include <net/vxlan.h>
 #include "ice_devids.h"
 #include "ice_type.h"
 #include "ice_txrx.h"
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 2c0d8fd3d5cd..1a613199d6cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -746,6 +746,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	status = ice_init_hw_tbls(hw);
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
+	mutex_init(&hw->tnl_lock);
 	return 0;
 
 err_unroll_fltr_mgmt_struct:
@@ -775,6 +776,7 @@ void ice_deinit_hw(struct ice_hw *hw)
 	ice_sched_clear_agg(hw);
 	ice_free_seg(hw);
 	ice_free_hw_tbls(hw);
+	mutex_destroy(&hw->tnl_lock);
 
 	if (hw->port_info) {
 		devm_kfree(ice_hw_to_dev(hw), hw->port_info);
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index e7a2671222d2..62e305511c7e 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -5,6 +5,15 @@
 #include "ice_flex_pipe.h"
 #include "ice_flow.h"
 
+/* To support tunneling entries by PF, the package will append the PF number to
+ * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc.
+ */
+static const struct ice_tunnel_type_scan tnls[] = {
+	{ TNL_VXLAN,		"TNL_VXLAN_PF" },
+	{ TNL_GENEVE,		"TNL_GENEVE_PF" },
+	{ TNL_LAST,		"" }
+};
+
 static const u32 ice_sect_lkup[ICE_BLK_COUNT][ICE_SECT_COUNT] = {
 	/* SWITCH */
 	{
@@ -239,6 +248,268 @@ ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
 	return state->sect;
 }
 
+/**
+ * ice_pkg_enum_entry
+ * @ice_seg: pointer to the ice segment (or NULL on subsequent calls)
+ * @state: pointer to the enum state
+ * @sect_type: section type to enumerate
+ * @offset: pointer to variable that receives the offset in the table (optional)
+ * @handler: function that handles access to the entries into the section type
+ *
+ * This function will enumerate all the entries in particular section type in
+ * the ice segment. The first call is made with the ice_seg parameter non-NULL;
+ * on subsequent calls, ice_seg is set to NULL which continues the enumeration.
+ * When the function returns a NULL pointer, then the end of the entries has
+ * been reached.
+ *
+ * Since each section may have a different header and entry size, the handler
+ * function is needed to determine the number and location entries in each
+ * section.
+ *
+ * The offset parameter is optional, but should be used for sections that
+ * contain an offset for each section table. For such cases, the section handler
+ * function must return the appropriate offset + index to give the absolution
+ * offset for each entry. For example, if the base for a section's header
+ * indicates a base offset of 10, and the index for the entry is 2, then
+ * section handler function should set the offset to 10 + 2 = 12.
+ */
+static void *
+ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
+		   u32 sect_type, u32 *offset,
+		   void *(*handler)(u32 sect_type, void *section,
+				    u32 index, u32 *offset))
+{
+	void *entry;
+
+	if (ice_seg) {
+		if (!handler)
+			return NULL;
+
+		if (!ice_pkg_enum_section(ice_seg, state, sect_type))
+			return NULL;
+
+		state->entry_idx = 0;
+		state->handler = handler;
+	} else {
+		state->entry_idx++;
+	}
+
+	if (!state->handler)
+		return NULL;
+
+	/* get entry */
+	entry = state->handler(state->sect_type, state->sect, state->entry_idx,
+			       offset);
+	if (!entry) {
+		/* end of a section, look for another section of this type */
+		if (!ice_pkg_enum_section(NULL, state, 0))
+			return NULL;
+
+		state->entry_idx = 0;
+		entry = state->handler(state->sect_type, state->sect,
+				       state->entry_idx, offset);
+	}
+
+	return entry;
+}
+
+/**
+ * ice_boost_tcam_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the boost TCAM entry to be returned
+ * @offset: pointer to receive absolute offset, always 0 for boost TCAM sections
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * Handles enumeration of individual boost TCAM entries.
+ */
+static void *
+ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, u32 *offset)
+{
+	struct ice_boost_tcam_section *boost;
+
+	if (!section)
+		return NULL;
+
+	if (sect_type != ICE_SID_RXPARSER_BOOST_TCAM)
+		return NULL;
+
+	if (index > ICE_MAX_BST_TCAMS_IN_BUF)
+		return NULL;
+
+	if (offset)
+		*offset = 0;
+
+	boost = section;
+	if (index >= le16_to_cpu(boost->count))
+		return NULL;
+
+	return boost->tcam + index;
+}
+
+/**
+ * ice_find_boost_entry
+ * @ice_seg: pointer to the ice segment (non-NULL)
+ * @addr: Boost TCAM address of entry to search for
+ * @entry: returns pointer to the entry
+ *
+ * Finds a particular Boost TCAM entry and returns a pointer to that entry
+ * if it is found. The ice_seg parameter must not be NULL since the first call
+ * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure.
+ */
+static enum ice_status
+ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr,
+		     struct ice_boost_tcam_entry **entry)
+{
+	struct ice_boost_tcam_entry *tcam;
+	struct ice_pkg_enum state;
+
+	memset(&state, 0, sizeof(state));
+
+	if (!ice_seg)
+		return ICE_ERR_PARAM;
+
+	do {
+		tcam = ice_pkg_enum_entry(ice_seg, &state,
+					  ICE_SID_RXPARSER_BOOST_TCAM, NULL,
+					  ice_boost_tcam_handler);
+		if (tcam && le16_to_cpu(tcam->addr) == addr) {
+			*entry = tcam;
+			return 0;
+		}
+
+		ice_seg = NULL;
+	} while (tcam);
+
+	*entry = NULL;
+	return ICE_ERR_CFG;
+}
+
+/**
+ * ice_label_enum_handler
+ * @sect_type: section type
+ * @section: pointer to section
+ * @index: index of the label entry to be returned
+ * @offset: pointer to receive absolute offset, always zero for label sections
+ *
+ * This is a callback function that can be passed to ice_pkg_enum_entry.
+ * Handles enumeration of individual label entries.
+ */
+static void *
+ice_label_enum_handler(u32 __always_unused sect_type, void *section, u32 index,
+		       u32 *offset)
+{
+	struct ice_label_section *labels;
+
+	if (!section)
+		return NULL;
+
+	if (index > ICE_MAX_LABELS_IN_BUF)
+		return NULL;
+
+	if (offset)
+		*offset = 0;
+
+	labels = section;
+	if (index >= le16_to_cpu(labels->count))
+		return NULL;
+
+	return labels->label + index;
+}
+
+/**
+ * ice_enum_labels
+ * @ice_seg: pointer to the ice segment (NULL on subsequent calls)
+ * @type: the section type that will contain the label (0 on subsequent calls)
+ * @state: ice_pkg_enum structure that will hold the state of the enumeration
+ * @value: pointer to a value that will return the label's value if found
+ *
+ * Enumerates a list of labels in the package. The caller will call
+ * ice_enum_labels(ice_seg, type, ...) to start the enumeration, then call
+ * ice_enum_labels(NULL, 0, ...) to continue. When the function returns a NULL
+ * the end of the list has been reached.
+ */
+static char *
+ice_enum_labels(struct ice_seg *ice_seg, u32 type, struct ice_pkg_enum *state,
+		u16 *value)
+{
+	struct ice_label *label;
+
+	/* Check for valid label section on first call */
+	if (type && !(type >= ICE_SID_LBL_FIRST && type <= ICE_SID_LBL_LAST))
+		return NULL;
+
+	label = ice_pkg_enum_entry(ice_seg, state, type, NULL,
+				   ice_label_enum_handler);
+	if (!label)
+		return NULL;
+
+	*value = le16_to_cpu(label->value);
+	return label->name;
+}
+
+/**
+ * ice_init_pkg_hints
+ * @hw: pointer to the HW structure
+ * @ice_seg: pointer to the segment of the package scan (non-NULL)
+ *
+ * This function will scan the package and save off relevant information
+ * (hints or metadata) for driver use. The ice_seg parameter must not be NULL
+ * since the first call to ice_enum_labels requires a pointer to an actual
+ * ice_seg structure.
+ */
+static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+	struct ice_pkg_enum state;
+	char *label_name;
+	u16 val;
+	int i;
+
+	memset(&hw->tnl, 0, sizeof(hw->tnl));
+	memset(&state, 0, sizeof(state));
+
+	if (!ice_seg)
+		return;
+
+	label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state,
+				     &val);
+
+	while (label_name && hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) {
+		for (i = 0; tnls[i].type != TNL_LAST; i++) {
+			size_t len = strlen(tnls[i].label_prefix);
+
+			/* Look for matching label start, before continuing */
+			if (strncmp(label_name, tnls[i].label_prefix, len))
+				continue;
+
+			/* Make sure this label matches our PF. Note that the PF
+			 * character ('0' - '7') will be located where our
+			 * prefix string's null terminator is located.
+			 */
+			if ((label_name[len] - '0') == hw->pf_id) {
+				hw->tnl.tbl[hw->tnl.count].type = tnls[i].type;
+				hw->tnl.tbl[hw->tnl.count].valid = false;
+				hw->tnl.tbl[hw->tnl.count].in_use = false;
+				hw->tnl.tbl[hw->tnl.count].marked = false;
+				hw->tnl.tbl[hw->tnl.count].boost_addr = val;
+				hw->tnl.tbl[hw->tnl.count].port = 0;
+				hw->tnl.count++;
+				break;
+			}
+		}
+
+		label_name = ice_enum_labels(NULL, 0, &state, &val);
+	}
+
+	/* Cache the appropriate boost TCAM entry pointers */
+	for (i = 0; i < hw->tnl.count; i++) {
+		ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr,
+				     &hw->tnl.tbl[i].boost_entry);
+		if (hw->tnl.tbl[i].boost_entry)
+			hw->tnl.tbl[i].valid = true;
+	}
+}
+
 /* Key creation */
 
 #define ICE_DC_KEY	0x1	/* don't care */
@@ -1050,7 +1321,8 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
 		return ICE_ERR_CFG;
 	}
 
-	/* download package */
+	/* initialize package hints and then download package */
+	ice_init_pkg_hints(hw, seg);
 	status = ice_download_pkg(hw, seg);
 	if (status == ICE_ERR_AQ_NO_WORK) {
 		ice_debug(hw, ICE_DBG_INIT,
@@ -1292,6 +1564,256 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
 	return &bld->buf;
 }
 
+/**
+ * ice_tunnel_port_in_use_hlpr - helper function to determine tunnel usage
+ * @hw: pointer to the HW structure
+ * @port: port to search for
+ * @index: optionally returns index
+ *
+ * Returns whether a port is already in use as a tunnel, and optionally its
+ * index
+ */
+static bool ice_tunnel_port_in_use_hlpr(struct ice_hw *hw, u16 port, u16 *index)
+{
+	u16 i;
+
+	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
+		if (hw->tnl.tbl[i].in_use && hw->tnl.tbl[i].port == port) {
+			if (index)
+				*index = i;
+			return true;
+		}
+
+	return false;
+}
+
+/**
+ * ice_tunnel_port_in_use
+ * @hw: pointer to the HW structure
+ * @port: port to search for
+ * @index: optionally returns index
+ *
+ * Returns whether a port is already in use as a tunnel, and optionally its
+ * index
+ */
+bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index)
+{
+	bool res;
+
+	mutex_lock(&hw->tnl_lock);
+	res = ice_tunnel_port_in_use_hlpr(hw, port, index);
+	mutex_unlock(&hw->tnl_lock);
+
+	return res;
+}
+
+/**
+ * ice_find_free_tunnel_entry
+ * @hw: pointer to the HW structure
+ * @type: tunnel type
+ * @index: optionally returns index
+ *
+ * Returns whether there is a free tunnel entry, and optionally its index
+ */
+static bool
+ice_find_free_tunnel_entry(struct ice_hw *hw, enum ice_tunnel_type type,
+			   u16 *index)
+{
+	u16 i;
+
+	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
+		if (hw->tnl.tbl[i].valid && !hw->tnl.tbl[i].in_use &&
+		    hw->tnl.tbl[i].type == type) {
+			if (index)
+				*index = i;
+			return true;
+		}
+
+	return false;
+}
+
+/**
+ * ice_create_tunnel
+ * @hw: pointer to the HW structure
+ * @type: type of tunnel
+ * @port: port of tunnel to create
+ *
+ * Create a tunnel by updating the parse graph in the parser. We do that by
+ * creating a package buffer with the tunnel info and issuing an update package
+ * command.
+ */
+enum ice_status
+ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
+{
+	struct ice_boost_tcam_section *sect_rx, *sect_tx;
+	enum ice_status status = ICE_ERR_MAX_LIMIT;
+	struct ice_buf_build *bld;
+	u16 index;
+
+	mutex_lock(&hw->tnl_lock);
+
+	if (ice_tunnel_port_in_use_hlpr(hw, port, &index)) {
+		hw->tnl.tbl[index].ref++;
+		status = 0;
+		goto ice_create_tunnel_end;
+	}
+
+	if (!ice_find_free_tunnel_entry(hw, type, &index)) {
+		status = ICE_ERR_OUT_OF_RANGE;
+		goto ice_create_tunnel_end;
+	}
+
+	bld = ice_pkg_buf_alloc(hw);
+	if (!bld) {
+		status = ICE_ERR_NO_MEMORY;
+		goto ice_create_tunnel_end;
+	}
+
+	/* allocate 2 sections, one for Rx parser, one for Tx parser */
+	if (ice_pkg_buf_reserve_section(bld, 2))
+		goto ice_create_tunnel_err;
+
+	sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM,
+					    sizeof(*sect_rx));
+	if (!sect_rx)
+		goto ice_create_tunnel_err;
+	sect_rx->count = cpu_to_le16(1);
+
+	sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM,
+					    sizeof(*sect_tx));
+	if (!sect_tx)
+		goto ice_create_tunnel_err;
+	sect_tx->count = cpu_to_le16(1);
+
+	/* copy original boost entry to update package buffer */
+	memcpy(sect_rx->tcam, hw->tnl.tbl[index].boost_entry,
+	       sizeof(*sect_rx->tcam));
+
+	/* over-write the never-match dest port key bits with the encoded port
+	 * bits
+	 */
+	ice_set_key((u8 *)&sect_rx->tcam[0].key, sizeof(sect_rx->tcam[0].key),
+		    (u8 *)&port, NULL, NULL, NULL,
+		    offsetof(struct ice_boost_key_value, hv_dst_port_key),
+		    sizeof(sect_rx->tcam[0].key.key.hv_dst_port_key));
+
+	/* exact copy of entry to Tx section entry */
+	memcpy(sect_tx->tcam, sect_rx->tcam, sizeof(*sect_tx->tcam));
+
+	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
+	if (!status) {
+		hw->tnl.tbl[index].port = port;
+		hw->tnl.tbl[index].in_use = true;
+		hw->tnl.tbl[index].ref = 1;
+	}
+
+ice_create_tunnel_err:
+	ice_pkg_buf_free(hw, bld);
+
+ice_create_tunnel_end:
+	mutex_unlock(&hw->tnl_lock);
+
+	return status;
+}
+
+/**
+ * ice_destroy_tunnel
+ * @hw: pointer to the HW structure
+ * @port: port of tunnel to destroy (ignored if the all parameter is true)
+ * @all: flag that states to destroy all tunnels
+ *
+ * Destroys a tunnel or all tunnels by creating an update package buffer
+ * targeting the specific updates requested and then performing an update
+ * package.
+ */
+enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
+{
+	struct ice_boost_tcam_section *sect_rx, *sect_tx;
+	enum ice_status status = ICE_ERR_MAX_LIMIT;
+	struct ice_buf_build *bld;
+	u16 count = 0;
+	u16 index;
+	u16 size;
+	u16 i;
+
+	mutex_lock(&hw->tnl_lock);
+
+	if (!all && ice_tunnel_port_in_use_hlpr(hw, port, &index))
+		if (hw->tnl.tbl[index].ref > 1) {
+			hw->tnl.tbl[index].ref--;
+			status = 0;
+			goto ice_destroy_tunnel_end;
+		}
+
+	/* determine count */
+	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
+		    (all || hw->tnl.tbl[i].port == port))
+			count++;
+
+	if (!count) {
+		status = ICE_ERR_PARAM;
+		goto ice_destroy_tunnel_end;
+	}
+
+	/* size of section - there is at least one entry */
+	size = struct_size(sect_rx, tcam, count - 1);
+
+	bld = ice_pkg_buf_alloc(hw);
+	if (!bld) {
+		status = ICE_ERR_NO_MEMORY;
+		goto ice_destroy_tunnel_end;
+	}
+
+	/* allocate 2 sections, one for Rx parser, one for Tx parser */
+	if (ice_pkg_buf_reserve_section(bld, 2))
+		goto ice_destroy_tunnel_err;
+
+	sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM,
+					    size);
+	if (!sect_rx)
+		goto ice_destroy_tunnel_err;
+	sect_rx->count = cpu_to_le16(1);
+
+	sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM,
+					    size);
+	if (!sect_tx)
+		goto ice_destroy_tunnel_err;
+	sect_tx->count = cpu_to_le16(1);
+
+	/* copy original boost entry to update package buffer, one copy to Rx
+	 * section, another copy to the Tx section
+	 */
+	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
+		    (all || hw->tnl.tbl[i].port == port)) {
+			memcpy(sect_rx->tcam + i, hw->tnl.tbl[i].boost_entry,
+			       sizeof(*sect_rx->tcam));
+			memcpy(sect_tx->tcam + i, hw->tnl.tbl[i].boost_entry,
+			       sizeof(*sect_tx->tcam));
+			hw->tnl.tbl[i].marked = true;
+		}
+
+	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
+	if (!status)
+		for (i = 0; i < hw->tnl.count &&
+		     i < ICE_TUNNEL_MAX_ENTRIES; i++)
+			if (hw->tnl.tbl[i].marked) {
+				hw->tnl.tbl[i].ref = 0;
+				hw->tnl.tbl[i].port = 0;
+				hw->tnl.tbl[i].in_use = false;
+				hw->tnl.tbl[i].marked = false;
+			}
+
+ice_destroy_tunnel_err:
+	ice_pkg_buf_free(hw, bld);
+
+ice_destroy_tunnel_end:
+	mutex_unlock(&hw->tnl_lock);
+
+	return status;
+}
+
 /* PTG Management */
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index c7b5e1a6ea2b..70db213c9fe3 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -18,6 +18,11 @@
 
 #define ICE_PKG_CNT 4
 
+enum ice_status
+ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port);
+enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all);
+bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index);
+
 enum ice_status
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	     struct ice_fv_word *es);
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 0fb3fe3ff3ea..249fb66fc230 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -149,6 +149,7 @@ struct ice_buf_hdr {
 #define ICE_SID_CDID_REDIR_RSS		48
 
 #define ICE_SID_RXPARSER_BOOST_TCAM	56
+#define ICE_SID_TXPARSER_BOOST_TCAM	66
 
 #define ICE_SID_XLT0_PE			80
 #define ICE_SID_XLT_KEY_BUILDER_PE	81
@@ -291,6 +292,38 @@ struct ice_pkg_enum {
 	void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset);
 };
 
+/* Tunnel enabling */
+
+enum ice_tunnel_type {
+	TNL_VXLAN = 0,
+	TNL_GENEVE,
+	TNL_LAST = 0xFF,
+	TNL_ALL = 0xFF,
+};
+
+struct ice_tunnel_type_scan {
+	enum ice_tunnel_type type;
+	const char *label_prefix;
+};
+
+struct ice_tunnel_entry {
+	enum ice_tunnel_type type;
+	u16 boost_addr;
+	u16 port;
+	u16 ref;
+	struct ice_boost_tcam_entry *boost_entry;
+	u8 valid;
+	u8 in_use;
+	u8 marked;
+};
+
+#define ICE_TUNNEL_MAX_ENTRIES	16
+
+struct ice_tunnel_table {
+	struct ice_tunnel_entry tbl[ICE_TUNNEL_MAX_ENTRIES];
+	u16 count;
+};
+
 struct ice_pkg_es {
 	__le16 count;
 	__le16 offset;
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index 3de862a3c789..07875db08c3f 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -42,7 +42,10 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = {
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 0, sizeof(__be16)),
 	/* ICE_FLOW_FIELD_IDX_SCTP_DST_PORT */
 	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 2, sizeof(__be16)),
-
+	/* GRE */
+	/* ICE_FLOW_FIELD_IDX_GRE_KEYID */
+	ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GRE, 12,
+			  sizeof_field(struct gre_full_hdr, key)),
 };
 
 /* Bitmaps indicating relevant packet types for a particular protocol header
@@ -134,6 +137,18 @@ static const u32 ice_ptypes_sctp_il[] = {
 	0x00000000, 0x00000000, 0x00000000, 0x00000000,
 };
 
+/* Packet types for packets with an Outermost/First GRE header */
+static const u32 ice_ptypes_gre_of[] = {
+	0x00000000, 0xBFBF7800, 0x000001DF, 0xFEFDE000,
+	0x0000017E, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000,
+};
+
 /* Manage parameters and info. used during the creation of a flow profile */
 struct ice_flow_prof_params {
 	enum ice_block blk;
@@ -225,6 +240,12 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params)
 			src = (const unsigned long *)ice_ptypes_sctp_il;
 			bitmap_and(params->ptypes, params->ptypes, src,
 				   ICE_FLOW_PTYPE_MAX);
+		} else if (hdrs & ICE_FLOW_SEG_HDR_GRE) {
+			if (!i) {
+				src = (const unsigned long *)ice_ptypes_gre_of;
+				bitmap_and(params->ptypes, params->ptypes,
+					   src, ICE_FLOW_PTYPE_MAX);
+			}
 		}
 	}
 
@@ -275,6 +296,9 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params,
 	case ICE_FLOW_FIELD_IDX_SCTP_DST_PORT:
 		prot_id = ICE_PROT_SCTP_IL;
 		break;
+	case ICE_FLOW_FIELD_IDX_GRE_KEYID:
+		prot_id = ICE_PROT_GRE_OF;
+		break;
 	default:
 		return ICE_ERR_NOT_IMPL;
 	}
@@ -945,6 +969,7 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 #define ICE_FLOW_PROF_ENCAP_M	(BIT_ULL(ICE_FLOW_PROF_ENCAP_S))
 
 #define ICE_RSS_OUTER_HEADERS	1
+#define ICE_RSS_INNER_HEADERS	2
 
 /* Flow profile ID format:
  * [0:31] - Packet match fields
@@ -1085,6 +1110,9 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 	mutex_lock(&hw->rss_locks);
 	status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
 				      ICE_RSS_OUTER_HEADERS);
+	if (!status)
+		status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds,
+					      addl_hdrs, ICE_RSS_INNER_HEADERS);
 	mutex_unlock(&hw->rss_locks);
 
 	return status;
@@ -1238,6 +1266,12 @@ enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 						      ICE_RSS_OUTER_HEADERS);
 			if (status)
 				break;
+			status = ice_add_rss_cfg_sync(hw, vsi_handle,
+						      r->hashed_flds,
+						      r->packet_hdr,
+						      ICE_RSS_INNER_HEADERS);
+			if (status)
+				break;
 		}
 	}
 	mutex_unlock(&hw->rss_locks);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 5558627bd5eb..00f2b7a9feed 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -43,6 +43,7 @@ enum ice_flow_seg_hdr {
 	ICE_FLOW_SEG_HDR_TCP		= 0x00000040,
 	ICE_FLOW_SEG_HDR_UDP		= 0x00000080,
 	ICE_FLOW_SEG_HDR_SCTP		= 0x00000100,
+	ICE_FLOW_SEG_HDR_GRE		= 0x00000200,
 };
 
 enum ice_flow_field {
@@ -58,6 +59,8 @@ enum ice_flow_field {
 	ICE_FLOW_FIELD_IDX_UDP_DST_PORT,
 	ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT,
 	ICE_FLOW_FIELD_IDX_SCTP_DST_PORT,
+	/* GRE */
+	ICE_FLOW_FIELD_IDX_GRE_KEYID,
 	/* The total number of enums must not exceed 64 */
 	ICE_FLOW_FIELD_IDX_MAX
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 878e125d8b42..5d61acdec7ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -262,6 +262,12 @@ enum ice_rx_flex_desc_status_error_0_bits {
 	ICE_RX_FLEX_DESC_STATUS0_LAST /* this entry must be last!!! */
 };
 
+enum ice_rx_flex_desc_status_error_1_bits {
+	/* Note: These are predefined bit offsets */
+	ICE_RX_FLEX_DESC_STATUS1_NAT_S = 4,
+	ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */
+};
+
 #define ICE_RXQ_CTX_SIZE_DWORDS		8
 #define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
 #define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS	22
@@ -413,6 +419,25 @@ enum ice_tx_ctx_desc_cmd_bits {
 	ICE_TX_CTX_DESC_RESERVED	= 0x40
 };
 
+enum ice_tx_ctx_desc_eipt_offload {
+	ICE_TX_CTX_EIPT_NONE		= 0x0,
+	ICE_TX_CTX_EIPT_IPV6		= 0x1,
+	ICE_TX_CTX_EIPT_IPV4_NO_CSUM	= 0x2,
+	ICE_TX_CTX_EIPT_IPV4		= 0x3
+};
+
+#define ICE_TXD_CTX_QW0_EIPLEN_S	2
+
+#define ICE_TXD_CTX_QW0_L4TUNT_S	9
+
+#define ICE_TXD_CTX_UDP_TUNNELING	BIT_ULL(ICE_TXD_CTX_QW0_L4TUNT_S)
+#define ICE_TXD_CTX_GRE_TUNNELING	(0x2ULL << ICE_TXD_CTX_QW0_L4TUNT_S)
+
+#define ICE_TXD_CTX_QW0_NATLEN_S	12
+
+#define ICE_TXD_CTX_QW0_L4T_CS_S	23
+#define ICE_TXD_CTX_QW0_L4T_CS_M	BIT_ULL(ICE_TXD_CTX_QW0_L4T_CS_S)
+
 #define ICE_LAN_TXQ_MAX_QGRPS	127
 #define ICE_LAN_TXQ_MAX_QDIS	1023
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 5b190c257124..44ff4fe45a56 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2342,13 +2342,27 @@ static void ice_set_netdev_features(struct net_device *netdev)
 			 NETIF_F_HW_VLAN_CTAG_TX     |
 			 NETIF_F_HW_VLAN_CTAG_RX;
 
-	tso_features = NETIF_F_TSO		|
+	tso_features = NETIF_F_TSO			|
+		       NETIF_F_TSO_ECN			|
+		       NETIF_F_TSO6			|
+		       NETIF_F_GSO_GRE			|
+		       NETIF_F_GSO_UDP_TUNNEL		|
+		       NETIF_F_GSO_GRE_CSUM		|
+		       NETIF_F_GSO_UDP_TUNNEL_CSUM	|
+		       NETIF_F_GSO_PARTIAL		|
+		       NETIF_F_GSO_IPXIP4		|
+		       NETIF_F_GSO_IPXIP6		|
 		       NETIF_F_GSO_UDP_L4;
 
+	netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM |
+					NETIF_F_GSO_GRE_CSUM;
 	/* set features that user can change */
 	netdev->hw_features = dflt_features | csumo_features |
 			      vlano_features | tso_features;
 
+	/* add support for HW_CSUM on packets with MPLS header */
+	netdev->mpls_features =  NETIF_F_HW_CSUM;
+
 	/* enable features */
 	netdev->features |= netdev->hw_features;
 	/* encap and VLAN devices inherit default, csumo and tso features */
@@ -5157,6 +5171,70 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	pf->tx_timeout_recovery_level++;
 }
 
+/**
+ * ice_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
+ * @netdev: This physical port's netdev
+ * @ti: Tunnel endpoint information
+ */
+static void
+ice_udp_tunnel_add(struct net_device *netdev, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	enum ice_tunnel_type tnl_type;
+	u16 port = ntohs(ti->port);
+	enum ice_status status;
+
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		tnl_type = TNL_VXLAN;
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		tnl_type = TNL_GENEVE;
+		break;
+	default:
+		netdev_err(netdev, "Unknown tunnel type\n");
+		return;
+	}
+
+	status = ice_create_tunnel(&pf->hw, tnl_type, port);
+	if (status == ICE_ERR_OUT_OF_RANGE)
+		netdev_info(netdev, "Max tunneled UDP ports reached, port %d not added\n",
+			    port);
+	else if (status)
+		netdev_err(netdev, "Error adding UDP tunnel - %d\n",
+			   status);
+}
+
+/**
+ * ice_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
+ * @netdev: This physical port's netdev
+ * @ti: Tunnel endpoint information
+ */
+static void
+ice_udp_tunnel_del(struct net_device *netdev, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	u16 port = ntohs(ti->port);
+	enum ice_status status;
+	bool retval;
+
+	retval = ice_tunnel_port_in_use(&pf->hw, port, NULL);
+	if (!retval) {
+		netdev_info(netdev, "port %d not found in UDP tunnels list\n",
+			    port);
+		return;
+	}
+
+	status = ice_destroy_tunnel(&pf->hw, port, false);
+	if (status)
+		netdev_err(netdev, "error deleting port %d from UDP tunnels list\n",
+			   port);
+}
+
 /**
  * ice_open - Called when a network interface becomes active
  * @netdev: network interface device structure
@@ -5213,6 +5291,10 @@ int ice_open(struct net_device *netdev)
 	if (err)
 		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
+
+	/* Update existing tunnels information */
+	udp_tunnel_get_rx_info(netdev);
+
 	return err;
 }
 
@@ -5263,21 +5345,21 @@ ice_features_check(struct sk_buff *skb,
 		features &= ~NETIF_F_GSO_MASK;
 
 	len = skb_network_header(skb) - skb->data;
-	if (len & ~(ICE_TXD_MACLEN_MAX))
+	if (len > ICE_TXD_MACLEN_MAX || len & 0x1)
 		goto out_rm_features;
 
 	len = skb_transport_header(skb) - skb_network_header(skb);
-	if (len & ~(ICE_TXD_IPLEN_MAX))
+	if (len > ICE_TXD_IPLEN_MAX || len & 0x1)
 		goto out_rm_features;
 
 	if (skb->encapsulation) {
 		len = skb_inner_network_header(skb) - skb_transport_header(skb);
-		if (len & ~(ICE_TXD_L4LEN_MAX))
+		if (len > ICE_TXD_L4LEN_MAX || len & 0x1)
 			goto out_rm_features;
 
 		len = skb_inner_transport_header(skb) -
 		      skb_inner_network_header(skb);
-		if (len & ~(ICE_TXD_IPLEN_MAX))
+		if (len > ICE_TXD_IPLEN_MAX || len & 0x1)
 			goto out_rm_features;
 	}
 
@@ -5326,4 +5408,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_bpf = ice_xdp,
 	.ndo_xdp_xmit = ice_xdp_xmit,
 	.ndo_xsk_wakeup = ice_xsk_wakeup,
+	.ndo_udp_tunnel_add = ice_udp_tunnel_add,
+	.ndo_udp_tunnel_del = ice_udp_tunnel_del,
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index 71647566964e..678db6bf7f57 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -18,6 +18,7 @@ enum ice_prot_id {
 	ICE_PROT_IPV6_IL	= 41,
 	ICE_PROT_TCP_IL		= 49,
 	ICE_PROT_UDP_IL_OR_S	= 53,
+	ICE_PROT_GRE_OF		= 64,
 	ICE_PROT_SCTP_IL	= 96,
 	ICE_PROT_META_ID	= 255, /* when offset == metadata */
 	ICE_PROT_INVALID	= 255  /* when offset == ICE_FV_OFFSET_INVAL */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 69b21b436f9a..4ba1fc8261d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1807,12 +1807,94 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	l2_len = ip.hdr - skb->data;
 	offset = (l2_len / 2) << ICE_TX_DESC_LEN_MACLEN_S;
 
-	if (skb->encapsulation)
-		return -1;
+	protocol = vlan_get_protocol(skb);
+
+	if (protocol == htons(ETH_P_IP))
+		first->tx_flags |= ICE_TX_FLAGS_IPV4;
+	else if (protocol == htons(ETH_P_IPV6))
+		first->tx_flags |= ICE_TX_FLAGS_IPV6;
+
+	if (skb->encapsulation) {
+		bool gso_ena = false;
+		u32 tunnel = 0;
+
+		/* define outer network header type */
+		if (first->tx_flags & ICE_TX_FLAGS_IPV4) {
+			tunnel |= (first->tx_flags & ICE_TX_FLAGS_TSO) ?
+				  ICE_TX_CTX_EIPT_IPV4 :
+				  ICE_TX_CTX_EIPT_IPV4_NO_CSUM;
+			l4_proto = ip.v4->protocol;
+		} else if (first->tx_flags & ICE_TX_FLAGS_IPV6) {
+			tunnel |= ICE_TX_CTX_EIPT_IPV6;
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		}
+
+		/* define outer transport */
+		switch (l4_proto) {
+		case IPPROTO_UDP:
+			tunnel |= ICE_TXD_CTX_UDP_TUNNELING;
+			first->tx_flags |= ICE_TX_FLAGS_TUNNEL;
+			break;
+		case IPPROTO_GRE:
+			tunnel |= ICE_TXD_CTX_GRE_TUNNELING;
+			first->tx_flags |= ICE_TX_FLAGS_TUNNEL;
+			break;
+		case IPPROTO_IPIP:
+		case IPPROTO_IPV6:
+			first->tx_flags |= ICE_TX_FLAGS_TUNNEL;
+			l4.hdr = skb_inner_network_header(skb);
+			break;
+		default:
+			if (first->tx_flags & ICE_TX_FLAGS_TSO)
+				return -1;
+
+			skb_checksum_help(skb);
+			return 0;
+		}
+
+		/* compute outer L3 header size */
+		tunnel |= ((l4.hdr - ip.hdr) / 4) <<
+			  ICE_TXD_CTX_QW0_EIPLEN_S;
+
+		/* switch IP header pointer from outer to inner header */
+		ip.hdr = skb_inner_network_header(skb);
+
+		/* compute tunnel header size */
+		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
+			   ICE_TXD_CTX_QW0_NATLEN_S;
+
+		gso_ena = skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL;
+		/* indicate if we need to offload outer UDP header */
+		if ((first->tx_flags & ICE_TX_FLAGS_TSO) && !gso_ena &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= ICE_TXD_CTX_QW0_L4T_CS_M;
+
+		/* record tunnel offload values */
+		off->cd_tunnel_params |= tunnel;
+
+		/* set DTYP=1 to indicate that it's an Tx context descriptor
+		 * in IPsec tunnel mode with Tx offloads in Quad word 1
+		 */
+		off->cd_qw1 |= (u64)ICE_TX_DESC_DTYPE_CTX;
+
+		/* switch L4 header pointer from outer to inner */
+		l4.hdr = skb_inner_transport_header(skb);
+		l4_proto = 0;
+
+		/* reset type as we transition from outer to inner headers */
+		first->tx_flags &= ~(ICE_TX_FLAGS_IPV4 | ICE_TX_FLAGS_IPV6);
+		if (ip.v4->version == 4)
+			first->tx_flags |= ICE_TX_FLAGS_IPV4;
+		if (ip.v6->version == 6)
+			first->tx_flags |= ICE_TX_FLAGS_IPV6;
+	}
 
 	/* Enable IP checksum offloads */
-	protocol = vlan_get_protocol(skb);
-	if (protocol == htons(ETH_P_IP)) {
+	if (first->tx_flags & ICE_TX_FLAGS_IPV4) {
 		l4_proto = ip.v4->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
@@ -1822,7 +1904,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		else
 			cmd |= ICE_TX_DESC_CMD_IIPT_IPV4;
 
-	} else if (protocol == htons(ETH_P_IPV6)) {
+	} else if (first->tx_flags & ICE_TX_FLAGS_IPV6) {
 		cmd |= ICE_TX_DESC_CMD_IIPT_IPV6;
 		exthdr = ip.hdr + sizeof(*ip.v6);
 		l4_proto = ip.v6->nexthdr;
@@ -1969,6 +2051,40 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		ip.v6->payload_len = 0;
 	}
 
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
+					 SKB_GSO_GRE_CSUM |
+					 SKB_GSO_IPXIP4 |
+					 SKB_GSO_IPXIP6 |
+					 SKB_GSO_UDP_TUNNEL |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) {
+			l4.udp->len = 0;
+
+			/* determine offset of outer transport header */
+			l4_start = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = skb->len - l4_start;
+			csum_replace_by_diff(&l4.udp->check,
+					     (__force __wsum)htonl(paylen));
+		}
+
+		/* reset pointers to inner headers */
+
+		/* cppcheck-suppress unreadVariable */
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+
+		/* initialize inner IP header fields */
+		if (ip.v4->version == 4) {
+			ip.v4->tot_len = 0;
+			ip.v4->check = 0;
+		} else {
+			ip.v6->payload_len = 0;
+		}
+	}
+
 	/* determine offset of transport header */
 	l4_start = l4.hdr - skb->data;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 7ee00a128663..025dd642cf28 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -113,6 +113,9 @@ static inline int ice_skb_pad(void)
 #define ICE_TX_FLAGS_TSO	BIT(0)
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
 #define ICE_TX_FLAGS_SW_VLAN	BIT(2)
+#define ICE_TX_FLAGS_IPV4	BIT(5)
+#define ICE_TX_FLAGS_IPV6	BIT(6)
+#define ICE_TX_FLAGS_TUNNEL	BIT(7)
 #define ICE_TX_FLAGS_VLAN_M	0xffff0000
 #define ICE_TX_FLAGS_VLAN_PR_M	0xe0000000
 #define ICE_TX_FLAGS_VLAN_PR_S	29
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 6da048a6ca7c..1f9c3d24cde7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -84,12 +84,17 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
-	u32 rx_error, rx_status;
+	u16 rx_error, rx_status;
+	u16 rx_stat_err1;
 	bool ipv4, ipv6;
 
 	rx_status = le16_to_cpu(rx_desc->wb.status_error0);
-	rx_error = rx_status;
+	rx_error = rx_status & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
+				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S) |
+				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S) |
+				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S));
 
+	rx_stat_err1 = le16_to_cpu(rx_desc->wb.status_error1);
 	decoded = ice_decode_rx_desc_ptype(ptype);
 
 	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
@@ -125,6 +130,18 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	if (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S))
 		goto checksum_fail;
 
+	/* check for outer UDP checksum error in tunneled packets */
+	if ((rx_stat_err1 & BIT(ICE_RX_FLEX_DESC_STATUS1_NAT_S)) &&
+	    (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S)))
+		goto checksum_fail;
+
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
+	 */
+	if (decoded.tunnel_type >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
+
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
 	switch (decoded.inner_prot) {
 	case ICE_RX_PTYPE_INNER_PROT_TCP:
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 35ea5adbb3e5..c56b2e77a48c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -579,6 +579,10 @@ struct ice_hw {
 	u8 *pkg_copy;
 	u32 pkg_size;
 
+	/* tunneling info */
+	struct mutex tnl_lock;
+	struct ice_tunnel_table tnl;
+
 	/* HW block tables */
 	struct ice_blk_info blk[ICE_BLK_COUNT];
 	struct mutex fl_profs_locks[ICE_BLK_COUNT];	/* lock fltr profiles */
-- 
cgit v1.2.3


From 01b5e89aab498dad5a38d04a71beca2b562d9449 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Thu, 7 May 2020 17:40:59 -0700
Subject: ice: Add VF promiscuous support

Implement promiscuous support for VF VSIs. Behaviour of promiscuous support
is based on VF trust as well as the, introduced, vf-true-promisc flag.

A trusted VF with vf-true-promisc disabled will be the default VSI, which
means that all traffic without a matching destination MAC address in the
device's internal switch will be forwarded to this VF VSI.

A trusted VF with vf-true-promisc enabled will go into "true promiscuous
mode". This amounts to the VF receiving all ingress and egress traffic
that hits the device's internal switch.

An untrusted VF will only receive traffic destined for that VF.

The vf-true-promisc-support flag cannot be toggled while any VF is in
promiscuous mode. This flag should be set prior to loading the iavf driver
or spawning VF(s).

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h             |   1 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c     |  12 ++
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 206 ++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h |   6 +
 4 files changed, 223 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 43349eaa02b2..ce7172901428 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -345,6 +345,7 @@ enum ice_pf_flags {
 	ICE_FLAG_FW_LLDP_AGENT,
 	ICE_FLAG_ETHTOOL_CTXT,		/* set when ethtool holds RTNL lock */
 	ICE_FLAG_LEGACY_RX,
+	ICE_FLAG_VF_TRUE_PROMISC_ENA,
 	ICE_FLAG_MDD_AUTO_RESET_VF,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 593fb37bd59e..66d0bcc51ad9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -157,6 +157,8 @@ struct ice_priv_flag {
 static const struct ice_priv_flag ice_gstrings_priv_flags[] = {
 	ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA),
 	ICE_PRIV_FLAG("fw-lldp-agent", ICE_FLAG_FW_LLDP_AGENT),
+	ICE_PRIV_FLAG("vf-true-promisc-support",
+		      ICE_FLAG_VF_TRUE_PROMISC_ENA),
 	ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF),
 	ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX),
 };
@@ -1308,6 +1310,16 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 		ice_down(vsi);
 		ice_up(vsi);
 	}
+	/* don't allow modification of this flag when a single VF is in
+	 * promiscuous mode because it's not supported
+	 */
+	if (test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, change_flags) &&
+	    ice_is_any_vf_in_promisc(pf)) {
+		dev_err(dev, "Changing vf-true-promisc-support flag while VF(s) are in promiscuous mode not supported\n");
+		/* toggle bit back to previous state */
+		change_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags);
+		ret = -EAGAIN;
+	}
 	clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
 	return ret;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 15191a325918..1389d0d6d3d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -34,6 +34,37 @@ static int ice_check_vf_init(struct ice_pf *pf, struct ice_vf *vf)
 	return 0;
 }
 
+/**
+ * ice_err_to_virt_err - translate errors for VF return code
+ * @ice_err: error return code
+ */
+static enum virtchnl_status_code ice_err_to_virt_err(enum ice_status ice_err)
+{
+	switch (ice_err) {
+	case ICE_SUCCESS:
+		return VIRTCHNL_STATUS_SUCCESS;
+	case ICE_ERR_BAD_PTR:
+	case ICE_ERR_INVAL_SIZE:
+	case ICE_ERR_DEVICE_NOT_SUPPORTED:
+	case ICE_ERR_PARAM:
+	case ICE_ERR_CFG:
+		return VIRTCHNL_STATUS_ERR_PARAM;
+	case ICE_ERR_NO_MEMORY:
+		return VIRTCHNL_STATUS_ERR_NO_MEMORY;
+	case ICE_ERR_NOT_READY:
+	case ICE_ERR_RESET_FAILED:
+	case ICE_ERR_FW_API_VER:
+	case ICE_ERR_AQ_ERROR:
+	case ICE_ERR_AQ_TIMEOUT:
+	case ICE_ERR_AQ_FULL:
+	case ICE_ERR_AQ_NO_WORK:
+	case ICE_ERR_AQ_EMPTY:
+		return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+	default:
+		return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+	}
+}
+
 /**
  * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF
  * @pf: pointer to the PF structure
@@ -2059,6 +2090,173 @@ out:
 	return ret;
 }
 
+/**
+ * ice_is_any_vf_in_promisc - check if any VF(s) are in promiscuous mode
+ * @pf: PF structure for accessing VF(s)
+ *
+ * Return false if no VF(s) are in unicast and/or multicast promiscuous mode,
+ * else return true
+ */
+bool ice_is_any_vf_in_promisc(struct ice_pf *pf)
+{
+	int vf_idx;
+
+	ice_for_each_vf(pf, vf_idx) {
+		struct ice_vf *vf = &pf->vf[vf_idx];
+
+		/* found a VF that has promiscuous mode configured */
+		if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+		    test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states))
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * ice_vc_cfg_promiscuous_mode_msg
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * called from the VF to configure VF VSIs promiscuous mode
+ */
+static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_promisc_info *info =
+	    (struct virtchnl_promisc_info *)msg;
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	bool rm_promisc;
+	int ret = 0;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, info->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	dev = ice_pf_to_dev(pf);
+	if (!test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
+		dev_err(dev, "Unprivileged VF %d is attempting to configure promiscuous mode\n",
+			vf->vf_id);
+		/* Leave v_ret alone, lie to the VF on purpose. */
+		goto error_param;
+	}
+
+	rm_promisc = !(info->flags & FLAG_VF_UNICAST_PROMISC) &&
+		!(info->flags & FLAG_VF_MULTICAST_PROMISC);
+
+	if (vsi->num_vlan || vf->port_vlan_info) {
+		struct ice_vsi *pf_vsi = ice_get_main_vsi(pf);
+		struct net_device *pf_netdev;
+
+		if (!pf_vsi) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+
+		pf_netdev = pf_vsi->netdev;
+
+		ret = ice_set_vf_spoofchk(pf_netdev, vf->vf_id, rm_promisc);
+		if (ret) {
+			dev_err(dev, "Failed to update spoofchk to %s for VF %d VSI %d when setting promiscuous mode\n",
+				rm_promisc ? "ON" : "OFF", vf->vf_id,
+				vsi->vsi_num);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		}
+
+		ret = ice_cfg_vlan_pruning(vsi, true, !rm_promisc);
+		if (ret) {
+			dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n");
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+	}
+
+	if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) {
+		bool set_dflt_vsi = !!(info->flags & FLAG_VF_UNICAST_PROMISC);
+
+		if (set_dflt_vsi && !ice_is_dflt_vsi_in_use(pf->first_sw))
+			/* only attempt to set the default forwarding VSI if
+			 * it's not currently set
+			 */
+			ret = ice_set_dflt_vsi(pf->first_sw, vsi);
+		else if (!set_dflt_vsi &&
+			 ice_is_vsi_dflt_vsi(pf->first_sw, vsi))
+			/* only attempt to free the default forwarding VSI if we
+			 * are the owner
+			 */
+			ret = ice_clear_dflt_vsi(pf->first_sw);
+
+		if (ret) {
+			dev_err(dev, "%sable VF %d as the default VSI failed, error %d\n",
+				set_dflt_vsi ? "en" : "dis", vf->vf_id, ret);
+			v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+			goto error_param;
+		}
+	} else {
+		enum ice_status status;
+		u8 promisc_m;
+
+		if (info->flags & FLAG_VF_UNICAST_PROMISC) {
+			if (vf->port_vlan_info || vsi->num_vlan)
+				promisc_m = ICE_UCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_UCAST_PROMISC_BITS;
+		} else if (info->flags & FLAG_VF_MULTICAST_PROMISC) {
+			if (vf->port_vlan_info || vsi->num_vlan)
+				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_MCAST_PROMISC_BITS;
+		} else {
+			if (vf->port_vlan_info || vsi->num_vlan)
+				promisc_m = ICE_UCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_UCAST_PROMISC_BITS;
+		}
+
+		/* Configure multicast/unicast with or without VLAN promiscuous
+		 * mode
+		 */
+		status = ice_vf_set_vsi_promisc(vf, vsi, promisc_m, rm_promisc);
+		if (status) {
+			dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed, error: %d\n",
+				rm_promisc ? "dis" : "en", vf->vf_id, status);
+			v_ret = ice_err_to_virt_err(status);
+			goto error_param;
+		} else {
+			dev_dbg(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d succeeded\n",
+				rm_promisc ? "dis" : "en", vf->vf_id);
+		}
+	}
+
+	if (info->flags & FLAG_VF_MULTICAST_PROMISC)
+		set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
+	else
+		clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
+
+	if (info->flags & FLAG_VF_UNICAST_PROMISC)
+		set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
+	else
+		clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
+
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
+				     v_ret, NULL, 0);
+}
+
 /**
  * ice_vc_get_stats_msg
  * @vf: pointer to the VF info
@@ -2992,8 +3190,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 		goto error_param;
 	}
 
-	if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
-	    test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states))
+	if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+	     test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) &&
+	    test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags))
 		vlan_promisc = true;
 
 	if (add_v) {
@@ -3317,6 +3516,9 @@ error_handler:
 	case VIRTCHNL_OP_GET_STATS:
 		err = ice_vc_get_stats_msg(vf, msg);
 		break;
+	case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
+		err = ice_vc_cfg_promiscuous_mode_msg(vf, msg);
+		break;
 	case VIRTCHNL_OP_ADD_VLAN:
 		err = ice_vc_add_vlan_msg(vf, msg);
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 3f9464269bd2..f7fd1188efa4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -128,6 +128,7 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf);
 int
 ice_get_vf_stats(struct net_device *netdev, int vf_id,
 		 struct ifla_vf_stats *vf_stats);
+bool ice_is_any_vf_in_promisc(struct ice_pf *pf);
 void
 ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event);
 void ice_print_vfs_mdd_events(struct ice_pf *pf);
@@ -219,5 +220,10 @@ ice_get_vf_stats(struct net_device __always_unused *netdev,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline bool ice_is_any_vf_in_promisc(struct ice_pf __always_unused *pf)
+{
+	return false;
+}
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_VIRTCHNL_PF_H_ */
-- 
cgit v1.2.3


From 610ed0e93e7dd107afc2398d54de6b6fe9513f8d Mon Sep 17 00:00:00 2001
From: Avinash JD <avinash.dayanand@intel.com>
Date: Thu, 7 May 2020 17:41:00 -0700
Subject: ice: Don't reset and rebuild for Tx timeout on PFC enabled queue

When there's a Tx timeout for a queue which belongs to a PFC enabled TC,
then it's not because the queue is hung but because PFC is in action.

In PFC, peer sends a pause frame for a specified period of time when its
buffer threshold is exceeded (due to congestion). Netdev on the other
hand checks if ACK is received within a specified time for a TX packet, if
not, it'll invoke the tx_timeout routine.

Signed-off-by: Avinash JD <avinash.dayanand@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c    | 58 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_dcb_lib.h    | 23 ++++++++++
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h |  1 +
 drivers/net/ethernet/intel/ice/ice_main.c       | 10 +++++
 drivers/net/ethernet/intel/ice/ice_type.h       |  2 +
 5 files changed, 94 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 7bea09363b42..448b7d2fb808 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -62,6 +62,64 @@ u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg)
 	return ena_tc;
 }
 
+/**
+ * ice_is_pfc_causing_hung_q
+ * @pf: pointer to PF structure
+ * @txqueue: Tx queue which is supposedly hung queue
+ *
+ * find if PFC is causing the hung queue, if yes return true else false
+ */
+bool ice_is_pfc_causing_hung_q(struct ice_pf *pf, unsigned int txqueue)
+{
+	u8 num_tcs = 0, i, tc, up_mapped_tc, up_in_tc = 0;
+	u64 ref_prio_xoff[ICE_MAX_UP];
+	struct ice_vsi *vsi;
+	u32 up2tc;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return false;
+
+	ice_for_each_traffic_class(i)
+		if (vsi->tc_cfg.ena_tc & BIT(i))
+			num_tcs++;
+
+	/* first find out the TC to which the hung queue belongs to */
+	for (tc = 0; tc < num_tcs - 1; tc++)
+		if (ice_find_q_in_range(vsi->tc_cfg.tc_info[tc].qoffset,
+					vsi->tc_cfg.tc_info[tc + 1].qoffset,
+					txqueue))
+			break;
+
+	/* Build a bit map of all UPs associated to the suspect hung queue TC,
+	 * so that we check for its counter increment.
+	 */
+	up2tc = rd32(&pf->hw, PRTDCB_TUP2TC);
+	for (i = 0; i < ICE_MAX_UP; i++) {
+		up_mapped_tc = (up2tc >> (i * 3)) & 0x7;
+		if (up_mapped_tc == tc)
+			up_in_tc |= BIT(i);
+	}
+
+	/* Now that we figured out that hung queue is PFC enabled, still the
+	 * Tx timeout can be legitimate. So to make sure Tx timeout is
+	 * absolutely caused by PFC storm, check if the counters are
+	 * incrementing.
+	 */
+	for (i = 0; i < ICE_MAX_UP; i++)
+		if (up_in_tc & BIT(i))
+			ref_prio_xoff[i] = pf->stats.priority_xoff_rx[i];
+
+	ice_update_dcb_stats(pf);
+
+	for (i = 0; i < ICE_MAX_UP; i++)
+		if (up_in_tc & BIT(i))
+			if (pf->stats.priority_xoff_rx[i] > ref_prio_xoff[i])
+				return true;
+
+	return false;
+}
+
 /**
  * ice_dcb_get_mode - gets the DCB mode
  * @port_info: pointer to port info structure
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 37680e815b02..7c42324494d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -17,6 +17,8 @@
 void ice_dcb_rebuild(struct ice_pf *pf);
 u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg);
 u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg);
+void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi);
+bool ice_is_pfc_causing_hung_q(struct ice_pf *pf, unsigned int txqueue);
 u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index);
 int
 ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked);
@@ -32,6 +34,20 @@ void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 				    struct ice_rq_event_info *event);
 void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
+
+/**
+ * ice_find_q_in_range
+ * @low: start of queue range for a TC i.e. offset of TC
+ * @high: start of queue for next TC
+ * @tx_q: hung_queue/tx_queue
+ *
+ * finds if queue 'tx_q' falls between the two offsets of any given TC
+ */
+static inline bool ice_find_q_in_range(u16 low, u16 high, unsigned int tx_q)
+{
+	return (tx_q >= low) && (tx_q < high);
+}
+
 static inline void
 ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring)
 {
@@ -79,6 +95,13 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring,
 	return 0;
 }
 
+static inline bool
+ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf,
+			  unsigned int __always_unused txqueue)
+{
+	return false;
+}
+
 #define ice_update_dcb_stats(pf) do {} while (0)
 #define ice_pf_dcb_recfg(pf) do {} while (0)
 #define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 1d37a9f02c1c..bc48eda67c81 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -58,6 +58,7 @@
 #define PRTDCB_GENS				0x00083020
 #define PRTDCB_GENS_DCBX_STATUS_S		0
 #define PRTDCB_GENS_DCBX_STATUS_M		ICE_M(0x7, 0)
+#define PRTDCB_TUP2TC				0x001D26C0 /* Reset Source: CORER */
 #define GL_PREEXT_L2_PMASK0(_i)			(0x0020F0FC + ((_i) * 4))
 #define GL_PREEXT_L2_PMASK1(_i)			(0x0020F108 + ((_i) * 4))
 #define GLFLXP_RXDID_FLX_WRD_0(_i)		(0x0045c800 + ((_i) * 4))
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 44ff4fe45a56..8c792ecc6550 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5114,6 +5114,16 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 	pf->tx_timeout_count++;
 
+	/* Check if PFC is enabled for the TC to which the queue belongs
+	 * to. If yes then Tx timeout is not caused by a hung queue, no
+	 * need to reset and rebuild
+	 */
+	if (ice_is_pfc_causing_hung_q(pf, txqueue)) {
+		dev_info(ice_pf_to_dev(pf), "Fake Tx hang detected on queue %u, timeout caused by PFC storm\n",
+			 txqueue);
+		return;
+	}
+
 	/* now that we have an index, find the tx_ring struct */
 	for (i = 0; i < vsi->num_txq; i++)
 		if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index c56b2e77a48c..4f5345a7c15d 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -607,6 +607,8 @@ struct ice_eth_stats {
 	u64 tx_errors;			/* tepc */
 };
 
+#define ICE_MAX_UP	8
+
 /* Statistics collected by the MAC */
 struct ice_hw_port_stats {
 	/* eth stats collected by the port */
-- 
cgit v1.2.3


From 891540024bb959c3ce8b71b851ba24cd3ad9423f Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Thu, 7 May 2020 17:41:01 -0700
Subject: ice: Fix check for contiguous TCs

The current implementation for contiguous TC check
is assuming that the UPs will be mapped to TCs in
a linear progressing fashion.  This is obviously
not always true.

Change the check to allow for various UP2TC mapping
configurations.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 448b7d2fb808..3c7f604c0c49 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -584,16 +584,21 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked)
  */
 static bool ice_dcb_tc_contig(u8 *prio_table)
 {
-	u8 max_tc = 0;
+	bool found_empty = false;
+	u8 used_tc = 0;
 	int i;
 
-	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) {
-		u8 cur_tc = prio_table[i];
+	/* Create a bitmap of used TCs */
+	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
+		used_tc |= BIT(prio_table[i]);
 
-		if (cur_tc > max_tc)
-			return false;
-		else if (cur_tc == max_tc)
-			max_tc++;
+	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) {
+		if (used_tc & BIT(i)) {
+			if (found_empty)
+				return false;
+		} else {
+			found_empty = true;
+		}
 	}
 
 	return true;
-- 
cgit v1.2.3


From 46a316500e060abd4c5745f45ffdc28d426dc99b Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Thu, 7 May 2020 17:41:02 -0700
Subject: ice: only drop link once when setting pauseparams

Currently, the ice driver is setting a PHY configuration,
which causes a link drop, and then additionally it calls
for a nway_reset, which restarts auto-negotiation on the
link, which also causes a link drop.  These two link
events in such close timing is causing the FW to not be
able to generate a link interrupt for the driver to
respond to.

Remove the unnecessary auto-negotiation restart from the
set pauseparams flow.  Also remove error path that
would have performed an ice_down/ice_up as that is
also unnecessary.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 66d0bcc51ad9..db547c0c7c6f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2977,18 +2977,6 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 		err = -EAGAIN;
 	}
 
-	if (!test_bit(__ICE_DOWN, pf->state)) {
-		/* Give it a little more time to try to come back. If still
-		 * down, restart autoneg link or reinitialize the interface.
-		 */
-		msleep(75);
-		if (!test_bit(__ICE_DOWN, pf->state))
-			return ice_nway_reset(netdev);
-
-		ice_down(vsi);
-		ice_up(vsi);
-	}
-
 	return err;
 }
 
-- 
cgit v1.2.3


From de75135b5c04c96dc8bbb005511b7a79d952d7eb Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Thu, 7 May 2020 17:41:03 -0700
Subject: ice: Fix probe/open race condition

As soon as the driver registers the PF netdev, userspace utilities
like NetworkManager try to bring up the associated interface. When
this happens, the driver may not have finished initializing fully,
resulting in a bunch of errors in the interface up flow.

The driver already has a mechanism to indicate if it's not up yet;
by setting the __ICE_DOWN bit in pf->state, but this bit gets
cleared too early in the current flow. So clear this bit only when
the driver is fully up. Also check for the same bit in the ice_open
flow, and return -EBUSY if the bit is set.

Also in ice_open, replace references of vsi->back with a local
variable.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 8c792ecc6550..de81d9049b97 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2137,10 +2137,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	}
 	ret = IRQ_HANDLED;
 
-	if (!test_bit(__ICE_DOWN, pf->state)) {
-		ice_service_task_schedule(pf);
-		ice_irq_dynamic_ena(hw, NULL, NULL);
-	}
+	ice_service_task_schedule(pf);
+	ice_irq_dynamic_ena(hw, NULL, NULL);
 
 	return ret;
 }
@@ -3312,9 +3310,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		goto err_init_interrupt_unroll;
 	}
 
-	/* Driver is mostly up */
-	clear_bit(__ICE_DOWN, pf->state);
-
 	/* In case of MSIX we are going to setup the misc vector right here
 	 * to handle admin queue events etc. In case of legacy and MSI
 	 * the misc functionality and queue processing is combined in
@@ -3370,9 +3365,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	ice_verify_cacheline_size(pf);
 
-	/* If no DDP driven features have to be setup, return here */
+	/* If no DDP driven features have to be setup, we are done with probe */
 	if (ice_is_safe_mode(pf))
-		return 0;
+		goto probe_done;
 
 	/* initialize DDP driven features */
 
@@ -3387,6 +3382,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	/* print PCI link speed and width */
 	pcie_print_link_status(pf->pdev);
 
+probe_done:
+	/* ready to go, so clear down state bit */
+	clear_bit(__ICE_DOWN, pf->state);
 	return 0;
 
 err_alloc_sw_unroll:
@@ -5261,14 +5259,20 @@ int ice_open(struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
 	struct ice_port_info *pi;
 	int err;
 
-	if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) {
+	if (test_bit(__ICE_NEEDS_RESTART, pf->state)) {
 		netdev_err(netdev, "driver needs to be unloaded and reloaded\n");
 		return -EIO;
 	}
 
+	if (test_bit(__ICE_DOWN, pf->state)) {
+		netdev_err(netdev, "device is not ready yet\n");
+		return -EBUSY;
+	}
+
 	netif_carrier_off(netdev);
 
 	pi = vsi->port_info;
-- 
cgit v1.2.3


From 0fee35774d8f2277cfb101dd1d9d0d5e39015b93 Mon Sep 17 00:00:00 2001
From: Lihong Yang <lihong.yang@intel.com>
Date: Thu, 7 May 2020 17:41:04 -0700
Subject: ice: Provide more meaningful error message

When printing the ice status or AQ error codes, instead of printing out the
numerical value, provide the description of the error code. This provides
more info about the issue than a number.

Signed-off-by: Lihong Yang <lihong.yang@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h             |   2 +
 drivers/net/ethernet/intel/ice/ice_base.c        |   8 +-
 drivers/net/ethernet/intel/ice/ice_ethtool.c     |  42 +++---
 drivers/net/ethernet/intel/ice/ice_lib.c         | 103 ++++++-------
 drivers/net/ethernet/intel/ice/ice_main.c        | 177 +++++++++++++++++++----
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c |  28 ++--
 6 files changed, 247 insertions(+), 113 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index ce7172901428..be90337cabb8 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -528,6 +528,8 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
+const char *ice_stat_str(enum ice_status stat_err);
+const char *ice_aq_str(enum ice_aq_err aq_err);
 int ice_open(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index a19cd6f5436b..ee1c698ff056 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -662,8 +662,8 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring,
 	status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle,
 				 1, qg_buf, buf_len, NULL);
 	if (status) {
-		dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %d\n",
-			status);
+		dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %s\n",
+			ice_stat_str(status));
 		return -ENODEV;
 	}
 
@@ -832,8 +832,8 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 	} else if (status == ICE_ERR_DOES_NOT_EXIST) {
 		dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n");
 	} else if (status) {
-		dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %d\n",
-			status);
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %s\n",
+			ice_stat_str(status));
 		return -ENODEV;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index db547c0c7c6f..b814bc54f752 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -275,8 +275,9 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 
 	status = ice_acquire_nvm(hw, ICE_RES_READ);
 	if (status) {
-		dev_err(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
-			status, hw->adminq.sq_last_status);
+		dev_err(dev, "ice_acquire_nvm failed, err %s aq_err %s\n",
+			ice_stat_str(status),
+			ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto out;
 	}
@@ -284,8 +285,9 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	status = ice_read_flat_nvm(hw, eeprom->offset, &eeprom->len, buf,
 				   false);
 	if (status) {
-		dev_err(dev, "ice_read_flat_nvm failed, err %d aq_err %d\n",
-			status, hw->adminq.sq_last_status);
+		dev_err(dev, "ice_read_flat_nvm failed, err %s aq_err %s\n",
+			ice_stat_str(status),
+			ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto release;
 	}
@@ -334,7 +336,8 @@ static u64 ice_link_test(struct net_device *netdev)
 	netdev_info(netdev, "link test\n");
 	status = ice_get_link_status(np->vsi->port_info, &link_up);
 	if (status) {
-		netdev_err(netdev, "link query error, status = %d\n", status);
+		netdev_err(netdev, "link query error, status = %s\n",
+			   ice_stat_str(status));
 		return 1;
 	}
 
@@ -1160,8 +1163,9 @@ static int ice_nway_reset(struct net_device *netdev)
 		status = ice_aq_set_link_restart_an(pi, false, NULL);
 
 	if (status) {
-		netdev_info(netdev, "link restart failed, err %d aq_err %d\n",
-			    status, pi->hw->adminq.sq_last_status);
+		netdev_info(netdev, "link restart failed, err %s aq_err %s\n",
+			    ice_stat_str(status),
+			    ice_aq_str(pi->hw->adminq.sq_last_status));
 		return -EIO;
 	}
 
@@ -2462,8 +2466,8 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 
 	status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs);
 	if (status) {
-		dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n",
-			vsi->vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 		return -EINVAL;
 	}
 
@@ -2964,16 +2968,19 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	status = ice_set_fc(pi, &aq_failures, link_up);
 
 	if (aq_failures & ICE_SET_FC_AQ_FAIL_GET) {
-		netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %d aq_err %d\n",
-			    status, hw->adminq.sq_last_status);
+		netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %s aq_err %s\n",
+			    ice_stat_str(status),
+			    ice_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	} else if (aq_failures & ICE_SET_FC_AQ_FAIL_SET) {
-		netdev_info(netdev, "Set fc failed on the set_phy_config call with err %d aq_err %d\n",
-			    status, hw->adminq.sq_last_status);
+		netdev_info(netdev, "Set fc failed on the set_phy_config call with err %s aq_err %s\n",
+			    ice_stat_str(status),
+			    ice_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	} else if (aq_failures & ICE_SET_FC_AQ_FAIL_UPDATE) {
-		netdev_info(netdev, "Set fc failed on the get_link_info call with err %d aq_err %d\n",
-			    status, hw->adminq.sq_last_status);
+		netdev_info(netdev, "Set fc failed on the get_link_info call with err %s aq_err %s\n",
+			    ice_stat_str(status),
+			    ice_aq_str(hw->adminq.sq_last_status));
 		err = -EAGAIN;
 	}
 
@@ -3227,8 +3234,9 @@ static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size)
 	status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type, lut,
 				    vsi->rss_table_size);
 	if (status) {
-		dev_err(dev, "Cannot set RSS lut, err %d aq_err %d\n",
-			status, hw->adminq.rq_last_status);
+		dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n",
+			ice_stat_str(status),
+			ice_aq_str(hw->adminq.rq_last_status));
 		err = -EIO;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 2f256bf45efc..bf4c538c94bb 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -248,8 +248,8 @@ void ice_vsi_delete(struct ice_vsi *vsi)
 
 	status = ice_free_vsi(&pf->hw, vsi->idx, ctxt, false, NULL);
 	if (status)
-		dev_err(ice_pf_to_dev(pf), "Failed to delete VSI %i in FW - error: %d\n",
-			vsi->vsi_num, status);
+		dev_err(ice_pf_to_dev(pf), "Failed to delete VSI %i in FW - error: %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 
 	kfree(ctxt);
 }
@@ -521,8 +521,8 @@ static void ice_vsi_clean_rss_flow_fld(struct ice_vsi *vsi)
 
 	status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx);
 	if (status)
-		dev_dbg(ice_pf_to_dev(pf), "ice_rem_vsi_rss_cfg failed for vsi = %d, error = %d\n",
-			vsi->vsi_num, status);
+		dev_dbg(ice_pf_to_dev(pf), "ice_rem_vsi_rss_cfg failed for vsi = %d, error = %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 }
 
 /**
@@ -1193,7 +1193,8 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
 				    vsi->rss_table_size);
 
 	if (status) {
-		dev_err(dev, "set_rss_lut failed, error %d\n", status);
+		dev_err(dev, "set_rss_lut failed, error %s\n",
+			ice_stat_str(status));
 		err = -EIO;
 		goto ice_vsi_cfg_rss_exit;
 	}
@@ -1215,7 +1216,8 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
 	status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key);
 
 	if (status) {
-		dev_err(dev, "set_rss_key failed, error %d\n", status);
+		dev_err(dev, "set_rss_key failed, error %s\n",
+			ice_stat_str(status));
 		err = -EIO;
 	}
 
@@ -1248,8 +1250,8 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
 
 	status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA);
 	if (status)
-		dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n",
-			vsi->vsi_num, status);
+		dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 }
 
 /**
@@ -1281,57 +1283,57 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
 				 ICE_FLOW_SEG_HDR_IPV4);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for IPv6 with input set IPv6 src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
 				 ICE_FLOW_SEG_HDR_IPV6);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4,
 				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4,
 				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for sctp4 with input set IP src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
 				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6,
 				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6,
 				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 
 	/* configure RSS for sctp6 with input set IPv6 src/dst */
 	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
 				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6);
 	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %s\n",
+			vsi_num, ice_stat_str(status));
 }
 
 /**
@@ -1509,11 +1511,11 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
 	if (!status) {
 		vsi->num_vlan--;
 	} else if (status == ICE_ERR_DOES_NOT_EXIST) {
-		dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n",
-			vid, vsi->vsi_num, status);
+		dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %s\n",
+			vid, vsi->vsi_num, ice_stat_str(status));
 	} else {
-		dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n",
-			vid, vsi->vsi_num, status);
+		dev_err(dev, "Error removing VLAN %d on vsi %i error: %s\n",
+			vid, vsi->vsi_num, ice_stat_str(status));
 		err = -EIO;
 	}
 
@@ -1737,8 +1739,9 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %d\n",
-			status, hw->adminq.sq_last_status);
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %s aq_err %s\n",
+			ice_stat_str(status),
+			ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto out;
 	}
@@ -1783,8 +1786,9 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
-			ena, status, hw->adminq.sq_last_status);
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %s aq_err %s\n",
+			ena, ice_stat_str(status),
+			ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto out;
 	}
@@ -1922,9 +1926,10 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc)
 
 	status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n",
-			   ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status,
-			   pf->hw.adminq.sq_last_status);
+		netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %s, aq_err = %s\n",
+			   ena ? "En" : "Dis", vsi->idx, vsi->vsi_num,
+			   ice_stat_str(status),
+			   ice_aq_str(pf->hw.adminq.sq_last_status));
 		goto err_out;
 	}
 
@@ -2025,8 +2030,8 @@ ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule)
 		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
 
 	if (status)
-		dev_err(dev, "Failure Adding or Removing Ethertype on VSI %i error: %d\n",
-			vsi->vsi_num, status);
+		dev_err(dev, "Failure Adding or Removing Ethertype on VSI %i error: %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 
 	ice_free_fltr_list(dev, &tmp_add_list);
 }
@@ -2073,9 +2078,9 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
 
 	if (status)
-		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n",
+		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
 			create ? "adding" : "removing", tx ? "TX" : "RX",
-			vsi->vsi_num, status);
+			vsi->vsi_num, ice_stat_str(status));
 
 	ice_free_fltr_list(dev, &tmp_add_list);
 }
@@ -2223,8 +2228,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 				 max_txqs);
 	if (status) {
-		dev_err(dev, "VSI %d failed lan queue config, error %d\n",
-			vsi->vsi_num, status);
+		dev_err(dev, "VSI %d failed lan queue config, error %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 		goto unroll_vector_base;
 	}
 
@@ -2814,8 +2819,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 				 max_txqs);
 	if (status) {
-		dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n",
-			vsi->vsi_num, status);
+		dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 		if (init_vsi) {
 			ret = -EIO;
 			goto err_vectors;
@@ -2924,8 +2929,8 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 				 max_txqs);
 
 	if (status) {
-		dev_err(dev, "VSI %d failed TC config, error %d\n",
-			vsi->vsi_num, status);
+		dev_err(dev, "VSI %d failed TC config, error %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 		ret = -EIO;
 		goto out;
 	}
@@ -3079,8 +3084,8 @@ int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi)
 
 	status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX);
 	if (status) {
-		dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %d\n",
-			vsi->vsi_num, status);
+		dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %s\n",
+			vsi->vsi_num, ice_stat_str(status));
 		return -EIO;
 	}
 
@@ -3118,8 +3123,8 @@ int ice_clear_dflt_vsi(struct ice_sw *sw)
 	status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false,
 				  ICE_FLTR_RX);
 	if (status) {
-		dev_err(dev, "Failed to clear the default forwarding VSI %d, error %d\n",
-			dflt_vsi->vsi_num, status);
+		dev_err(dev, "Failed to clear the default forwarding VSI %d, error %s\n",
+			dflt_vsi->vsi_num, ice_stat_str(status));
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index de81d9049b97..c4dda1fa5853 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -163,8 +163,8 @@ unregister:
 	 * had an error
 	 */
 	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
-		dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %d. Unregistering device\n",
-			status);
+		dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %s. Unregistering device\n",
+			ice_stat_str(status));
 		unregister_netdev(vsi->netdev);
 		free_netdev(vsi->netdev);
 		vsi->netdev = NULL;
@@ -1017,8 +1017,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		if (ret == ICE_ERR_AQ_NO_WORK)
 			break;
 		if (ret) {
-			dev_err(dev, "%s Receive Queue event error %d\n", qtype,
-				ret);
+			dev_err(dev, "%s Receive Queue event error %s\n", qtype,
+				ice_stat_str(ret));
 			break;
 		}
 
@@ -1809,8 +1809,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 				 max_txqs);
 	if (status) {
-		dev_err(dev, "Failed VSI LAN queue config for XDP, error:%d\n",
-			status);
+		dev_err(dev, "Failed VSI LAN queue config for XDP, error: %s\n",
+			ice_stat_str(status));
 		goto clear_xdp_rings;
 	}
 	ice_vsi_assign_bpf_prog(vsi, prog);
@@ -3752,8 +3752,8 @@ err_update_filters:
 	flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
 	status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
 	if (status) {
-		netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %d\n",
-			   mac, status);
+		netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %s\n",
+			   mac, ice_stat_str(status));
 	}
 	return 0;
 }
@@ -3817,8 +3817,8 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
 		status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc,
 					  q_handle, ICE_MAX_BW, maxrate * 1000);
 	if (status) {
-		netdev_err(netdev, "Unable to set Tx max rate, error %d\n",
-			   status);
+		netdev_err(netdev, "Unable to set Tx max rate, error %s\n",
+			   ice_stat_str(status));
 		return -EIO;
 	}
 
@@ -4616,8 +4616,9 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 		/* replay filters for the VSI */
 		status = ice_replay_vsi(&pf->hw, vsi->idx);
 		if (status) {
-			dev_err(dev, "replay VSI failed, status %d, VSI index %d, type %s\n",
-				status, vsi->idx, ice_vsi_type_str(type));
+			dev_err(dev, "replay VSI failed, status %s, VSI index %d, type %s\n",
+				ice_stat_str(status), vsi->idx,
+				ice_vsi_type_str(type));
 			return -EIO;
 		}
 
@@ -4686,7 +4687,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ret = ice_init_all_ctrlq(hw);
 	if (ret) {
-		dev_err(dev, "control queues init failed %d\n", ret);
+		dev_err(dev, "control queues init failed %s\n",
+			ice_stat_str(ret));
 		goto err_init_ctrlq;
 	}
 
@@ -4702,7 +4704,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ret = ice_clear_pf_cfg(hw);
 	if (ret) {
-		dev_err(dev, "clear PF configuration failed %d\n", ret);
+		dev_err(dev, "clear PF configuration failed %s\n",
+			ice_stat_str(ret));
 		goto err_init_ctrlq;
 	}
 
@@ -4716,7 +4719,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ret = ice_get_caps(hw);
 	if (ret) {
-		dev_err(dev, "ice_get_caps failed %d\n", ret);
+		dev_err(dev, "ice_get_caps failed %s\n", ice_stat_str(ret));
 		goto err_init_ctrlq;
 	}
 
@@ -4758,8 +4761,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	/* tell the firmware we are up */
 	ret = ice_send_version(pf);
 	if (ret) {
-		dev_err(dev, "Rebuild failed due to error sending driver version: %d\n",
-			ret);
+		dev_err(dev, "Rebuild failed due to error sending driver version: %s\n",
+			ice_stat_str(ret));
 		goto err_vsi_rebuild;
 	}
 
@@ -4870,6 +4873,112 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
+/**
+ * ice_aq_str - convert AQ err code to a string
+ * @aq_err: the AQ error code to convert
+ */
+const char *ice_aq_str(enum ice_aq_err aq_err)
+{
+	switch (aq_err) {
+	case ICE_AQ_RC_OK:
+		return "OK";
+	case ICE_AQ_RC_EPERM:
+		return "ICE_AQ_RC_EPERM";
+	case ICE_AQ_RC_ENOENT:
+		return "ICE_AQ_RC_ENOENT";
+	case ICE_AQ_RC_ENOMEM:
+		return "ICE_AQ_RC_ENOMEM";
+	case ICE_AQ_RC_EBUSY:
+		return "ICE_AQ_RC_EBUSY";
+	case ICE_AQ_RC_EEXIST:
+		return "ICE_AQ_RC_EEXIST";
+	case ICE_AQ_RC_EINVAL:
+		return "ICE_AQ_RC_EINVAL";
+	case ICE_AQ_RC_ENOSPC:
+		return "ICE_AQ_RC_ENOSPC";
+	case ICE_AQ_RC_ENOSYS:
+		return "ICE_AQ_RC_ENOSYS";
+	case ICE_AQ_RC_ENOSEC:
+		return "ICE_AQ_RC_ENOSEC";
+	case ICE_AQ_RC_EBADSIG:
+		return "ICE_AQ_RC_EBADSIG";
+	case ICE_AQ_RC_ESVN:
+		return "ICE_AQ_RC_ESVN";
+	case ICE_AQ_RC_EBADMAN:
+		return "ICE_AQ_RC_EBADMAN";
+	case ICE_AQ_RC_EBADBUF:
+		return "ICE_AQ_RC_EBADBUF";
+	}
+
+	return "ICE_AQ_RC_UNKNOWN";
+}
+
+/**
+ * ice_stat_str - convert status err code to a string
+ * @stat_err: the status error code to convert
+ */
+const char *ice_stat_str(enum ice_status stat_err)
+{
+	switch (stat_err) {
+	case ICE_SUCCESS:
+		return "OK";
+	case ICE_ERR_PARAM:
+		return "ICE_ERR_PARAM";
+	case ICE_ERR_NOT_IMPL:
+		return "ICE_ERR_NOT_IMPL";
+	case ICE_ERR_NOT_READY:
+		return "ICE_ERR_NOT_READY";
+	case ICE_ERR_NOT_SUPPORTED:
+		return "ICE_ERR_NOT_SUPPORTED";
+	case ICE_ERR_BAD_PTR:
+		return "ICE_ERR_BAD_PTR";
+	case ICE_ERR_INVAL_SIZE:
+		return "ICE_ERR_INVAL_SIZE";
+	case ICE_ERR_DEVICE_NOT_SUPPORTED:
+		return "ICE_ERR_DEVICE_NOT_SUPPORTED";
+	case ICE_ERR_RESET_FAILED:
+		return "ICE_ERR_RESET_FAILED";
+	case ICE_ERR_FW_API_VER:
+		return "ICE_ERR_FW_API_VER";
+	case ICE_ERR_NO_MEMORY:
+		return "ICE_ERR_NO_MEMORY";
+	case ICE_ERR_CFG:
+		return "ICE_ERR_CFG";
+	case ICE_ERR_OUT_OF_RANGE:
+		return "ICE_ERR_OUT_OF_RANGE";
+	case ICE_ERR_ALREADY_EXISTS:
+		return "ICE_ERR_ALREADY_EXISTS";
+	case ICE_ERR_NVM_CHECKSUM:
+		return "ICE_ERR_NVM_CHECKSUM";
+	case ICE_ERR_BUF_TOO_SHORT:
+		return "ICE_ERR_BUF_TOO_SHORT";
+	case ICE_ERR_NVM_BLANK_MODE:
+		return "ICE_ERR_NVM_BLANK_MODE";
+	case ICE_ERR_IN_USE:
+		return "ICE_ERR_IN_USE";
+	case ICE_ERR_MAX_LIMIT:
+		return "ICE_ERR_MAX_LIMIT";
+	case ICE_ERR_RESET_ONGOING:
+		return "ICE_ERR_RESET_ONGOING";
+	case ICE_ERR_HW_TABLE:
+		return "ICE_ERR_HW_TABLE";
+	case ICE_ERR_DOES_NOT_EXIST:
+		return "ICE_ERR_DOES_NOT_EXIST";
+	case ICE_ERR_AQ_ERROR:
+		return "ICE_ERR_AQ_ERROR";
+	case ICE_ERR_AQ_TIMEOUT:
+		return "ICE_ERR_AQ_TIMEOUT";
+	case ICE_ERR_AQ_FULL:
+		return "ICE_ERR_AQ_FULL";
+	case ICE_ERR_AQ_NO_WORK:
+		return "ICE_ERR_AQ_NO_WORK";
+	case ICE_ERR_AQ_EMPTY:
+		return "ICE_ERR_AQ_EMPTY";
+	}
+
+	return "ICE_ERR_UNKNOWN";
+}
+
 /**
  * ice_set_rss - Set RSS keys and lut
  * @vsi: Pointer to VSI structure
@@ -4894,8 +5003,9 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_set_rss_key(hw, vsi->idx, buf);
 
 		if (status) {
-			dev_err(dev, "Cannot set RSS key, err %d aq_err %d\n",
-				status, hw->adminq.rq_last_status);
+			dev_err(dev, "Cannot set RSS key, err %s aq_err %s\n",
+				ice_stat_str(status),
+				ice_aq_str(hw->adminq.rq_last_status));
 			return -EIO;
 		}
 	}
@@ -4904,8 +5014,9 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_set_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
 					    lut, lut_size);
 		if (status) {
-			dev_err(dev, "Cannot set RSS lut, err %d aq_err %d\n",
-				status, hw->adminq.rq_last_status);
+			dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n",
+				ice_stat_str(status),
+				ice_aq_str(hw->adminq.rq_last_status));
 			return -EIO;
 		}
 	}
@@ -4936,8 +5047,9 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 
 		status = ice_aq_get_rss_key(hw, vsi->idx, buf);
 		if (status) {
-			dev_err(dev, "Cannot get RSS key, err %d aq_err %d\n",
-				status, hw->adminq.rq_last_status);
+			dev_err(dev, "Cannot get RSS key, err %s aq_err %s\n",
+				ice_stat_str(status),
+				ice_aq_str(hw->adminq.rq_last_status));
 			return -EIO;
 		}
 	}
@@ -4946,8 +5058,9 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		status = ice_aq_get_rss_lut(hw, vsi->idx, vsi->rss_lut_type,
 					    lut, lut_size);
 		if (status) {
-			dev_err(dev, "Cannot get RSS lut, err %d aq_err %d\n",
-				status, hw->adminq.rq_last_status);
+			dev_err(dev, "Cannot get RSS lut, err %s aq_err %s\n",
+				ice_stat_str(status),
+				ice_aq_str(hw->adminq.rq_last_status));
 			return -EIO;
 		}
 	}
@@ -5014,8 +5127,9 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
-			bmode, status, hw->adminq.sq_last_status);
+		dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %s aq_err %s\n",
+			bmode, ice_stat_str(status),
+			ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto out;
 	}
@@ -5084,8 +5198,9 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		 */
 		status = ice_update_sw_rule_bridge_mode(hw);
 		if (status) {
-			netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n",
-				   mode, status, hw->adminq.sq_last_status);
+			netdev_err(dev, "switch rule update failed, mode = %d err %s aq_err %s\n",
+				   mode, ice_stat_str(status),
+				   ice_aq_str(hw->adminq.sq_last_status));
 			/* revert hw->evb_veb */
 			hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
 			return -EIO;
@@ -5211,8 +5326,8 @@ ice_udp_tunnel_add(struct net_device *netdev, struct udp_tunnel_info *ti)
 		netdev_info(netdev, "Max tunneled UDP ports reached, port %d not added\n",
 			    port);
 	else if (status)
-		netdev_err(netdev, "Error adding UDP tunnel - %d\n",
-			   status);
+		netdev_err(netdev, "Error adding UDP tunnel - %s\n",
+			   ice_stat_str(status));
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 1389d0d6d3d2..fc03b278370b 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -491,8 +491,9 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable)
 
 	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
-		dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %d\n",
-			 status, hw->adminq.sq_last_status);
+		dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %s aq_err %s\n",
+			 ice_stat_str(status),
+			 ice_aq_str(hw->adminq.sq_last_status));
 		ret = -EIO;
 		goto out;
 	}
@@ -1659,8 +1660,9 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 	aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval,
 				       msg, msglen, NULL);
 	if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) {
-		dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %d\n",
-			 vf->vf_id, aq_ret, pf->hw.mailboxq.sq_last_status);
+		dev_info(dev, "Unable to send the message to VF %d ret %s aq_err %s\n",
+			 vf->vf_id, ice_stat_str(aq_ret),
+			 ice_aq_str(pf->hw.mailboxq.sq_last_status));
 		return -EIO;
 	}
 
@@ -2075,8 +2077,9 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 
 	status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL);
 	if (status) {
-		dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d\n",
-			ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, status);
+		dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %s\n",
+			ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num,
+			ice_stat_str(status));
 		ret = -EIO;
 		goto out;
 	}
@@ -2232,8 +2235,9 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg)
 		 */
 		status = ice_vf_set_vsi_promisc(vf, vsi, promisc_m, rm_promisc);
 		if (status) {
-			dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed, error: %d\n",
-				rm_promisc ? "dis" : "en", vf->vf_id, status);
+			dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed, error: %s\n",
+				rm_promisc ? "dis" : "en", vf->vf_id,
+				ice_stat_str(status));
 			v_ret = ice_err_to_virt_err(status);
 			goto error_param;
 		} else {
@@ -2808,8 +2812,8 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 			vf->vf_id);
 		return -EEXIST;
 	} else if (status) {
-		dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %d\n",
-			mac_addr, vf->vf_id, status);
+		dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %s\n",
+			mac_addr, vf->vf_id, ice_stat_str(status));
 		return -EIO;
 	}
 
@@ -2845,8 +2849,8 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 			vf->vf_id);
 		return -ENOENT;
 	} else if (status) {
-		dev_err(dev, "Failed to delete MAC %pM for VF %d, error %d\n",
-			mac_addr, vf->vf_id, status);
+		dev_err(dev, "Failed to delete MAC %pM for VF %d, error %s\n",
+			mac_addr, vf->vf_id, ice_stat_str(status));
 		return -EIO;
 	}
 
-- 
cgit v1.2.3


From 88865fc4bbd61e48d04e2747d59b85d2014cca82 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Thu, 7 May 2020 17:41:05 -0700
Subject: ice: Fix casting issues

Change min() macros to min_t() which has compare type specified and it
helps avoid precision loss.

In some cases there was precision loss during calls or assignments.
Some fields in structs were unnecessarily large and gave multiple
warnings.

There were also some minor type differences which are now fixed as well as
some cases where a simple cast was needed.

Callers were were passing data that is a u16 to
ice_sched_cfg_node_bw_alloc() but the function was truncating that to a u8.
Fix that by changing the function to take a u16.

Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h           | 10 ++++-----
 drivers/net/ethernet/intel/ice/ice_base.c      | 24 ++++++++++++---------
 drivers/net/ethernet/intel/ice/ice_controlq.c  |  2 +-
 drivers/net/ethernet/intel/ice/ice_ethtool.c   |  6 +++---
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c | 13 ++++++------
 drivers/net/ethernet/intel/ice/ice_lib.c       | 29 ++++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_main.c      | 13 ++++++------
 drivers/net/ethernet/intel/ice/ice_sched.c     |  2 +-
 drivers/net/ethernet/intel/ice/ice_switch.c    | 12 +++++------
 drivers/net/ethernet/intel/ice/ice_txrx.c      | 19 +++++++++--------
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c  |  2 +-
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h  |  2 +-
 drivers/net/ethernet/intel/ice/ice_type.h      |  4 ++--
 13 files changed, 74 insertions(+), 64 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index be90337cabb8..cd2bf9b8e385 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -248,8 +248,8 @@ struct ice_vsi {
 	u32 tx_busy;
 	u32 rx_buf_failed;
 	u32 rx_page_failed;
-	int num_q_vectors;
-	int base_vector;		/* IRQ base for OS reserved vectors */
+	u16 num_q_vectors;
+	u16 base_vector;		/* IRQ base for OS reserved vectors */
 	enum ice_vsi_type type;
 	u16 vsi_num;			/* HW (absolute) index of this VSI */
 	u16 idx;			/* software index in pf->vsi[] */
@@ -390,11 +390,11 @@ struct ice_pf {
 	struct mutex tc_mutex;		/* lock to protect TC changes */
 	u32 msg_enable;
 	u32 hw_csum_rx_error;
-	u32 oicr_idx;		/* Other interrupt cause MSIX vector index */
-	u32 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */
+	u16 oicr_idx;		/* Other interrupt cause MSIX vector index */
+	u16 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
-	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
+	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index ee1c698ff056..4c835c144907 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -24,7 +24,7 @@ static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
 
 	bitmap_set(qs_cfg->pf_map, offset, qs_cfg->q_count);
 	for (i = 0; i < qs_cfg->q_count; i++)
-		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = i + offset;
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = (u16)(i + offset);
 	mutex_unlock(qs_cfg->qs_mutex);
 
 	return 0;
@@ -47,7 +47,7 @@ static int __ice_vsi_get_qs_sc(struct ice_qs_cfg *qs_cfg)
 		if (index >= qs_cfg->pf_map_size)
 			goto err_scatter;
 		set_bit(index, qs_cfg->pf_map);
-		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = index;
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = (u16)index;
 	}
 	mutex_unlock(qs_cfg->qs_mutex);
 
@@ -96,7 +96,7 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
  * We allocate one q_vector and set default value for ITR setting associated
  * with this q_vector. If allocation fails we return -ENOMEM.
  */
-static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
+static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_q_vector *q_vector;
@@ -376,7 +376,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
-	rlan_ctx.rxmax = min_t(u16, vsi->max_frame,
+	rlan_ctx.rxmax = min_t(u32, vsi->max_frame,
 			       chain_len * ring->rx_buf_len);
 
 	/* Rx queue threshold in units of 64 */
@@ -453,7 +453,7 @@ int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg)
 	if (ret) {
 		/* contig failed, so try with scatter approach */
 		qs_cfg->mapping_mode = ICE_VSI_MAP_SCATTER;
-		qs_cfg->q_count = min_t(u16, qs_cfg->q_count,
+		qs_cfg->q_count = min_t(unsigned int, qs_cfg->q_count,
 					qs_cfg->scatter_count);
 		ret = __ice_vsi_get_qs_sc(qs_cfg);
 	}
@@ -526,7 +526,8 @@ int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx)
 int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 {
 	struct device *dev = ice_pf_to_dev(vsi->back);
-	int v_idx, err;
+	u16 v_idx;
+	int err;
 
 	if (vsi->q_vectors[0]) {
 		dev_dbg(dev, "VSI %d has existing q_vectors\n", vsi->vsi_num);
@@ -562,7 +563,7 @@ err_out:
 void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
 {
 	int q_vectors = vsi->num_q_vectors;
-	int tx_rings_rem, rx_rings_rem;
+	u16 tx_rings_rem, rx_rings_rem;
 	int v_id;
 
 	/* initially assigning remaining rings count to VSIs num queue value */
@@ -571,10 +572,12 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
 
 	for (v_id = 0; v_id < q_vectors; v_id++) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[v_id];
-		int tx_rings_per_v, rx_rings_per_v, q_id, q_base;
+		u8 tx_rings_per_v, rx_rings_per_v;
+		u16 q_id, q_base;
 
 		/* Tx rings mapping to vector */
-		tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id);
+		tx_rings_per_v = (u8)DIV_ROUND_UP(tx_rings_rem,
+						  q_vectors - v_id);
 		q_vector->num_ring_tx = tx_rings_per_v;
 		q_vector->tx.ring = NULL;
 		q_vector->tx.itr_idx = ICE_TX_ITR;
@@ -590,7 +593,8 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
 		tx_rings_rem -= tx_rings_per_v;
 
 		/* Rx rings mapping to vector */
-		rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id);
+		rx_rings_per_v = (u8)DIV_ROUND_UP(rx_rings_rem,
+						  q_vectors - v_id);
 		q_vector->num_ring_rx = rx_rings_per_v;
 		q_vector->rx.ring = NULL;
 		q_vector->rx.itr_idx = ICE_RX_ITR;
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index dd946866d7b8..9a865962296d 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -1128,7 +1128,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	}
 	memcpy(&e->desc, desc, sizeof(e->desc));
 	datalen = le16_to_cpu(desc->datalen);
-	e->msg_len = min(datalen, e->buf_len);
+	e->msg_len = min_t(u16, datalen, e->buf_len);
 	if (e->msg_buf && e->msg_len)
 		memcpy(e->msg_buf, cq->rq.r.rq_bi[desc_idx].va, e->msg_len);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index b814bc54f752..41a6aa4ebb02 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2609,7 +2609,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	int i, timeout = 50, err = 0;
-	u32 new_rx_cnt, new_tx_cnt;
+	u16 new_rx_cnt, new_tx_cnt;
 
 	if (ring->tx_pending > ICE_MAX_NUM_DESC ||
 	    ring->tx_pending < ICE_MIN_NUM_DESC ||
@@ -2661,8 +2661,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
 		if (ice_is_xdp_ena_vsi(vsi))
 			for (i = 0; i < vsi->num_xdp_txq; i++)
 				vsi->xdp_rings[i]->count = new_tx_cnt;
-		vsi->num_tx_desc = new_tx_cnt;
-		vsi->num_rx_desc = new_rx_cnt;
+		vsi->num_tx_desc = (u16)new_tx_cnt;
+		vsi->num_rx_desc = (u16)new_rx_cnt;
 		netdev_dbg(netdev, "Link is down, descriptor count change happens when link is brought up\n");
 		goto done;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 62e305511c7e..4dc72aef5381 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -1694,7 +1694,7 @@ ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
 	 */
 	ice_set_key((u8 *)&sect_rx->tcam[0].key, sizeof(sect_rx->tcam[0].key),
 		    (u8 *)&port, NULL, NULL, NULL,
-		    offsetof(struct ice_boost_key_value, hv_dst_port_key),
+		    (u16)offsetof(struct ice_boost_key_value, hv_dst_port_key),
 		    sizeof(sect_rx->tcam[0].key.key.hv_dst_port_key));
 
 	/* exact copy of entry to Tx section entry */
@@ -2329,9 +2329,10 @@ ice_find_prof_id(struct ice_hw *hw, enum ice_block blk,
 		 struct ice_fv_word *fv, u8 *prof_id)
 {
 	struct ice_es *es = &hw->blk[blk].es;
-	u16 off, i;
+	u16 off;
+	u8 i;
 
-	for (i = 0; i < es->count; i++) {
+	for (i = 0; i < (u8)es->count; i++) {
 		off = i * es->fvw;
 
 		if (memcmp(&es->t[off], fv, es->fvw * sizeof(*fv)))
@@ -3461,7 +3462,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
 	struct ice_prof_map *prof;
 	enum ice_status status;
-	u32 byte = 0;
+	u8 byte = 0;
 	u8 prof_id;
 
 	bitmap_zero(ptgs_used, ICE_XLT1_CNT);
@@ -3496,7 +3497,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 
 	/* build list of ptgs */
 	while (bytes && prof->ptg_cnt < ICE_MAX_PTG_PER_PROFILE) {
-		u32 bit;
+		u8 bit;
 
 		if (!ptypes[byte]) {
 			bytes--;
@@ -3530,7 +3531,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 				break;
 
 			/* nothing left in byte, then exit */
-			m = ~((1 << (bit + 1)) - 1);
+			m = ~(u8)((1 << (bit + 1)) - 1);
 			if (!(ptypes[byte] & m))
 				break;
 		}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index bf4c538c94bb..9330989ddb40 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -37,7 +37,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type)
  */
 static int ice_vsi_ctrl_all_rx_rings(struct ice_vsi *vsi, bool ena)
 {
-	int i, ret = 0;
+	int ret = 0;
+	u16 i;
 
 	for (i = 0; i < vsi->num_rxq; i++)
 		ice_vsi_ctrl_one_rx_ring(vsi, ena, i, false);
@@ -565,8 +566,8 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 		/* PF VSI will inherit RSS instance of PF */
-		vsi->rss_table_size = cap->rss_table_size;
-		vsi->rss_size = min_t(int, num_online_cpus(),
+		vsi->rss_table_size = (u16)cap->rss_table_size;
+		vsi->rss_size = min_t(u16, num_online_cpus(),
 				      BIT(cap->rss_table_entry_width));
 		vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF;
 		break;
@@ -684,15 +685,15 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 				max_rss = ICE_MAX_LG_RSS_QS;
 			else
 				max_rss = ICE_MAX_RSS_QS_PER_VF;
-			qcount_rx = min_t(int, rx_numq_tc, max_rss);
+			qcount_rx = min_t(u16, rx_numq_tc, max_rss);
 			if (!vsi->req_rxq)
-				qcount_rx = min_t(int, qcount_rx,
+				qcount_rx = min_t(u16, qcount_rx,
 						  vsi->rss_size);
 		}
 	}
 
 	/* find the (rounded up) power-of-2 of qcount */
-	pow = order_base_2(qcount_rx);
+	pow = (u16)order_base_2(qcount_rx);
 
 	ice_for_each_traffic_class(i) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
@@ -941,7 +942,7 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
  */
 static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 {
-	int start = 0, end = 0;
+	u16 start = 0, end = 0;
 
 	if (needed > res->end)
 		return -ENOMEM;
@@ -1024,6 +1025,7 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u16 num_q_vectors;
+	int base;
 
 	dev = ice_pf_to_dev(pf);
 	/* SRIOV doesn't grab irq_tracker entries for each VSI */
@@ -1038,14 +1040,15 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 
 	num_q_vectors = vsi->num_q_vectors;
 	/* reserve slots from OS requested IRQs */
-	vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors,
-				       vsi->idx);
-	if (vsi->base_vector < 0) {
+	base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, vsi->idx);
+
+	if (base < 0) {
 		dev_err(dev, "%d MSI-X interrupts available. %s %d failed to get %d MSI-X vectors\n",
 			ice_get_free_res_count(pf->irq_tracker),
 			ice_vsi_type_str(vsi->type), vsi->idx, num_q_vectors);
 		return -ENOENT;
 	}
+	vsi->base_vector = (u16)base;
 	pf->num_avail_sw_msix -= num_q_vectors;
 
 	return 0;
@@ -1085,7 +1088,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
-	int i;
+	u16 i;
 
 	dev = ice_pf_to_dev(pf);
 	/* Allocate Tx rings */
@@ -1178,7 +1181,7 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
 	u8 *lut;
 
 	dev = ice_pf_to_dev(pf);
-	vsi->rss_size = min_t(int, vsi->rss_size, vsi->num_rxq);
+	vsi->rss_size = min_t(u16, vsi->rss_size, vsi->num_rxq);
 
 	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
 	if (!lut)
@@ -1673,7 +1676,7 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	u32 txq = 0, rxq = 0;
+	u16 txq = 0, rxq = 0;
 	int i, q;
 
 	for (i = 0; i < vsi->num_q_vectors; i++) {
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c4dda1fa5853..cbfd54867be1 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2245,7 +2245,7 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 		return oicr_idx;
 
 	pf->num_avail_sw_msix -= 1;
-	pf->oicr_idx = oicr_idx;
+	pf->oicr_idx = (u16)oicr_idx;
 
 	err = devm_request_irq(dev, pf->msix_entries[pf->oicr_idx].vector,
 			       ice_misc_intr, 0, pf->int_name, pf);
@@ -2642,7 +2642,8 @@ unroll_vsi_setup:
 static u16
 ice_get_avail_q_count(unsigned long *pf_qmap, struct mutex *lock, u16 size)
 {
-	u16 count = 0, bit;
+	unsigned long bit;
+	u16 count = 0;
 
 	mutex_lock(lock);
 	for_each_clear_bit(bit, pf_qmap, size)
@@ -2881,8 +2882,8 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 	}
 
 	/* populate SW interrupts pool with number of OS granted IRQs. */
-	pf->num_avail_sw_msix = vectors;
-	pf->irq_tracker->num_entries = vectors;
+	pf->num_avail_sw_msix = (u16)vectors;
+	pf->irq_tracker->num_entries = (u16)vectors;
 	pf->irq_tracker->end = pf->irq_tracker->num_entries;
 
 	return 0;
@@ -2914,9 +2915,9 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx)
 	}
 
 	if (new_tx)
-		vsi->req_txq = new_tx;
+		vsi->req_txq = (u16)new_tx;
 	if (new_rx)
-		vsi->req_rxq = new_rx;
+		vsi->req_rxq = (u16)new_rx;
 
 	/* set for the next time the netdev is started */
 	if (!netif_running(vsi->netdev)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index eae707ddf8e8..d63acd2fcf79 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1917,7 +1917,7 @@ ice_sched_update_elem(struct ice_hw *hw, struct ice_sched_node *node,
  */
 static enum ice_status
 ice_sched_cfg_node_bw_alloc(struct ice_hw *hw, struct ice_sched_node *node,
-			    enum ice_rl_type rl_type, u8 bw_alloc)
+			    enum ice_rl_type rl_type, u16 bw_alloc)
 {
 	struct ice_aqc_txsched_elem_data buf;
 	struct ice_aqc_txsched_elem *data;
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 51825a203e35..7d88944de31a 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -593,8 +593,8 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw)
 			    ICE_AQC_GET_SW_CONF_RESP_IS_VF)
 				is_vf = true;
 
-			res_type = le16_to_cpu(ele->vsi_port_num) >>
-				ICE_AQC_GET_SW_CONF_RESP_TYPE_S;
+			res_type = (u8)(le16_to_cpu(ele->vsi_port_num) >>
+					ICE_AQC_GET_SW_CONF_RESP_TYPE_S);
 
 			if (res_type == ICE_AQC_GET_SW_CONF_RESP_VSI) {
 				/* FW VSI is not needed. Just continue. */
@@ -1618,12 +1618,12 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
 	struct ice_aqc_sw_rules_elem *s_rule, *r_iter;
 	struct ice_fltr_list_entry *m_list_itr;
 	struct list_head *rule_head;
-	u16 elem_sent, total_elem_left;
+	u16 total_elem_left, s_rule_size;
 	struct ice_switch_info *sw;
 	struct mutex *rule_lock; /* Lock to protect filter rule list */
 	enum ice_status status = 0;
 	u16 num_unicast = 0;
-	u16 s_rule_size;
+	u8 elem_sent;
 
 	if (!m_list || !hw)
 		return ICE_ERR_PARAM;
@@ -1707,8 +1707,8 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
 	     total_elem_left -= elem_sent) {
 		struct ice_aqc_sw_rules_elem *entry = r_iter;
 
-		elem_sent = min(total_elem_left,
-				(u16)(ICE_AQ_MAX_BUF_LEN / s_rule_size));
+		elem_sent = min_t(u8, total_elem_left,
+				  (ICE_AQ_MAX_BUF_LEN / s_rule_size));
 		status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size,
 					 elem_sent, ice_aqc_opc_add_sw_rules,
 					 NULL);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 4ba1fc8261d9..05d1077f80c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -819,7 +819,7 @@ static struct sk_buff *
 ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	      struct xdp_buff *xdp)
 {
-	unsigned int metasize = xdp->data - xdp->data_meta;
+	u8 metasize = xdp->data - xdp->data_meta;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
 #else
@@ -934,7 +934,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
  */
 static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-	u32 ntc = rx_ring->next_to_clean + 1;
+	u16 ntc = rx_ring->next_to_clean + 1;
 
 	/* fetch, update, and store next to clean */
 	ntc = (ntc < rx_ring->count) ? ntc : 0;
@@ -1544,7 +1544,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * don't allow the budget to go below 1 because that would exit
 		 * polling early.
 		 */
-		budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
+		budget_per_ring = max_t(int, budget / q_vector->num_ring_rx, 1);
 	else
 		/* Max of 1 Rx ring in this q_vector so give it the budget */
 		budget_per_ring = budget;
@@ -2026,7 +2026,8 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		unsigned char *hdr;
 	} l4;
 	u64 cd_mss, cd_tso_len;
-	u32 paylen, l4_start;
+	u32 paylen;
+	u8 l4_start;
 	int err;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -2062,7 +2063,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 			l4.udp->len = 0;
 
 			/* determine offset of outer transport header */
-			l4_start = l4.hdr - skb->data;
+			l4_start = (u8)(l4.hdr - skb->data);
 
 			/* remove payload length from outer checksum */
 			paylen = skb->len - l4_start;
@@ -2086,7 +2087,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	}
 
 	/* determine offset of transport header */
-	l4_start = l4.hdr - skb->data;
+	l4_start = (u8)(l4.hdr - skb->data);
 
 	/* remove payload length from checksum */
 	paylen = skb->len - l4_start;
@@ -2095,12 +2096,12 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		csum_replace_by_diff(&l4.udp->check,
 				     (__force __wsum)htonl(paylen));
 		/* compute length of UDP segmentation header */
-		off->header_len = sizeof(l4.udp) + l4_start;
+		off->header_len = (u8)sizeof(l4.udp) + l4_start;
 	} else {
 		csum_replace_by_diff(&l4.tcp->check,
 				     (__force __wsum)htonl(paylen));
 		/* compute length of TCP segmentation header */
-		off->header_len = (l4.tcp->doff * 4) + l4_start;
+		off->header_len = (u8)((l4.tcp->doff * 4) + l4_start);
 	}
 
 	/* update gso_segs and bytecount */
@@ -2331,7 +2332,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
-		int i = tx_ring->next_to_use;
+		u16 i = tx_ring->next_to_use;
 
 		/* grab the next descriptor */
 		cdesc = ICE_TX_CTX_DESC(tx_ring, i);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1f9c3d24cde7..9d6512f96b8c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -8,7 +8,7 @@
  * @rx_ring: ring to bump
  * @val: new head index
  */
-void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
+void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val)
 {
 	u16 prev_ntu = rx_ring->next_to_use & ~0x7;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index ba9164dad9ae..af0fca5b91ff 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -49,7 +49,7 @@ static inline void ice_xdp_ring_update_tail(struct ice_ring *xdp_ring)
 void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res);
 int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring);
 int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring);
-void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val);
+void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val);
 void
 ice_process_skb_fields(struct ice_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4f5345a7c15d..9f6578eb4672 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -501,8 +501,8 @@ struct ice_hw {
 	u16 max_burst_size;	/* driver sets this value */
 
 	/* Tx Scheduler values */
-	u16 num_tx_sched_layers;
-	u16 num_tx_sched_phys_layers;
+	u8 num_tx_sched_layers;
+	u8 num_tx_sched_phys_layers;
 	u8 flattened_layers;
 	u8 max_cgds;
 	u8 sw_entry_point_layer;
-- 
cgit v1.2.3


From 53bb66983f34d4ff0af179fe228e2c55e1e45921 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Thu, 7 May 2020 17:41:06 -0700
Subject: ice: cleanup vf_id signedness

The vf_id variable is dealt with in the code in inconsistent
ways of sign usage, preventing compilation with -Werror=sign-compare.
Fix this problem in the code by always treating vf_id as unsigned, since
there are no valid values of vf_id that are negative.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h             |  2 +-
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 17 +++++++++--------
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h |  2 +-
 3 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index cd2bf9b8e385..58d0d6436c7f 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -371,7 +371,7 @@ struct ice_pf {
 	struct ice_sw *first_sw;	/* first switch created by firmware */
 	/* Virtchnl/SR-IOV config info */
 	struct ice_vf *vf;
-	int num_alloc_vfs;		/* actual number of VFs allocated */
+	u16 num_alloc_vfs;		/* actual number of VFs allocated */
 	u16 num_vfs_supported;		/* num VFs supported for this PF */
 	u16 num_qps_per_vf;
 	u16 num_msix_per_vf;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index fc03b278370b..9fb74a390b8c 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -10,10 +10,11 @@
  * @pf: pointer to the PF structure
  * @vf_id: the ID of the VF to check
  */
-static int ice_validate_vf_id(struct ice_pf *pf, int vf_id)
+static int ice_validate_vf_id(struct ice_pf *pf, u16 vf_id)
 {
+	/* vf_id range is only valid for 0-255, and should always be unsigned */
 	if (vf_id >= pf->num_alloc_vfs) {
-		dev_err(ice_pf_to_dev(pf), "Invalid VF ID: %d\n", vf_id);
+		dev_err(ice_pf_to_dev(pf), "Invalid VF ID: %u\n", vf_id);
 		return -EINVAL;
 	}
 	return 0;
@@ -27,7 +28,7 @@ static int ice_validate_vf_id(struct ice_pf *pf, int vf_id)
 static int ice_check_vf_init(struct ice_pf *pf, struct ice_vf *vf)
 {
 	if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
-		dev_err(ice_pf_to_dev(pf), "VF ID: %d in reset. Try again.\n",
+		dev_err(ice_pf_to_dev(pf), "VF ID: %u in reset. Try again.\n",
 			vf->vf_id);
 		return -EBUSY;
 	}
@@ -368,7 +369,7 @@ void ice_free_vfs(struct ice_pf *pf)
 	 * before this function ever gets called.
 	 */
 	if (!pci_vfs_assigned(pf->pdev)) {
-		int vf_id;
+		unsigned int vf_id;
 
 		/* Acknowledge VFLR for all VFs. Without this, VFs will fail to
 		 * work correctly when SR-IOV gets re-enabled.
@@ -399,9 +400,9 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 {
 	struct ice_pf *pf = vf->pf;
 	u32 reg, reg_idx, bit_idx;
+	unsigned int vf_abs_id, i;
 	struct device *dev;
 	struct ice_hw *hw;
-	int vf_abs_id, i;
 
 	dev = ice_pf_to_dev(pf);
 	hw = &pf->hw;
@@ -449,7 +450,7 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 		if ((reg & VF_TRANS_PENDING_M) == 0)
 			break;
 
-		dev_err(dev, "VF %d PCI transactions stuck\n", vf->vf_id);
+		dev_err(dev, "VF %u PCI transactions stuck\n", vf->vf_id);
 		udelay(ICE_PCI_CIAD_WAIT_DELAY_US);
 	}
 }
@@ -1515,7 +1516,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
 void ice_process_vflr_event(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
-	int vf_id;
+	unsigned int vf_id;
 	u32 reg;
 
 	if (!test_and_clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
@@ -1556,7 +1557,7 @@ static void ice_vc_reset_vf(struct ice_vf *vf)
  */
 static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq)
 {
-	int vf_id;
+	unsigned int vf_id;
 
 	ice_for_each_vf(pf, vf_id) {
 		struct ice_vf *vf = &pf->vf[vf_id];
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index f7fd1188efa4..474293ff4fe5 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -64,7 +64,7 @@ struct ice_mdd_vf_events {
 struct ice_vf {
 	struct ice_pf *pf;
 
-	s16 vf_id;			/* VF ID in the PF space */
+	u16 vf_id;			/* VF ID in the PF space */
 	u16 lan_vsi_idx;		/* index into PF struct */
 	/* first vector index of this VF in the PF space */
 	int first_vector_idx;
-- 
cgit v1.2.3


From 857a4f0e9f4956fffc0cedcaa2ba187a2e987153 Mon Sep 17 00:00:00 2001
From: Eric Joyner <eric.joyner@intel.com>
Date: Thu, 7 May 2020 17:41:07 -0700
Subject: ice: Fix resource leak on early exit from function

Memory allocated in the ice_add_prof_id_vsig() function wasn't being
properly freed if an error occurred inside the for-loop in the function.

In particular, 'p' wasn't being freed if an error occurred before it was
added to the resource list at the end of the for-loop.

Signed-off-by: Eric Joyner <eric.joyner@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 4dc72aef5381..38c37f506257 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -4228,8 +4228,10 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl,
 					      t->tcam[i].prof_id,
 					      t->tcam[i].ptg, vsig, 0, 0,
 					      vl_msk, dc_msk, nm_msk);
-		if (status)
+		if (status) {
+			devm_kfree(ice_hw_to_dev(hw), p);
 			goto err_ice_add_prof_id_vsig;
+		}
 
 		/* log change */
 		list_add(&p->list_entry, chg);
-- 
cgit v1.2.3


From 1b8f15b64a006b5fbbfbc898c612a48a86fff6de Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@intel.com>
Date: Thu, 7 May 2020 17:41:08 -0700
Subject: ice: refactor filter functions

Move filter functions to separate file.

Add functions that prepare suitable ice_fltr_info struct
depending on the filter type and add this struct to earlier created
list:
- ice_fltr_add_mac_to_list
- ice_fltr_add_vlan_to_list
- ice_fltr_add_eth_to_list
This functions are used in adding and removing filters.

Create wrappers for functions mentioned above that alloc list,
add suitable ice_fltr_info to it and call add or remove function.
- ice_fltr_prepare_mac
- ice_fltr_prepare_mac_and_broadcast
- ice_fltr_prepare_vlan
- ice_fltr_prepare_eth

Signed-off-by: Michal Swiatkowski <michal.swiatkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile          |   1 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c     |  13 +-
 drivers/net/ethernet/intel/ice/ice_fltr.c        | 397 +++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_fltr.h        |  39 +++
 drivers/net/ethernet/intel/ice/ice_lib.c         | 212 ++----------
 drivers/net/ethernet/intel/ice/ice_lib.h         |   9 +-
 drivers/net/ethernet/intel/ice/ice_main.c        |  53 +--
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c |  34 +-
 8 files changed, 494 insertions(+), 264 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_fltr.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_fltr.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 29c6c6743450..2055e61eaf24 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -17,6 +17,7 @@ ice-y := ice_main.o	\
 	 ice_lib.o	\
 	 ice_txrx_lib.o	\
 	 ice_txrx.o	\
+	 ice_fltr.o	\
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
 	 ice_devlink.o	\
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 41a6aa4ebb02..9fb82c993df9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -5,6 +5,7 @@
 
 #include "ice.h"
 #include "ice_flow.h"
+#include "ice_fltr.h"
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
@@ -676,7 +677,6 @@ static u64 ice_loopback_test(struct net_device *netdev)
 	struct ice_ring *tx_ring, *rx_ring;
 	u8 broadcast[ETH_ALEN], ret = 0;
 	int num_frames, valid_frames;
-	LIST_HEAD(tmp_list);
 	struct device *dev;
 	u8 *tx_frame;
 	int i;
@@ -712,16 +712,11 @@ static u64 ice_loopback_test(struct net_device *netdev)
 
 	/* Test VSI needs to receive broadcast packets */
 	eth_broadcast_addr(broadcast);
-	if (ice_add_mac_to_list(test_vsi, &tmp_list, broadcast)) {
+	if (ice_fltr_add_mac(test_vsi, broadcast, ICE_FWD_TO_VSI)) {
 		ret = 5;
 		goto lbtest_mac_dis;
 	}
 
-	if (ice_add_mac(&pf->hw, &tmp_list)) {
-		ret = 6;
-		goto free_mac_list;
-	}
-
 	if (ice_lbtest_create_frame(pf, &tx_frame, ICE_LB_FRAME_SIZE)) {
 		ret = 7;
 		goto remove_mac_filters;
@@ -744,10 +739,8 @@ static u64 ice_loopback_test(struct net_device *netdev)
 lbtest_free_frame:
 	devm_kfree(dev, tx_frame);
 remove_mac_filters:
-	if (ice_remove_mac(&pf->hw, &tmp_list))
+	if (ice_fltr_remove_mac(test_vsi, broadcast, ICE_FWD_TO_VSI))
 		netdev_err(netdev, "Could not remove MAC filter for the test VSI\n");
-free_mac_list:
-	ice_free_fltr_list(dev, &tmp_list);
 lbtest_mac_dis:
 	/* Disable MAC loopback after the test is completed. */
 	if (ice_aq_set_mac_loopback(&pf->hw, false, NULL))
diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c
new file mode 100644
index 000000000000..2418d4fff037
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fltr.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_fltr.h"
+
+/**
+ * ice_fltr_free_list - free filter lists helper
+ * @dev: pointer to the device struct
+ * @h: pointer to the list head to be freed
+ *
+ * Helper function to free filter lists previously created using
+ * ice_fltr_add_mac_to_list
+ */
+void ice_fltr_free_list(struct device *dev, struct list_head *h)
+{
+	struct ice_fltr_list_entry *e, *tmp;
+
+	list_for_each_entry_safe(e, tmp, h, list_entry) {
+		list_del(&e->list_entry);
+		devm_kfree(dev, e);
+	}
+}
+
+/**
+ * ice_fltr_add_entry_to_list - allocate and add filter entry to list
+ * @dev: pointer to device needed by alloc function
+ * @info: filter info struct that gets added to the passed in list
+ * @list: pointer to the list which contains MAC filters entry
+ */
+static int
+ice_fltr_add_entry_to_list(struct device *dev, struct ice_fltr_info *info,
+			   struct list_head *list)
+{
+	struct ice_fltr_list_entry *entry;
+
+	entry = devm_kzalloc(dev, sizeof(*entry), GFP_ATOMIC);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->fltr_info = *info;
+
+	INIT_LIST_HEAD(&entry->list_entry);
+	list_add(&entry->list_entry, list);
+
+	return 0;
+}
+
+/**
+ * ice_fltr_add_mac_list - add list of MAC filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+enum ice_status
+ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_add_mac(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_remove_mac_list - remove list of MAC filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+enum ice_status
+ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_remove_mac(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_add_vlan_list - add list of VLAN filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+static enum ice_status
+ice_fltr_add_vlan_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_add_vlan(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_remove_vlan_list - remove list of VLAN filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+static enum ice_status
+ice_fltr_remove_vlan_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_remove_vlan(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_add_eth_list - add list of ethertype filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+static enum ice_status
+ice_fltr_add_eth_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_add_eth_mac(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_remove_eth_list - remove list of ethertype filters
+ * @vsi: pointer to VSI struct
+ * @list: list of filters
+ */
+static enum ice_status
+ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list)
+{
+	return ice_remove_eth_mac(&vsi->back->hw, list);
+}
+
+/**
+ * ice_fltr_remove_all - remove all filters associated with VSI
+ * @vsi: pointer to VSI struct
+ */
+void ice_fltr_remove_all(struct ice_vsi *vsi)
+{
+	ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx);
+}
+
+/**
+ * ice_fltr_add_mac_to_list - add MAC filter info to exsisting list
+ * @vsi: pointer to VSI struct
+ * @list: list to add filter info to
+ * @mac: MAC address to add
+ * @action: filter action
+ */
+int
+ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list,
+			 const u8 *mac, enum ice_sw_fwd_act_type action)
+{
+	struct ice_fltr_info info = { 0 };
+
+	info.flag = ICE_FLTR_TX;
+	info.src_id = ICE_SRC_ID_VSI;
+	info.lkup_type = ICE_SW_LKUP_MAC;
+	info.fltr_act = action;
+	info.vsi_handle = vsi->idx;
+
+	ether_addr_copy(info.l_data.mac.mac_addr, mac);
+
+	return ice_fltr_add_entry_to_list(ice_pf_to_dev(vsi->back), &info,
+					  list);
+}
+
+/**
+ * ice_fltr_add_vlan_to_list - add VLAN filter info to exsisting list
+ * @vsi: pointer to VSI struct
+ * @list: list to add filter info to
+ * @vlan_id: VLAN ID to add
+ * @action: filter action
+ */
+static int
+ice_fltr_add_vlan_to_list(struct ice_vsi *vsi, struct list_head *list,
+			  u16 vlan_id, enum ice_sw_fwd_act_type action)
+{
+	struct ice_fltr_info info = { 0 };
+
+	info.flag = ICE_FLTR_TX;
+	info.src_id = ICE_SRC_ID_VSI;
+	info.lkup_type = ICE_SW_LKUP_VLAN;
+	info.fltr_act = action;
+	info.vsi_handle = vsi->idx;
+	info.l_data.vlan.vlan_id = vlan_id;
+
+	return ice_fltr_add_entry_to_list(ice_pf_to_dev(vsi->back), &info,
+					  list);
+}
+
+/**
+ * ice_fltr_add_eth_to_list - add ethertype filter info to exsisting list
+ * @vsi: pointer to VSI struct
+ * @list: list to add filter info to
+ * @ethertype: ethertype of packet that matches filter
+ * @flag: filter direction, Tx or Rx
+ * @action: filter action
+ */
+static int
+ice_fltr_add_eth_to_list(struct ice_vsi *vsi, struct list_head *list,
+			 u16 ethertype, u16 flag,
+			 enum ice_sw_fwd_act_type action)
+{
+	struct ice_fltr_info info = { 0 };
+
+	info.flag = flag;
+	info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
+	info.fltr_act = action;
+	info.vsi_handle = vsi->idx;
+	info.l_data.ethertype_mac.ethertype = ethertype;
+
+	if (flag == ICE_FLTR_TX)
+		info.src_id = ICE_SRC_ID_VSI;
+	else
+		info.src_id = ICE_SRC_ID_LPORT;
+
+	return ice_fltr_add_entry_to_list(ice_pf_to_dev(vsi->back), &info,
+					  list);
+}
+
+/**
+ * ice_fltr_prepare_mac - add or remove MAC rule
+ * @vsi: pointer to VSI struct
+ * @mac: MAC address to add
+ * @action: action to be performed on filter match
+ * @mac_action: pointer to add or remove MAC function
+ */
+static enum ice_status
+ice_fltr_prepare_mac(struct ice_vsi *vsi, const u8 *mac,
+		     enum ice_sw_fwd_act_type action,
+		     enum ice_status (*mac_action)(struct ice_vsi *,
+						   struct list_head *))
+{
+	enum ice_status result;
+	LIST_HEAD(tmp_list);
+
+	if (ice_fltr_add_mac_to_list(vsi, &tmp_list, mac, action)) {
+		ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+		return ICE_ERR_NO_MEMORY;
+	}
+
+	result = mac_action(vsi, &tmp_list);
+	ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+	return result;
+}
+
+/**
+ * ice_fltr_prepare_mac_and_broadcast - add or remove MAC and broadcast filter
+ * @vsi: pointer to VSI struct
+ * @mac: MAC address to add
+ * @action: action to be performed on filter match
+ * @mac_action: pointer to add or remove MAC function
+ */
+static enum ice_status
+ice_fltr_prepare_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac,
+				   enum ice_sw_fwd_act_type action,
+				   enum ice_status(*mac_action)
+				   (struct ice_vsi *, struct list_head *))
+{
+	u8 broadcast[ETH_ALEN];
+	enum ice_status result;
+	LIST_HEAD(tmp_list);
+
+	eth_broadcast_addr(broadcast);
+	if (ice_fltr_add_mac_to_list(vsi, &tmp_list, mac, action) ||
+	    ice_fltr_add_mac_to_list(vsi, &tmp_list, broadcast, action)) {
+		ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+		return ICE_ERR_NO_MEMORY;
+	}
+
+	result = mac_action(vsi, &tmp_list);
+	ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+	return result;
+}
+
+/**
+ * ice_fltr_prepare_vlan - add or remove VLAN filter
+ * @vsi: pointer to VSI struct
+ * @vlan_id: VLAN ID to add
+ * @action: action to be performed on filter match
+ * @vlan_action: pointer to add or remove VLAN function
+ */
+static enum ice_status
+ice_fltr_prepare_vlan(struct ice_vsi *vsi, u16 vlan_id,
+		      enum ice_sw_fwd_act_type action,
+		      enum ice_status (*vlan_action)(struct ice_vsi *,
+						     struct list_head *))
+{
+	enum ice_status result;
+	LIST_HEAD(tmp_list);
+
+	if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan_id, action))
+		return ICE_ERR_NO_MEMORY;
+
+	result = vlan_action(vsi, &tmp_list);
+	ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+	return result;
+}
+
+/**
+ * ice_fltr_prepare_eth - add or remove ethertype filter
+ * @vsi: pointer to VSI struct
+ * @ethertype: ethertype of packet to be filtered
+ * @flag: direction of packet, Tx or Rx
+ * @action: action to be performed on filter match
+ * @eth_action: pointer to add or remove ethertype function
+ */
+static enum ice_status
+ice_fltr_prepare_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag,
+		     enum ice_sw_fwd_act_type action,
+		     enum ice_status (*eth_action)(struct ice_vsi *,
+						   struct list_head *))
+{
+	enum ice_status result;
+	LIST_HEAD(tmp_list);
+
+	if (ice_fltr_add_eth_to_list(vsi, &tmp_list, ethertype, flag, action))
+		return ICE_ERR_NO_MEMORY;
+
+	result = eth_action(vsi, &tmp_list);
+	ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list);
+	return result;
+}
+
+/**
+ * ice_fltr_add_mac - add single MAC filter
+ * @vsi: pointer to VSI struct
+ * @mac: MAC to add
+ * @action: action to be performed on filter match
+ */
+enum ice_status ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac,
+				 enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_mac(vsi, mac, action, ice_fltr_add_mac_list);
+}
+
+/**
+ * ice_fltr_add_mac_and_broadcast - add single MAC and broadcast
+ * @vsi: pointer to VSI struct
+ * @mac: MAC to add
+ * @action: action to be performed on filter match
+ */
+enum ice_status
+ice_fltr_add_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac,
+			       enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_mac_and_broadcast(vsi, mac, action,
+						  ice_fltr_add_mac_list);
+}
+
+/**
+ * ice_fltr_remove_mac - remove MAC filter
+ * @vsi: pointer to VSI struct
+ * @mac: filter MAC to remove
+ * @action: action to remove
+ */
+enum ice_status ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac,
+				    enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_mac(vsi, mac, action, ice_fltr_remove_mac_list);
+}
+
+/**
+ * ice_fltr_add_vlan - add single VLAN filter
+ * @vsi: pointer to VSI struct
+ * @vlan_id: VLAN ID to add
+ * @action: action to be performed on filter match
+ */
+enum ice_status ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id,
+				  enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_vlan(vsi, vlan_id, action,
+				     ice_fltr_add_vlan_list);
+}
+
+/**
+ * ice_fltr_remove_vlan - remove VLAN filter
+ * @vsi: pointer to VSI struct
+ * @vlan_id: filter VLAN to remove
+ * @action: action to remove
+ */
+enum ice_status ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id,
+				     enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_vlan(vsi, vlan_id, action,
+				     ice_fltr_remove_vlan_list);
+}
+
+/**
+ * ice_fltr_add_eth - add specyfic ethertype filter
+ * @vsi: pointer to VSI struct
+ * @ethertype: ethertype of filter
+ * @flag: direction of packet to be filtered, Tx or Rx
+ * @action: action to be performed on filter match
+ */
+enum ice_status ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag,
+				 enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_eth(vsi, ethertype, flag, action,
+				    ice_fltr_add_eth_list);
+}
+
+/**
+ * ice_fltr_remove_eth - remove ethertype filter
+ * @vsi: pointer to VSI struct
+ * @ethertype: ethertype of filter
+ * @flag: direction of filter
+ * @action: action to remove
+ */
+enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype,
+				    u16 flag, enum ice_sw_fwd_act_type action)
+{
+	return ice_fltr_prepare_eth(vsi, ethertype, flag, action,
+				    ice_fltr_remove_eth_list);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h
new file mode 100644
index 000000000000..361cb4da9b43
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fltr.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#ifndef _ICE_FLTR_H_
+#define _ICE_FLTR_H_
+
+void ice_fltr_free_list(struct device *dev, struct list_head *h);
+enum ice_status
+ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list,
+			 const u8 *mac, enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac,
+		 enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_add_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac,
+			       enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list);
+enum ice_status
+ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac,
+		    enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list);
+
+enum ice_status
+ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vid,
+		  enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vid,
+		     enum ice_sw_fwd_act_type action);
+
+enum ice_status
+ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag,
+		 enum ice_sw_fwd_act_type action);
+enum ice_status
+ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag,
+		    enum ice_sw_fwd_act_type action);
+void ice_fltr_remove_all(struct ice_vsi *vsi);
+#endif
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 9330989ddb40..c73c977f6967 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -5,6 +5,7 @@
 #include "ice_base.h"
 #include "ice_flow.h"
 #include "ice_lib.h"
+#include "ice_fltr.h"
 #include "ice_dcb_lib.h"
 
 /**
@@ -1339,40 +1340,6 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 			vsi_num, ice_stat_str(status));
 }
 
-/**
- * ice_add_mac_to_list - Add a MAC address filter entry to the list
- * @vsi: the VSI to be forwarded to
- * @add_list: pointer to the list which contains MAC filter entries
- * @macaddr: the MAC address to be added.
- *
- * Adds MAC address filter entry to the temp list
- *
- * Returns 0 on success or ENOMEM on failure.
- */
-int
-ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
-		    const u8 *macaddr)
-{
-	struct ice_fltr_list_entry *tmp;
-	struct ice_pf *pf = vsi->back;
-
-	tmp = devm_kzalloc(ice_pf_to_dev(pf), sizeof(*tmp), GFP_ATOMIC);
-	if (!tmp)
-		return -ENOMEM;
-
-	tmp->fltr_info.flag = ICE_FLTR_TX;
-	tmp->fltr_info.src_id = ICE_SRC_ID_VSI;
-	tmp->fltr_info.lkup_type = ICE_SW_LKUP_MAC;
-	tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
-	tmp->fltr_info.vsi_handle = vsi->idx;
-	ether_addr_copy(tmp->fltr_info.l_data.mac.mac_addr, macaddr);
-
-	INIT_LIST_HEAD(&tmp->list_entry);
-	list_add(&tmp->list_entry, add_list);
-
-	return 0;
-}
-
 /**
  * ice_update_eth_stats - Update VSI-specific ethernet statistics counters
  * @vsi: the VSI to be updated
@@ -1419,55 +1386,22 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
 	vsi->stat_offsets_loaded = true;
 }
 
-/**
- * ice_free_fltr_list - free filter lists helper
- * @dev: pointer to the device struct
- * @h: pointer to the list head to be freed
- *
- * Helper function to free filter lists previously created using
- * ice_add_mac_to_list
- */
-void ice_free_fltr_list(struct device *dev, struct list_head *h)
-{
-	struct ice_fltr_list_entry *e, *tmp;
-
-	list_for_each_entry_safe(e, tmp, h, list_entry) {
-		list_del(&e->list_entry);
-		devm_kfree(dev, e);
-	}
-}
-
 /**
  * ice_vsi_add_vlan - Add VSI membership for given VLAN
  * @vsi: the VSI being configured
  * @vid: VLAN ID to be added
+ * @action: filter action to be performed on match
  */
-int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
+int
+ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action)
 {
-	struct ice_fltr_list_entry *tmp;
 	struct ice_pf *pf = vsi->back;
-	LIST_HEAD(tmp_add_list);
-	enum ice_status status;
 	struct device *dev;
 	int err = 0;
 
 	dev = ice_pf_to_dev(pf);
-	tmp = devm_kzalloc(dev, sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	tmp->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
-	tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI;
-	tmp->fltr_info.flag = ICE_FLTR_TX;
-	tmp->fltr_info.src_id = ICE_SRC_ID_VSI;
-	tmp->fltr_info.vsi_handle = vsi->idx;
-	tmp->fltr_info.l_data.vlan.vlan_id = vid;
-
-	INIT_LIST_HEAD(&tmp->list_entry);
-	list_add(&tmp->list_entry, &tmp_add_list);
 
-	status = ice_add_vlan(&pf->hw, &tmp_add_list);
-	if (!status) {
+	if (!ice_fltr_add_vlan(vsi, vid, action)) {
 		vsi->num_vlan++;
 	} else {
 		err = -ENODEV;
@@ -1475,7 +1409,6 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
 			vsi->vsi_num);
 	}
 
-	ice_free_fltr_list(dev, &tmp_add_list);
 	return err;
 }
 
@@ -1488,29 +1421,14 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
  */
 int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
 {
-	struct ice_fltr_list_entry *list;
 	struct ice_pf *pf = vsi->back;
-	LIST_HEAD(tmp_add_list);
 	enum ice_status status;
 	struct device *dev;
 	int err = 0;
 
 	dev = ice_pf_to_dev(pf);
-	list = devm_kzalloc(dev, sizeof(*list), GFP_KERNEL);
-	if (!list)
-		return -ENOMEM;
-
-	list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN;
-	list->fltr_info.vsi_handle = vsi->idx;
-	list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
-	list->fltr_info.l_data.vlan.vlan_id = vid;
-	list->fltr_info.flag = ICE_FLTR_TX;
-	list->fltr_info.src_id = ICE_SRC_ID_VSI;
 
-	INIT_LIST_HEAD(&list->list_entry);
-	list_add(&list->list_entry, &tmp_add_list);
-
-	status = ice_remove_vlan(&pf->hw, &tmp_add_list);
+	status = ice_fltr_remove_vlan(vsi, vid, ICE_FWD_TO_VSI);
 	if (!status) {
 		vsi->num_vlan--;
 	} else if (status == ICE_ERR_DOES_NOT_EXIST) {
@@ -1522,7 +1440,6 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
 		err = -EIO;
 	}
 
-	ice_free_fltr_list(dev, &tmp_add_list);
 	return err;
 }
 
@@ -1998,47 +1915,6 @@ clear_reg_idx:
 	return -EINVAL;
 }
 
-/**
- * ice_vsi_add_rem_eth_mac - Program VSI ethertype based filter with rule
- * @vsi: the VSI being configured
- * @add_rule: boolean value to add or remove ethertype filter rule
- */
-static void
-ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule)
-{
-	struct ice_fltr_list_entry *list;
-	struct ice_pf *pf = vsi->back;
-	LIST_HEAD(tmp_add_list);
-	enum ice_status status;
-	struct device *dev;
-
-	dev = ice_pf_to_dev(pf);
-	list = devm_kzalloc(dev, sizeof(*list), GFP_KERNEL);
-	if (!list)
-		return;
-
-	list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
-	list->fltr_info.fltr_act = ICE_DROP_PACKET;
-	list->fltr_info.flag = ICE_FLTR_TX;
-	list->fltr_info.src_id = ICE_SRC_ID_VSI;
-	list->fltr_info.vsi_handle = vsi->idx;
-	list->fltr_info.l_data.ethertype_mac.ethertype = vsi->ethtype;
-
-	INIT_LIST_HEAD(&list->list_entry);
-	list_add(&list->list_entry, &tmp_add_list);
-
-	if (add_rule)
-		status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
-	else
-		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
-
-	if (status)
-		dev_err(dev, "Failure Adding or Removing Ethertype on VSI %i error: %s\n",
-			vsi->vsi_num, ice_stat_str(status));
-
-	ice_free_fltr_list(dev, &tmp_add_list);
-}
-
 /**
  * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
  * @vsi: the VSI being configured
@@ -2047,45 +1923,25 @@ ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule)
  */
 void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 {
-	struct ice_fltr_list_entry *list;
+	enum ice_status (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag,
+				    enum ice_sw_fwd_act_type act);
 	struct ice_pf *pf = vsi->back;
-	LIST_HEAD(tmp_add_list);
 	enum ice_status status;
 	struct device *dev;
 
 	dev = ice_pf_to_dev(pf);
-	list = devm_kzalloc(dev, sizeof(*list), GFP_KERNEL);
-	if (!list)
-		return;
-
-	list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
-	list->fltr_info.vsi_handle = vsi->idx;
-	list->fltr_info.l_data.ethertype_mac.ethertype = ETH_P_LLDP;
+	eth_fltr = create ? ice_fltr_add_eth : ice_fltr_remove_eth;
 
-	if (tx) {
-		list->fltr_info.fltr_act = ICE_DROP_PACKET;
-		list->fltr_info.flag = ICE_FLTR_TX;
-		list->fltr_info.src_id = ICE_SRC_ID_VSI;
-	} else {
-		list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
-		list->fltr_info.flag = ICE_FLTR_RX;
-		list->fltr_info.src_id = ICE_SRC_ID_LPORT;
-	}
-
-	INIT_LIST_HEAD(&list->list_entry);
-	list_add(&list->list_entry, &tmp_add_list);
-
-	if (create)
-		status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
+	if (tx)
+		status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_TX,
+				  ICE_DROP_PACKET);
 	else
-		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
+		status = eth_fltr(vsi, ETH_P_LLDP, ICE_FLTR_RX, ICE_FWD_TO_VSI);
 
 	if (status)
 		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
 			create ? "adding" : "removing", tx ? "TX" : "RX",
 			vsi->vsi_num, ice_stat_str(status));
-
-	ice_free_fltr_list(dev, &tmp_add_list);
 }
 
 /**
@@ -2172,7 +2028,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		 * so this handles those cases (i.e. adding the PF to a bridge
 		 * without the 8021q module loaded).
 		 */
-		ret = ice_vsi_add_vlan(vsi, 0);
+		ret = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI);
 		if (ret)
 			goto unroll_clear_rings;
 
@@ -2247,9 +2103,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	 */
 	if (!ice_is_safe_mode(pf))
 		if (vsi->type == ICE_VSI_PF) {
-			ice_vsi_add_rem_eth_mac(vsi, true);
-
-			/* Tx LLDP packets */
+			ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
+					 ICE_DROP_PACKET);
 			ice_cfg_sw_lldp(vsi, true, true);
 		}
 
@@ -2566,7 +2421,8 @@ int ice_vsi_release(struct ice_vsi *vsi)
 
 	if (!ice_is_safe_mode(pf)) {
 		if (vsi->type == ICE_VSI_PF) {
-			ice_vsi_add_rem_eth_mac(vsi, false);
+			ice_fltr_remove_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX,
+					    ICE_DROP_PACKET);
 			ice_cfg_sw_lldp(vsi, true, false);
 			/* The Rx rule will only exist to remove if the LLDP FW
 			 * engine is currently stopped
@@ -2576,7 +2432,7 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		}
 	}
 
-	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	ice_fltr_remove_all(vsi);
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_delete(vsi);
 	ice_vsi_free_q_vectors(vsi);
@@ -2992,36 +2848,6 @@ void ice_update_rx_ring_stats(struct ice_ring *rx_ring, u64 pkts, u64 bytes)
 	u64_stats_update_end(&rx_ring->syncp);
 }
 
-/**
- * ice_vsi_cfg_mac_fltr - Add or remove a MAC address filter for a VSI
- * @vsi: the VSI being configured MAC filter
- * @macaddr: the MAC address to be added.
- * @set: Add or delete a MAC filter
- *
- * Adds or removes MAC address filter entry for VF VSI
- */
-enum ice_status
-ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set)
-{
-	LIST_HEAD(tmp_add_list);
-	enum ice_status status;
-
-	 /* Update MAC filter list to be added or removed for a VSI */
-	if (ice_add_mac_to_list(vsi, &tmp_add_list, macaddr)) {
-		status = ICE_ERR_NO_MEMORY;
-		goto cfg_mac_fltr_exit;
-	}
-
-	if (set)
-		status = ice_add_mac(&vsi->back->hw, &tmp_add_list);
-	else
-		status = ice_remove_mac(&vsi->back->hw, &tmp_add_list);
-
-cfg_mac_fltr_exit:
-	ice_free_fltr_list(ice_pf_to_dev(vsi->back), &tmp_add_list);
-	return status;
-}
-
 /**
  * ice_is_dflt_vsi_in_use - check if the default forwarding VSI is being used
  * @sw: switch to check if its default forwarding VSI is free
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 04ca00799364..9746de9b25fe 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -8,12 +8,6 @@
 
 const char *ice_vsi_type_str(enum ice_vsi_type vsi_type);
 
-int
-ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,
-		    const u8 *macaddr);
-
-void ice_free_fltr_list(struct device *dev, struct list_head *h);
-
 void ice_update_eth_stats(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
@@ -22,7 +16,8 @@ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
 
 void ice_vsi_cfg_msix(struct ice_vsi *vsi);
 
-int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid);
+int
+ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action);
 
 int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index cbfd54867be1..7fee3e4b39eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -8,6 +8,7 @@
 #include "ice.h"
 #include "ice_base.h"
 #include "ice_lib.h"
+#include "ice_fltr.h"
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "ice_devlink.h"
@@ -133,32 +134,18 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 static int ice_init_mac_fltr(struct ice_pf *pf)
 {
 	enum ice_status status;
-	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
+	u8 *perm_addr;
 
 	vsi = ice_get_main_vsi(pf);
 	if (!vsi)
 		return -EINVAL;
 
-	/* To add a MAC filter, first add the MAC to a list and then
-	 * pass the list to ice_add_mac.
-	 */
-
-	 /* Add a unicast MAC filter so the VSI can get its packets */
-	status = ice_vsi_cfg_mac_fltr(vsi, vsi->port_info->mac.perm_addr, true);
-	if (status)
-		goto unregister;
-
-	/* VSI needs to receive broadcast traffic, so add the broadcast
-	 * MAC address to the list as well.
-	 */
-	eth_broadcast_addr(broadcast);
-	status = ice_vsi_cfg_mac_fltr(vsi, broadcast, true);
-	if (status)
-		goto unregister;
+	perm_addr = vsi->port_info->mac.perm_addr;
+	status = ice_fltr_add_mac_and_broadcast(vsi, perm_addr, ICE_FWD_TO_VSI);
+	if (!status)
+		return 0;
 
-	return 0;
-unregister:
 	/* We aren't useful with no MAC filters, so unregister if we
 	 * had an error
 	 */
@@ -188,7 +175,8 @@ static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 
-	if (ice_add_mac_to_list(vsi, &vsi->tmp_sync_list, addr))
+	if (ice_fltr_add_mac_to_list(vsi, &vsi->tmp_sync_list, addr,
+				     ICE_FWD_TO_VSI))
 		return -EINVAL;
 
 	return 0;
@@ -209,7 +197,8 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 
-	if (ice_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr))
+	if (ice_fltr_add_mac_to_list(vsi, &vsi->tmp_unsync_list, addr,
+				     ICE_FWD_TO_VSI))
 		return -EINVAL;
 
 	return 0;
@@ -307,8 +296,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	}
 
 	/* Remove MAC addresses in the unsync list */
-	status = ice_remove_mac(hw, &vsi->tmp_unsync_list);
-	ice_free_fltr_list(dev, &vsi->tmp_unsync_list);
+	status = ice_fltr_remove_mac_list(vsi, &vsi->tmp_unsync_list);
+	ice_fltr_free_list(dev, &vsi->tmp_unsync_list);
 	if (status) {
 		netdev_err(netdev, "Failed to delete MAC filters\n");
 		/* if we failed because of alloc failures, just bail */
@@ -319,8 +308,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	}
 
 	/* Add MAC addresses in the sync list */
-	status = ice_add_mac(hw, &vsi->tmp_sync_list);
-	ice_free_fltr_list(dev, &vsi->tmp_sync_list);
+	status = ice_fltr_add_mac_list(vsi, &vsi->tmp_sync_list);
+	ice_fltr_free_list(dev, &vsi->tmp_sync_list);
 	/* If filter is added successfully or already exists, do not go into
 	 * 'if' condition and report it as error. Instead continue processing
 	 * rest of the function.
@@ -2521,7 +2510,7 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto,
 	/* Add a switch rule for this VLAN ID so its corresponding VLAN tagged
 	 * packets aren't pruned by the device's internal switch on Rx
 	 */
-	ret = ice_vsi_add_vlan(vsi, vid);
+	ret = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI);
 	if (!ret) {
 		vsi->vlan_ena = true;
 		set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
@@ -3718,20 +3707,14 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 		return -EBUSY;
 	}
 
-	/* When we change the MAC address we also have to change the MAC address
-	 * based filter rules that were created previously for the old MAC
-	 * address. So first, we remove the old filter rule using ice_remove_mac
-	 * and then create a new filter rule using ice_add_mac via
-	 * ice_vsi_cfg_mac_fltr function call for both add and/or remove
-	 * filters.
-	 */
-	status = ice_vsi_cfg_mac_fltr(vsi, netdev->dev_addr, false);
+	/* Clean up old MAC filter before changing the MAC address */
+	status = ice_fltr_remove_mac(vsi, netdev->dev_addr, ICE_FWD_TO_VSI);
 	if (status) {
 		err = -EADDRNOTAVAIL;
 		goto err_update_filters;
 	}
 
-	status = ice_vsi_cfg_mac_fltr(vsi, mac, true);
+	status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI);
 	if (status) {
 		err = -EADDRNOTAVAIL;
 		goto err_update_filters;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 9fb74a390b8c..62c100d47592 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -4,6 +4,7 @@
 #include "ice.h"
 #include "ice_base.h"
 #include "ice_lib.h"
+#include "ice_fltr.h"
 
 /**
  * ice_validate_vf_id - helper to check if VF ID is valid
@@ -548,7 +549,6 @@ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
 static int ice_alloc_vsi_res(struct ice_vf *vf)
 {
 	struct ice_pf *pf = vf->pf;
-	LIST_HEAD(tmp_add_list);
 	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
 	struct device *dev;
@@ -570,7 +570,8 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	/* Check if port VLAN exist before, and restore it accordingly */
 	if (vf->port_vlan_info) {
 		ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true);
-		if (ice_vsi_add_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK))
+		if (ice_vsi_add_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK,
+				     ICE_FWD_TO_VSI))
 			dev_warn(ice_pf_to_dev(pf), "Failed to add Port VLAN %d filter for VF %d\n",
 				 vf->port_vlan_info & VLAN_VID_MASK, vf->vf_id);
 	} else {
@@ -579,27 +580,23 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 		 * untagged broadcast/multicast traffic seen on the VF
 		 * interface.
 		 */
-		if (ice_vsi_add_vlan(vsi, 0))
+		if (ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI))
 			dev_warn(ice_pf_to_dev(pf), "Failed to add VLAN 0 filter for VF %d, MDD events will trigger. Reset the VF, disable spoofchk, or enable 8021q module on the guest\n",
 				 vf->vf_id);
 	}
 
-	eth_broadcast_addr(broadcast);
-
-	status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast);
-	if (status)
-		goto ice_alloc_vsi_res_exit;
-
 	if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) {
-		status = ice_add_mac_to_list(vsi, &tmp_add_list,
-					     vf->dflt_lan_addr.addr);
+		status = ice_fltr_add_mac(vsi, vf->dflt_lan_addr.addr,
+					  ICE_FWD_TO_VSI);
 		if (status)
 			goto ice_alloc_vsi_res_exit;
 	}
 
-	status = ice_add_mac(&pf->hw, &tmp_add_list);
+	eth_broadcast_addr(broadcast);
+	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
 	if (status)
-		dev_err(dev, "could not add mac filters error %d\n", status);
+		dev_err(dev, "could not add mac filters error %d\n",
+			status);
 	else
 		vf->num_mac = 1;
 
@@ -610,7 +607,6 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	 * more vectors.
 	 */
 ice_alloc_vsi_res_exit:
-	ice_free_fltr_list(dev, &tmp_add_list);
 	return status;
 }
 
@@ -2807,7 +2803,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 		return -EPERM;
 	}
 
-	status = ice_vsi_cfg_mac_fltr(vsi, mac_addr, true);
+	status = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
 	if (status == ICE_ERR_ALREADY_EXISTS) {
 		dev_err(dev, "MAC %pM already exists for VF %d\n", mac_addr,
 			vf->vf_id);
@@ -2844,7 +2840,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 	    ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr))
 		return 0;
 
-	status = ice_vsi_cfg_mac_fltr(vsi, mac_addr, false);
+	status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI);
 	if (status == ICE_ERR_DOES_NOT_EXIST) {
 		dev_err(dev, "MAC %pM does not exist for VF %d\n", mac_addr,
 			vf->vf_id);
@@ -3088,7 +3084,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 		/* add VLAN 0 filter back when transitioning from port VLAN to
 		 * no port VLAN. No change to old port VLAN on failure.
 		 */
-		ret = ice_vsi_add_vlan(vsi, 0);
+		ret = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI);
 		if (ret)
 			return ret;
 		ret = ice_vsi_manage_pvid(vsi, 0, false);
@@ -3101,7 +3097,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 			 vlan_id, qos, vf_id);
 
 		/* add VLAN filter for the port VLAN */
-		ret = ice_vsi_add_vlan(vsi, vlan_id);
+		ret = ice_vsi_add_vlan(vsi, vlan_id, ICE_FWD_TO_VSI);
 		if (ret)
 			return ret;
 	}
@@ -3222,7 +3218,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 			if (!vid)
 				continue;
 
-			status = ice_vsi_add_vlan(vsi, vid);
+			status = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI);
 			if (status) {
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
-- 
cgit v1.2.3


From 757976ab16be0d07e316998182d82ea7fcf561e2 Mon Sep 17 00:00:00 2001
From: Lihong Yang <lihong.yang@intel.com>
Date: Thu, 7 May 2020 17:41:09 -0700
Subject: ice: Fix check for removing/adding mac filters

In function ice_set_mac_address, we will remove old dev_addr before
adding the new MAC. In the removing and adding process of the MAC,
there is no need to return error if the check finds the to-be-removed
dev_addr does not exist in the MAC filter list or the to-be-added mac
already exists, keep going or return success accordingly.

Signed-off-by: Lihong Yang <lihong.yang@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 7fee3e4b39eb..6ac3e5540119 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3707,19 +3707,24 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 		return -EBUSY;
 	}
 
-	/* Clean up old MAC filter before changing the MAC address */
+	/* Clean up old MAC filter. Not an error if old filter doesn't exist */
 	status = ice_fltr_remove_mac(vsi, netdev->dev_addr, ICE_FWD_TO_VSI);
-	if (status) {
+	if (status && status != ICE_ERR_DOES_NOT_EXIST) {
 		err = -EADDRNOTAVAIL;
 		goto err_update_filters;
 	}
 
+	/* Add filter for new MAC. If filter exists, just return success */
 	status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI);
-	if (status) {
-		err = -EADDRNOTAVAIL;
-		goto err_update_filters;
+	if (status == ICE_ERR_ALREADY_EXISTS) {
+		netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac);
+		return 0;
 	}
 
+	/* error if the new filter addition failed */
+	if (status)
+		err = -EADDRNOTAVAIL;
+
 err_update_filters:
 	if (err) {
 		netdev_err(netdev, "can't set MAC %pM. filter update failed\n",
-- 
cgit v1.2.3


From 92ace4824c1cf0cf2094e51501e3c48176a4f2a2 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Thu, 7 May 2020 17:41:10 -0700
Subject: ice: remove unnecessary expression that is always true

The else conditional expression is always true due to the if conditional
expression; remove it and add a comment to make it obvious still.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6ac3e5540119..fffb3433969c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -346,7 +346,8 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 				vsi->current_netdev_flags &= ~IFF_ALLMULTI;
 				goto out_promisc;
 			}
-		} else if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) {
+		} else {
+			/* !(vsi->current_netdev_flags & IFF_ALLMULTI) */
 			if (vsi->vlan_ena)
 				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
 			else
-- 
cgit v1.2.3


From 86a2e00d20bd4f7fd0efd1cccd8d5a5d7270b640 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Thu, 7 May 2020 17:41:11 -0700
Subject: ice: remove unnecessary check

The variable status cannot be zero due to a prior check of it; remove this
check.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index fffb3433969c..c3e5c4334e26 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -149,7 +149,7 @@ static int ice_init_mac_fltr(struct ice_pf *pf)
 	/* We aren't useful with no MAC filters, so unregister if we
 	 * had an error
 	 */
-	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
+	if (vsi->netdev->reg_state == NETREG_REGISTERED) {
 		dev_err(ice_pf_to_dev(pf), "Could not add MAC filters error %s. Unregistering device\n",
 			ice_stat_str(status));
 		unregister_netdev(vsi->netdev);
-- 
cgit v1.2.3


From c522d1f686752d9f85cedc3e3bb7423c5abd03e5 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Thu, 7 May 2020 17:41:12 -0700
Subject: ice: remove unnecessary backslash

Self-explanatory.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 8767a78038e0..979e9c6254af 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -541,7 +541,7 @@ struct ice_sw_rule_lkup_rx_tx {
 #define ICE_SINGLE_ACT_OTHER_ACTS		0x3
 #define ICE_SINGLE_OTHER_ACT_IDENTIFIER_S	17
 #define ICE_SINGLE_OTHER_ACT_IDENTIFIER_M	\
-				(0x3 << \ ICE_SINGLE_OTHER_ACT_IDENTIFIER_S)
+				(0x3 << ICE_SINGLE_OTHER_ACT_IDENTIFIER_S)
 
 	/* Bit 17:18 - Defines other actions */
 	/* Other action = 0 - Mirror VSI */
-- 
cgit v1.2.3


From 5757cc7c8b71d5114aca0034cee42d22e6977d19 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Thu, 7 May 2020 17:41:13 -0700
Subject: ice: Rename build_ctob to ice_build_ctob

To make the function easier to identify as being part of the ice driver,
prepend ice to the function name.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 11 ++++++-----
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c |  4 ++--
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h |  2 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c      |  4 ++--
 4 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 05d1077f80c3..0d90e32efab9 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1680,7 +1680,8 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 		 */
 		while (unlikely(size > ICE_MAX_DATA_PER_TXD)) {
 			tx_desc->cmd_type_offset_bsz =
-				build_ctob(td_cmd, td_offset, max_data, td_tag);
+				ice_build_ctob(td_cmd, td_offset, max_data,
+					       td_tag);
 
 			tx_desc++;
 			i++;
@@ -1700,8 +1701,8 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 		if (likely(!data_len))
 			break;
 
-		tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
-							  size, td_tag);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(td_cmd, td_offset,
+							      size, td_tag);
 
 		tx_desc++;
 		i++;
@@ -1732,8 +1733,8 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 
 	/* write last descriptor with RS and EOP bits */
 	td_cmd |= (u64)ICE_TXD_LAST_DESC_CMD;
-	tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size,
-						  td_tag);
+	tx_desc->cmd_type_offset_bsz =
+			ice_build_ctob(td_cmd, td_offset, size, td_tag);
 
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 9d6512f96b8c..1ba97172d8d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -232,8 +232,8 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring)
 
 	tx_desc = ICE_TX_DESC(xdp_ring, i);
 	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = build_ctob(ICE_TXD_LAST_DESC_CMD, 0,
-						  size, 0);
+	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0,
+						      size, 0);
 
 	/* Make certain all of the status bits have been updated
 	 * before next_to_watch is written.
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index af0fca5b91ff..58ff58f0f972 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -22,7 +22,7 @@ ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, const u16 stat_err_bits)
 }
 
 static inline __le64
-build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
+ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 {
 	return cpu_to_le64(ICE_TX_DESC_DTYPE_DATA |
 			   (td_cmd    << ICE_TXD_QW1_CMD_S) |
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 23e5515d4527..20ac54e3156d 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -988,8 +988,8 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 
 		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
 		tx_desc->buf_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz = build_ctob(ICE_TXD_LAST_DESC_CMD,
-							  0, desc.len, 0);
+		tx_desc->cmd_type_offset_bsz =
+			ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0, desc.len, 0);
 
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
-- 
cgit v1.2.3


From 8ce84271697a2346e88582480b26b7e244a8603a Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dbezrukov@marvell.com>
Date: Fri, 22 May 2020 11:19:37 +0300
Subject: net: atlantic: changes for multi-TC support

This patch contains the following changes:
* access cfg via aq_nic_get_cfg() in aq_nic_start() and aq_nic_map_skb();
* call aq_nic_get_dev() just once in aq_nic_map_skb();
* move ring allocation/deallocation out of aq_vec_alloc()/aq_vec_free();
* add the missing aq_nic_deinit() in atl_resume_common();
* rename 'tcs' field to 'tcs_max' in aq_hw_caps_s to differentiate it from
  the 'tcs' field in aq_nic_cfg_s, which is used for the current number of
  TCs;
* update _TC_MAX defines to the actual number of supported TCs;
* move tx_tc_mode register defines slightly higher (just to keep the order
  of definitions);
* separate variables for TX/RX buff_size in hw_atl*_hw_qos_set();
* use AQ_HW_*_TC instead of hardcoded magic numbers;
* actually use the 'ret' value in aq_mdo_add_secy();

Signed-off-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Co-developed-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  4 +-
 drivers/net/ethernet/aquantia/atlantic/aq_macsec.c |  2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 43 +++++++++++++-------
 .../net/ethernet/aquantia/atlantic/aq_pci_func.c   |  3 ++
 drivers/net/ethernet/aquantia/atlantic/aq_vec.c    | 47 ++++++++++++++--------
 drivers/net/ethernet/aquantia/atlantic/aq_vec.h    |  3 ++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c  |  2 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 34 +++++++---------
 .../aquantia/atlantic/hw_atl/hw_atl_b0_internal.h  |  2 +-
 .../aquantia/atlantic/hw_atl/hw_atl_llh_internal.h | 31 ++++++++------
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   |  4 +-
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |  2 +-
 12 files changed, 105 insertions(+), 72 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 03fea9469f01..703ef8d064a2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -46,7 +46,7 @@ struct aq_hw_caps_s {
 	u32 mac_regs_count;
 	u32 hw_alive_check_addr;
 	u8 msix_irqs;
-	u8 tcs;
+	u8 tcs_max;
 	u8 rxd_alignment;
 	u8 rxd_size;
 	u8 txd_alignment;
@@ -120,6 +120,8 @@ struct aq_stats_s {
 
 #define AQ_HW_MULTICAST_ADDRESS_MAX     32U
 
+#define AQ_HW_PTP_TC                    2U
+
 #define AQ_HW_LED_BLINK    0x2U
 #define AQ_HW_LED_DEFAULT  0x0U
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
index 91870ceaf3fe..4a6dfac857ca 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
@@ -478,7 +478,7 @@ static int aq_mdo_add_secy(struct macsec_context *ctx)
 
 	set_bit(txsc_idx, &cfg->txsc_idx_busy);
 
-	return 0;
+	return ret;
 }
 
 static int aq_mdo_upd_secy(struct macsec_context *ctx)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1c6d12deb47a..b003f1035701 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -399,9 +399,15 @@ int aq_nic_init(struct aq_nic_s *self)
 		err = aq_phy_init(self->aq_hw);
 	}
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
+	for (i = 0U; i < self->aq_vecs; i++) {
+		aq_vec = self->aq_vec[i];
+		err = aq_vec_ring_alloc(aq_vec, self, i,
+					aq_nic_get_cfg(self));
+		if (err)
+			goto err_exit;
+
 		aq_vec_init(aq_vec, self->aq_hw_ops, self->aq_hw);
+	}
 
 	err = aq_ptp_init(self, self->irqvecs - 1);
 	if (err < 0)
@@ -424,9 +430,12 @@ err_exit:
 int aq_nic_start(struct aq_nic_s *self)
 {
 	struct aq_vec_s *aq_vec = NULL;
+	struct aq_nic_cfg_s *cfg;
 	unsigned int i = 0U;
 	int err = 0;
 
+	cfg = aq_nic_get_cfg(self);
+
 	err = self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
 						     self->mc_list.ar,
 						     self->mc_list.count);
@@ -464,7 +473,7 @@ int aq_nic_start(struct aq_nic_s *self)
 	timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0);
 	aq_nic_service_timer_cb(&self->service_timer);
 
-	if (self->aq_nic_cfg.is_polling) {
+	if (cfg->is_polling) {
 		timer_setup(&self->polling_timer, aq_nic_polling_timer_cb, 0);
 		mod_timer(&self->polling_timer, jiffies +
 			  AQ_CFG_POLLING_TIMER_INTERVAL);
@@ -482,16 +491,16 @@ int aq_nic_start(struct aq_nic_s *self)
 		if (err < 0)
 			goto err_exit;
 
-		if (self->aq_nic_cfg.link_irq_vec) {
+		if (cfg->link_irq_vec) {
 			int irqvec = pci_irq_vector(self->pdev,
-						   self->aq_nic_cfg.link_irq_vec);
+						    cfg->link_irq_vec);
 			err = request_threaded_irq(irqvec, NULL,
 						   aq_linkstate_threaded_isr,
 						   IRQF_SHARED | IRQF_ONESHOT,
 						   self->ndev->name, self);
 			if (err < 0)
 				goto err_exit;
-			self->msix_entry_mask |= (1 << self->aq_nic_cfg.link_irq_vec);
+			self->msix_entry_mask |= (1 << cfg->link_irq_vec);
 		}
 
 		err = self->aq_hw_ops->hw_irq_enable(self->aq_hw,
@@ -518,6 +527,8 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 			    struct aq_ring_s *ring)
 {
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+	struct device *dev = aq_nic_get_dev(self);
 	struct aq_ring_buff_s *first = NULL;
 	u8 ipver = ip_hdr(skb)->version;
 	struct aq_ring_buff_s *dx_buff;
@@ -559,7 +570,7 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 		need_context_tag = true;
 	}
 
-	if (self->aq_nic_cfg.is_vlan_tx_insert && skb_vlan_tag_present(skb)) {
+	if (cfg->is_vlan_tx_insert && skb_vlan_tag_present(skb)) {
 		dx_buff->vlan_tx_tag = skb_vlan_tag_get(skb);
 		dx_buff->len_pkt = skb->len;
 		dx_buff->is_vlan = 1U;
@@ -574,12 +585,12 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 	}
 
 	dx_buff->len = skb_headlen(skb);
-	dx_buff->pa = dma_map_single(aq_nic_get_dev(self),
+	dx_buff->pa = dma_map_single(dev,
 				     skb->data,
 				     dx_buff->len,
 				     DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+	if (unlikely(dma_mapping_error(dev, dx_buff->pa))) {
 		ret = 0;
 		goto exit;
 	}
@@ -611,13 +622,13 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 			else
 				buff_size = frag_len;
 
-			frag_pa = skb_frag_dma_map(aq_nic_get_dev(self),
+			frag_pa = skb_frag_dma_map(dev,
 						   frag,
 						   buff_offset,
 						   buff_size,
 						   DMA_TO_DEVICE);
 
-			if (unlikely(dma_mapping_error(aq_nic_get_dev(self),
+			if (unlikely(dma_mapping_error(dev,
 						       frag_pa)))
 				goto mapping_error;
 
@@ -651,12 +662,12 @@ mapping_error:
 		if (!(dx_buff->is_gso_tcp || dx_buff->is_gso_udp) &&
 		    !dx_buff->is_vlan && dx_buff->pa) {
 			if (unlikely(dx_buff->is_sop)) {
-				dma_unmap_single(aq_nic_get_dev(self),
+				dma_unmap_single(dev,
 						 dx_buff->pa,
 						 dx_buff->len,
 						 DMA_TO_DEVICE);
 			} else {
-				dma_unmap_page(aq_nic_get_dev(self),
+				dma_unmap_page(dev,
 					       dx_buff->pa,
 					       dx_buff->len,
 					       DMA_TO_DEVICE);
@@ -1145,9 +1156,11 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	if (!self)
 		goto err_exit;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
+	for (i = 0U; i < self->aq_vecs; i++) {
+		aq_vec = self->aq_vec[i];
 		aq_vec_deinit(aq_vec);
+		aq_vec_ring_free(aq_vec);
+	}
 
 	aq_ptp_unregister(self);
 	aq_ptp_ring_deinit(self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index d10fff8a8c71..41c0f560f95b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -431,6 +431,9 @@ static int atl_resume_common(struct device *dev, bool deep)
 	netif_tx_start_all_queues(nic->ndev);
 
 err_exit:
+	if (ret < 0)
+		aq_nic_deinit(nic, true);
+
 	rtnl_unlock();
 
 	return ret;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index f40a427970dc..d5650cd6e236 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -103,16 +103,11 @@ err_exit:
 struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 			      struct aq_nic_cfg_s *aq_nic_cfg)
 {
-	struct aq_ring_s *ring = NULL;
 	struct aq_vec_s *self = NULL;
-	unsigned int i = 0U;
-	int err = 0;
 
 	self = kzalloc(sizeof(*self), GFP_KERNEL);
-	if (!self) {
-		err = -ENOMEM;
+	if (!self)
 		goto err_exit;
-	}
 
 	self->aq_nic = aq_nic;
 	self->aq_ring_param.vec_idx = idx;
@@ -128,10 +123,19 @@ struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 	netif_napi_add(aq_nic_get_ndev(aq_nic), &self->napi,
 		       aq_vec_poll, AQ_CFG_NAPI_WEIGHT);
 
+err_exit:
+	return self;
+}
+
+int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
+		      unsigned int idx, struct aq_nic_cfg_s *aq_nic_cfg)
+{
+	struct aq_ring_s *ring = NULL;
+	unsigned int i = 0U;
+	int err = 0;
+
 	for (i = 0; i < aq_nic_cfg->tcs; ++i) {
-		unsigned int idx_ring = AQ_NIC_TCVEC2RING(self->nic,
-						self->tx_rings,
-						self->aq_ring_param.vec_idx);
+		unsigned int idx_ring = AQ_NIC_TCVEC2RING(aq_nic, i, idx);
 
 		ring = aq_ring_tx_alloc(&self->ring[i][AQ_VEC_TX_ID], aq_nic,
 					idx_ring, aq_nic_cfg);
@@ -156,11 +160,11 @@ struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 
 err_exit:
 	if (err < 0) {
-		aq_vec_free(self);
+		aq_vec_ring_free(self);
 		self = NULL;
 	}
 
-	return self;
+	return err;
 }
 
 int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops,
@@ -269,6 +273,18 @@ err_exit:;
 }
 
 void aq_vec_free(struct aq_vec_s *self)
+{
+	if (!self)
+		goto err_exit;
+
+	netif_napi_del(&self->napi);
+
+	kfree(self);
+
+err_exit:;
+}
+
+void aq_vec_ring_free(struct aq_vec_s *self)
 {
 	struct aq_ring_s *ring = NULL;
 	unsigned int i = 0U;
@@ -279,13 +295,12 @@ void aq_vec_free(struct aq_vec_s *self)
 	for (i = 0U, ring = self->ring[0];
 		self->tx_rings > i; ++i, ring = self->ring[i]) {
 		aq_ring_free(&ring[AQ_VEC_TX_ID]);
-		aq_ring_free(&ring[AQ_VEC_RX_ID]);
+		if (i < self->rx_rings)
+			aq_ring_free(&ring[AQ_VEC_RX_ID]);
 	}
 
-	netif_napi_del(&self->napi);
-
-	kfree(self);
-
+	self->tx_rings = 0;
+	self->rx_rings = 0;
 err_exit:;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
index 0fe8e0904c7f..0ee86b26df8a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
@@ -25,10 +25,13 @@ irqreturn_t aq_vec_isr(int irq, void *private);
 irqreturn_t aq_vec_isr_legacy(int irq, void *private);
 struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 			      struct aq_nic_cfg_s *aq_nic_cfg);
+int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
+		      unsigned int idx, struct aq_nic_cfg_s *aq_nic_cfg);
 int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops,
 		struct aq_hw_s *aq_hw);
 void aq_vec_deinit(struct aq_vec_s *self);
 void aq_vec_free(struct aq_vec_s *self);
+void aq_vec_ring_free(struct aq_vec_s *self);
 int aq_vec_start(struct aq_vec_s *self);
 void aq_vec_stop(struct aq_vec_s *self);
 cpumask_t *aq_vec_get_affinity_mask(struct aq_vec_s *self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 1b0670a8ae33..88b17cf77625 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -21,7 +21,7 @@
 	.msix_irqs = 4U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_A0_RSS_MAX,	  \
-	.tcs = HW_ATL_A0_TC_MAX,	  \
+	.tcs_max = HW_ATL_A0_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL_A0_RXD_SIZE,   \
 	.rxds_max = HW_ATL_A0_MAX_RXD,    \
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index fa3cd7e9954b..bee4fb3c8741 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -23,7 +23,7 @@
 	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_B0_RSS_MAX,	  \
-	.tcs = HW_ATL_B0_TC_MAX,	  \
+	.tcs_max = HW_ATL_B0_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL_B0_RXD_SIZE,   \
 	.rxds_max = HW_ATL_B0_MAX_RXD,    \
@@ -116,8 +116,9 @@ static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc)
 
 static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 {
+	u32 tx_buff_size = HW_ATL_B0_TXBUF_MAX;
+	u32 rx_buff_size = HW_ATL_B0_RXBUF_MAX;
 	unsigned int i_priority = 0U;
-	u32 buff_size = 0U;
 	u32 tc = 0U;
 
 	/* TPS Descriptor rate init */
@@ -131,8 +132,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	tc = 0;
-
 	/* TX Packet Scheduler Data TC0 */
 	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
 	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
@@ -140,46 +139,41 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
 
 	/* Tx buf size TC0 */
-	buff_size = HW_ATL_B0_TXBUF_MAX - HW_ATL_B0_PTP_TXBUF_SIZE;
+	tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
 
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, buff_size, tc);
+	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self,
-						   (buff_size *
+						   (tx_buff_size *
 						   (1024 / 32U) * 66U) /
 						   100U, tc);
 	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self,
-						   (buff_size *
+						   (tx_buff_size *
 						   (1024 / 32U) * 50U) /
 						   100U, tc);
 	/* Init TC2 for PTP_TX */
-	tc = 2;
-
 	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_TXBUF_SIZE,
-					       tc);
+					       AQ_HW_PTP_TC);
 
 	/* QoS Rx buf size per TC */
-	tc = 0;
-	buff_size = HW_ATL_B0_RXBUF_MAX - HW_ATL_B0_PTP_RXBUF_SIZE;
+	rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
 
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, buff_size, tc);
+	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
 	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self,
-						   (buff_size *
+						   (rx_buff_size *
 						   (1024U / 32U) * 66U) /
 						   100U, tc);
 	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self,
-						   (buff_size *
+						   (rx_buff_size *
 						   (1024U / 32U) * 50U) /
 						   100U, tc);
 
 	hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
 
 	/* Init TC2 for PTP_RX */
-	tc = 2;
-
 	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_RXBUF_SIZE,
-					       tc);
+					       AQ_HW_PTP_TC);
 	/* No flow control for PTP */
-	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, tc);
+	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, AQ_HW_PTP_TC);
 
 	/* QoS 802.1p priority -> TC mapping */
 	for (i_priority = 8U; i_priority--;)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 7ab23a1751d3..4fba4e0928c7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -75,7 +75,7 @@
 #define HW_ATL_B0_RSS_HASHKEY_BITS 320U
 
 #define HW_ATL_B0_TCRSS_4_8  1
-#define HW_ATL_B0_TC_MAX 1U
+#define HW_ATL_B0_TC_MAX 8U
 #define HW_ATL_B0_RSS_MAX 8U
 
 #define HW_ATL_B0_LRO_RXD_MAX 16U
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index 18de2f7b8959..5d86ffab4ece 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -2038,6 +2038,24 @@
 /* default value of bitfield lso_tcp_flag_mid[b:0] */
 #define HW_ATL_THM_LSO_TCP_FLAG_MID_DEFAULT 0x0
 
+/* tx tx_tc_mode bitfield definitions
+ * preprocessor definitions for the bitfield "tx_tc_mode".
+ * port="pif_tpb_tx_tc_mode_i,pif_tps_tx_tc_mode_i"
+ */
+
+/* register address for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
+/* bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
+/* inverted bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
+/* lower bit position of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
+/* width of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
+/* default value of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
+
 /* tx tx_buf_en bitfield definitions
  * preprocessor definitions for the bitfield "tx_buf_en".
  * port="pif_tpb_tx_buf_en_i"
@@ -2056,19 +2074,6 @@
 /* default value of bitfield tx_buf_en */
 #define HW_ATL_TPB_TX_BUF_EN_DEFAULT 0x0
 
-/* register address for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
-/* bitmask for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
-/* inverted bitmask for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
-/* lower bit position of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
-/* width of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
-/* default value of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
-
 /* tx tx{b}_hi_thresh[c:0] bitfield definitions
  * preprocessor definitions for the bitfield "tx{b}_hi_thresh[c:0]".
  * parameter: buffer {b} | stride size 0x10 | range [0, 7]
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 6f2b33ae3d06..ccdb74562270 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -23,7 +23,7 @@ static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL2_RSS_MAX,	  \
-	.tcs = HW_ATL2_TC_MAX,	  \
+	.tcs_max = HW_ATL2_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL2_RXD_SIZE,   \
 	.rxds_max = HW_ATL2_MAX_RXD,    \
@@ -126,8 +126,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	tc = 0;
-
 	/* TX Packet Scheduler Data TC0 */
 	hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0, tc);
 	hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index e66b3583bfe9..be0c049ea582 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -31,7 +31,7 @@
 
 #define HW_ATL2_RSS_REDIRECTION_MAX 64U
 
-#define HW_ATL2_TC_MAX 1U
+#define HW_ATL2_TC_MAX 8U
 #define HW_ATL2_RSS_MAX 8U
 
 #define HW_ATL2_INTR_MODER_MAX  0x1FF
-- 
cgit v1.2.3


From 593dd0fc202eed27de07c5df9ef24a3c00cf0c09 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dbezrukov@marvell.com>
Date: Fri, 22 May 2020 11:19:38 +0300
Subject: net: atlantic: move PTP TC initialization to a separate function

This patch moves the PTP TC initialization into a separate function.

Signed-off-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Co-developed-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 31 +++++++++++++---------
 1 file changed, 19 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index bee4fb3c8741..0ff3f6eea022 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -114,6 +114,21 @@ static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc)
 	return 0;
 }
 
+static int hw_atl_b0_tc_ptp_set(struct aq_hw_s *self)
+{
+	/* Init TC2 for PTP_TX */
+	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_TXBUF_SIZE,
+					       AQ_HW_PTP_TC);
+
+	/* Init TC2 for PTP_RX */
+	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_RXBUF_SIZE,
+					       AQ_HW_PTP_TC);
+	/* No flow control for PTP */
+	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, AQ_HW_PTP_TC);
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 {
 	u32 tx_buff_size = HW_ATL_B0_TXBUF_MAX;
@@ -121,6 +136,9 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	unsigned int i_priority = 0U;
 	u32 tc = 0U;
 
+	tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
+	rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
+
 	/* TPS Descriptor rate init */
 	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
 	hw_atl_tps_tx_pkt_shed_desc_rate_lim_set(self, 0xA);
@@ -139,8 +157,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
 
 	/* Tx buf size TC0 */
-	tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
-
 	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self,
 						   (tx_buff_size *
@@ -150,13 +166,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 						   (tx_buff_size *
 						   (1024 / 32U) * 50U) /
 						   100U, tc);
-	/* Init TC2 for PTP_TX */
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_TXBUF_SIZE,
-					       AQ_HW_PTP_TC);
 
 	/* QoS Rx buf size per TC */
-	rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
-
 	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
 	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self,
 						   (rx_buff_size *
@@ -169,11 +180,7 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 
 	hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
 
-	/* Init TC2 for PTP_RX */
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_RXBUF_SIZE,
-					       AQ_HW_PTP_TC);
-	/* No flow control for PTP */
-	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, AQ_HW_PTP_TC);
+	hw_atl_b0_tc_ptp_set(self);
 
 	/* QoS 802.1p priority -> TC mapping */
 	for (i_priority = 8U; i_priority--;)
-- 
cgit v1.2.3


From 0aa7bc3ee4652e0790f9b42c93c769b59b9f2308 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dbezrukov@marvell.com>
Date: Fri, 22 May 2020 11:19:39 +0300
Subject: net: atlantic: changes for multi-TC support

This patch contains the following changes:
* add cfg->is_ptp (used for PTP enable/disable switch, which
  is described in more details below);
* add cfg->tc_mode (A1 supports 2 HW modes only);
* setup queue to TC mapping based on TC mode on A2;
* remove hw_tx_tc_mode_get / hw_rx_tc_mode_get hw_ops.

In the first generation of our hardware (A1), a whole traffic class is
consumed for PTP handling in FW (FW uses it to send the ptp data and to
send back timestamps).
The 'is_ptp' flag introduced in this patch will be used in to automatically
disable PTP when a conflicting configuration is detected, e.g. when
multiple TCs are enabled.

Signed-off-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Co-developed-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     | 10 +++---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 26 +++++++++-----
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |  2 ++
 drivers/net/ethernet/aquantia/atlantic/aq_ptp.c    | 27 +++++++--------
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 25 ++++----------
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 40 ++++++++++++++++------
 6 files changed, 75 insertions(+), 55 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 703ef8d064a2..c3df9da6088c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -18,6 +18,12 @@
 #define AQ_HW_MAC_COUNTER_HZ   312500000ll
 #define AQ_HW_PHY_COUNTER_HZ   160000000ll
 
+enum aq_tc_mode {
+	AQ_TC_MODE_INVALID = -1,
+	AQ_TC_MODE_8TCS,
+	AQ_TC_MODE_4TCS,
+};
+
 #define AQ_RX_FIRST_LOC_FVLANID     0U
 #define AQ_RX_LAST_LOC_FVLANID	   15U
 #define AQ_RX_FIRST_LOC_FETHERT    16U
@@ -281,10 +287,6 @@ struct aq_hw_ops {
 	int (*hw_set_offload)(struct aq_hw_s *self,
 			      struct aq_nic_cfg_s *aq_nic_cfg);
 
-	int (*hw_tx_tc_mode_get)(struct aq_hw_s *self, u32 *tc_mode);
-
-	int (*hw_rx_tc_mode_get)(struct aq_hw_s *self, u32 *tc_mode);
-
 	int (*hw_ring_hwts_rx_fill)(struct aq_hw_s *self,
 				    struct aq_ring_s *aq_ring);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index b003f1035701..3eeb652068e2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -89,6 +89,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->is_autoneg = AQ_CFG_IS_AUTONEG_DEF;
 
 	cfg->is_lro = AQ_CFG_IS_LRO_DEF;
+	cfg->is_ptp = true;
 
 	/*descriptors */
 	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
@@ -122,6 +123,11 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 		cfg->vecs = 1U;
 	}
 
+	if (cfg->vecs <= 4)
+		cfg->tc_mode = AQ_TC_MODE_8TCS;
+	else
+		cfg->tc_mode = AQ_TC_MODE_4TCS;
+
 	/* Check if we have enough vectors allocated for
 	 * link status IRQ. If no - we'll know link state from
 	 * slower service task.
@@ -409,17 +415,19 @@ int aq_nic_init(struct aq_nic_s *self)
 		aq_vec_init(aq_vec, self->aq_hw_ops, self->aq_hw);
 	}
 
-	err = aq_ptp_init(self, self->irqvecs - 1);
-	if (err < 0)
-		goto err_exit;
+	if (aq_nic_get_cfg(self)->is_ptp) {
+		err = aq_ptp_init(self, self->irqvecs - 1);
+		if (err < 0)
+			goto err_exit;
 
-	err = aq_ptp_ring_alloc(self);
-	if (err < 0)
-		goto err_exit;
+		err = aq_ptp_ring_alloc(self);
+		if (err < 0)
+			goto err_exit;
 
-	err = aq_ptp_ring_init(self);
-	if (err < 0)
-		goto err_exit;
+		err = aq_ptp_ring_init(self);
+		if (err < 0)
+			goto err_exit;
+	}
 
 	netif_carrier_off(self->ndev);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 0663b8d0220d..3434f8206823 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -59,6 +59,8 @@ struct aq_nic_cfg_s {
 	bool is_polling;
 	bool is_rss;
 	bool is_lro;
+	bool is_ptp;
+	enum aq_tc_mode tc_mode;
 	u32 priv_flags;
 	u8  tcs;
 	struct aq_rss_parameters aq_rss;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index 58e8c641e8b3..599ced261b2a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -945,26 +945,29 @@ void aq_ptp_ring_deinit(struct aq_nic_s *aq_nic)
 #define PTP_4TC_RING_IDX            16
 #define PTP_HWST_RING_IDX           31
 
+/* Index must be 8 (8 TCs) or 16 (4 TCs).
+ * It depends on Traffic Class mode.
+ */
+static unsigned int ptp_ring_idx(const enum aq_tc_mode tc_mode)
+{
+	if (tc_mode == AQ_TC_MODE_8TCS)
+		return PTP_8TC_RING_IDX;
+
+	return PTP_4TC_RING_IDX;
+}
+
 int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 {
 	struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp;
 	unsigned int tx_ring_idx, rx_ring_idx;
 	struct aq_ring_s *hwts;
-	u32 tx_tc_mode, rx_tc_mode;
 	struct aq_ring_s *ring;
 	int err;
 
 	if (!aq_ptp)
 		return 0;
 
-	/* Index must to be 8 (8 TCs) or 16 (4 TCs).
-	 * It depends from Traffic Class mode.
-	 */
-	aq_nic->aq_hw_ops->hw_tx_tc_mode_get(aq_nic->aq_hw, &tx_tc_mode);
-	if (tx_tc_mode == 0)
-		tx_ring_idx = PTP_8TC_RING_IDX;
-	else
-		tx_ring_idx = PTP_4TC_RING_IDX;
+	tx_ring_idx = ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
 	ring = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic,
 				tx_ring_idx, &aq_nic->aq_nic_cfg);
@@ -973,11 +976,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 		goto err_exit;
 	}
 
-	aq_nic->aq_hw_ops->hw_rx_tc_mode_get(aq_nic->aq_hw, &rx_tc_mode);
-	if (rx_tc_mode == 0)
-		rx_ring_idx = PTP_8TC_RING_IDX;
-	else
-		rx_ring_idx = PTP_4TC_RING_IDX;
+	rx_ring_idx = ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
 	ring = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic,
 				rx_ring_idx, &aq_nic->aq_nic_cfg);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 0ff3f6eea022..7caf586ea56c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -131,13 +131,16 @@ static int hw_atl_b0_tc_ptp_set(struct aq_hw_s *self)
 
 static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 {
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	u32 tx_buff_size = HW_ATL_B0_TXBUF_MAX;
 	u32 rx_buff_size = HW_ATL_B0_RXBUF_MAX;
 	unsigned int i_priority = 0U;
 	u32 tc = 0U;
 
-	tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
-	rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
+	if (cfg->is_ptp) {
+		tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
+		rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
+	}
 
 	/* TPS Descriptor rate init */
 	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
@@ -180,7 +183,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 
 	hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
 
-	hw_atl_b0_tc_ptp_set(self);
+	if (cfg->is_ptp)
+		hw_atl_b0_tc_ptp_set(self);
 
 	/* QoS 802.1p priority -> TC mapping */
 	for (i_priority = 8U; i_priority--;)
@@ -1079,18 +1083,6 @@ int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_tx_tc_mode_get(struct aq_hw_s *self, u32 *tc_mode)
-{
-	*tc_mode = hw_atl_tpb_tps_tx_tc_mode_get(self);
-	return aq_hw_err_from_flags(self);
-}
-
-static int hw_atl_b0_rx_tc_mode_get(struct aq_hw_s *self, u32 *tc_mode)
-{
-	*tc_mode = hw_atl_rpb_rpf_rx_traf_class_mode_get(self);
-	return aq_hw_err_from_flags(self);
-}
-
 #define get_ptp_ts_val_u64(self, indx) \
 	((u64)(hw_atl_pcs_ptp_clock_get(self, indx) & 0xffff))
 
@@ -1508,9 +1500,6 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 
-	.hw_tx_tc_mode_get       = hw_atl_b0_tx_tc_mode_get,
-	.hw_rx_tc_mode_get       = hw_atl_b0_rx_tc_mode_get,
-
 	.hw_ring_hwts_rx_fill        = hw_atl_b0_hw_ring_hwts_rx_fill,
 	.hw_ring_hwts_rx_receive     = hw_atl_b0_hw_ring_hwts_rx_receive,
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index ccdb74562270..a14118550882 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -91,16 +91,36 @@ static int hw_atl2_hw_reset(struct aq_hw_s *self)
 
 static int hw_atl2_hw_queue_to_tc_map_set(struct aq_hw_s *self)
 {
-	if (!hw_atl_rpb_rpf_rx_traf_class_mode_get(self)) {
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x11110000);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x33332222);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x55554444);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x77776666);
-	} else {
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x00000000);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x11111111);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x22222222);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x33333333);
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	unsigned int tcs, q_per_tc;
+	unsigned int tc, q;
+	u32 value = 0;
+
+	switch (cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		tcs = 8;
+		q_per_tc = 4;
+		break;
+	case AQ_TC_MODE_4TCS:
+		tcs = 4;
+		q_per_tc = 8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (tc = 0; tc != tcs; tc++) {
+		unsigned int tc_q_offset = tc * q_per_tc;
+
+		for (q = tc_q_offset; q != tc_q_offset + q_per_tc; q++)
+			value |= tc << HW_ATL2_RX_Q_TC_MAP_SHIFT(q);
+
+		if (HW_ATL2_RX_Q_TC_MAP_ADR(q) !=
+		    HW_ATL2_RX_Q_TC_MAP_ADR(q - 1)) {
+			aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(q - 1),
+					value);
+			value = 0;
+		}
 	}
 
 	return aq_hw_err_from_flags(self);
-- 
cgit v1.2.3


From a83fe6b6ad6b10f6912025ae23bd5c2596a4e7f4 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dbezrukov@marvell.com>
Date: Fri, 22 May 2020 11:19:40 +0300
Subject: net: atlantic: QoS implementation: multi-TC support

This patch adds multi-TC support.

PTP is automatically disabled when the user enables more than 2 TCs,
otherwise traffic on TC2 won't quite work, because it's reserved for PTP.

Signed-off-by: Dmitry Bezrukov <dbezrukov@marvell.com>
Co-developed-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Co-developed-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_filters.c    |  11 +-
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |   1 +
 .../net/ethernet/aquantia/atlantic/aq_hw_utils.c   |  26 +++++
 .../net/ethernet/aquantia/atlantic/aq_hw_utils.h   |   2 +
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  39 ++++++-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |  61 ++++++++++-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |  14 ++-
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c   |  19 +++-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  74 +++++++------
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c |   9 +-
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 122 ++++++++++++---------
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h   |   7 --
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |   8 ++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |   4 +
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        |  10 ++
 15 files changed, 293 insertions(+), 114 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 03ff92bc4a7f..1bc4d33a0ce5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -153,6 +153,8 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		       struct aq_hw_rx_fltrs_s *rx_fltrs,
 		       struct ethtool_rx_flow_spec *fsp)
 {
+	struct aq_nic_cfg_s *cfg = &aq_nic->aq_nic_cfg;
+
 	if (fsp->location < AQ_RX_FIRST_LOC_FVLANID ||
 	    fsp->location > AQ_RX_LAST_LOC_FVLANID) {
 		netdev_err(aq_nic->ndev,
@@ -170,10 +172,10 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		return -EINVAL;
 	}
 
-	if (fsp->ring_cookie > aq_nic->aq_nic_cfg.num_rss_queues) {
+	if (fsp->ring_cookie > cfg->num_rss_queues * cfg->tcs) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: queue number must be in range [0, %d]",
-			   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+			   cfg->num_rss_queues * cfg->tcs - 1);
 		return -EINVAL;
 	}
 	return 0;
@@ -262,6 +264,7 @@ static bool __must_check
 aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
 		       struct ethtool_rx_flow_spec *fsp)
 {
+	struct aq_nic_cfg_s *cfg = &aq_nic->aq_nic_cfg;
 	bool rule_is_not_correct = false;
 
 	if (!aq_nic) {
@@ -274,11 +277,11 @@ aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
 	} else if (aq_check_filter(aq_nic, fsp)) {
 		rule_is_not_correct = true;
 	} else if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
-		if (fsp->ring_cookie >= aq_nic->aq_nic_cfg.num_rss_queues) {
+		if (fsp->ring_cookie >= cfg->num_rss_queues * cfg->tcs) {
 			netdev_err(aq_nic->ndev,
 				   "ethtool: The specified action is invalid.\n"
 				   "Maximum allowable value action is %u.\n",
-				   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+				   cfg->num_rss_queues * cfg->tcs - 1);
 			rule_is_not_correct = true;
 		}
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index c3df9da6088c..1dccaaee04b3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -124,6 +124,7 @@ struct aq_stats_s {
 #define AQ_HW_TXD_MULTIPLE 8U
 #define AQ_HW_RXD_MULTIPLE 8U
 
+#define AQ_HW_QUEUES_MAX                32U
 #define AQ_HW_MULTICAST_ADDRESS_MAX     32U
 
 #define AQ_HW_PTP_TC                    2U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
index 7dbf49adcea6..342c5179f846 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
@@ -79,3 +79,29 @@ int aq_hw_err_from_flags(struct aq_hw_s *hw)
 err_exit:
 	return err;
 }
+
+int aq_hw_num_tcs(struct aq_hw_s *hw)
+{
+	switch (hw->aq_nic_cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		return 8;
+	case AQ_TC_MODE_4TCS:
+		return 4;
+	default:
+		break;
+	}
+
+	return 1;
+}
+
+int aq_hw_q_per_tc(struct aq_hw_s *hw)
+{
+	switch (hw->aq_nic_cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		return 4;
+	case AQ_TC_MODE_4TCS:
+		return 8;
+	default:
+		return 4;
+	}
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
index 9ef82d487e01..32aa5f2fb840 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
@@ -34,5 +34,7 @@ u32 aq_hw_read_reg(struct aq_hw_s *hw, u32 reg);
 void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value);
 u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg);
 int aq_hw_err_from_flags(struct aq_hw_s *hw);
+int aq_hw_num_tcs(struct aq_hw_s *hw);
+int aq_hw_q_per_tc(struct aq_hw_s *hw);
 
 #endif /* AQ_HW_UTILS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 9fcab646cbd5..ef9e969fbf7a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -12,11 +12,13 @@
 #include "aq_ethtool.h"
 #include "aq_ptp.h"
 #include "aq_filters.h"
+#include "aq_hw_utils.h"
 
 #include <linux/netdevice.h>
 #include <linux/module.h>
 #include <linux/ip.h>
 #include <linux/udp.h>
+#include <net/pkt_cls.h>
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR(AQ_CFG_DRV_AUTHOR);
@@ -38,7 +40,7 @@ struct net_device *aq_ndev_alloc(void)
 	struct net_device *ndev = NULL;
 	struct aq_nic_s *aq_nic = NULL;
 
-	ndev = alloc_etherdev_mq(sizeof(struct aq_nic_s), AQ_CFG_VECS_MAX);
+	ndev = alloc_etherdev_mq(sizeof(struct aq_nic_s), AQ_HW_QUEUES_MAX);
 	if (!ndev)
 		return NULL;
 
@@ -330,6 +332,40 @@ static int aq_ndo_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto,
 	return 0;
 }
 
+static int aq_validate_mqprio_opt(struct aq_nic_s *self,
+				  const unsigned int num_tc)
+{
+	if (num_tc > aq_hw_num_tcs(self->aq_hw)) {
+		netdev_err(self->ndev, "Too many TCs requested\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (num_tc != 0 && !is_power_of_2(num_tc)) {
+		netdev_err(self->ndev, "TC count should be power of 2\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int aq_ndo_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			   void *type_data)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(dev);
+	struct tc_mqprio_qopt *mqprio = type_data;
+	int err;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EOPNOTSUPP;
+
+	err = aq_validate_mqprio_opt(aq_nic, mqprio->num_tc);
+	if (err)
+		return err;
+
+	return aq_nic_setup_tc_mqprio(aq_nic, mqprio->num_tc,
+				      mqprio->prio_tc_map);
+}
+
 static const struct net_device_ops aq_ndev_ops = {
 	.ndo_open = aq_ndev_open,
 	.ndo_stop = aq_ndev_close,
@@ -341,6 +377,7 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_do_ioctl = aq_ndev_ioctl,
 	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc = aq_ndo_setup_tc,
 };
 
 static int __init aq_ndev_init_module(void)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 3eeb652068e2..da781082be32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -26,6 +26,7 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <net/ip.h>
+#include <net/pkt_cls.h>
 
 static unsigned int aq_itr = AQ_CFG_INTERRUPT_MODERATION_AUTO;
 module_param_named(aq_itr, aq_itr, uint, 0644);
@@ -68,6 +69,7 @@ static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 void aq_nic_cfg_start(struct aq_nic_s *self)
 {
 	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	int i;
 
 	cfg->tcs = AQ_CFG_TCS_DEF;
 
@@ -142,6 +144,9 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->is_vlan_rx_strip = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_RX);
 	cfg->is_vlan_tx_insert = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_TX);
 	cfg->is_vlan_force_promisc = true;
+
+	for (i = 0; i < sizeof(cfg->prio_tc_map); i++)
+		cfg->prio_tc_map[i] = cfg->tcs * i / 8;
 }
 
 static int aq_nic_update_link_status(struct aq_nic_s *self)
@@ -517,14 +522,21 @@ int aq_nic_start(struct aq_nic_s *self)
 			goto err_exit;
 	}
 
-	err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs);
+	err = netif_set_real_num_tx_queues(self->ndev,
+					   self->aq_vecs * cfg->tcs);
 	if (err < 0)
 		goto err_exit;
 
-	err = netif_set_real_num_rx_queues(self->ndev, self->aq_vecs);
+	err = netif_set_real_num_rx_queues(self->ndev,
+					   self->aq_vecs * cfg->tcs);
 	if (err < 0)
 		goto err_exit;
 
+	for (i = 0; i < cfg->tcs; i++) {
+		u16 offset = self->aq_vecs * i;
+
+		netdev_set_tc_queue(self->ndev, i, self->aq_vecs, offset);
+	}
 	netif_tx_start_all_queues(self->ndev);
 
 err_exit:
@@ -690,10 +702,10 @@ exit:
 int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 {
 	unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs;
+	unsigned int tc = skb->queue_mapping / self->aq_nic_cfg.vecs;
 	struct aq_ring_s *ring = NULL;
 	unsigned int frags = 0U;
 	int err = NETDEV_TX_OK;
-	unsigned int tc = 0U;
 
 	frags = skb_shinfo(skb)->nr_frags + 1;
 
@@ -712,7 +724,8 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 	}
 
 	/* Above status update may stop the queue. Check this. */
-	if (__netif_subqueue_stopped(self->ndev, ring->idx)) {
+	if (__netif_subqueue_stopped(self->ndev,
+				     AQ_NIC_RING2QMAP(self, ring->idx))) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
@@ -1266,3 +1279,43 @@ void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 		break;
 	}
 }
+
+int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	bool ndev_running;
+	int err = 0;
+	int i;
+
+	/* if already the same configuration or
+	 * disable request (tcs is 0) and we already is disabled
+	 */
+	if (tcs == cfg->tcs || (tcs == 0 && !cfg->is_qos))
+		return 0;
+
+	ndev_running = netif_running(self->ndev);
+	if (ndev_running)
+		dev_close(self->ndev);
+
+	cfg->tcs = tcs;
+	if (cfg->tcs == 0)
+		cfg->tcs = 1;
+	if (prio_tc_map)
+		memcpy(cfg->prio_tc_map, prio_tc_map, sizeof(cfg->prio_tc_map));
+	else
+		for (i = 0; i < sizeof(cfg->prio_tc_map); i++)
+			cfg->prio_tc_map[i] = cfg->tcs * i / 8;
+
+	cfg->is_qos = (tcs != 0 ? true : false);
+	cfg->is_ptp = (cfg->tcs <= AQ_HW_PTP_TC);
+	if (!cfg->is_ptp)
+		netdev_warn(self->ndev, "%s\n",
+			    "PTP is auto disabled due to requested TC count.");
+
+	netdev_set_num_tc(self->ndev, cfg->tcs);
+
+	if (ndev_running)
+		err = dev_open(self->ndev, NULL);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 3434f8206823..29e129411945 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -59,10 +59,12 @@ struct aq_nic_cfg_s {
 	bool is_polling;
 	bool is_rss;
 	bool is_lro;
+	bool is_qos;
 	bool is_ptp;
 	enum aq_tc_mode tc_mode;
 	u32 priv_flags;
 	u8  tcs;
+	u8 prio_tc_map[8];
 	struct aq_rss_parameters aq_rss;
 	u32 eee_speeds;
 };
@@ -79,8 +81,15 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_WOL_MODES        (WAKE_MAGIC |\
 				 WAKE_PHY)
 
+#define AQ_NIC_RING_PER_TC(_NIC_) \
+	(((_NIC_)->aq_nic_cfg.tc_mode == AQ_TC_MODE_4TCS) ? 8 : 4)
+
 #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
-	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
+	((_TC_) * AQ_NIC_RING_PER_TC(_NIC_) + (_VEC_))
+
+#define AQ_NIC_RING2QMAP(_NIC_, _ID_) \
+	((_ID_) / AQ_NIC_RING_PER_TC(_NIC_) * (_NIC_)->aq_vecs + \
+	((_ID_) % AQ_NIC_RING_PER_TC(_NIC_)))
 
 struct aq_hw_rx_fl2 {
 	struct aq_rx_filter_vlan aq_vlans[AQ_VLAN_MAX_FILTERS];
@@ -106,7 +115,7 @@ struct aq_nic_s {
 	atomic_t flags;
 	u32 msg_enable;
 	struct aq_vec_s *aq_vec[AQ_CFG_VECS_MAX];
-	struct aq_ring_s *aq_ring_tx[AQ_CFG_VECS_MAX * AQ_CFG_TCS_MAX];
+	struct aq_ring_s *aq_ring_tx[AQ_HW_QUEUES_MAX];
 	struct aq_hw_s *aq_hw;
 	struct net_device *ndev;
 	unsigned int aq_vecs;
@@ -183,4 +192,5 @@ void aq_nic_shutdown(struct aq_nic_s *self);
 u8 aq_nic_reserve_filter(struct aq_nic_s *self, enum aq_rx_filter_type type);
 void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 			   u32 location);
+int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map);
 #endif /* AQ_NIC_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index bae95a618560..68fdb3994088 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -232,8 +232,11 @@ void aq_ring_queue_wake(struct aq_ring_s *ring)
 {
 	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
 
-	if (__netif_subqueue_stopped(ndev, ring->idx)) {
-		netif_wake_subqueue(ndev, ring->idx);
+	if (__netif_subqueue_stopped(ndev,
+				     AQ_NIC_RING2QMAP(ring->aq_nic,
+						      ring->idx))) {
+		netif_wake_subqueue(ndev,
+				    AQ_NIC_RING2QMAP(ring->aq_nic, ring->idx));
 		ring->stats.tx.queue_restarts++;
 	}
 }
@@ -242,8 +245,11 @@ void aq_ring_queue_stop(struct aq_ring_s *ring)
 {
 	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
 
-	if (!__netif_subqueue_stopped(ndev, ring->idx))
-		netif_stop_subqueue(ndev, ring->idx);
+	if (!__netif_subqueue_stopped(ndev,
+				      AQ_NIC_RING2QMAP(ring->aq_nic,
+						       ring->idx)))
+		netif_stop_subqueue(ndev,
+				    AQ_NIC_RING2QMAP(ring->aq_nic, ring->idx));
 }
 
 bool aq_ring_tx_clean(struct aq_ring_s *self)
@@ -466,7 +472,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			     buff->is_hash_l4 ? PKT_HASH_TYPE_L4 :
 			     PKT_HASH_TYPE_NONE);
 		/* Send all PTP traffic to 0 queue */
-		skb_record_rx_queue(skb, is_ptp_ring ? 0 : self->idx);
+		skb_record_rx_queue(skb,
+				    is_ptp_ring ? 0
+						: AQ_NIC_RING2QMAP(self->aq_nic,
+								   self->idx));
 
 		++self->stats.rx.packets;
 		self->stats.rx.bytes += skb->len;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 7caf586ea56c..775382440b47 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -46,7 +46,8 @@
 			NETIF_F_HW_VLAN_CTAG_RX |     \
 			NETIF_F_HW_VLAN_CTAG_TX |     \
 			NETIF_F_GSO_UDP_L4      |     \
-			NETIF_F_GSO_PARTIAL,          \
+			NETIF_F_GSO_PARTIAL |         \
+			NETIF_F_HW_TC,                \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
@@ -134,7 +135,7 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	u32 tx_buff_size = HW_ATL_B0_TXBUF_MAX;
 	u32 rx_buff_size = HW_ATL_B0_RXBUF_MAX;
-	unsigned int i_priority = 0U;
+	unsigned int prio = 0U;
 	u32 tc = 0U;
 
 	if (cfg->is_ptp) {
@@ -153,42 +154,45 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	/* TX Packet Scheduler Data TC0 */
-	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
-	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
-
-	/* Tx buf size TC0 */
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
-	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self,
-						   (tx_buff_size *
-						   (1024 / 32U) * 66U) /
-						   100U, tc);
-	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self,
-						   (tx_buff_size *
-						   (1024 / 32U) * 50U) /
-						   100U, tc);
-
-	/* QoS Rx buf size per TC */
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
-	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self,
-						   (rx_buff_size *
-						   (1024U / 32U) * 66U) /
-						   100U, tc);
-	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self,
-						   (rx_buff_size *
-						   (1024U / 32U) * 50U) /
-						   100U, tc);
-
-	hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
+	tx_buff_size /= cfg->tcs;
+	rx_buff_size /= cfg->tcs;
+	for (tc = 0; tc < cfg->tcs; tc++) {
+		u32 threshold = 0U;
+
+		/* TX Packet Scheduler Data TC0 */
+		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
+		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+
+		/* Tx buf size TC0 */
+		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
+
+		threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
+		hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+
+		threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
+		hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+
+		/* QoS Rx buf size per TC */
+		hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
+
+		threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
+		hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+
+		threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
+		hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+
+		hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
+	}
 
 	if (cfg->is_ptp)
 		hw_atl_b0_tc_ptp_set(self);
 
 	/* QoS 802.1p priority -> TC mapping */
-	for (i_priority = 8U; i_priority--;)
-		hw_atl_rpf_rpb_user_priority_tc_map_set(self, i_priority, 0U);
+	for (prio = 0; prio < 8; ++prio)
+		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
+							cfg->prio_tc_map[prio]);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -319,7 +323,7 @@ int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
 	/* Tx TC/Queue number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, self->aq_nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
@@ -345,7 +349,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	int i;
 
 	/* Rx TC/RSS number config */
-	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, 1U);
+	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, cfg->tc_mode);
 
 	/* Rx flow control */
 	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 9e2d01a6aac8..8cb6765a1398 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -754,7 +754,7 @@ void hw_atl_rpfl2_accept_all_mc_packets_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_rpf_rpb_user_priority_tc_map_set(struct aq_hw_s *aq_hw,
-					     u32 user_priority_tc_map, u32 tc)
+					     u32 user_priority, u32 tc)
 {
 /* register address for bitfield rx_tc_up{t}[2:0] */
 	static u32 rpf_rpb_rx_tc_upt_adr[8] = {
@@ -773,10 +773,9 @@ void hw_atl_rpf_rpb_user_priority_tc_map_set(struct aq_hw_s *aq_hw,
 			0U, 4U, 8U, 12U, 16U, 20U, 24U, 28U
 		};
 
-	aq_hw_write_reg_bit(aq_hw, rpf_rpb_rx_tc_upt_adr[tc],
-			    rpf_rpb_rx_tc_upt_msk[tc],
-			    rpf_rpb_rx_tc_upt_shft[tc],
-			    user_priority_tc_map);
+	aq_hw_write_reg_bit(aq_hw, rpf_rpb_rx_tc_upt_adr[user_priority],
+			    rpf_rpb_rx_tc_upt_msk[user_priority],
+			    rpf_rpb_rx_tc_upt_shft[user_priority], tc);
 }
 
 void hw_atl_rpf_rss_key_addr_set(struct aq_hw_s *aq_hw, u32 rss_key_addr)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index a14118550882..05c049661b2e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -47,7 +47,8 @@ static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 			NETIF_F_HW_VLAN_CTAG_RX |     \
 			NETIF_F_HW_VLAN_CTAG_TX |     \
 			NETIF_F_GSO_UDP_L4      |     \
-			NETIF_F_GSO_PARTIAL,          \
+			NETIF_F_GSO_PARTIAL     |     \
+			NETIF_F_HW_TC,                \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL2_MTU_JUMBO,	  \
@@ -132,7 +133,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	u32 tx_buff_size = HW_ATL2_TXBUF_MAX;
 	u32 rx_buff_size = HW_ATL2_RXBUF_MAX;
 	unsigned int prio = 0U;
-	u32 threshold = 0U;
 	u32 tc = 0U;
 
 	/* TPS Descriptor rate init */
@@ -146,34 +146,41 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	/* TX Packet Scheduler Data TC0 */
-	hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0, tc);
-	hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+	tx_buff_size /= cfg->tcs;
+	rx_buff_size /= cfg->tcs;
+	for (tc = 0; tc < cfg->tcs; tc++) {
+		u32 threshold = 0U;
 
-	/* Tx buf size TC0 */
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
+		/* TX Packet Scheduler Data TC0 */
+		hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0,
+							       tc);
+		hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
 
-	threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
-	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+		/* Tx buf size TC0 */
+		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 
-	threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
-	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+		threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
+		hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
 
-	/* QoS Rx buf size per TC */
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
+		threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
+		hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
 
-	threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
-	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+		/* QoS Rx buf size per TC */
+		hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
 
-	threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
-	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+		threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
+		hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+
+		threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
+		hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+	}
 
 	/* QoS 802.1p priority -> TC mapping */
 	for (prio = 0; prio < 8; ++prio)
 		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
-							cfg->tcs * prio / 8);
+							cfg->prio_tc_map[prio]);
 
 	/* ATL2 Apply legacy ring to TC mapping */
 	hw_atl2_hw_queue_to_tc_map_set(self);
@@ -184,11 +191,24 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 			      struct aq_rss_parameters *rss_params)
 {
-	u8 *indirection_table =	rss_params->indirection_table;
+	u8 *indirection_table = rss_params->indirection_table;
+	const u32 num_tcs = aq_hw_num_tcs(self);
+	u32 rpf_redir2_enable;
+	int tc;
 	int i;
 
-	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;)
-		hw_atl2_new_rpf_rss_redir_set(self, 0, i, indirection_table[i]);
+	rpf_redir2_enable = num_tcs > 4 ? 1 : 0;
+
+	hw_atl2_rpf_redirection_table2_select_set(self, rpf_redir2_enable);
+
+	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;) {
+		for (tc = 0; tc != num_tcs; tc++) {
+			hw_atl2_new_rpf_rss_redir_set(self, tc, i,
+						      tc *
+						      aq_hw_q_per_tc(self) +
+						      indirection_table[i]);
+		}
+	}
 
 	return aq_hw_err_from_flags(self);
 }
@@ -196,7 +216,7 @@ static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 {
 	/* Tx TC/RSS number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, self->aq_nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
@@ -219,13 +239,29 @@ static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
 {
 	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u8 *prio_tc_map = self->aq_nic_cfg->prio_tc_map;
+	u16 action;
 	u8 index;
+	int i;
 
+	/* Action Resolver Table (ART) is used by RPF to decide which action
+	 * to take with a packet based upon input tag and tag mask, where:
+	 *  - input tag is a combination of 3-bit VLan Prio (PTP) and
+	 *    29-bit concatenation of all tags from filter block;
+	 *  - tag mask is a mask used for matching against input tag.
+	 * The input_tag is compared with the all the Requested_tags in the
+	 * Record table to find a match. Action field of the selected matched
+	 * REC entry is used for further processing. If multiple entries match,
+	 * the lowest REC entry, Action field will be selected.
+	 */
 	hw_atl2_rpf_act_rslvr_section_en_set(self, 0xFFFF);
 	hw_atl2_rpfl2_uc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC,
 				     HW_ATL2_MAC_UC);
 	hw_atl2_rpfl2_bc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC);
 
+	/* FW reserves the beginning of ART, thus all driver entries must
+	 * start from the offset specified in FW caps.
+	 */
 	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_OFF_INDEX;
 	hw_atl2_act_rslvr_table_set(self, index, 0,
 				    HW_ATL2_RPF_TAG_UC_MASK |
@@ -238,33 +274,17 @@ static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
 					HW_ATL2_RPF_TAG_UNTAG_MASK,
 				    HW_ATL2_ACTION_DROP);
 
-	index = priv->art_base_index + HW_ATL2_RPF_VLAN_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_VLAN,
-				    HW_ATL2_RPF_TAG_VLAN_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
+	/* Configure ART to map given VLan Prio (PCP) to the TC index for
+	 * RSS redirection table.
+	 */
+	for (i = 0; i < 8; i++) {
+		action = HW_ATL2_ACTION_ASSIGN_TC(prio_tc_map[i]);
 
-	index = priv->art_base_index + HW_ATL2_RPF_MAC_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_UC,
-				    HW_ATL2_RPF_TAG_UC_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_ALLMC_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_ALLMC,
-				    HW_ATL2_RPF_TAG_ALLMC_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_UNTAG_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_UNTAG_MASK,
-				    HW_ATL2_RPF_TAG_UNTAG_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_VLAN_MASK,
-				    HW_ATL2_ACTION_DISABLE);
-
-	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_ON_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_UC_MASK,
-				    HW_ATL2_ACTION_DISABLE);
+		index = priv->art_base_index + HW_ATL2_RPF_PCP_TO_TC_INDEX + i;
+		hw_atl2_act_rslvr_table_set(self, index,
+					    i << HW_ATL2_RPF_TAG_PCP_OFFSET,
+					    HW_ATL2_RPF_TAG_PCP_MASK, action);
+	}
 }
 
 static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
@@ -327,7 +347,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
 	int i;
 
 	/* Rx TC/RSS number config */
-	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, 1U);
+	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, cfg->tc_mode);
 
 	/* Rx flow control */
 	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index be0c049ea582..9ac1979a4867 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -82,13 +82,6 @@ enum HW_ATL2_RPF_ART_INDEX {
 	HW_ATL2_RPF_VLAN_USER_INDEX	= HW_ATL2_RPF_ET_PCP_USER_INDEX + 16,
 	HW_ATL2_RPF_PCP_TO_TC_INDEX	= HW_ATL2_RPF_VLAN_USER_INDEX +
 					  HW_ATL_VLAN_MAX_FILTERS,
-	HW_ATL2_RPF_VLAN_INDEX		= HW_ATL2_RPF_PCP_TO_TC_INDEX +
-					  AQ_CFG_TCS_MAX,
-	HW_ATL2_RPF_MAC_INDEX,
-	HW_ATL2_RPF_ALLMC_INDEX,
-	HW_ATL2_RPF_UNTAG_INDEX,
-	HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX,
-	HW_ATL2_RPF_L2_PROMISC_ON_INDEX,
 };
 
 #define HW_ATL2_ACTION(ACTION, RSS, INDEX, VALID) \
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index e779d70fde66..f096d0a6bda9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -7,6 +7,14 @@
 #include "hw_atl2_llh_internal.h"
 #include "aq_hw_utils.h"
 
+void hw_atl2_rpf_redirection_table2_select_set(struct aq_hw_s *aq_hw,
+					       u32 select)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_ADR,
+			    HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSK,
+			    HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_SHIFT, select);
+}
+
 void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index 8c6d78a64d42..5c1ae755ffae 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -15,6 +15,10 @@ void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
 					u32 tx_intr_moderation_ctl,
 					u32 queue);
 
+/* Set Redirection Table 2 Select */
+void hw_atl2_rpf_redirection_table2_select_set(struct aq_hw_s *aq_hw,
+					       u32 select);
+
 /** Set RSS HASH type */
 void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index cde9e9d2836d..b0ac8cd581d7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -6,6 +6,16 @@
 #ifndef HW_ATL2_LLH_INTERNAL_H
 #define HW_ATL2_LLH_INTERNAL_H
 
+/* RX pif_rpf_redir_2_en_i Bitfield Definitions
+ * PORT="pif_rpf_redir_2_en_i"
+ */
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_ADR 0x000054C8
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSK 0x00001000
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSKN 0xFFFFEFFF
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_SHIFT 12
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_WIDTH 1
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_DEFAULT 0x0
+
 /* RX pif_rpf_rss_hash_type_i Bitfield Definitions
  */
 #define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR 0x000054C8
-- 
cgit v1.2.3


From 4272ba8b11f88be8daca5e2477bfe110145d559c Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:41 +0300
Subject: net: atlantic: per-TC queue statistics

This patch adds support for per-TC queue statistics.

By default (single TC), the output is the same as it used to be, e.g.:
     Queue[0] InPackets: 2
     Queue[0] OutPackets: 8
     Queue[0] Restarts: 0
     Queue[0] InJumboPackets: 0
     Queue[0] InLroPackets: 0
     Queue[0] InErrors: 0

If several TCs are enabled, then each queue statistics line is prefixed
with TC number, e.g.:
     TC0 Queue[0] InPackets: 6
     TC0 Queue[0] OutPackets: 11
Queue numbering is end-to-end, so:
     TC1 Queue[4] InPackets: 0
     TC1 Queue[4] OutPackets: 22

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 59 +++++++++++++---------
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 12 +++--
 drivers/net/ethernet/aquantia/atlantic/aq_vec.c    | 24 +++++----
 drivers/net/ethernet/aquantia/atlantic/aq_vec.h    |  5 +-
 4 files changed, 59 insertions(+), 41 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 86fc77d85fda..440a7d129848 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -88,13 +88,13 @@ static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = {
 	"InDroppedDma",
 };
 
-static const char aq_ethtool_queue_stat_names[][ETH_GSTRING_LEN] = {
-	"Queue[%d] InPackets",
-	"Queue[%d] OutPackets",
-	"Queue[%d] Restarts",
-	"Queue[%d] InJumboPackets",
-	"Queue[%d] InLroPackets",
-	"Queue[%d] InErrors",
+static const char * const aq_ethtool_queue_stat_names[] = {
+	"%sQueue[%d] InPackets",
+	"%sQueue[%d] OutPackets",
+	"%sQueue[%d] Restarts",
+	"%sQueue[%d] InJumboPackets",
+	"%sQueue[%d] InLroPackets",
+	"%sQueue[%d] InErrors",
 };
 
 #if IS_ENABLED(CONFIG_MACSEC)
@@ -166,7 +166,8 @@ static u32 aq_ethtool_n_stats(struct net_device *ndev)
 	struct aq_nic_s *nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(nic);
 	u32 n_stats = ARRAY_SIZE(aq_ethtool_stat_names) +
-		      ARRAY_SIZE(aq_ethtool_queue_stat_names) * cfg->vecs;
+		      ARRAY_SIZE(aq_ethtool_queue_stat_names) * cfg->vecs *
+			cfg->tcs;
 
 #if IS_ENABLED(CONFIG_MACSEC)
 	if (nic->macsec_cfg) {
@@ -223,7 +224,7 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev,
 static void aq_ethtool_get_strings(struct net_device *ndev,
 				   u32 stringset, u8 *data)
 {
-	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_s *nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
 	u8 *p = data;
 	int i, si;
@@ -231,24 +232,35 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 	int sa;
 #endif
 
-	cfg = aq_nic_get_cfg(aq_nic);
+	cfg = aq_nic_get_cfg(nic);
 
 	switch (stringset) {
-	case ETH_SS_STATS:
+	case ETH_SS_STATS: {
+		const int stat_cnt = ARRAY_SIZE(aq_ethtool_queue_stat_names);
+		char tc_string[8];
+		int tc;
+
+		memset(tc_string, 0, sizeof(tc_string));
 		memcpy(p, aq_ethtool_stat_names,
 		       sizeof(aq_ethtool_stat_names));
 		p = p + sizeof(aq_ethtool_stat_names);
-		for (i = 0; i < cfg->vecs; i++) {
-			for (si = 0;
-				si < ARRAY_SIZE(aq_ethtool_queue_stat_names);
-				si++) {
-				snprintf(p, ETH_GSTRING_LEN,
-					 aq_ethtool_queue_stat_names[si], i);
-				p += ETH_GSTRING_LEN;
+
+		for (tc = 0; tc < cfg->tcs; tc++) {
+			if (cfg->is_qos)
+				snprintf(tc_string, 8, "TC%d ", tc);
+
+			for (i = 0; i < cfg->vecs; i++) {
+				for (si = 0; si < stat_cnt; si++) {
+					snprintf(p, ETH_GSTRING_LEN,
+					     aq_ethtool_queue_stat_names[si],
+					     tc_string,
+					     AQ_NIC_TCVEC2RING(nic, tc, i));
+					p += ETH_GSTRING_LEN;
+				}
 			}
 		}
 #if IS_ENABLED(CONFIG_MACSEC)
-		if (!aq_nic->macsec_cfg)
+		if (!nic->macsec_cfg)
 			break;
 
 		memcpy(p, aq_macsec_stat_names, sizeof(aq_macsec_stat_names));
@@ -256,7 +268,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
 			struct aq_macsec_txsc *aq_txsc;
 
-			if (!(test_bit(i, &aq_nic->macsec_cfg->txsc_idx_busy)))
+			if (!(test_bit(i, &nic->macsec_cfg->txsc_idx_busy)))
 				continue;
 
 			for (si = 0;
@@ -266,7 +278,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 					 aq_macsec_txsc_stat_names[si], i);
 				p += ETH_GSTRING_LEN;
 			}
-			aq_txsc = &aq_nic->macsec_cfg->aq_txsc[i];
+			aq_txsc = &nic->macsec_cfg->aq_txsc[i];
 			for (sa = 0; sa < MACSEC_NUM_AN; sa++) {
 				if (!(test_bit(sa, &aq_txsc->tx_sa_idx_busy)))
 					continue;
@@ -283,10 +295,10 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
 			struct aq_macsec_rxsc *aq_rxsc;
 
-			if (!(test_bit(i, &aq_nic->macsec_cfg->rxsc_idx_busy)))
+			if (!(test_bit(i, &nic->macsec_cfg->rxsc_idx_busy)))
 				continue;
 
-			aq_rxsc = &aq_nic->macsec_cfg->aq_rxsc[i];
+			aq_rxsc = &nic->macsec_cfg->aq_rxsc[i];
 			for (sa = 0; sa < MACSEC_NUM_AN; sa++) {
 				if (!(test_bit(sa, &aq_rxsc->rx_sa_idx_busy)))
 					continue;
@@ -302,6 +314,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		}
 #endif
 		break;
+	}
 	case ETH_SS_PRIV_FLAGS:
 		memcpy(p, aq_ethtool_priv_flag_names,
 		       sizeof(aq_ethtool_priv_flag_names));
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index da781082be32..851f22aadea1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -855,6 +855,7 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	struct aq_stats_s *stats;
 	unsigned int count = 0U;
 	unsigned int i = 0U;
+	unsigned int tc;
 
 	if (self->aq_fw_ops->update_stats) {
 		mutex_lock(&self->fwreq_mutex);
@@ -893,10 +894,13 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 
 	data += i;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		aq_vec && self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) {
-		data += count;
-		aq_vec_get_sw_stats(aq_vec, data, &count);
+	for (tc = 0U; tc < self->aq_nic_cfg.tcs; tc++) {
+		for (i = 0U, aq_vec = self->aq_vec[0];
+		     aq_vec && self->aq_vecs > i;
+		     ++i, aq_vec = self->aq_vec[i]) {
+			data += count;
+			aq_vec_get_sw_stats(aq_vec, tc, data, &count);
+		}
 	}
 
 	data += count;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index d5650cd6e236..41826c10700f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -348,16 +348,14 @@ cpumask_t *aq_vec_get_affinity_mask(struct aq_vec_s *self)
 	return &self->aq_ring_param.affinity_mask;
 }
 
-void aq_vec_add_stats(struct aq_vec_s *self,
-		      struct aq_ring_stats_rx_s *stats_rx,
-		      struct aq_ring_stats_tx_s *stats_tx)
+static void aq_vec_add_stats(struct aq_vec_s *self,
+			     const unsigned int tc,
+			     struct aq_ring_stats_rx_s *stats_rx,
+			     struct aq_ring_stats_tx_s *stats_tx)
 {
-	struct aq_ring_s *ring = NULL;
-	unsigned int r = 0U;
+	struct aq_ring_s *ring = self->ring[tc];
 
-	for (r = 0U, ring = self->ring[0];
-		self->tx_rings > r; ++r, ring = self->ring[r]) {
-		struct aq_ring_stats_tx_s *tx = &ring[AQ_VEC_TX_ID].stats.tx;
+	if (tc < self->rx_rings) {
 		struct aq_ring_stats_rx_s *rx = &ring[AQ_VEC_RX_ID].stats.rx;
 
 		stats_rx->packets += rx->packets;
@@ -368,6 +366,10 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 		stats_rx->pg_losts += rx->pg_losts;
 		stats_rx->pg_flips += rx->pg_flips;
 		stats_rx->pg_reuses += rx->pg_reuses;
+	}
+
+	if (tc < self->tx_rings) {
+		struct aq_ring_stats_tx_s *tx = &ring[AQ_VEC_TX_ID].stats.tx;
 
 		stats_tx->packets += tx->packets;
 		stats_tx->bytes += tx->bytes;
@@ -376,7 +378,8 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 	}
 }
 
-int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count)
+int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u64 *data,
+			unsigned int *p_count)
 {
 	struct aq_ring_stats_rx_s stats_rx;
 	struct aq_ring_stats_tx_s stats_tx;
@@ -384,7 +387,8 @@ int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count)
 
 	memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s));
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
-	aq_vec_add_stats(self, &stats_rx, &stats_tx);
+
+	aq_vec_add_stats(self, tc, &stats_rx, &stats_tx);
 
 	/* This data should mimic aq_ethtool_queue_stat_names structure
 	 */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
index 0ee86b26df8a..541af85e6510 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
@@ -35,10 +35,7 @@ void aq_vec_ring_free(struct aq_vec_s *self);
 int aq_vec_start(struct aq_vec_s *self);
 void aq_vec_stop(struct aq_vec_s *self);
 cpumask_t *aq_vec_get_affinity_mask(struct aq_vec_s *self);
-int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data,
+int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u64 *data,
 			unsigned int *p_count);
-void aq_vec_add_stats(struct aq_vec_s *self,
-		      struct aq_ring_stats_rx_s *stats_rx,
-		      struct aq_ring_stats_tx_s *stats_tx);
 
 #endif /* AQ_VEC_H */
-- 
cgit v1.2.3


From b9e989262a3e2e9b795361a7e7978d64851eb98f Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:42 +0300
Subject: net: atlantic: make TCVEC2RING accept nic_cfg

This patch updates TCVEC2RING to accept nic_cfg, which is needed to be able
to use it from hw_atl.
The name is updated to reflect the changes.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c |  2 +-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c     |  9 +++++----
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h     | 13 +++++++------
 drivers/net/ethernet/aquantia/atlantic/aq_vec.c     |  3 ++-
 4 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 440a7d129848..90a52a4b2d48 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -254,7 +254,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 					snprintf(p, ETH_GSTRING_LEN,
 					     aq_ethtool_queue_stat_names[si],
 					     tc_string,
-					     AQ_NIC_TCVEC2RING(nic, tc, i));
+					     AQ_NIC_CFG_TCVEC2RING(cfg, tc, i));
 					p += ETH_GSTRING_LEN;
 				}
 			}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 851f22aadea1..b2ef0115c293 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -701,15 +701,16 @@ exit:
 
 int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 {
-	unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs;
-	unsigned int tc = skb->queue_mapping / self->aq_nic_cfg.vecs;
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+	unsigned int vec = skb->queue_mapping % cfg->vecs;
+	unsigned int tc = skb->queue_mapping / cfg->vecs;
 	struct aq_ring_s *ring = NULL;
 	unsigned int frags = 0U;
 	int err = NETDEV_TX_OK;
 
 	frags = skb_shinfo(skb)->nr_frags + 1;
 
-	ring = self->aq_ring_tx[AQ_NIC_TCVEC2RING(self, tc, vec)];
+	ring = self->aq_ring_tx[AQ_NIC_CFG_TCVEC2RING(cfg, tc, vec)];
 
 	if (frags > AQ_CFG_SKB_FRAGS_MAX) {
 		dev_kfree_skb_any(skb);
@@ -718,7 +719,7 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	aq_ring_update_queue_state(ring);
 
-	if (self->aq_nic_cfg.priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
+	if (cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 29e129411945..6cc2ebfe6a44 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -81,15 +81,16 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_WOL_MODES        (WAKE_MAGIC |\
 				 WAKE_PHY)
 
-#define AQ_NIC_RING_PER_TC(_NIC_) \
-	(((_NIC_)->aq_nic_cfg.tc_mode == AQ_TC_MODE_4TCS) ? 8 : 4)
+#define AQ_NIC_CFG_RING_PER_TC(_NIC_CFG_) \
+	(((_NIC_CFG_)->tc_mode == AQ_TC_MODE_4TCS) ? 8 : 4)
 
-#define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
-	((_TC_) * AQ_NIC_RING_PER_TC(_NIC_) + (_VEC_))
+#define AQ_NIC_CFG_TCVEC2RING(_NIC_CFG_, _TC_, _VEC_) \
+	((_TC_) * AQ_NIC_CFG_RING_PER_TC(_NIC_CFG_) + (_VEC_))
 
 #define AQ_NIC_RING2QMAP(_NIC_, _ID_) \
-	((_ID_) / AQ_NIC_RING_PER_TC(_NIC_) * (_NIC_)->aq_vecs + \
-	((_ID_) % AQ_NIC_RING_PER_TC(_NIC_)))
+	((_ID_) / AQ_NIC_CFG_RING_PER_TC(&(_NIC_)->aq_nic_cfg) * \
+		(_NIC_)->aq_vecs + \
+	((_ID_) % AQ_NIC_CFG_RING_PER_TC(&(_NIC_)->aq_nic_cfg)))
 
 struct aq_hw_rx_fl2 {
 	struct aq_rx_filter_vlan aq_vlans[AQ_VLAN_MAX_FILTERS];
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index 41826c10700f..d1d43c8ce400 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -135,7 +135,8 @@ int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
 	int err = 0;
 
 	for (i = 0; i < aq_nic_cfg->tcs; ++i) {
-		unsigned int idx_ring = AQ_NIC_TCVEC2RING(aq_nic, i, idx);
+		const unsigned int idx_ring = AQ_NIC_CFG_TCVEC2RING(aq_nic_cfg,
+								    i, idx);
 
 		ring = aq_ring_tx_alloc(&self->ring[i][AQ_VEC_TX_ID], aq_nic,
 					idx_ring, aq_nic_cfg);
-- 
cgit v1.2.3


From 7327699f35f8e90b32c03080b5cba4e9aa95e087 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:43 +0300
Subject: net: atlantic: QoS implementation: max_rate

This patch adds initial support for mqprio rate limiters (max_rate only).

Atlantic HW supports Rate-Shaping for time-sensitive traffic at per
Traffic Class (TC) granularity.
Target rate is defined by:
* nominal link rate (always 10G);
* rate factor (ratio between nominal rate and max allowed).

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  3 +
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   | 30 ++++++++--
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 20 +++++++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |  3 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 58 ++++++++++++++++--
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h  |  2 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c | 36 +++++++++++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h | 16 +++++
 .../aquantia/atlantic/hw_atl/hw_atl_llh_internal.h | 70 ++++++++++++++++++++++
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   |  9 +--
 10 files changed, 235 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 1dccaaee04b3..d31e576f8b86 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -35,6 +35,9 @@ enum aq_tc_mode {
 			(AQ_RX_LAST_LOC_FVLANID - AQ_RX_FIRST_LOC_FVLANID + 1U)
 #define AQ_RX_QUEUE_NOT_ASSIGNED   0xFFU
 
+/* Used for rate to Mbps conversion */
+#define AQ_MBPS_DIVISOR         125000 /* 1000000 / 8 */
+
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
 	u64 hw_features;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index ef9e969fbf7a..d8817047f4ef 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -333,8 +333,12 @@ static int aq_ndo_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto,
 }
 
 static int aq_validate_mqprio_opt(struct aq_nic_s *self,
+				  struct tc_mqprio_qopt_offload *mqprio,
 				  const unsigned int num_tc)
 {
+	const bool has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	int i;
+
 	if (num_tc > aq_hw_num_tcs(self->aq_hw)) {
 		netdev_err(self->ndev, "Too many TCs requested\n");
 		return -EOPNOTSUPP;
@@ -345,25 +349,43 @@ static int aq_validate_mqprio_opt(struct aq_nic_s *self,
 		return -EOPNOTSUPP;
 	}
 
+	for (i = 0; i < num_tc; i++) {
+		if (has_min_rate && mqprio->min_rate[i]) {
+			netdev_err(self->ndev,
+				   "Min tx rate is not supported\n");
+			return -EOPNOTSUPP;
+		}
+	}
+
 	return 0;
 }
 
 static int aq_ndo_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			   void *type_data)
 {
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
 	struct aq_nic_s *aq_nic = netdev_priv(dev);
-	struct tc_mqprio_qopt *mqprio = type_data;
 	int err;
+	int i;
 
 	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
-	err = aq_validate_mqprio_opt(aq_nic, mqprio->num_tc);
+	err = aq_validate_mqprio_opt(aq_nic, mqprio, mqprio->qopt.num_tc);
 	if (err)
 		return err;
 
-	return aq_nic_setup_tc_mqprio(aq_nic, mqprio->num_tc,
-				      mqprio->prio_tc_map);
+	if (mqprio->flags & TC_MQPRIO_F_MAX_RATE) {
+		for (i = 0; i < mqprio->qopt.num_tc; i++) {
+			u64 max_rate = mqprio->max_rate[i];
+
+			do_div(max_rate, AQ_MBPS_DIVISOR);
+			aq_nic_setup_tc_max_rate(aq_nic, i, (u32)max_rate);
+		}
+	}
+
+	return aq_nic_setup_tc_mqprio(aq_nic, mqprio->qopt.num_tc,
+				      mqprio->qopt.prio_tc_map);
 }
 
 static const struct net_device_ops aq_ndev_ops = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index b2ef0115c293..2e0e7d34fda0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1324,3 +1324,23 @@ int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map)
 
 	return err;
 }
+
+int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 max_rate)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	if (tc >= AQ_CFG_TCS_MAX)
+		return -EINVAL;
+
+	if (max_rate && max_rate < 10) {
+		netdev_warn(self->ndev,
+			"Setting %s to the minimum usable value of %dMbps.\n",
+			"max rate", 10);
+		cfg->tc_max_rate[tc] = 10;
+	} else {
+		cfg->tc_max_rate[tc] = max_rate;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 6cc2ebfe6a44..351c4e68f40d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -65,6 +65,7 @@ struct aq_nic_cfg_s {
 	u32 priv_flags;
 	u8  tcs;
 	u8 prio_tc_map[8];
+	u32 tc_max_rate[AQ_CFG_TCS_MAX];
 	struct aq_rss_parameters aq_rss;
 	u32 eee_speeds;
 };
@@ -194,4 +195,6 @@ u8 aq_nic_reserve_filter(struct aq_nic_s *self, enum aq_rx_filter_type type);
 void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 			   u32 location);
 int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map);
+int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 max_rate);
 #endif /* AQ_NIC_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 775382440b47..abc86eb4f525 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -138,6 +138,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	unsigned int prio = 0U;
 	u32 tc = 0U;
 
+	hw_atl_b0_hw_init_tx_tc_rate_limit(self);
+
 	if (cfg->is_ptp) {
 		tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
 		rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
@@ -151,7 +153,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
 	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
 	tx_buff_size /= cfg->tcs;
@@ -162,8 +163,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 		/* TX Packet Scheduler Data TC0 */
 		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
 		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
-		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
 
 		/* Tx buf size TC0 */
 		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
@@ -320,10 +319,61 @@ int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
+{
+	/* Scale factor is based on the number of bits in fractional portion */
+	static const u32 scale = BIT(HW_ATL_TPS_DESC_RATE_Y_WIDTH);
+	static const u32 frac_msk = HW_ATL_TPS_DESC_RATE_Y_MSK >>
+				    HW_ATL_TPS_DESC_RATE_Y_SHIFT;
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+	int tc;
+
+	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+	hw_atl_tps_tx_desc_rate_mode_set(self, nic_cfg->is_qos ? 1U : 0U);
+	for (tc = 0; tc != nic_cfg->tcs; tc++) {
+		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
+
+		if (en) {
+			/* Nominal rate is always 10G */
+			const u32 rate = 10000U * scale /
+					 nic_cfg->tc_max_rate[tc];
+			const u32 rate_int = rate >>
+					     HW_ATL_TPS_DESC_RATE_Y_WIDTH;
+			const u32 rate_frac = rate & frac_msk;
+
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, rate_int);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, rate_frac);
+		} else {
+			/* A value of 1 indicates the queue is not
+			 * rate controlled.
+			 */
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+		}
+	}
+	for (tc = nic_cfg->tcs; tc != AQ_CFG_TCS_MAX; tc++) {
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, 0U);
+		hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+		hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+
 	/* Tx TC/Queue number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, self->aq_nic_cfg->tc_mode);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index b855459272ca..992ee4ed37cc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -62,6 +62,8 @@ int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr);
 
 int hw_atl_b0_hw_start(struct aq_hw_s *self);
 
+int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self);
+
 int hw_atl_b0_hw_irq_enable(struct aq_hw_s *self, u64 mask);
 int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask);
 int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 8cb6765a1398..0ea791a9c100 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1511,6 +1511,42 @@ void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
 			    tx_pkt_shed_tc_data_weight);
 }
 
+void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
+				      const u32 rate_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_TX_DESC_RATE_MODE_ADR,
+			    HW_ATL_TPS_TX_DESC_RATE_MODE_MSK,
+			    HW_ATL_TPS_TX_DESC_RATE_MODE_SHIFT,
+			    rate_mode);
+}
+
+void hw_atl_tps_tx_desc_rate_en_set(struct aq_hw_s *aq_hw, const u32 desc,
+				    const u32 enable)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_EN_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_EN_MSK,
+			    HW_ATL_TPS_DESC_RATE_EN_SHIFT,
+			    enable);
+}
+
+void hw_atl_tps_tx_desc_rate_x_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_int)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_X_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_X_MSK,
+			    HW_ATL_TPS_DESC_RATE_X_SHIFT,
+			    rate_int);
+}
+
+void hw_atl_tps_tx_desc_rate_y_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_frac)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_Y_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_Y_MSK,
+			    HW_ATL_TPS_DESC_RATE_Y_SHIFT,
+			    rate_frac);
+}
+
 /* tx */
 void hw_atl_tx_tx_reg_res_dis_set(struct aq_hw_s *aq_hw, u32 tx_reg_res_dis)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index b88cb84805d5..c56cc4e8e13c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -710,6 +710,22 @@ void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
 					       u32 tx_pkt_shed_tc_data_weight,
 					u32 tc);
 
+/* set tx descriptor rate mode */
+void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
+				      const u32 rate_mode);
+
+/* set tx packet scheduler descriptor rate enable */
+void hw_atl_tps_tx_desc_rate_en_set(struct aq_hw_s *aq_hw, const u32 desc,
+				    const u32 enable);
+
+/* set tx packet scheduler descriptor rate integral value */
+void hw_atl_tps_tx_desc_rate_x_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_int);
+
+/* set tx packet scheduler descriptor rate fractional value */
+void hw_atl_tps_tx_desc_rate_y_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_frac);
+
 /* tx */
 
 /* set tx register reset disable */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index 5d86ffab4ece..06220792daf1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -2056,6 +2056,24 @@
 /* default value of bitfield tx_tc_mode */
 #define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
 
+/* tx tx_desc_rate_mode bitfield definitions
+ * preprocessor definitions for the bitfield "tx_desc_rate_mode".
+ * port="pif_tps_desc_rate_mode_i"
+ */
+
+/* register address for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_ADR 0x00007900
+/* bitmask for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_MSK 0x00000080
+/* inverted bitmask for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_MSKN 0xFFFFFF7F
+/* lower bit position of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_SHIFT 7
+/* width of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_WIDTH 1
+/* default value of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_DEFAULT 0x0
+
 /* tx tx_buf_en bitfield definitions
  * preprocessor definitions for the bitfield "tx_buf_en".
  * port="pif_tpb_tx_buf_en_i"
@@ -2275,6 +2293,58 @@
 /* default value of bitfield data_tc_arb_mode */
 #define HW_ATL_TPS_DATA_TC_ARB_MODE_DEFAULT 0x0
 
+/* tx desc{r}_rate_en bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_en".
+ * port="pif_tps_desc_rate_en_i[0]"
+ */
+
+/* register address for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_MSK 0x80000000
+/* inverted bitmask for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_MSKN 0x7FFFFFFF
+/* lower bit position of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_SHIFT 31
+/* width of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_WIDTH 1
+/* default value of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_DEFAULT 0x0
+
+/* tx desc{r}_rate_x bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_x".
+ * port="pif_tps_desc0_rate_x"
+ */
+/* register address for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_MSK 0x03FF0000
+/* inverted bitmask for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_MSKN 0xFC00FFFF
+/* lower bit position of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_SHIFT 16
+/* width of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_WIDTH 10
+/* default value of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_DEFAULT 0x0
+
+/* tx desc{r}_rate_y bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_y".
+ * port="pif_tps_desc0_rate_y"
+ */
+/* register address for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_MSK 0x00003FFF
+/* inverted bitmask for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_MSKN 0xFFFFC000
+/* lower bit position of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_SHIFT 0
+/* width of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_WIDTH 14
+/* default value of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_DEFAULT 0x0
+
 /* tx desc_rate_ta_rst bitfield definitions
  * preprocessor definitions for the bitfield "desc_rate_ta_rst".
  * port="pif_tps_desc_rate_ta_rst_i"
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index 05c049661b2e..b42ff81adfeb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -135,6 +135,8 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	unsigned int prio = 0U;
 	u32 tc = 0U;
 
+	hw_atl_b0_hw_init_tx_tc_rate_limit(self);
+
 	/* TPS Descriptor rate init */
 	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
 	hw_atl_tps_tx_pkt_shed_desc_rate_lim_set(self, 0xA);
@@ -143,7 +145,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
 	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
 	tx_buff_size /= cfg->tcs;
@@ -155,8 +156,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 		hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0,
 							       tc);
 		hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
-		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
 
 		/* Tx buf size TC0 */
 		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
@@ -215,8 +214,10 @@ static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 {
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+
 	/* Tx TC/RSS number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, self->aq_nic_cfg->tc_mode);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
-- 
cgit v1.2.3


From 14ef766b13822001087d468aa41f22caa2a42022 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:44 +0300
Subject: net: atlantic: automatically downgrade the number of queues if
 necessary

This patch adds support for automatic queue number downgrade.

On A2: this is a must have, because only TC0/TC1 support more than 4Q.
Other TCs support 4Qs maximum.
Thus, on A2 we must downgrade the number of queues per TC to 4, if more
than 2 TCs are requested.

On A1: this allows using 8TCs even on systems with cpu count >= 8, when
we have 8 queues by default.
We will just automatically switch to 8TCx4Q mode in this case.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 15 ++---
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  5 +-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 78 +++++++++++++++-------
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |  1 +
 4 files changed, 63 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 90a52a4b2d48..743d3b13b39d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -793,8 +793,6 @@ static int aq_set_ringparam(struct net_device *ndev,
 		dev_close(ndev);
 	}
 
-	aq_nic_free_vectors(aq_nic);
-
 	cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min);
 	cfg->rxds = min(cfg->rxds, hw_caps->rxds_max);
 	cfg->rxds = ALIGN(cfg->rxds, AQ_HW_RXD_MULTIPLE);
@@ -803,15 +801,10 @@ static int aq_set_ringparam(struct net_device *ndev,
 	cfg->txds = min(cfg->txds, hw_caps->txds_max);
 	cfg->txds = ALIGN(cfg->txds, AQ_HW_TXD_MULTIPLE);
 
-	for (aq_nic->aq_vecs = 0; aq_nic->aq_vecs < cfg->vecs;
-	     aq_nic->aq_vecs++) {
-		aq_nic->aq_vec[aq_nic->aq_vecs] =
-		    aq_vec_alloc(aq_nic, aq_nic->aq_vecs, cfg);
-		if (unlikely(!aq_nic->aq_vec[aq_nic->aq_vecs])) {
-			err = -ENOMEM;
-			goto err_exit;
-		}
-	}
+	err = aq_nic_realloc_vectors(aq_nic);
+	if (err)
+		goto err_exit;
+
 	if (ndev_running)
 		err = dev_open(ndev, NULL);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index d8817047f4ef..57a116ccad55 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -337,9 +337,12 @@ static int aq_validate_mqprio_opt(struct aq_nic_s *self,
 				  const unsigned int num_tc)
 {
 	const bool has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(self);
+	const unsigned int tcs_max = min_t(u8, aq_nic_cfg->aq_hw_caps->tcs_max,
+					   AQ_CFG_TCS_MAX);
 	int i;
 
-	if (num_tc > aq_hw_num_tcs(self->aq_hw)) {
+	if (num_tc > tcs_max) {
 		netdev_err(self->ndev, "Too many TCs requested\n");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 2e0e7d34fda0..0973214db20f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -65,6 +65,33 @@ static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 		rss_params->indirection_table[i] = i & (num_rss_queues - 1);
 }
 
+/* Recalculate the number of vectors */
+static void aq_nic_cfg_update_num_vecs(struct aq_nic_s *self)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
+	cfg->vecs = min(cfg->vecs, num_online_cpus());
+	if (self->irqvecs > AQ_HW_SERVICE_IRQS)
+		cfg->vecs = min(cfg->vecs, self->irqvecs - AQ_HW_SERVICE_IRQS);
+	/* cfg->vecs should be power of 2 for RSS */
+	cfg->vecs = rounddown_pow_of_two(cfg->vecs);
+
+	if (ATL_HW_IS_CHIP_FEATURE(self->aq_hw, ANTIGUA)) {
+		if (cfg->tcs > 2)
+			cfg->vecs = min(cfg->vecs, 4U);
+	}
+
+	if (cfg->vecs <= 4)
+		cfg->tc_mode = AQ_TC_MODE_8TCS;
+	else
+		cfg->tc_mode = AQ_TC_MODE_4TCS;
+
+	/*rss rings */
+	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
+	aq_nic_rss_init(self, cfg->num_rss_queues);
+}
+
 /* Checks hw_caps and 'corrects' aq_nic_cfg in runtime */
 void aq_nic_cfg_start(struct aq_nic_s *self)
 {
@@ -81,7 +108,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->rxpageorder = AQ_CFG_RX_PAGEORDER;
 	cfg->is_rss = AQ_CFG_IS_RSS_DEF;
-	cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF;
 	cfg->aq_rss.base_cpu_number = AQ_CFG_RSS_BASE_CPU_NUM_DEF;
 	cfg->fc.req = AQ_CFG_FC_MODE;
 	cfg->wol = AQ_CFG_WOL_MODES;
@@ -97,24 +123,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
 	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
 
-	/*rss rings */
-	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
-	cfg->vecs = min(cfg->vecs, num_online_cpus());
-	if (self->irqvecs > AQ_HW_SERVICE_IRQS)
-		cfg->vecs = min(cfg->vecs, self->irqvecs - AQ_HW_SERVICE_IRQS);
-	/* cfg->vecs should be power of 2 for RSS */
-	if (cfg->vecs >= 8U)
-		cfg->vecs = 8U;
-	else if (cfg->vecs >= 4U)
-		cfg->vecs = 4U;
-	else if (cfg->vecs >= 2U)
-		cfg->vecs = 2U;
-	else
-		cfg->vecs = 1U;
-
-	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
-
-	aq_nic_rss_init(self, cfg->num_rss_queues);
+	aq_nic_cfg_update_num_vecs(self);
 
 	cfg->irq_type = aq_pci_func_get_irq_type(self);
 
@@ -125,11 +134,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 		cfg->vecs = 1U;
 	}
 
-	if (cfg->vecs <= 4)
-		cfg->tc_mode = AQ_TC_MODE_8TCS;
-	else
-		cfg->tc_mode = AQ_TC_MODE_4TCS;
-
 	/* Check if we have enough vectors allocated for
 	 * link status IRQ. If no - we'll know link state from
 	 * slower service task.
@@ -1219,6 +1223,22 @@ void aq_nic_free_vectors(struct aq_nic_s *self)
 err_exit:;
 }
 
+int aq_nic_realloc_vectors(struct aq_nic_s *self)
+{
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+
+	aq_nic_free_vectors(self);
+
+	for (self->aq_vecs = 0; self->aq_vecs < cfg->vecs; self->aq_vecs++) {
+		self->aq_vec[self->aq_vecs] = aq_vec_alloc(self, self->aq_vecs,
+							   cfg);
+		if (unlikely(!self->aq_vec[self->aq_vecs]))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 void aq_nic_shutdown(struct aq_nic_s *self)
 {
 	int err = 0;
@@ -1288,6 +1308,7 @@ void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map)
 {
 	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	const unsigned int prev_vecs = cfg->vecs;
 	bool ndev_running;
 	int err = 0;
 	int i;
@@ -1319,9 +1340,18 @@ int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map)
 
 	netdev_set_num_tc(self->ndev, cfg->tcs);
 
+	/* Changing the number of TCs might change the number of vectors */
+	aq_nic_cfg_update_num_vecs(self);
+	if (prev_vecs != cfg->vecs) {
+		err = aq_nic_realloc_vectors(self);
+		if (err)
+			goto err_exit;
+	}
+
 	if (ndev_running)
 		err = dev_open(self->ndev, NULL);
 
+err_exit:
 	return err;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 351c4e68f40d..7a1d799b1e0d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -177,6 +177,7 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down);
 void aq_nic_set_power(struct aq_nic_s *self);
 void aq_nic_free_hot_resources(struct aq_nic_s *self);
 void aq_nic_free_vectors(struct aq_nic_s *self);
+int aq_nic_realloc_vectors(struct aq_nic_s *self);
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu);
 int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev);
 int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags);
-- 
cgit v1.2.3


From 5479e8436f32cdbe76d63119459a7d651c1c39ed Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:45 +0300
Subject: net: atlantic: always use random TC-queue mapping for TX on A2.

This patch changes the TC-queue mapping mechanism used on A2.
Configure the A2 HW in such a way that we can keep queue index mapping
exactly as it was on A1.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 31 ++++++++++++-----
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |  9 +++++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |  4 +++
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        | 39 ++++++++++++++++++++--
 4 files changed, 72 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index b42ff81adfeb..a5bffadde6df 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -95,7 +95,10 @@ static int hw_atl2_hw_queue_to_tc_map_set(struct aq_hw_s *self)
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	unsigned int tcs, q_per_tc;
 	unsigned int tc, q;
-	u32 value = 0;
+	u32 rx_map = 0;
+	u32 tx_map = 0;
+
+	hw_atl2_tpb_tx_tc_q_rand_map_en_set(self, 1U);
 
 	switch (cfg->tc_mode) {
 	case AQ_TC_MODE_8TCS:
@@ -113,14 +116,24 @@ static int hw_atl2_hw_queue_to_tc_map_set(struct aq_hw_s *self)
 	for (tc = 0; tc != tcs; tc++) {
 		unsigned int tc_q_offset = tc * q_per_tc;
 
-		for (q = tc_q_offset; q != tc_q_offset + q_per_tc; q++)
-			value |= tc << HW_ATL2_RX_Q_TC_MAP_SHIFT(q);
+		for (q = tc_q_offset; q != tc_q_offset + q_per_tc; q++) {
+			rx_map |= tc << HW_ATL2_RX_Q_TC_MAP_SHIFT(q);
+			if (HW_ATL2_RX_Q_TC_MAP_ADR(q) !=
+			    HW_ATL2_RX_Q_TC_MAP_ADR(q + 1)) {
+				aq_hw_write_reg(self,
+						HW_ATL2_RX_Q_TC_MAP_ADR(q),
+						rx_map);
+				rx_map = 0;
+			}
 
-		if (HW_ATL2_RX_Q_TC_MAP_ADR(q) !=
-		    HW_ATL2_RX_Q_TC_MAP_ADR(q - 1)) {
-			aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(q - 1),
-					value);
-			value = 0;
+			tx_map |= tc << HW_ATL2_TX_Q_TC_MAP_SHIFT(q);
+			if (HW_ATL2_TX_Q_TC_MAP_ADR(q) !=
+			    HW_ATL2_TX_Q_TC_MAP_ADR(q + 1)) {
+				aq_hw_write_reg(self,
+						HW_ATL2_TX_Q_TC_MAP_ADR(q),
+						tx_map);
+				tx_map = 0;
+			}
 		}
 	}
 
@@ -181,7 +194,7 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
 							cfg->prio_tc_map[prio]);
 
-	/* ATL2 Apply legacy ring to TC mapping */
+	/* ATL2 Apply ring to TC mapping */
 	hw_atl2_hw_queue_to_tc_map_set(self);
 
 	return aq_hw_err_from_flags(self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index f096d0a6bda9..6817fa57cc83 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -68,6 +68,15 @@ void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter)
 
 /* TX */
 
+void hw_atl2_tpb_tx_tc_q_rand_map_en_set(struct aq_hw_s *aq_hw,
+					 const u32 tc_q_rand_map_en)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_ADR,
+			    HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSK,
+			    HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_SHIFT,
+			    tc_q_rand_map_en);
+}
+
 void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_ADR,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index 5c1ae755ffae..d4b087d1dec1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -38,6 +38,10 @@ void hw_atl2_new_rpf_rss_redir_set(struct aq_hw_s *aq_hw, u32 tc, u32 index,
 /* Set VLAN filter tag */
 void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter);
 
+/* set tx random TC-queue mapping enable bit */
+void hw_atl2_tpb_tx_tc_q_rand_map_en_set(struct aq_hw_s *aq_hw,
+					 const u32 tc_q_rand_map_en);
+
 /* set tx buffer clock gate enable */
 void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index b0ac8cd581d7..bf0198ca4e85 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -132,6 +132,24 @@
 /* Default value of bitfield rx_q{Q}_tc_map[2:0] */
 #define HW_ATL2_RX_Q_TC_MAP_DEFAULT 0x0
 
+/* tx tx_tc_q_rand_map_en bitfield definitions
+ * preprocessor definitions for the bitfield "tx_tc_q_rand_map_en".
+ * port="pif_tpb_tx_tc_q_rand_map_en_i"
+ */
+
+/* register address for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_ADR 0x00007900
+/* bitmask for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSK 0x00000200
+/* inverted bitmask for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSKN 0xFFFFFDFF
+/* lower bit position of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_SHIFT 9
+/* width of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_WIDTH 1
+/* default value of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_DEFAULT 0x0
+
 /* tx tx_buffer_clk_gate_en bitfield definitions
  * preprocessor definitions for the bitfield "tx_buffer_clk_gate_en".
  * port="pif_tpb_tx_buffer_clk_gate_en_i"
@@ -150,8 +168,25 @@
 /* default value of bitfield tx_buffer_clk_gate_en */
 #define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_DEFAULT 0x0
 
-/* tx data_tc{t}_credit_max[b:0] bitfield definitions
- * preprocessor definitions for the bitfield "data_tc{t}_credit_max[b:0]".
+/* tx tx_q_tc_map{q} bitfield definitions
+ * preprocessor definitions for the bitfield "tx_q_tc_map{q}".
+ * parameter: queue {q} | bit-level stride | range [0, 31]
+ * port="pif_tpb_tx_q_tc_map0_i[2:0]"
+ */
+
+/* register address for bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_ADR(queue) \
+	(((queue) < 32) ? 0x0000799C + ((queue) / 4) * 4 : 0)
+/* lower bit position of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_SHIFT(queue) \
+	(((queue) < 32) ? ((queue) * 8) % 32 : 0)
+/* width of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_WIDTH 3
+/* default value of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_DEFAULT 0x0
+
+/* tx data_tc{t}_credit_max[f:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_credit_max[f:0]".
  * parameter: tc {t} | stride size 0x4 | range [0, 7]
  * port="pif_tps_data_tc0_credit_max_i[11:0]"
  */
-- 
cgit v1.2.3


From b64f2ac9955bcd3547329c30d8f7a55f84297df8 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:46 +0300
Subject: net: atlantic: change the order of arguments for TC weight/credit
 setters

This patch changes the order of arguments for TC weight/credit setter
functions.
Having the "value to be set" on the right is slightly more robust in
a sense that it's more natural for the humans, so it's a bit more
error-proof this way.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c    |  8 ++++----
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c    |  8 ++++----
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c   | 20 ++++++++++----------
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h   | 16 ++++++++--------
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c | 10 +++++-----
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h |  8 ++++----
 6 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 88b17cf77625..a312864969af 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -136,10 +136,10 @@ static int hw_atl_a0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, 0U);
-	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, 0U);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, 0U);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, 0U);
+	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0U, 0xFFF);
+	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0U, 0x64);
+	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0U, 0x50);
+	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0U, 0x1E);
 
 	/* Tx buf size */
 	buff_size = HW_ATL_A0_TXBUF_MAX;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index abc86eb4f525..2448a09ef7b9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -161,8 +161,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 		u32 threshold = 0U;
 
 		/* TX Packet Scheduler Data TC0 */
-		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
-		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
+		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc, 0xFFF);
+		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, tc, 0x64);
 
 		/* Tx buf size TC0 */
 		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
@@ -334,8 +334,8 @@ int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
 		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
 		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
 
-		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc, 0x50);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, tc, 0x1E);
 
 		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 0ea791a9c100..3c8e8047ea1e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1463,8 +1463,8 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-						   u32 tc)
+						   const u32 tc,
+						   const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL_TPS_DESC_TCTCREDIT_MAX_MSK,
@@ -1473,13 +1473,13 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_desc_tc_weight,
-					       u32 tc)
+					       const u32 tc,
+					       const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_TCTWEIGHT_ADR(tc),
 			    HW_ATL_TPS_DESC_TCTWEIGHT_MSK,
 			    HW_ATL_TPS_DESC_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_desc_tc_weight);
+			    weight);
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
@@ -1492,8 +1492,8 @@ void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-						   u32 tc)
+						   const u32 tc,
+						   const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DATA_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL_TPS_DATA_TCTCREDIT_MAX_MSK,
@@ -1502,13 +1502,13 @@ void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_tc_data_weight,
-					       u32 tc)
+					       const u32 tc,
+					       const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DATA_TCTWEIGHT_ADR(tc),
 			    HW_ATL_TPS_DATA_TCTWEIGHT_MSK,
 			    HW_ATL_TPS_DATA_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_tc_data_weight);
+			    weight);
 }
 
 void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index c56cc4e8e13c..61a6f70c51cd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -688,13 +688,13 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(struct aq_hw_s *aq_hw,
 
 /* set tx packet scheduler descriptor tc max credit */
 void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-					    u32 tc);
+						   const u32 tc,
+						   const u32 max_credit);
 
 /* set tx packet scheduler descriptor tc weight */
 void hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_desc_tc_weight,
-					u32 tc);
+					       const u32 tc,
+					       const u32 weight);
 
 /* set tx packet scheduler descriptor vm arbitration mode */
 void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
@@ -702,13 +702,13 @@ void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
 
 /* set tx packet scheduler tc data max credit */
 void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-					    u32 tc);
+						   const u32 tc,
+						   const u32 max_credit);
 
 /* set tx packet scheduler tc data weight */
 void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_tc_data_weight,
-					u32 tc);
+					       const u32 tc,
+					       const u32 weight);
 
 /* set tx descriptor rate mode */
 void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index 6817fa57cc83..c6a6ba66eb05 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -94,8 +94,8 @@ void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						    u32 max_credit,
-						    u32 tc)
+						    const u32 tc,
+						    const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK,
@@ -104,13 +104,13 @@ void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-						u32 tx_pkt_shed_tc_data_weight,
-						u32 tc)
+						const u32 tc,
+						const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc),
 			    HW_ATL2_TPS_DATA_TCTWEIGHT_MSK,
 			    HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_tc_data_weight);
+			    weight);
 }
 
 u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index d4b087d1dec1..883fa009bc0e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -47,13 +47,13 @@ void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en);
 
 /* set tx packet scheduler tc data max credit */
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						    u32 max_credit,
-						    u32 tc);
+						    const u32 tc,
+						    const u32 max_credit);
 
 /* set tx packet scheduler tc data weight */
 void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-						u32 tx_pkt_shed_tc_data_weight,
-						u32 tc);
+						const u32 tc,
+						const u32 weight);
 
 u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw);
 
-- 
cgit v1.2.3


From 2deac71ac492a6025b163701436e0aa39435a05f Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:47 +0300
Subject: net: atlantic: QoS implementation: min_rate

This patch adds support for mqprio min_rate limiters.

A2 HW supports Weighted Strict Priority (WSP) arbitration for Tx Descriptor
Queue scheduling among TCs, which can be used for min_rate shaping.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |   2 +
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  26 +++--
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |  28 +++++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h    |   4 +
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  77 +++++++++++--
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h  |   2 -
 .../ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c   | 127 +++++++++++++++++++--
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.c        |   9 ++
 .../aquantia/atlantic/hw_atl2/hw_atl2_llh.h        |   3 +
 .../atlantic/hw_atl2/hw_atl2_llh_internal.h        |  62 ++++++----
 10 files changed, 286 insertions(+), 54 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index d31e576f8b86..ed5b465bc664 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -280,6 +280,8 @@ struct aq_hw_ops {
 	int (*hw_rss_hash_set)(struct aq_hw_s *self,
 			       struct aq_rss_parameters *rss_params);
 
+	int (*hw_tc_rate_limit_set)(struct aq_hw_s *self);
+
 	int (*hw_get_regs)(struct aq_hw_s *self,
 			   const struct aq_hw_caps_s *aq_hw_caps,
 			   u32 *regs_buff);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 57a116ccad55..8a1da044e908 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -340,7 +340,6 @@ static int aq_validate_mqprio_opt(struct aq_nic_s *self,
 	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(self);
 	const unsigned int tcs_max = min_t(u8, aq_nic_cfg->aq_hw_caps->tcs_max,
 					   AQ_CFG_TCS_MAX);
-	int i;
 
 	if (num_tc > tcs_max) {
 		netdev_err(self->ndev, "Too many TCs requested\n");
@@ -352,12 +351,9 @@ static int aq_validate_mqprio_opt(struct aq_nic_s *self,
 		return -EOPNOTSUPP;
 	}
 
-	for (i = 0; i < num_tc; i++) {
-		if (has_min_rate && mqprio->min_rate[i]) {
-			netdev_err(self->ndev,
-				   "Min tx rate is not supported\n");
-			return -EOPNOTSUPP;
-		}
+	if (has_min_rate && !ATL_HW_IS_CHIP_FEATURE(self->aq_hw, ANTIGUA)) {
+		netdev_err(self->ndev, "Min tx rate is not supported\n");
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -368,23 +364,35 @@ static int aq_ndo_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct tc_mqprio_qopt_offload *mqprio = type_data;
 	struct aq_nic_s *aq_nic = netdev_priv(dev);
+	bool has_min_rate;
+	bool has_max_rate;
 	int err;
 	int i;
 
 	if (type != TC_SETUP_QDISC_MQPRIO)
 		return -EOPNOTSUPP;
 
+	has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
+
 	err = aq_validate_mqprio_opt(aq_nic, mqprio, mqprio->qopt.num_tc);
 	if (err)
 		return err;
 
-	if (mqprio->flags & TC_MQPRIO_F_MAX_RATE) {
-		for (i = 0; i < mqprio->qopt.num_tc; i++) {
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		if (has_max_rate) {
 			u64 max_rate = mqprio->max_rate[i];
 
 			do_div(max_rate, AQ_MBPS_DIVISOR);
 			aq_nic_setup_tc_max_rate(aq_nic, i, (u32)max_rate);
 		}
+
+		if (has_min_rate) {
+			u64 min_rate = mqprio->min_rate[i];
+
+			do_div(min_rate, AQ_MBPS_DIVISOR);
+			aq_nic_setup_tc_min_rate(aq_nic, i, (u32)min_rate);
+		}
 	}
 
 	return aq_nic_setup_tc_mqprio(aq_nic, mqprio->qopt.num_tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 0973214db20f..4435c6374f7e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -196,6 +196,9 @@ static int aq_nic_update_link_status(struct aq_nic_s *self)
 #if IS_ENABLED(CONFIG_MACSEC)
 		aq_macsec_enable(self);
 #endif
+		if (self->aq_hw_ops->hw_tc_rate_limit_set)
+			self->aq_hw_ops->hw_tc_rate_limit_set(self->aq_hw);
+
 		netif_tx_wake_all_queues(self->ndev);
 	}
 	if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) {
@@ -1374,3 +1377,28 @@ int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
 
 	return 0;
 }
+
+int aq_nic_setup_tc_min_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 min_rate)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	if (tc >= AQ_CFG_TCS_MAX)
+		return -EINVAL;
+
+	if (min_rate)
+		set_bit(tc, &cfg->tc_min_rate_msk);
+	else
+		clear_bit(tc, &cfg->tc_min_rate_msk);
+
+	if (min_rate && min_rate < 20) {
+		netdev_warn(self->ndev,
+			"Setting %s to the minimum usable value of %dMbps.\n",
+			"min rate", 20);
+		cfg->tc_min_rate[tc] = 20;
+	} else {
+		cfg->tc_min_rate[tc] = min_rate;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 7a1d799b1e0d..2ab003065e62 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -66,6 +66,8 @@ struct aq_nic_cfg_s {
 	u8  tcs;
 	u8 prio_tc_map[8];
 	u32 tc_max_rate[AQ_CFG_TCS_MAX];
+	unsigned long tc_min_rate_msk;
+	u32 tc_min_rate[AQ_CFG_TCS_MAX];
 	struct aq_rss_parameters aq_rss;
 	u32 eee_speeds;
 };
@@ -198,4 +200,6 @@ void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map);
 int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
 			     const u32 max_rate);
+int aq_nic_setup_tc_min_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 min_rate);
 #endif /* AQ_NIC_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 2448a09ef7b9..320f3669305d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -138,8 +138,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	unsigned int prio = 0U;
 	u32 tc = 0U;
 
-	hw_atl_b0_hw_init_tx_tc_rate_limit(self);
-
 	if (cfg->is_ptp) {
 		tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
 		rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
@@ -152,18 +150,11 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	/* TPS VM init */
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
-	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
-
 	tx_buff_size /= cfg->tcs;
 	rx_buff_size /= cfg->tcs;
 	for (tc = 0; tc < cfg->tcs; tc++) {
 		u32 threshold = 0U;
 
-		/* TX Packet Scheduler Data TC0 */
-		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc, 0xFFF);
-		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, tc, 0x64);
-
 		/* Tx buf size TC0 */
 		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 
@@ -319,24 +310,87 @@ int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
+static int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
 {
+	static const u32 max_weight = BIT(HW_ATL_TPS_DATA_TCTWEIGHT_WIDTH) - 1;
 	/* Scale factor is based on the number of bits in fractional portion */
 	static const u32 scale = BIT(HW_ATL_TPS_DESC_RATE_Y_WIDTH);
 	static const u32 frac_msk = HW_ATL_TPS_DESC_RATE_Y_MSK >>
 				    HW_ATL_TPS_DESC_RATE_Y_SHIFT;
+	const u32 link_speed = self->aq_link_status.mbps;
 	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+	unsigned long num_min_rated_tcs = 0;
+	u32 tc_weight[AQ_CFG_TCS_MAX];
+	u32 fixed_max_credit;
+	u8 min_rate_msk = 0;
+	u32 sum_weight = 0;
 	int tc;
 
+	/* By default max_credit is based upon MTU (in unit of 64b) */
+	fixed_max_credit = nic_cfg->aq_hw_caps->mtu / 64;
+
+	if (link_speed) {
+		min_rate_msk = nic_cfg->tc_min_rate_msk &
+			       (BIT(nic_cfg->tcs) - 1);
+		num_min_rated_tcs = hweight8(min_rate_msk);
+	}
+
+	/* First, calculate weights where min_rate is specified */
+	if (num_min_rated_tcs) {
+		for (tc = 0; tc != nic_cfg->tcs; tc++) {
+			if (!nic_cfg->tc_min_rate[tc]) {
+				tc_weight[tc] = 0;
+				continue;
+			}
+
+			tc_weight[tc] = (-1L + link_speed +
+					 nic_cfg->tc_min_rate[tc] *
+					 max_weight) /
+					link_speed;
+			tc_weight[tc] = min(tc_weight[tc], max_weight);
+			sum_weight += tc_weight[tc];
+		}
+	}
+
+	/* WSP, if min_rate is set for at least one TC.
+	 * RR otherwise.
+	 */
+	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U);
+	/* Data TC Arbiter takes precedence over Descriptor TC Arbiter,
+	 * leave Descriptor TC Arbiter as RR.
+	 */
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+
 	hw_atl_tps_tx_desc_rate_mode_set(self, nic_cfg->is_qos ? 1U : 0U);
+
 	for (tc = 0; tc != nic_cfg->tcs; tc++) {
 		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
 		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+		u32 weight, max_credit;
 
-		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc, 0x50);
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc,
+							      fixed_max_credit);
 		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, tc, 0x1E);
 
+		if (num_min_rated_tcs) {
+			weight = tc_weight[tc];
+
+			if (!weight && sum_weight < max_weight)
+				weight = (max_weight - sum_weight) /
+					 (nic_cfg->tcs - num_min_rated_tcs);
+			else if (!weight)
+				weight = 0x64;
+
+			max_credit = max(8 * weight, fixed_max_credit);
+		} else {
+			weight = 0x64;
+			max_credit = 0xFFF;
+		}
+
+		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, tc, weight);
+		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc,
+							      max_credit);
+
 		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
 
 		if (en) {
@@ -1550,6 +1604,7 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
+	.hw_tc_rate_limit_set        = hw_atl_b0_hw_init_tx_tc_rate_limit,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index 992ee4ed37cc..b855459272ca 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -62,8 +62,6 @@ int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr);
 
 int hw_atl_b0_hw_start(struct aq_hw_s *self);
 
-int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self);
-
 int hw_atl_b0_hw_irq_enable(struct aq_hw_s *self, u64 mask);
 int hw_atl_b0_hw_irq_disable(struct aq_hw_s *self, u64 mask);
 int hw_atl_b0_hw_irq_read(struct aq_hw_s *self, u64 *mask);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index a5bffadde6df..f941773b3e20 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -10,6 +10,7 @@
 #include "hw_atl/hw_atl_b0.h"
 #include "hw_atl/hw_atl_utils.h"
 #include "hw_atl/hw_atl_llh.h"
+#include "hw_atl/hw_atl_llh_internal.h"
 #include "hw_atl2_utils.h"
 #include "hw_atl2_llh.h"
 #include "hw_atl2_internal.h"
@@ -148,8 +149,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	unsigned int prio = 0U;
 	u32 tc = 0U;
 
-	hw_atl_b0_hw_init_tx_tc_rate_limit(self);
-
 	/* TPS Descriptor rate init */
 	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
 	hw_atl_tps_tx_pkt_shed_desc_rate_lim_set(self, 0xA);
@@ -157,19 +156,11 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	/* TPS VM init */
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
-	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
-
 	tx_buff_size /= cfg->tcs;
 	rx_buff_size /= cfg->tcs;
 	for (tc = 0; tc < cfg->tcs; tc++) {
 		u32 threshold = 0U;
 
-		/* TX Packet Scheduler Data TC0 */
-		hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0,
-							       tc);
-		hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
-
 		/* Tx buf size TC0 */
 		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 
@@ -225,6 +216,121 @@ static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl2_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
+{
+	static const u32 max_weight = BIT(HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH) - 1;
+	/* Scale factor is based on the number of bits in fractional portion */
+	static const u32 scale = BIT(HW_ATL_TPS_DESC_RATE_Y_WIDTH);
+	static const u32 frac_msk = HW_ATL_TPS_DESC_RATE_Y_MSK >>
+				    HW_ATL_TPS_DESC_RATE_Y_SHIFT;
+	const u32 link_speed = self->aq_link_status.mbps;
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+	unsigned long num_min_rated_tcs = 0;
+	u32 tc_weight[AQ_CFG_TCS_MAX];
+	u32 fixed_max_credit_4b;
+	u32 fixed_max_credit;
+	u8 min_rate_msk = 0;
+	u32 sum_weight = 0;
+	int tc;
+
+	/* By default max_credit is based upon MTU (in unit of 64b) */
+	fixed_max_credit = nic_cfg->aq_hw_caps->mtu / 64;
+	/* in unit of 4b */
+	fixed_max_credit_4b = nic_cfg->aq_hw_caps->mtu / 4;
+
+	if (link_speed) {
+		min_rate_msk = nic_cfg->tc_min_rate_msk &
+			       (BIT(nic_cfg->tcs) - 1);
+		num_min_rated_tcs = hweight8(min_rate_msk);
+	}
+
+	/* First, calculate weights where min_rate is specified */
+	if (num_min_rated_tcs) {
+		for (tc = 0; tc != nic_cfg->tcs; tc++) {
+			if (!nic_cfg->tc_min_rate[tc]) {
+				tc_weight[tc] = 0;
+				continue;
+			}
+
+			tc_weight[tc] = (-1L + link_speed +
+					 nic_cfg->tc_min_rate[tc] *
+					 max_weight) /
+					link_speed;
+			tc_weight[tc] = min(tc_weight[tc], max_weight);
+			sum_weight += tc_weight[tc];
+		}
+	}
+
+	/* WSP, if min_rate is set for at least one TC.
+	 * RR otherwise.
+	 */
+	hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U);
+	/* Data TC Arbiter takes precedence over Descriptor TC Arbiter,
+	 * leave Descriptor TC Arbiter as RR.
+	 */
+	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+
+	hw_atl_tps_tx_desc_rate_mode_set(self, nic_cfg->is_qos ? 1U : 0U);
+
+	for (tc = 0; tc != nic_cfg->tcs; tc++) {
+		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+		u32 weight, max_credit;
+
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc,
+							      fixed_max_credit);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, tc, 0x1E);
+
+		if (num_min_rated_tcs) {
+			weight = tc_weight[tc];
+
+			if (!weight && sum_weight < max_weight)
+				weight = (max_weight - sum_weight) /
+					 (nic_cfg->tcs - num_min_rated_tcs);
+			else if (!weight)
+				weight = 0x640;
+
+			max_credit = max(2 * weight, fixed_max_credit_4b);
+		} else {
+			weight = 0x640;
+			max_credit = 0xFFF0;
+		}
+
+		hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, tc, weight);
+		hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc,
+							       max_credit);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
+
+		if (en) {
+			/* Nominal rate is always 10G */
+			const u32 rate = 10000U * scale /
+					 nic_cfg->tc_max_rate[tc];
+			const u32 rate_int = rate >>
+					     HW_ATL_TPS_DESC_RATE_Y_WIDTH;
+			const u32 rate_frac = rate & frac_msk;
+
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, rate_int);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, rate_frac);
+		} else {
+			/* A value of 1 indicates the queue is not
+			 * rate controlled.
+			 */
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+		}
+	}
+	for (tc = nic_cfg->tcs; tc != AQ_CFG_TCS_MAX; tc++) {
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, 0U);
+		hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+		hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 {
 	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
@@ -730,6 +836,7 @@ const struct aq_hw_ops hw_atl2_ops = {
 	.hw_interrupt_moderation_set = hw_atl2_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl2_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
+	.hw_tc_rate_limit_set        = hw_atl2_hw_init_tx_tc_rate_limit,
 	.hw_get_hw_stats             = hw_atl2_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl2_utils_get_fw_version,
 	.hw_set_offload              = hw_atl_b0_hw_offload_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
index c6a6ba66eb05..cd954b11d24a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c
@@ -93,6 +93,15 @@ void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
 			tx_intr_moderation_ctl);
 }
 
+void hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(struct aq_hw_s *aq_hw,
+					       const u32 data_arb_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TC_ARB_MODE_ADR,
+			    HW_ATL2_TPS_DATA_TC_ARB_MODE_MSK,
+			    HW_ATL2_TPS_DATA_TC_ARB_MODE_SHIFT,
+			    data_arb_mode);
+}
+
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 						    const u32 tc,
 						    const u32 max_credit)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
index 883fa009bc0e..98c7a4621297 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h
@@ -45,6 +45,9 @@ void hw_atl2_tpb_tx_tc_q_rand_map_en_set(struct aq_hw_s *aq_hw,
 /* set tx buffer clock gate enable */
 void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en);
 
+void hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(struct aq_hw_s *aq_hw,
+					       const u32 data_arb_mode);
+
 /* set tx packet scheduler tc data max credit */
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 						    const u32 tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
index bf0198ca4e85..e34c5cda061e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h
@@ -185,42 +185,60 @@
 /* default value of bitfield tx_q_tc_map{q} */
 #define HW_ATL2_TX_Q_TC_MAP_DEFAULT 0x0
 
+/* tx data_tc_arb_mode bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc_arb_mode".
+ * port="pif_tps_data_tc_arb_mode_i"
+ */
+
+/* register address for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_ADR 0x00007100
+/* bitmask for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_MSK 0x00000003
+/* inverted bitmask for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_MSKN 0xfffffffc
+/* lower bit position of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_SHIFT 0
+/* width of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_WIDTH 2
+/* default value of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_DEFAULT 0x0
+
 /* tx data_tc{t}_credit_max[f:0] bitfield definitions
  * preprocessor definitions for the bitfield "data_tc{t}_credit_max[f:0]".
  * parameter: tc {t} | stride size 0x4 | range [0, 7]
- * port="pif_tps_data_tc0_credit_max_i[11:0]"
+ * port="pif_tps_data_tc0_credit_max_i[15:0]"
  */
 
-/* register address for bitfield data_tc{t}_credit_max[b:0] */
+/* register address for bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc) (0x00007110 + (tc) * 0x4)
-/* bitmask for bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK 0x0fff0000
-/* inverted bitmask for bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSKN 0xf000ffff
-/* lower bit position of bitfield data_tc{t}_credit_max[b:0] */
+/* bitmask for bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK 0xffff0000
+/* inverted bitmask for bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSKN 0x0000ffff
+/* lower bit position of bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_SHIFT 16
-/* width of bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_WIDTH 12
-/* default value of bitfield data_tc{t}_credit_max[b:0] */
+/* width of bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_WIDTH 16
+/* default value of bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_DEFAULT 0x0
 
-/* tx data_tc{t}_weight[8:0] bitfield definitions
- * preprocessor definitions for the bitfield "data_tc{t}_weight[8:0]".
+/* tx data_tc{t}_weight[e:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_weight[e:0]".
  * parameter: tc {t} | stride size 0x4 | range [0, 7]
- * port="pif_tps_data_tc0_weight_i[8:0]"
+ * port="pif_tps_data_tc0_weight_i[14:0]"
  */
 
-/* register address for bitfield data_tc{t}_weight[8:0] */
+/* register address for bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc) (0x00007110 + (tc) * 0x4)
-/* bitmask for bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSK 0x000001ff
-/* inverted bitmask for bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSKN 0xfffffe00
-/* lower bit position of bitfield data_tc{t}_weight[8:0] */
+/* bitmask for bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSK 0x00007fff
+/* inverted bitmask for bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSKN 0xffff8000
+/* lower bit position of bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT 0
-/* width of bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH 9
-/* default value of bitfield data_tc{t}_weight[8:0] */
+/* width of bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH 15
+/* default value of bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_DEFAULT 0x0
 
 /* tx interrupt moderation control register definitions
-- 
cgit v1.2.3


From 40f05e5b0d0e6ed5cc868cd09fa976495716b8f9 Mon Sep 17 00:00:00 2001
From: Mark Starovoytov <mstarovoitov@marvell.com>
Date: Fri, 22 May 2020 11:19:48 +0300
Subject: net: atlantic: proper rss_ctrl1 (54c0) initialization

This patch fixes an inconsistency between code and spec, which
was found while working on the QoS implementation.

When 8TCs are used, 2 is the maximum supported number of index bits.
In a 4TC mode, we do support 3, but we shouldn't really use the bytes,
which are intended for the 8TC mode.

Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c    | 16 ++++++++++++++--
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h    |  2 ++
 .../aquantia/atlantic/hw_atl/hw_atl_b0_internal.h        |  4 ++++
 drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c |  4 +---
 .../aquantia/atlantic/hw_atl2/hw_atl2_internal.h         |  3 ---
 5 files changed, 21 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 320f3669305d..14d79f70cad7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -447,6 +447,19 @@ static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 	return aq_hw_err_from_flags(self);
 }
 
+void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	u32 rss_ctrl1 = HW_ATL_RSS_DISABLED;
+
+	if (cfg->is_rss)
+		rss_ctrl1 = (cfg->tc_mode == AQ_TC_MODE_8TCS) ?
+			    HW_ATL_RSS_ENABLED_8TCS_2INDEX_BITS :
+			    HW_ATL_RSS_ENABLED_4TCS_3INDEX_BITS;
+
+	hw_atl_reg_rx_flr_rss_control1set(self, rss_ctrl1);
+}
+
 static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
@@ -459,8 +472,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
 
 	/* RSS Ring selection */
-	hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ?
-					0xB3333333U : 0x00000000U);
+	hw_atl_b0_hw_init_rx_rss_ctrl1(self);
 
 	/* Multicast filters */
 	for (i = HW_ATL_B0_MAC_MAX; i--;) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index b855459272ca..30f468f2084d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -58,6 +58,8 @@ int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self,
 int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
 int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
 
+void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self);
+
 int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr);
 
 int hw_atl_b0_hw_start(struct aq_hw_s *self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 4fba4e0928c7..cf460d61a45e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -151,6 +151,10 @@
 #define HW_ATL_B0_MAX_RXD 8184U
 #define HW_ATL_B0_MAX_TXD 8184U
 
+#define HW_ATL_RSS_DISABLED 0x00000000U
+#define HW_ATL_RSS_ENABLED_8TCS_2INDEX_BITS 0xA2222222U
+#define HW_ATL_RSS_ENABLED_4TCS_3INDEX_BITS 0x80003333U
+
 /* HW layer capabilities */
 
 #endif /* HW_ATL_B0_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index f941773b3e20..8df9d4ef36f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -475,9 +475,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl2_rpf_rss_hash_type_set(self, HW_ATL2_RPF_RSS_HASH_TYPE_ALL);
 
 	/* RSS Ring selection */
-	hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ?
-						HW_ATL_RSS_ENABLED_3INDEX_BITS :
-						HW_ATL_RSS_DISABLED);
+	hw_atl_b0_hw_init_rx_rss_ctrl1(self);
 
 	/* Multicast filters */
 	for (i = HW_ATL2_MAC_MAX; i--;) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
index 9ac1979a4867..5a89bb8722f9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h
@@ -117,9 +117,6 @@ enum HW_ATL2_RPF_RSS_HASH_TYPE {
 					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_UDP,
 };
 
-#define HW_ATL_RSS_DISABLED 0x00000000U
-#define HW_ATL_RSS_ENABLED_3INDEX_BITS 0xB3333333U
-
 #define HW_ATL_MCAST_FLT_ANY_TO_HOST 0x00010FFFU
 
 struct hw_atl2_priv {
-- 
cgit v1.2.3


From 68f236df93a986379e61191157848b4e7d303285 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:52 +0300
Subject: net: ena: add support for the rx offset feature

Newer ENA devices can write data to rx buffers with an offset
from the beginning of the buffer.

This commit adds support for this feature in the driver.

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_admin_defs.h  |  5 ++++-
 drivers/net/ethernet/amazon/ena/ena_eth_com.c     | 18 ++++++++++++------
 drivers/net/ethernet/amazon/ena/ena_eth_com.h     |  1 +
 drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h |  4 +++-
 drivers/net/ethernet/amazon/ena/ena_netdev.c      |  8 ++++++++
 5 files changed, 28 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 7be3dcbf3d16..727836f638ad 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -813,7 +813,8 @@ struct ena_admin_host_info {
 
 	u16 reserved;
 
-	/* 1 :0 : reserved
+	/* 0 : reserved
+	 * 1 : rx_offset
 	 * 2 : interrupt_moderation
 	 * 31:3 : reserved
 	 */
@@ -1124,6 +1125,8 @@ struct ena_admin_ena_mmio_req_read_less_resp {
 #define ENA_ADMIN_HOST_INFO_DEVICE_MASK                     GENMASK(7, 3)
 #define ENA_ADMIN_HOST_INFO_BUS_SHIFT                       8
 #define ENA_ADMIN_HOST_INFO_BUS_MASK                        GENMASK(15, 8)
+#define ENA_ADMIN_HOST_INFO_RX_OFFSET_SHIFT                 1
+#define ENA_ADMIN_HOST_INFO_RX_OFFSET_MASK                  BIT(1)
 #define ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_SHIFT      2
 #define ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK       BIT(2)
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 2845ac277724..a014f514c069 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -519,7 +519,7 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq,
 	struct ena_eth_io_rx_cdesc_base *cdesc = NULL;
 	u16 cdesc_idx = 0;
 	u16 nb_hw_desc;
-	u16 i;
+	u16 i = 0;
 
 	WARN(io_cq->direction != ENA_COM_IO_QUEUE_DIRECTION_RX, "wrong Q type");
 
@@ -538,13 +538,19 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq,
 		return -ENOSPC;
 	}
 
-	for (i = 0; i < nb_hw_desc; i++) {
+	cdesc = ena_com_rx_cdesc_idx_to_ptr(io_cq, cdesc_idx);
+	ena_rx_ctx->pkt_offset = cdesc->offset;
+
+	do {
+		ena_buf[i].len = cdesc->length;
+		ena_buf[i].req_id = cdesc->req_id;
+
+		if (++i >= nb_hw_desc)
+			break;
+
 		cdesc = ena_com_rx_cdesc_idx_to_ptr(io_cq, cdesc_idx + i);
 
-		ena_buf->len = cdesc->length;
-		ena_buf->req_id = cdesc->req_id;
-		ena_buf++;
-	}
+	} while (1);
 
 	/* Update SQ head ptr */
 	io_sq->next_to_comp += nb_hw_desc;
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index 77986c0ea52c..9834b5cdb655 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -73,6 +73,7 @@ struct ena_com_rx_ctx {
 	u32 hash;
 	u16 descs;
 	int max_bufs;
+	u8 pkt_offset;
 };
 
 int ena_com_prepare_tx(struct ena_com_io_sq *io_sq,
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
index 00e0f056a741..ee28fb067d8c 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
@@ -264,7 +264,9 @@ struct ena_eth_io_rx_cdesc_base {
 
 	u16 sub_qid;
 
-	u16 reserved;
+	u8 offset;
+
+	u8 reserved;
 };
 
 /* 8-word format */
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 85b87ed02dd5..33578297dc56 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1435,6 +1435,8 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page,
 				rx_info->page_offset, len, ENA_PAGE_SIZE);
+		/* The offset is non zero only for the first buffer */
+		rx_info->page_offset = 0;
 
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "rx skb updated. len %d. data_len %d\n",
@@ -1590,6 +1592,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 {
 	u16 next_to_clean = rx_ring->next_to_clean;
 	struct ena_com_rx_ctx ena_rx_ctx;
+	struct ena_rx_buffer *rx_info;
 	struct ena_adapter *adapter;
 	u32 res_budget, work_done;
 	int rx_copybreak_pkt = 0;
@@ -1614,6 +1617,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 		ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
 		ena_rx_ctx.max_bufs = rx_ring->sgl_size;
 		ena_rx_ctx.descs = 0;
+		ena_rx_ctx.pkt_offset = 0;
 		rc = ena_com_rx_pkt(rx_ring->ena_com_io_cq,
 				    rx_ring->ena_com_io_sq,
 				    &ena_rx_ctx);
@@ -1623,6 +1627,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 		if (unlikely(ena_rx_ctx.descs == 0))
 			break;
 
+		rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
+		rx_info->page_offset = ena_rx_ctx.pkt_offset;
+
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
 			  rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto,
@@ -3111,6 +3118,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev,
 	host_info->num_cpus = num_online_cpus();
 
 	host_info->driver_supported_features =
+		ENA_ADMIN_HOST_INFO_RX_OFFSET_MASK |
 		ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK;
 
 	rc = ena_com_set_host_attributes(ena_dev);
-- 
cgit v1.2.3


From 7cfe9a55934627deb95da87e35c552bd6241133e Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:53 +0300
Subject: net: ena: rename ena_com_free_desc to make API more uniform

Rename ena_com_free_desc to ena_com_free_q_entries to match
the LLQ mode.

In non-LLQ mode, an entry in an IO ring corresponds to a
a descriptor. In LLQ mode an entry may correspond to several
descriptors (per LLQ definition).

Signed-off-by: Igor Chauskin <igorch@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_eth_com.h | 6 +++---
 drivers/net/ethernet/amazon/ena/ena_netdev.c  | 5 ++---
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index 9834b5cdb655..8b1afd3b32f2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -96,7 +96,7 @@ static inline void ena_com_unmask_intr(struct ena_com_io_cq *io_cq,
 	writel(intr_reg->intr_control, io_cq->unmask_reg);
 }
 
-static inline int ena_com_free_desc(struct ena_com_io_sq *io_sq)
+static inline int ena_com_free_q_entries(struct ena_com_io_sq *io_sq)
 {
 	u16 tail, next_to_comp, cnt;
 
@@ -114,7 +114,7 @@ static inline bool ena_com_sq_have_enough_space(struct ena_com_io_sq *io_sq,
 	int temp;
 
 	if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST)
-		return ena_com_free_desc(io_sq) >= required_buffers;
+		return ena_com_free_q_entries(io_sq) >= required_buffers;
 
 	/* This calculation doesn't need to be 100% accurate. So to reduce
 	 * the calculation overhead just Subtract 2 lines from the free descs
@@ -123,7 +123,7 @@ static inline bool ena_com_sq_have_enough_space(struct ena_com_io_sq *io_sq,
 	 */
 	temp = required_buffers / io_sq->llq_info.descs_per_entry + 2;
 
-	return ena_com_free_desc(io_sq) > temp;
+	return ena_com_free_q_entries(io_sq) > temp;
 }
 
 static inline bool ena_com_meta_desc_changed(struct ena_com_io_sq *io_sq,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 33578297dc56..c3cbe48b353e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1691,7 +1691,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 
 	rx_ring->next_to_clean = next_to_clean;
 
-	refill_required = ena_com_free_desc(rx_ring->ena_com_io_sq);
+	refill_required = ena_com_free_q_entries(rx_ring->ena_com_io_sq);
 	refill_threshold =
 		min_t(int, rx_ring->ring_size / ENA_RX_REFILL_THRESH_DIVIDER,
 		      ENA_RX_REFILL_THRESH_PACKET);
@@ -3694,8 +3694,7 @@ static void check_for_empty_rx_ring(struct ena_adapter *adapter)
 	for (i = 0; i < adapter->num_io_queues; i++) {
 		rx_ring = &adapter->rx_ring[i];
 
-		refill_required =
-			ena_com_free_desc(rx_ring->ena_com_io_sq);
+		refill_required = ena_com_free_q_entries(rx_ring->ena_com_io_sq);
 		if (unlikely(refill_required == (rx_ring->ring_size - 1))) {
 			rx_ring->empty_rx_queue++;
 
-- 
cgit v1.2.3


From f391503b7a11c6ca033a6e916cee23b85e21a1f1 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:54 +0300
Subject: net: ena: use explicit variable size for clarity

Use u64 instead of unsigned long long for clarity

Signed-off-by: Shai Brandes <shaibran@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index b51bf62af11b..02780f9fa586 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2003,7 +2003,7 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 	struct ena_admin_aenq_entry *aenq_e;
 	struct ena_admin_aenq_common_desc *aenq_common;
 	struct ena_com_aenq *aenq  = &dev->aenq;
-	unsigned long long timestamp;
+	u64 timestamp;
 	ena_aenq_handler handler_cb;
 	u16 masked_head, processed = 0;
 	u8 phase;
@@ -2021,9 +2021,8 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 		 */
 		dma_rmb();
 
-		timestamp =
-			(unsigned long long)aenq_common->timestamp_low |
-			((unsigned long long)aenq_common->timestamp_high << 32);
+		timestamp = (u64)aenq_common->timestamp_low |
+			    ((u64)aenq_common->timestamp_high << 32);
 		pr_debug("AENQ! Group[%x] Syndrom[%x] timestamp: [%llus]\n",
 			 aenq_common->group, aenq_common->syndrom, timestamp);
 
-- 
cgit v1.2.3


From adb3fb388933e03c61e941bce4a0dac4a6ae98c0 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:55 +0300
Subject: net: ena: fix ena_com_comp_status_to_errno() return value

Default return value should be -EINVAL since the input
in this case was unexpected.
Also remove the now redundant check in the beginning
of the function.

Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 02780f9fa586..921945dace22 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -523,9 +523,6 @@ static int ena_com_comp_status_to_errno(u8 comp_status)
 	if (unlikely(comp_status != 0))
 		pr_err("admin command failed[%u]\n", comp_status);
 
-	if (unlikely(comp_status > ENA_ADMIN_UNKNOWN_ERROR))
-		return -EINVAL;
-
 	switch (comp_status) {
 	case ENA_ADMIN_SUCCESS:
 		return 0;
@@ -540,7 +537,7 @@ static int ena_com_comp_status_to_errno(u8 comp_status)
 		return -EINVAL;
 	}
 
-	return 0;
+	return -EINVAL;
 }
 
 static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx,
-- 
cgit v1.2.3


From da447b3b542f2d89e368c8991203ae6aa025ddeb Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:56 +0300
Subject: net: ena: simplify ena_com_update_intr_delay_resolution()

Initialize prev_intr_delay_resolution with ena_dev->intr_delay_resolution
unconditionally, since it is initialized with
ENA_DEFAULT_INTR_DELAY_RESOLUTION in ena_probe(). This approach makes much
more sense than handling errors of not initializing it.

Also added unlikely to if condition.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 921945dace22..e2025eb86984 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -1281,13 +1281,9 @@ static int ena_com_ind_tbl_convert_to_device(struct ena_com_dev *ena_dev)
 static void ena_com_update_intr_delay_resolution(struct ena_com_dev *ena_dev,
 						 u16 intr_delay_resolution)
 {
-	/* Initial value of intr_delay_resolution might be 0 */
-	u16 prev_intr_delay_resolution =
-		ena_dev->intr_delay_resolution ?
-		ena_dev->intr_delay_resolution :
-		ENA_DEFAULT_INTR_DELAY_RESOLUTION;
+	u16 prev_intr_delay_resolution = ena_dev->intr_delay_resolution;
 
-	if (!intr_delay_resolution) {
+	if (unlikely(!intr_delay_resolution)) {
 		pr_err("Illegal intr_delay_resolution provided. Going to use default 1 usec resolution\n");
 		intr_delay_resolution = ENA_DEFAULT_INTR_DELAY_RESOLUTION;
 	}
-- 
cgit v1.2.3


From 95d0fcb5704aa179c1aa8e5ea54f7715f0252383 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:57 +0300
Subject: net: ena: cosmetic: rename ena_update_tx/rx_rings_intr_moderation()

Rename ena_update_tx/rx_rings_intr_moderation() to
ena_update_tx/rx_rings_nonadaptive_intr_moderation()
to distinguish between adaptive and non adaptive interrupt moderaion.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 830d3711d6ee..ca13efa13b63 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -326,7 +326,7 @@ static int ena_get_coalesce(struct net_device *net_dev,
 	return 0;
 }
 
-static void ena_update_tx_rings_intr_moderation(struct ena_adapter *adapter)
+static void ena_update_tx_rings_nonadaptive_intr_moderation(struct ena_adapter *adapter)
 {
 	unsigned int val;
 	int i;
@@ -337,7 +337,7 @@ static void ena_update_tx_rings_intr_moderation(struct ena_adapter *adapter)
 		adapter->tx_ring[i].smoothed_interval = val;
 }
 
-static void ena_update_rx_rings_intr_moderation(struct ena_adapter *adapter)
+static void ena_update_rx_rings_nonadaptive_intr_moderation(struct ena_adapter *adapter)
 {
 	unsigned int val;
 	int i;
@@ -365,14 +365,14 @@ static int ena_set_coalesce(struct net_device *net_dev,
 	if (rc)
 		return rc;
 
-	ena_update_tx_rings_intr_moderation(adapter);
+	ena_update_tx_rings_nonadaptive_intr_moderation(adapter);
 
 	rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev,
 							       coalesce->rx_coalesce_usecs);
 	if (rc)
 		return rc;
 
-	ena_update_rx_rings_intr_moderation(adapter);
+	ena_update_rx_rings_nonadaptive_intr_moderation(adapter);
 
 	if (coalesce->use_adaptive_rx_coalesce &&
 	    !ena_com_get_adaptive_moderation_enabled(ena_dev))
-- 
cgit v1.2.3


From ba6f6b4191f850ddf9363a4aa946f2432a28fb30 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:58 +0300
Subject: net: ena: cosmetic: set queue sizes to u32 for consistency

Make all types of variables that convey the number and sizeof queues to
be u32, for consistency with the API between the driver and device via
ena_admin_defs.h:ena_admin_get_feat_resp.max_queue_ext fields. Current
code sometimes uses int and there are multiple assignments between these
variables with different types.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c3cbe48b353e..0999fe3310fb 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3832,11 +3832,11 @@ static void ena_timer_service(struct timer_list *t)
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 }
 
-static int ena_calc_max_io_queue_num(struct pci_dev *pdev,
+static u32 ena_calc_max_io_queue_num(struct pci_dev *pdev,
 				     struct ena_com_dev *ena_dev,
 				     struct ena_com_dev_get_features_ctx *get_feat_ctx)
 {
-	int io_tx_sq_num, io_tx_cq_num, io_rx_num, max_num_io_queues;
+	u32 io_tx_sq_num, io_tx_cq_num, io_rx_num, max_num_io_queues;
 
 	if (ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) {
 		struct ena_admin_queue_ext_feature_fields *max_queue_ext =
-- 
cgit v1.2.3


From 13830937ccf68519ec3a40d8a8675af136cea8be Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:08:59 +0300
Subject: net: ena: cosmetic: fix spelling and grammar mistakes in comments

fix spelling and grammar mistakes in comments in ena_com.h,
ena_com.c and ena_netdev.c

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c    |  2 +-
 drivers/net/ethernet/amazon/ena/ena_com.h    | 30 ++++++++++++++--------------
 drivers/net/ethernet/amazon/ena/ena_netdev.c |  2 +-
 3 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index e2025eb86984..d47821655d61 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -772,7 +772,7 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com
 			if (admin_queue->auto_polling)
 				admin_queue->polling = true;
 		} else {
-			pr_err("The ena device doesn't send a completion for the admin cmd %d status %d\n",
+			pr_err("The ena device didn't send a completion for the admin cmd %d status %d\n",
 			       comp_ctx->cmd_opcode, comp_ctx->status);
 		}
 		/* Check if shifted to polling mode.
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 13a1b7812c46..bd65ae205f8d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -393,7 +393,7 @@ struct ena_aenq_handlers {
  */
 int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev);
 
-/* ena_com_set_mmio_read_mode - Enable/disable the mmio reg read mechanism
+/* ena_com_set_mmio_read_mode - Enable/disable the indirect mmio reg read mechanism
  * @ena_dev: ENA communication layer struct
  * @readless_supported: readless mode (enable/disable)
  */
@@ -515,7 +515,7 @@ void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev,
 /* ena_com_admin_q_comp_intr_handler - admin queue interrupt handler
  * @ena_dev: ENA communication layer struct
  *
- * This method go over the admin completion queue and wake up all the pending
+ * This method goes over the admin completion queue and wakes up all the pending
  * threads that wait on the commands wait event.
  *
  * @note: Should be called after MSI-X interrupt.
@@ -525,7 +525,7 @@ void ena_com_admin_q_comp_intr_handler(struct ena_com_dev *ena_dev);
 /* ena_com_aenq_intr_handler - AENQ interrupt handler
  * @ena_dev: ENA communication layer struct
  *
- * This method go over the async event notification queue and call the proper
+ * This method goes over the async event notification queue and calls the proper
  * aenq handler.
  */
 void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data);
@@ -542,14 +542,14 @@ void ena_com_abort_admin_commands(struct ena_com_dev *ena_dev);
 /* ena_com_wait_for_abort_completion - Wait for admin commands abort.
  * @ena_dev: ENA communication layer struct
  *
- * This method wait until all the outstanding admin commands will be completed.
+ * This method waits until all the outstanding admin commands are completed.
  */
 void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev);
 
 /* ena_com_validate_version - Validate the device parameters
  * @ena_dev: ENA communication layer struct
  *
- * This method validate the device parameters are the same as the saved
+ * This method verifies the device parameters are the same as the saved
  * parameters in ena_dev.
  * This method is useful after device reset, to validate the device mac address
  * and the device offloads are the same as before the reset.
@@ -689,7 +689,7 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev);
  *
  * Retrieve the hash function from the device.
  *
- * @note: If the caller called ena_com_fill_hash_function but didn't flash
+ * @note: If the caller called ena_com_fill_hash_function but didn't flush
  * it to the device, the new configuration will be lost.
  *
  * @return: 0 on Success and negative value otherwise.
@@ -703,7 +703,7 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
  *
  * Retrieve the hash key.
  *
- * @note: If the caller called ena_com_fill_hash_key but didn't flash
+ * @note: If the caller called ena_com_fill_hash_key but didn't flush
  * it to the device, the new configuration will be lost.
  *
  * @return: 0 on Success and negative value otherwise.
@@ -743,7 +743,7 @@ int ena_com_set_hash_ctrl(struct ena_com_dev *ena_dev);
  *
  * Retrieve the hash control from the device.
  *
- * @note, If the caller called ena_com_fill_hash_ctrl but didn't flash
+ * @note: If the caller called ena_com_fill_hash_ctrl but didn't flush
  * it to the device, the new configuration will be lost.
  *
  * @return: 0 on Success and negative value otherwise.
@@ -795,7 +795,7 @@ int ena_com_indirect_table_set(struct ena_com_dev *ena_dev);
  *
  * Retrieve the RSS indirection table from the device.
  *
- * @note: If the caller called ena_com_indirect_table_fill_entry but didn't flash
+ * @note: If the caller called ena_com_indirect_table_fill_entry but didn't flush
  * it to the device, the new configuration will be lost.
  *
  * @return: 0 on Success and negative value otherwise.
@@ -821,14 +821,14 @@ int ena_com_allocate_debug_area(struct ena_com_dev *ena_dev,
 /* ena_com_delete_debug_area - Free the debug area resources.
  * @ena_dev: ENA communication layer struct
  *
- * Free the allocate debug area.
+ * Free the allocated debug area.
  */
 void ena_com_delete_debug_area(struct ena_com_dev *ena_dev);
 
 /* ena_com_delete_host_info - Free the host info resources.
  * @ena_dev: ENA communication layer struct
  *
- * Free the allocate host info.
+ * Free the allocated host info.
  */
 void ena_com_delete_host_info(struct ena_com_dev *ena_dev);
 
@@ -869,9 +869,9 @@ int ena_com_destroy_io_cq(struct ena_com_dev *ena_dev,
  * @cmd_completion: command completion return value.
  * @cmd_comp_size: command completion size.
 
- * Submit an admin command and then wait until the device will return a
+ * Submit an admin command and then wait until the device returns a
  * completion.
- * The completion will be copyed into cmd_comp.
+ * The completion will be copied into cmd_comp.
  *
  * @return - 0 on success, negative value on failure.
  */
@@ -934,7 +934,7 @@ unsigned int ena_com_get_nonadaptive_moderation_interval_rx(struct ena_com_dev *
 /* ena_com_config_dev_mode - Configure the placement policy of the device.
  * @ena_dev: ENA communication layer struct
  * @llq_features: LLQ feature descriptor, retrieve via
- *                ena_com_get_dev_attr_feat.
+ *		   ena_com_get_dev_attr_feat.
  * @ena_llq_config: The default driver LLQ parameters configurations
  */
 int ena_com_config_dev_mode(struct ena_com_dev *ena_dev,
@@ -960,7 +960,7 @@ static inline void ena_com_disable_adaptive_moderation(struct ena_com_dev *ena_d
  * @intr_reg: interrupt register to update.
  * @rx_delay_interval: Rx interval in usecs
  * @tx_delay_interval: Tx interval in usecs
- * @unmask: unask enable/disable
+ * @unmask: unmask enable/disable
  *
  * Prepare interrupt update register with the supplied parameters.
  */
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 0999fe3310fb..0349e0305608 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -4190,7 +4190,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	calc_queue_ctx.get_feat_ctx = &get_feat_ctx;
 	calc_queue_ctx.pdev = pdev;
 
-	/* Initial Tx and RX interrupt delay. Assumes 1 usec granularity.
+	/* Initial TX and RX interrupt delay. Assumes 1 usec granularity.
 	 * Updated during device initialization with the real granularity
 	 */
 	ena_dev->intr_moder_tx_interval = ENA_INTR_INITIAL_TX_INTERVAL_USECS;
-- 
cgit v1.2.3


From 46143e58884025292bd977ca8bc0fdd9dac47c4c Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:00 +0300
Subject: net: ena: cosmetic: fix line break issues

1. Join unnecessarily broken short lines in ena_com.c ena_netdev.c
2. Fix Indentations of broken lines

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c    |  8 +++-----
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 13 ++++++-------
 2 files changed, 9 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index d47821655d61..a513d71576bd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -375,7 +375,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		io_sq->bounce_buf_ctrl.next_to_use = 0;
 
 		size = io_sq->bounce_buf_ctrl.buffer_size *
-			 io_sq->bounce_buf_ctrl.buffers_num;
+			io_sq->bounce_buf_ctrl.buffers_num;
 
 		dev_node = dev_to_node(ena_dev->dmadev);
 		set_dev_node(ena_dev->dmadev, ctx->numa_node);
@@ -699,8 +699,7 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev,
 		/* The desc list entry size should be whole multiply of 8
 		 * This requirement comes from __iowrite64_copy()
 		 */
-		pr_err("illegal entry size %d\n",
-		       llq_info->desc_list_entry_size);
+		pr_err("illegal entry size %d\n", llq_info->desc_list_entry_size);
 		return -EINVAL;
 	}
 
@@ -2045,8 +2044,7 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 
 	/* write the aenq doorbell after all AENQ descriptors were read */
 	mb();
-	writel_relaxed((u32)aenq->head,
-		       dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
+	writel_relaxed((u32)aenq->head, dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
 }
 
 int ena_com_dev_reset(struct ena_com_dev *ena_dev,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 0349e0305608..148d13cdd1bf 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2242,7 +2242,7 @@ static int ena_rss_configure(struct ena_adapter *adapter)
 		rc = ena_rss_init_default(adapter);
 		if (rc && (rc != -EOPNOTSUPP)) {
 			netif_err(adapter, ifup, adapter->netdev,
-					"Failed to init RSS rc: %d\n", rc);
+				  "Failed to init RSS rc: %d\n", rc);
 			return rc;
 		}
 	}
@@ -2315,7 +2315,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid)
 	if (rc) {
 		netif_err(adapter, ifup, adapter->netdev,
 			  "Failed to create I/O TX queue num %d rc: %d\n",
-			   qid, rc);
+			  qid, rc);
 		return rc;
 	}
 
@@ -2464,7 +2464,7 @@ static int create_queues_with_size_backoff(struct ena_adapter *adapter)
 	 * ones due to past queue allocation failures.
 	 */
 	set_io_rings_size(adapter, adapter->requested_tx_ring_size,
-			adapter->requested_rx_ring_size);
+			  adapter->requested_rx_ring_size);
 
 	while (1) {
 		if (ena_xdp_present(adapter)) {
@@ -2505,7 +2505,7 @@ err_setup_tx:
 		if (rc != -ENOMEM) {
 			netif_err(adapter, ifup, adapter->netdev,
 				  "Queue creation failed with error code %d\n",
-				   rc);
+				  rc);
 			return rc;
 		}
 
@@ -2528,7 +2528,7 @@ err_setup_tx:
 			new_rx_ring_size = cur_rx_ring_size / 2;
 
 		if (new_tx_ring_size < ENA_MIN_RING_SIZE ||
-				new_rx_ring_size < ENA_MIN_RING_SIZE) {
+		    new_rx_ring_size < ENA_MIN_RING_SIZE) {
 			netif_err(adapter, ifup, adapter->netdev,
 				  "Queue creation failed with the smallest possible queue size of %d for both queues. Not retrying with smaller queues\n",
 				  ENA_MIN_RING_SIZE);
@@ -3087,8 +3087,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return qid;
 }
 
-static void ena_config_host_info(struct ena_com_dev *ena_dev,
-				 struct pci_dev *pdev)
+static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pdev)
 {
 	struct ena_admin_host_info *host_info;
 	int rc;
-- 
cgit v1.2.3


From f3020447471c40024fbb4e5d720861b25ce46717 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:01 +0300
Subject: net: ena: cosmetic: remove unnecessary code

1. Remove unused definition of DRV_MODULE_VERSION
2. Remove {} from single line-of-code ifs
3. Remove unnecessary comments from ena_get/set_coalesce()
4. Remove unnecessary extra spaces and newlines

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 11 +++--------
 drivers/net/ethernet/amazon/ena/ena_netdev.h  |  6 ------
 2 files changed, 3 insertions(+), 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index ca13efa13b63..e340b65af08c 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -206,7 +206,7 @@ int ena_get_sset_count(struct net_device *netdev, int sset)
 	if (sset != ETH_SS_STATS)
 		return -EOPNOTSUPP;
 
-	return  adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX)
+	return adapter->num_io_queues * (ENA_STATS_ARRAY_TX + ENA_STATS_ARRAY_RX)
 		+ ENA_STATS_ARRAY_GLOBAL + ENA_STATS_ARRAY_ENA_COM;
 }
 
@@ -260,7 +260,6 @@ static void ena_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 
 	for (i = 0; i < ENA_STATS_ARRAY_GLOBAL; i++) {
 		ena_stats = &ena_stats_global_strings[i];
-
 		memcpy(data, ena_stats->name, ETH_GSTRING_LEN);
 		data += ETH_GSTRING_LEN;
 	}
@@ -307,10 +306,8 @@ static int ena_get_coalesce(struct net_device *net_dev,
 	struct ena_adapter *adapter = netdev_priv(net_dev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 
-	if (!ena_com_interrupt_moderation_supported(ena_dev)) {
-		/* the devie doesn't support interrupt moderation */
+	if (!ena_com_interrupt_moderation_supported(ena_dev))
 		return -EOPNOTSUPP;
-	}
 
 	coalesce->tx_coalesce_usecs =
 		ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) *
@@ -355,10 +352,8 @@ static int ena_set_coalesce(struct net_device *net_dev,
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	int rc;
 
-	if (!ena_com_interrupt_moderation_supported(ena_dev)) {
-		/* the devie doesn't support interrupt moderation */
+	if (!ena_com_interrupt_moderation_supported(ena_dev))
 		return -EOPNOTSUPP;
-	}
 
 	rc = ena_com_update_nonadaptive_moderation_interval_tx(ena_dev,
 							       coalesce->tx_coalesce_usecs);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 680099afcccf..5320b916a36b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -50,12 +50,6 @@
 #define DRV_MODULE_GEN_SUBMINOR 0
 
 #define DRV_MODULE_NAME		"ena"
-#ifndef DRV_MODULE_GENERATION
-#define DRV_MODULE_GENERATION \
-	__stringify(DRV_MODULE_GEN_MAJOR) "."	\
-	__stringify(DRV_MODULE_GEN_MINOR) "."	\
-	__stringify(DRV_MODULE_GEN_SUBMINOR) "K"
-#endif
 
 #define DEVICE_NAME	"Elastic Network Adapter (ENA)"
 
-- 
cgit v1.2.3


From 0a39a35f3f27f833282a2a87c26894167f336ba2 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:02 +0300
Subject: net: ena: cosmetic: code reorderings

1. Reorder sanity checks in get_comp_ctxt() to make more sense
2. Reorder variables in ena_com_fill_hash_function() and
   ena_calc_io_queue_size() in reverse christmas tree.
3. Move around member initializations.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c    | 17 +++++++++--------
 drivers/net/ethernet/amazon/ena/ena_netdev.c |  5 ++---
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index a513d71576bd..bf3465e5a2e7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -200,17 +200,17 @@ static void comp_ctxt_release(struct ena_com_admin_queue *queue,
 static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *queue,
 					  u16 command_id, bool capture)
 {
-	if (unlikely(!queue->comp_ctx)) {
-		pr_err("Completion context is NULL\n");
-		return NULL;
-	}
-
 	if (unlikely(command_id >= queue->q_depth)) {
 		pr_err("command id is larger than the queue size. cmd_id: %u queue size %d\n",
 		       command_id, queue->q_depth);
 		return NULL;
 	}
 
+	if (unlikely(!queue->comp_ctx)) {
+		pr_err("Completion context is NULL\n");
+		return NULL;
+	}
+
 	if (unlikely(queue->comp_ctx[command_id].occupied && capture)) {
 		pr_err("Completion context is occupied\n");
 		return NULL;
@@ -2266,13 +2266,14 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 			       enum ena_admin_hash_functions func,
 			       const u8 *key, u16 key_len, u32 init_val)
 {
-	struct ena_rss *rss = &ena_dev->rss;
+	struct ena_admin_feature_rss_flow_hash_control *hash_key;
 	struct ena_admin_get_feat_resp get_resp;
-	struct ena_admin_feature_rss_flow_hash_control *hash_key =
-		rss->hash_key;
 	enum ena_admin_hash_functions old_func;
+	struct ena_rss *rss = &ena_dev->rss;
 	int rc;
 
+	hash_key = rss->hash_key;
+
 	/* Make sure size is a mult of DWs */
 	if (unlikely(key_len & 0x3))
 		return -EINVAL;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 148d13cdd1bf..313e65b17492 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -4121,8 +4121,8 @@ static int ena_calc_io_queue_size(struct ena_calc_queue_size_ctx *ctx)
  */
 static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	struct ena_com_dev_get_features_ctx get_feat_ctx;
 	struct ena_calc_queue_size_ctx calc_queue_ctx = { 0 };
+	struct ena_com_dev_get_features_ctx get_feat_ctx;
 	struct ena_llq_configurations llq_config;
 	struct ena_com_dev *ena_dev = NULL;
 	struct ena_adapter *adapter;
@@ -4233,12 +4233,11 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	adapter->num_io_queues = max_num_io_queues;
 	adapter->max_num_io_queues = max_num_io_queues;
+	adapter->last_monitored_tx_qid = 0;
 
 	adapter->xdp_first_ring = 0;
 	adapter->xdp_num_queues = 0;
 
-	adapter->last_monitored_tx_qid = 0;
-
 	adapter->rx_copybreak = ENA_DEFAULT_RX_COPYBREAK;
 	adapter->wd_state = wd_state;
 
-- 
cgit v1.2.3


From 6d0862e0ec92d05e0b5bb9e46133e7460c0c675a Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:03 +0300
Subject: net: ena: cosmetic: fix spacing issues

1. Add leading and trailing spaces to several comments for better
   readability
2. Make tabs and spaces uniform in enum defines in ena_admin_defs.h

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_admin_defs.h  | 6 +++---
 drivers/net/ethernet/amazon/ena/ena_common_defs.h | 2 +-
 drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h | 2 +-
 drivers/net/ethernet/amazon/ena/ena_regs_defs.h   | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 727836f638ad..336742f6e3c3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -768,8 +768,8 @@ enum ena_admin_os_type {
 	ENA_ADMIN_OS_DPDK                           = 3,
 	ENA_ADMIN_OS_FREEBSD                        = 4,
 	ENA_ADMIN_OS_IPXE                           = 5,
-	ENA_ADMIN_OS_ESXI			    = 6,
-	ENA_ADMIN_OS_GROUPS_NUM			    = 6,
+	ENA_ADMIN_OS_ESXI                           = 6,
+	ENA_ADMIN_OS_GROUPS_NUM                     = 6,
 };
 
 struct ena_admin_host_info {
@@ -1136,4 +1136,4 @@ struct ena_admin_ena_mmio_req_read_less_resp {
 /* aenq_link_change_desc */
 #define ENA_ADMIN_AENQ_LINK_CHANGE_DESC_LINK_STATUS_MASK    BIT(0)
 
-#endif /*_ENA_ADMIN_H_ */
+#endif /* _ENA_ADMIN_H_ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_common_defs.h b/drivers/net/ethernet/amazon/ena/ena_common_defs.h
index 23beb7e7ed7b..8a8ded0de9ac 100644
--- a/drivers/net/ethernet/amazon/ena/ena_common_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_common_defs.h
@@ -45,4 +45,4 @@ struct ena_common_mem_addr {
 	u16 reserved16;
 };
 
-#endif /*_ENA_COMMON_H_ */
+#endif /* _ENA_COMMON_H_ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
index ee28fb067d8c..d105c9c56192 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_io_defs.h
@@ -414,4 +414,4 @@ struct ena_eth_io_numa_node_cfg_reg {
 #define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_SHIFT          31
 #define ENA_ETH_IO_NUMA_NODE_CFG_REG_ENABLED_MASK           BIT(31)
 
-#endif /*_ENA_ETH_IO_H_ */
+#endif /* _ENA_ETH_IO_H_ */
diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
index 04fcafcc059c..b514bb1b855d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h
@@ -154,4 +154,4 @@ enum ena_regs_reset_reason_types {
 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_SHIFT          16
 #define ENA_REGS_RSS_IND_ENTRY_UPDATE_CQ_IDX_MASK           0xffff0000
 
-#endif /*_ENA_REGS_H_ */
+#endif /* _ENA_REGS_H_ */
-- 
cgit v1.2.3


From b0ae3ac4847c6009e7b1963899cd121e84e5082a Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:04 +0300
Subject: net: ena: cosmetic: minor code changes

1. Use BIT macro instead of shift operator for code clarity
2. Replace multiple flag assignments to a single assignment of multiple
   flags in ena_com_add_single_rx_desc()
3. Move ENA_HASH_KEY_SIZE from ena_netdev.h to ena_com.h

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c     | 2 +-
 drivers/net/ethernet/amazon/ena/ena_com.h     | 2 ++
 drivers/net/ethernet/amazon/ena/ena_eth_com.c | 8 ++++----
 drivers/net/ethernet/amazon/ena/ena_netdev.h  | 2 --
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index bf3465e5a2e7..4b1dbedbe921 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2285,7 +2285,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 	if (unlikely(rc))
 		return rc;
 
-	if (!((1 << func) & get_resp.u.flow_hash_func.supported_func)) {
+	if (!(BIT(func) & get_resp.u.flow_hash_func.supported_func)) {
 		pr_err("Flow hash function %d isn't supported\n", func);
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index bd65ae205f8d..325c9a5f677b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -77,6 +77,8 @@
 #define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0
 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1
 
+#define ENA_HASH_KEY_SIZE 40
+
 #define ENA_HW_HINTS_NO_TIMEOUT	0xFFFF
 
 #define ENA_FEATURE_MAX_QUEUE_EXT_VER 1
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index a014f514c069..ec8ea25e988d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -584,10 +584,10 @@ int ena_com_add_single_rx_desc(struct ena_com_io_sq *io_sq,
 
 	desc->length = ena_buf->len;
 
-	desc->ctrl = ENA_ETH_IO_RX_DESC_FIRST_MASK;
-	desc->ctrl |= ENA_ETH_IO_RX_DESC_LAST_MASK;
-	desc->ctrl |= io_sq->phase & ENA_ETH_IO_RX_DESC_PHASE_MASK;
-	desc->ctrl |= ENA_ETH_IO_RX_DESC_COMP_REQ_MASK;
+	desc->ctrl = ENA_ETH_IO_RX_DESC_FIRST_MASK |
+		ENA_ETH_IO_RX_DESC_LAST_MASK |
+		(io_sq->phase & ENA_ETH_IO_RX_DESC_PHASE_MASK) |
+		ENA_ETH_IO_RX_DESC_COMP_REQ_MASK;
 
 	desc->req_id = req_id;
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 5320b916a36b..9b3948c7e8a0 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -98,8 +98,6 @@
 #define ENA_RX_RSS_TABLE_LOG_SIZE  7
 #define ENA_RX_RSS_TABLE_SIZE	(1 << ENA_RX_RSS_TABLE_LOG_SIZE)
 
-#define ENA_HASH_KEY_SIZE	40
-
 /* The number of tx packet completions that will be handled each NAPI poll
  * cycle is ring_size / ENA_TX_POLL_BUDGET_DIVIDER.
  */
-- 
cgit v1.2.3


From 4bb7f4cf60e38a00965d22aa5979ab143193d41f Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Fri, 22 May 2020 12:09:05 +0300
Subject: net: ena: reduce driver load time

This commit reduces the driver load time by using usec resolution
instead of msec when polling for hardware state change.

Also add back-off mechanism to handle cases where minimal sleep
time is not enough.

Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c    | 36 ++++++++++++++++++++--------
 drivers/net/ethernet/amazon/ena/ena_com.h    |  3 +++
 drivers/net/ethernet/amazon/ena/ena_netdev.c |  2 ++
 drivers/net/ethernet/amazon/ena/ena_netdev.h |  2 ++
 4 files changed, 33 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 4b1dbedbe921..432f143559a1 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -62,7 +62,9 @@
 
 #define ENA_REGS_ADMIN_INTR_MASK 1
 
-#define ENA_POLL_MS	5
+#define ENA_MIN_ADMIN_POLL_US 100
+
+#define ENA_MAX_ADMIN_POLL_US 5000
 
 /*****************************************************************************/
 /*****************************************************************************/
@@ -540,12 +542,20 @@ static int ena_com_comp_status_to_errno(u8 comp_status)
 	return -EINVAL;
 }
 
+static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us)
+{
+	delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us);
+	delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US);
+	usleep_range(delay_us, 2 * delay_us);
+}
+
 static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx,
 						     struct ena_com_admin_queue *admin_queue)
 {
 	unsigned long flags = 0;
 	unsigned long timeout;
 	int ret;
+	u32 exp = 0;
 
 	timeout = jiffies + usecs_to_jiffies(admin_queue->completion_timeout);
 
@@ -569,7 +579,8 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c
 			goto err;
 		}
 
-		msleep(ENA_POLL_MS);
+		ena_delay_exponential_backoff_us(exp++,
+						 admin_queue->ena_dev->ena_min_poll_delay_us);
 	}
 
 	if (unlikely(comp_ctx->status == ENA_CMD_ABORTED)) {
@@ -939,12 +950,13 @@ static void ena_com_io_queue_free(struct ena_com_dev *ena_dev,
 static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
 				u16 exp_state)
 {
-	u32 val, i;
+	u32 val, exp = 0;
+	unsigned long timeout_stamp;
 
-	/* Convert timeout from resolution of 100ms to ENA_POLL_MS */
-	timeout = (timeout * 100) / ENA_POLL_MS;
+	/* Convert timeout from resolution of 100ms to us resolution. */
+	timeout_stamp = jiffies + usecs_to_jiffies(100 * 1000 * timeout);
 
-	for (i = 0; i < timeout; i++) {
+	while (1) {
 		val = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF);
 
 		if (unlikely(val == ENA_MMIO_READ_TIMEOUT)) {
@@ -956,10 +968,11 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
 			exp_state)
 			return 0;
 
-		msleep(ENA_POLL_MS);
-	}
+		if (time_is_before_jiffies(timeout_stamp))
+			return -ETIME;
 
-	return -ETIME;
+		ena_delay_exponential_backoff_us(exp++, ena_dev->ena_min_poll_delay_us);
+	}
 }
 
 static bool ena_com_check_supported_feature_id(struct ena_com_dev *ena_dev,
@@ -1436,11 +1449,13 @@ void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev)
 {
 	struct ena_com_admin_queue *admin_queue = &ena_dev->admin_queue;
 	unsigned long flags = 0;
+	u32 exp = 0;
 
 	spin_lock_irqsave(&admin_queue->q_lock, flags);
 	while (atomic_read(&admin_queue->outstanding_cmds) != 0) {
 		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
-		msleep(ENA_POLL_MS);
+		ena_delay_exponential_backoff_us(exp++,
+						 ena_dev->ena_min_poll_delay_us);
 		spin_lock_irqsave(&admin_queue->q_lock, flags);
 	}
 	spin_unlock_irqrestore(&admin_queue->q_lock, flags);
@@ -1788,6 +1803,7 @@ int ena_com_admin_init(struct ena_com_dev *ena_dev,
 	if (ret)
 		goto error;
 
+	admin_queue->ena_dev = ena_dev;
 	admin_queue->running_state = true;
 
 	return 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 325c9a5f677b..bc187adf54e4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -239,6 +239,7 @@ struct ena_com_stats_admin {
 
 struct ena_com_admin_queue {
 	void *q_dmadev;
+	struct ena_com_dev *ena_dev;
 	spinlock_t q_lock; /* spinlock for the admin queue */
 
 	struct ena_comp_ctx *comp_ctx;
@@ -351,6 +352,8 @@ struct ena_com_dev {
 	struct ena_intr_moder_entry *intr_moder_tbl;
 
 	struct ena_com_llq_info llq_info;
+
+	u32 ena_min_poll_delay_us;
 };
 
 struct ena_com_dev_get_features_ctx {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 313e65b17492..46865d5bd7e7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -4166,6 +4166,8 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free_region;
 	}
 
+	ena_dev->ena_min_poll_delay_us = ENA_ADMIN_POLL_DELAY_US;
+
 	ena_dev->dmadev = &pdev->dev;
 
 	rc = ena_device_init(ena_dev, pdev, &get_feat_ctx, &wd_state);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 9b3948c7e8a0..ba030d260940 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -129,6 +129,8 @@
 #define ENA_IO_IRQ_FIRST_IDX		1
 #define ENA_IO_IRQ_IDX(q)		(ENA_IO_IRQ_FIRST_IDX + (q))
 
+#define ENA_ADMIN_POLL_DELAY_US 100
+
 /* ENA device should send keep alive msg every 1 sec.
  * We wait for 6 sec just to be on the safe side.
  */
-- 
cgit v1.2.3


From d3d6974bc539d2a4311a20230892a5e4b2fd5e8d Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 22 May 2020 14:06:53 +0200
Subject: net: ethernet: mediatek: rename Kconfig prompt

We'll soon by adding a second MediaTek Ethernet driver so modify the
Kconfig prompt.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 4968352ba188..5079b8090f16 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config NET_VENDOR_MEDIATEK
-	bool "MediaTek ethernet driver"
+	bool "MediaTek devices"
 	depends on ARCH_MEDIATEK || SOC_MT7621 || SOC_MT7620
 	---help---
 	  If you have a Mediatek SoC with ethernet, say Y.
-- 
cgit v1.2.3


From 22f076a279ecf78f4dc5697396a075651942ae5b Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 22 May 2020 14:06:54 +0200
Subject: net: ethernet: mediatek: remove unnecessary spaces from Makefile

The Makefile formatting in the kernel tree usually doesn't use tabs,
so remove them before we add a second driver.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index 2d8362f9341b..3362fb7ef859 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -3,5 +3,5 @@
 # Makefile for the Mediatek SoCs built-in ethernet macs
 #
 
-obj-$(CONFIG_NET_MEDIATEK_SOC)                 += mtk_eth.o
+obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o
 mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o
-- 
cgit v1.2.3


From 8c7bd5a454ffc2b0518d1499c4af95f00291d2af Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 22 May 2020 14:06:55 +0200
Subject: net: ethernet: mtk-star-emac: new driver

This adds the driver for the MediaTek STAR Ethernet MAC currently used
on the MT8* SoC family. For now we only support full-duplex.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/Kconfig         |    7 +
 drivers/net/ethernet/mediatek/Makefile        |    1 +
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 1678 +++++++++++++++++++++++++
 3 files changed, 1686 insertions(+)
 create mode 100644 drivers/net/ethernet/mediatek/mtk_star_emac.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 5079b8090f16..500c15e7ea4a 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -14,4 +14,11 @@ config NET_MEDIATEK_SOC
 	  This driver supports the gigabit ethernet MACs in the
 	  MediaTek SoC family.
 
+config NET_MEDIATEK_STAR_EMAC
+	tristate "MediaTek STAR Ethernet MAC support"
+	select PHYLIB
+	help
+	  This driver supports the ethernet MAC IP first used on
+	  MediaTek MT85** SoCs.
+
 endif #NET_VENDOR_MEDIATEK
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index 3362fb7ef859..3a777b4a6cd3 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -5,3 +5,4 @@
 
 obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o
 mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o
+obj-$(CONFIG_NET_MEDIATEK_STAR_EMAC) += mtk_star_emac.o
diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
new file mode 100644
index 000000000000..789c77af501f
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -0,0 +1,1678 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 MediaTek Corporation
+ * Copyright (c) 2020 BayLibre SAS
+ *
+ * Author: Bartosz Golaszewski <bgolaszewski@baylibre.com>
+ */
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/compiler.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/regmap.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+
+#define MTK_STAR_DRVNAME			"mtk_star_emac"
+
+#define MTK_STAR_WAIT_TIMEOUT			300
+#define MTK_STAR_MAX_FRAME_SIZE			1514
+#define MTK_STAR_SKB_ALIGNMENT			16
+#define MTK_STAR_NAPI_WEIGHT			64
+#define MTK_STAR_HASHTABLE_MC_LIMIT		256
+#define MTK_STAR_HASHTABLE_SIZE_MAX		512
+
+/* Normally we'd use NET_IP_ALIGN but on arm64 its value is 0 and it doesn't
+ * work for this controller.
+ */
+#define MTK_STAR_IP_ALIGN			2
+
+static const char *const mtk_star_clk_names[] = { "core", "reg", "trans" };
+#define MTK_STAR_NCLKS ARRAY_SIZE(mtk_star_clk_names)
+
+/* PHY Control Register 0 */
+#define MTK_STAR_REG_PHY_CTRL0			0x0000
+#define MTK_STAR_BIT_PHY_CTRL0_WTCMD		BIT(13)
+#define MTK_STAR_BIT_PHY_CTRL0_RDCMD		BIT(14)
+#define MTK_STAR_BIT_PHY_CTRL0_RWOK		BIT(15)
+#define MTK_STAR_MSK_PHY_CTRL0_PREG		GENMASK(12, 8)
+#define MTK_STAR_OFF_PHY_CTRL0_PREG		8
+#define MTK_STAR_MSK_PHY_CTRL0_RWDATA		GENMASK(31, 16)
+#define MTK_STAR_OFF_PHY_CTRL0_RWDATA		16
+
+/* PHY Control Register 1 */
+#define MTK_STAR_REG_PHY_CTRL1			0x0004
+#define MTK_STAR_BIT_PHY_CTRL1_LINK_ST		BIT(0)
+#define MTK_STAR_BIT_PHY_CTRL1_AN_EN		BIT(8)
+#define MTK_STAR_OFF_PHY_CTRL1_FORCE_SPD	9
+#define MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_10M	0x00
+#define MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_100M	0x01
+#define MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_1000M	0x02
+#define MTK_STAR_BIT_PHY_CTRL1_FORCE_DPX	BIT(11)
+#define MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_RX	BIT(12)
+#define MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_TX	BIT(13)
+
+/* MAC Configuration Register */
+#define MTK_STAR_REG_MAC_CFG			0x0008
+#define MTK_STAR_OFF_MAC_CFG_IPG		10
+#define MTK_STAR_VAL_MAC_CFG_IPG_96BIT		GENMASK(4, 0)
+#define MTK_STAR_BIT_MAC_CFG_MAXLEN_1522	BIT(16)
+#define MTK_STAR_BIT_MAC_CFG_AUTO_PAD		BIT(19)
+#define MTK_STAR_BIT_MAC_CFG_CRC_STRIP		BIT(20)
+#define MTK_STAR_BIT_MAC_CFG_VLAN_STRIP		BIT(22)
+#define MTK_STAR_BIT_MAC_CFG_NIC_PD		BIT(31)
+
+/* Flow-Control Configuration Register */
+#define MTK_STAR_REG_FC_CFG			0x000c
+#define MTK_STAR_BIT_FC_CFG_BP_EN		BIT(7)
+#define MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR	BIT(8)
+#define MTK_STAR_OFF_FC_CFG_SEND_PAUSE_TH	16
+#define MTK_STAR_MSK_FC_CFG_SEND_PAUSE_TH	GENMASK(27, 16)
+#define MTK_STAR_VAL_FC_CFG_SEND_PAUSE_TH_2K	0x800
+
+/* ARL Configuration Register */
+#define MTK_STAR_REG_ARL_CFG			0x0010
+#define MTK_STAR_BIT_ARL_CFG_HASH_ALG		BIT(0)
+#define MTK_STAR_BIT_ARL_CFG_MISC_MODE		BIT(4)
+
+/* MAC High and Low Bytes Registers */
+#define MTK_STAR_REG_MY_MAC_H			0x0014
+#define MTK_STAR_REG_MY_MAC_L			0x0018
+
+/* Hash Table Control Register */
+#define MTK_STAR_REG_HASH_CTRL			0x001c
+#define MTK_STAR_MSK_HASH_CTRL_HASH_BIT_ADDR	GENMASK(8, 0)
+#define MTK_STAR_BIT_HASH_CTRL_HASH_BIT_DATA	BIT(12)
+#define MTK_STAR_BIT_HASH_CTRL_ACC_CMD		BIT(13)
+#define MTK_STAR_BIT_HASH_CTRL_CMD_START	BIT(14)
+#define MTK_STAR_BIT_HASH_CTRL_BIST_OK		BIT(16)
+#define MTK_STAR_BIT_HASH_CTRL_BIST_DONE	BIT(17)
+#define MTK_STAR_BIT_HASH_CTRL_BIST_EN		BIT(31)
+
+/* TX DMA Control Register */
+#define MTK_STAR_REG_TX_DMA_CTRL		0x0034
+#define MTK_STAR_BIT_TX_DMA_CTRL_START		BIT(0)
+#define MTK_STAR_BIT_TX_DMA_CTRL_STOP		BIT(1)
+#define MTK_STAR_BIT_TX_DMA_CTRL_RESUME		BIT(2)
+
+/* RX DMA Control Register */
+#define MTK_STAR_REG_RX_DMA_CTRL		0x0038
+#define MTK_STAR_BIT_RX_DMA_CTRL_START		BIT(0)
+#define MTK_STAR_BIT_RX_DMA_CTRL_STOP		BIT(1)
+#define MTK_STAR_BIT_RX_DMA_CTRL_RESUME		BIT(2)
+
+/* DMA Address Registers */
+#define MTK_STAR_REG_TX_DPTR			0x003c
+#define MTK_STAR_REG_RX_DPTR			0x0040
+#define MTK_STAR_REG_TX_BASE_ADDR		0x0044
+#define MTK_STAR_REG_RX_BASE_ADDR		0x0048
+
+/* Interrupt Status Register */
+#define MTK_STAR_REG_INT_STS			0x0050
+#define MTK_STAR_REG_INT_STS_PORT_STS_CHG	BIT(2)
+#define MTK_STAR_REG_INT_STS_MIB_CNT_TH		BIT(3)
+#define MTK_STAR_BIT_INT_STS_FNRC		BIT(6)
+#define MTK_STAR_BIT_INT_STS_TNTC		BIT(8)
+
+/* Interrupt Mask Register */
+#define MTK_STAR_REG_INT_MASK			0x0054
+#define MTK_STAR_BIT_INT_MASK_FNRC		BIT(6)
+
+/* Misc. Config Register */
+#define MTK_STAR_REG_TEST1			0x005c
+#define MTK_STAR_BIT_TEST1_RST_HASH_MBIST	BIT(31)
+
+/* Extended Configuration Register */
+#define MTK_STAR_REG_EXT_CFG			0x0060
+#define MTK_STAR_OFF_EXT_CFG_SND_PAUSE_RLS	16
+#define MTK_STAR_MSK_EXT_CFG_SND_PAUSE_RLS	GENMASK(26, 16)
+#define MTK_STAR_VAL_EXT_CFG_SND_PAUSE_RLS_1K	0x400
+
+/* EthSys Configuration Register */
+#define MTK_STAR_REG_SYS_CONF			0x0094
+#define MTK_STAR_BIT_MII_PAD_OUT_ENABLE		BIT(0)
+#define MTK_STAR_BIT_EXT_MDC_MODE		BIT(1)
+#define MTK_STAR_BIT_SWC_MII_MODE		BIT(2)
+
+/* MAC Clock Configuration Register */
+#define MTK_STAR_REG_MAC_CLK_CONF		0x00ac
+#define MTK_STAR_MSK_MAC_CLK_CONF		GENMASK(7, 0)
+#define MTK_STAR_BIT_CLK_DIV_10			0x0a
+
+/* Counter registers. */
+#define MTK_STAR_REG_C_RXOKPKT			0x0100
+#define MTK_STAR_REG_C_RXOKBYTE			0x0104
+#define MTK_STAR_REG_C_RXRUNT			0x0108
+#define MTK_STAR_REG_C_RXLONG			0x010c
+#define MTK_STAR_REG_C_RXDROP			0x0110
+#define MTK_STAR_REG_C_RXCRC			0x0114
+#define MTK_STAR_REG_C_RXARLDROP		0x0118
+#define MTK_STAR_REG_C_RXVLANDROP		0x011c
+#define MTK_STAR_REG_C_RXCSERR			0x0120
+#define MTK_STAR_REG_C_RXPAUSE			0x0124
+#define MTK_STAR_REG_C_TXOKPKT			0x0128
+#define MTK_STAR_REG_C_TXOKBYTE			0x012c
+#define MTK_STAR_REG_C_TXPAUSECOL		0x0130
+#define MTK_STAR_REG_C_TXRTY			0x0134
+#define MTK_STAR_REG_C_TXSKIP			0x0138
+#define MTK_STAR_REG_C_TX_ARP			0x013c
+#define MTK_STAR_REG_C_RX_RERR			0x01d8
+#define MTK_STAR_REG_C_RX_UNI			0x01dc
+#define MTK_STAR_REG_C_RX_MULTI			0x01e0
+#define MTK_STAR_REG_C_RX_BROAD			0x01e4
+#define MTK_STAR_REG_C_RX_ALIGNERR		0x01e8
+#define MTK_STAR_REG_C_TX_UNI			0x01ec
+#define MTK_STAR_REG_C_TX_MULTI			0x01f0
+#define MTK_STAR_REG_C_TX_BROAD			0x01f4
+#define MTK_STAR_REG_C_TX_TIMEOUT		0x01f8
+#define MTK_STAR_REG_C_TX_LATECOL		0x01fc
+#define MTK_STAR_REG_C_RX_LENGTHERR		0x0214
+#define MTK_STAR_REG_C_RX_TWIST			0x0218
+
+/* Ethernet CFG Control */
+#define MTK_PERICFG_REG_NIC_CFG_CON		0x03c4
+#define MTK_PERICFG_MSK_NIC_CFG_CON_CFG_MII	GENMASK(3, 0)
+#define MTK_PERICFG_BIT_NIC_CFG_CON_RMII	BIT(0)
+
+/* Represents the actual structure of descriptors used by the MAC. We can
+ * reuse the same structure for both TX and RX - the layout is the same, only
+ * the flags differ slightly.
+ */
+struct mtk_star_ring_desc {
+	/* Contains both the status flags as well as packet length. */
+	u32 status;
+	u32 data_ptr;
+	u32 vtag;
+	u32 reserved;
+};
+
+#define MTK_STAR_DESC_MSK_LEN			GENMASK(15, 0)
+#define MTK_STAR_DESC_BIT_RX_CRCE		BIT(24)
+#define MTK_STAR_DESC_BIT_RX_OSIZE		BIT(25)
+#define MTK_STAR_DESC_BIT_INT			BIT(27)
+#define MTK_STAR_DESC_BIT_LS			BIT(28)
+#define MTK_STAR_DESC_BIT_FS			BIT(29)
+#define MTK_STAR_DESC_BIT_EOR			BIT(30)
+#define MTK_STAR_DESC_BIT_COWN			BIT(31)
+
+/* Helper structure for storing data read from/written to descriptors in order
+ * to limit reads from/writes to DMA memory.
+ */
+struct mtk_star_ring_desc_data {
+	unsigned int len;
+	unsigned int flags;
+	dma_addr_t dma_addr;
+	struct sk_buff *skb;
+};
+
+#define MTK_STAR_RING_NUM_DESCS			128
+#define MTK_STAR_NUM_TX_DESCS			MTK_STAR_RING_NUM_DESCS
+#define MTK_STAR_NUM_RX_DESCS			MTK_STAR_RING_NUM_DESCS
+#define MTK_STAR_NUM_DESCS_TOTAL		(MTK_STAR_RING_NUM_DESCS * 2)
+#define MTK_STAR_DMA_SIZE \
+		(MTK_STAR_NUM_DESCS_TOTAL * sizeof(struct mtk_star_ring_desc))
+
+struct mtk_star_ring {
+	struct mtk_star_ring_desc *descs;
+	struct sk_buff *skbs[MTK_STAR_RING_NUM_DESCS];
+	dma_addr_t dma_addrs[MTK_STAR_RING_NUM_DESCS];
+	unsigned int head;
+	unsigned int tail;
+};
+
+struct mtk_star_priv {
+	struct net_device *ndev;
+
+	struct regmap *regs;
+	struct regmap *pericfg;
+
+	struct clk_bulk_data clks[MTK_STAR_NCLKS];
+
+	void *ring_base;
+	struct mtk_star_ring_desc *descs_base;
+	dma_addr_t dma_addr;
+	struct mtk_star_ring tx_ring;
+	struct mtk_star_ring rx_ring;
+
+	struct mii_bus *mii;
+	struct napi_struct napi;
+
+	struct device_node *phy_node;
+	phy_interface_t phy_intf;
+	struct phy_device *phydev;
+	unsigned int link;
+	int speed;
+	int duplex;
+	int pause;
+
+	/* Protects against concurrent descriptor access. */
+	spinlock_t lock;
+
+	struct rtnl_link_stats64 stats;
+	struct work_struct stats_work;
+};
+
+static struct device *mtk_star_get_dev(struct mtk_star_priv *priv)
+{
+	return priv->ndev->dev.parent;
+}
+
+static const struct regmap_config mtk_star_regmap_config = {
+	.reg_bits		= 32,
+	.val_bits		= 32,
+	.reg_stride		= 4,
+	.disable_locking	= true,
+};
+
+static void mtk_star_ring_init(struct mtk_star_ring *ring,
+			       struct mtk_star_ring_desc *descs)
+{
+	memset(ring, 0, sizeof(*ring));
+	ring->descs = descs;
+	ring->head = 0;
+	ring->tail = 0;
+}
+
+static int mtk_star_ring_pop_tail(struct mtk_star_ring *ring,
+				  struct mtk_star_ring_desc_data *desc_data)
+{
+	struct mtk_star_ring_desc *desc = &ring->descs[ring->tail];
+	unsigned int status;
+
+	status = READ_ONCE(desc->status);
+	dma_rmb(); /* Make sure we read the status bits before checking it. */
+
+	if (!(status & MTK_STAR_DESC_BIT_COWN))
+		return -1;
+
+	desc_data->len = status & MTK_STAR_DESC_MSK_LEN;
+	desc_data->flags = status & ~MTK_STAR_DESC_MSK_LEN;
+	desc_data->dma_addr = ring->dma_addrs[ring->tail];
+	desc_data->skb = ring->skbs[ring->tail];
+
+	ring->dma_addrs[ring->tail] = 0;
+	ring->skbs[ring->tail] = NULL;
+
+	status &= MTK_STAR_DESC_BIT_COWN | MTK_STAR_DESC_BIT_EOR;
+
+	WRITE_ONCE(desc->data_ptr, 0);
+	WRITE_ONCE(desc->status, status);
+
+	ring->tail = (ring->tail + 1) % MTK_STAR_RING_NUM_DESCS;
+
+	return 0;
+}
+
+static void mtk_star_ring_push_head(struct mtk_star_ring *ring,
+				    struct mtk_star_ring_desc_data *desc_data,
+				    unsigned int flags)
+{
+	struct mtk_star_ring_desc *desc = &ring->descs[ring->head];
+	unsigned int status;
+
+	status = READ_ONCE(desc->status);
+
+	ring->skbs[ring->head] = desc_data->skb;
+	ring->dma_addrs[ring->head] = desc_data->dma_addr;
+
+	status |= desc_data->len;
+	if (flags)
+		status |= flags;
+
+	WRITE_ONCE(desc->data_ptr, desc_data->dma_addr);
+	WRITE_ONCE(desc->status, status);
+	status &= ~MTK_STAR_DESC_BIT_COWN;
+	/* Flush previous modifications before ownership change. */
+	dma_wmb();
+	WRITE_ONCE(desc->status, status);
+
+	ring->head = (ring->head + 1) % MTK_STAR_RING_NUM_DESCS;
+}
+
+static void
+mtk_star_ring_push_head_rx(struct mtk_star_ring *ring,
+			   struct mtk_star_ring_desc_data *desc_data)
+{
+	mtk_star_ring_push_head(ring, desc_data, 0);
+}
+
+static void
+mtk_star_ring_push_head_tx(struct mtk_star_ring *ring,
+			   struct mtk_star_ring_desc_data *desc_data)
+{
+	static const unsigned int flags = MTK_STAR_DESC_BIT_FS |
+					  MTK_STAR_DESC_BIT_LS |
+					  MTK_STAR_DESC_BIT_INT;
+
+	mtk_star_ring_push_head(ring, desc_data, flags);
+}
+
+static unsigned int mtk_star_ring_num_used_descs(struct mtk_star_ring *ring)
+{
+	return abs(ring->head - ring->tail);
+}
+
+static bool mtk_star_ring_full(struct mtk_star_ring *ring)
+{
+	return mtk_star_ring_num_used_descs(ring) == MTK_STAR_RING_NUM_DESCS;
+}
+
+static bool mtk_star_ring_descs_available(struct mtk_star_ring *ring)
+{
+	return mtk_star_ring_num_used_descs(ring) > 0;
+}
+
+static dma_addr_t mtk_star_dma_map_rx(struct mtk_star_priv *priv,
+				      struct sk_buff *skb)
+{
+	struct device *dev = mtk_star_get_dev(priv);
+
+	/* Data pointer for the RX DMA descriptor must be aligned to 4N + 2. */
+	return dma_map_single(dev, skb_tail_pointer(skb) - 2,
+			      skb_tailroom(skb), DMA_FROM_DEVICE);
+}
+
+static void mtk_star_dma_unmap_rx(struct mtk_star_priv *priv,
+				  struct mtk_star_ring_desc_data *desc_data)
+{
+	struct device *dev = mtk_star_get_dev(priv);
+
+	dma_unmap_single(dev, desc_data->dma_addr,
+			 skb_tailroom(desc_data->skb), DMA_FROM_DEVICE);
+}
+
+static dma_addr_t mtk_star_dma_map_tx(struct mtk_star_priv *priv,
+				      struct sk_buff *skb)
+{
+	struct device *dev = mtk_star_get_dev(priv);
+
+	return dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
+}
+
+static void mtk_star_dma_unmap_tx(struct mtk_star_priv *priv,
+				  struct mtk_star_ring_desc_data *desc_data)
+{
+	struct device *dev = mtk_star_get_dev(priv);
+
+	return dma_unmap_single(dev, desc_data->dma_addr,
+				skb_headlen(desc_data->skb), DMA_TO_DEVICE);
+}
+
+static void mtk_star_nic_disable_pd(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
+			   MTK_STAR_BIT_MAC_CFG_NIC_PD, 0);
+}
+
+/* Unmask the three interrupts we care about, mask all others. */
+static void mtk_star_intr_enable(struct mtk_star_priv *priv)
+{
+	unsigned int val = MTK_STAR_BIT_INT_STS_TNTC |
+			   MTK_STAR_BIT_INT_STS_FNRC |
+			   MTK_STAR_REG_INT_STS_MIB_CNT_TH;
+
+	regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~val);
+}
+
+static void mtk_star_intr_disable(struct mtk_star_priv *priv)
+{
+	regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~0);
+}
+
+static void mtk_star_intr_enable_tx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_BIT_INT_STS_TNTC, 0);
+}
+
+static void mtk_star_intr_enable_rx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_BIT_INT_STS_FNRC, 0);
+}
+
+static void mtk_star_intr_enable_stats(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_REG_INT_STS_MIB_CNT_TH, 0);
+}
+
+static void mtk_star_intr_disable_tx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_BIT_INT_STS_TNTC,
+			   MTK_STAR_BIT_INT_STS_TNTC);
+}
+
+static void mtk_star_intr_disable_rx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_BIT_INT_STS_FNRC,
+			   MTK_STAR_BIT_INT_STS_FNRC);
+}
+
+static void mtk_star_intr_disable_stats(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			   MTK_STAR_REG_INT_STS_MIB_CNT_TH,
+			   MTK_STAR_REG_INT_STS_MIB_CNT_TH);
+}
+
+static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	regmap_read(priv->regs, MTK_STAR_REG_INT_STS, &val);
+
+	return val;
+}
+
+static unsigned int mtk_star_intr_ack_all(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	val = mtk_star_intr_read(priv);
+	regmap_write(priv->regs, MTK_STAR_REG_INT_STS, val);
+
+	return val;
+}
+
+static void mtk_star_dma_init(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring_desc *desc;
+	unsigned int val;
+	int i;
+
+	priv->descs_base = (struct mtk_star_ring_desc *)priv->ring_base;
+
+	for (i = 0; i < MTK_STAR_NUM_DESCS_TOTAL; i++) {
+		desc = &priv->descs_base[i];
+
+		memset(desc, 0, sizeof(*desc));
+		desc->status = MTK_STAR_DESC_BIT_COWN;
+		if ((i == MTK_STAR_NUM_TX_DESCS - 1) ||
+		    (i == MTK_STAR_NUM_DESCS_TOTAL - 1))
+			desc->status |= MTK_STAR_DESC_BIT_EOR;
+	}
+
+	mtk_star_ring_init(&priv->tx_ring, priv->descs_base);
+	mtk_star_ring_init(&priv->rx_ring,
+			   priv->descs_base + MTK_STAR_NUM_TX_DESCS);
+
+	/* Set DMA pointers. */
+	val = (unsigned int)priv->dma_addr;
+	regmap_write(priv->regs, MTK_STAR_REG_TX_BASE_ADDR, val);
+	regmap_write(priv->regs, MTK_STAR_REG_TX_DPTR, val);
+
+	val += sizeof(struct mtk_star_ring_desc) * MTK_STAR_NUM_TX_DESCS;
+	regmap_write(priv->regs, MTK_STAR_REG_RX_BASE_ADDR, val);
+	regmap_write(priv->regs, MTK_STAR_REG_RX_DPTR, val);
+}
+
+static void mtk_star_dma_start(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
+			   MTK_STAR_BIT_TX_DMA_CTRL_START,
+			   MTK_STAR_BIT_TX_DMA_CTRL_START);
+	regmap_update_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
+			   MTK_STAR_BIT_RX_DMA_CTRL_START,
+			   MTK_STAR_BIT_RX_DMA_CTRL_START);
+}
+
+static void mtk_star_dma_stop(struct mtk_star_priv *priv)
+{
+	regmap_write(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
+		     MTK_STAR_BIT_TX_DMA_CTRL_STOP);
+	regmap_write(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
+		     MTK_STAR_BIT_RX_DMA_CTRL_STOP);
+}
+
+static void mtk_star_dma_disable(struct mtk_star_priv *priv)
+{
+	int i;
+
+	mtk_star_dma_stop(priv);
+
+	/* Take back all descriptors. */
+	for (i = 0; i < MTK_STAR_NUM_DESCS_TOTAL; i++)
+		priv->descs_base[i].status |= MTK_STAR_DESC_BIT_COWN;
+}
+
+static void mtk_star_dma_resume_rx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
+			   MTK_STAR_BIT_RX_DMA_CTRL_RESUME,
+			   MTK_STAR_BIT_RX_DMA_CTRL_RESUME);
+}
+
+static void mtk_star_dma_resume_tx(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
+			   MTK_STAR_BIT_TX_DMA_CTRL_RESUME,
+			   MTK_STAR_BIT_TX_DMA_CTRL_RESUME);
+}
+
+static void mtk_star_set_mac_addr(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	u8 *mac_addr = ndev->dev_addr;
+	unsigned int high, low;
+
+	high = mac_addr[0] << 8 | mac_addr[1] << 0;
+	low = mac_addr[2] << 24 | mac_addr[3] << 16 |
+	      mac_addr[4] << 8 | mac_addr[5];
+
+	regmap_write(priv->regs, MTK_STAR_REG_MY_MAC_H, high);
+	regmap_write(priv->regs, MTK_STAR_REG_MY_MAC_L, low);
+}
+
+static void mtk_star_reset_counters(struct mtk_star_priv *priv)
+{
+	static const unsigned int counter_regs[] = {
+		MTK_STAR_REG_C_RXOKPKT,
+		MTK_STAR_REG_C_RXOKBYTE,
+		MTK_STAR_REG_C_RXRUNT,
+		MTK_STAR_REG_C_RXLONG,
+		MTK_STAR_REG_C_RXDROP,
+		MTK_STAR_REG_C_RXCRC,
+		MTK_STAR_REG_C_RXARLDROP,
+		MTK_STAR_REG_C_RXVLANDROP,
+		MTK_STAR_REG_C_RXCSERR,
+		MTK_STAR_REG_C_RXPAUSE,
+		MTK_STAR_REG_C_TXOKPKT,
+		MTK_STAR_REG_C_TXOKBYTE,
+		MTK_STAR_REG_C_TXPAUSECOL,
+		MTK_STAR_REG_C_TXRTY,
+		MTK_STAR_REG_C_TXSKIP,
+		MTK_STAR_REG_C_TX_ARP,
+		MTK_STAR_REG_C_RX_RERR,
+		MTK_STAR_REG_C_RX_UNI,
+		MTK_STAR_REG_C_RX_MULTI,
+		MTK_STAR_REG_C_RX_BROAD,
+		MTK_STAR_REG_C_RX_ALIGNERR,
+		MTK_STAR_REG_C_TX_UNI,
+		MTK_STAR_REG_C_TX_MULTI,
+		MTK_STAR_REG_C_TX_BROAD,
+		MTK_STAR_REG_C_TX_TIMEOUT,
+		MTK_STAR_REG_C_TX_LATECOL,
+		MTK_STAR_REG_C_RX_LENGTHERR,
+		MTK_STAR_REG_C_RX_TWIST,
+	};
+
+	unsigned int i, val;
+
+	for (i = 0; i < ARRAY_SIZE(counter_regs); i++)
+		regmap_read(priv->regs, counter_regs[i], &val);
+}
+
+static void mtk_star_update_stat(struct mtk_star_priv *priv,
+				 unsigned int reg, u64 *stat)
+{
+	unsigned int val;
+
+	regmap_read(priv->regs, reg, &val);
+	*stat += val;
+}
+
+/* Try to get as many stats as possible from the internal registers instead
+ * of tracking them ourselves.
+ */
+static void mtk_star_update_stats(struct mtk_star_priv *priv)
+{
+	struct rtnl_link_stats64 *stats = &priv->stats;
+
+	/* OK packets and bytes. */
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXOKPKT, &stats->rx_packets);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_TXOKPKT, &stats->tx_packets);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXOKBYTE, &stats->rx_bytes);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_TXOKBYTE, &stats->tx_bytes);
+
+	/* RX & TX multicast. */
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RX_MULTI, &stats->multicast);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_TX_MULTI, &stats->multicast);
+
+	/* Collisions. */
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_TXPAUSECOL,
+			     &stats->collisions);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_TX_LATECOL,
+			     &stats->collisions);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXRUNT, &stats->collisions);
+
+	/* RX Errors. */
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RX_LENGTHERR,
+			     &stats->rx_length_errors);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXLONG,
+			     &stats->rx_over_errors);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXCRC, &stats->rx_crc_errors);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RX_ALIGNERR,
+			     &stats->rx_frame_errors);
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RXDROP,
+			     &stats->rx_fifo_errors);
+	/* Sum of the general RX error counter + all of the above. */
+	mtk_star_update_stat(priv, MTK_STAR_REG_C_RX_RERR, &stats->rx_errors);
+	stats->rx_errors += stats->rx_length_errors;
+	stats->rx_errors += stats->rx_over_errors;
+	stats->rx_errors += stats->rx_crc_errors;
+	stats->rx_errors += stats->rx_frame_errors;
+	stats->rx_errors += stats->rx_fifo_errors;
+}
+
+/* This runs in process context and parallel TX and RX paths executing in
+ * napi context may result in losing some stats data but this should happen
+ * seldom enough to be acceptable.
+ */
+static void mtk_star_update_stats_work(struct work_struct *work)
+{
+	struct mtk_star_priv *priv = container_of(work, struct mtk_star_priv,
+						 stats_work);
+
+	mtk_star_update_stats(priv);
+	mtk_star_reset_counters(priv);
+	mtk_star_intr_enable_stats(priv);
+}
+
+static struct sk_buff *mtk_star_alloc_skb(struct net_device *ndev)
+{
+	uintptr_t tail, offset;
+	struct sk_buff *skb;
+
+	skb = dev_alloc_skb(MTK_STAR_MAX_FRAME_SIZE);
+	if (!skb)
+		return NULL;
+
+	/* Align to 16 bytes. */
+	tail = (uintptr_t)skb_tail_pointer(skb);
+	if (tail & (MTK_STAR_SKB_ALIGNMENT - 1)) {
+		offset = tail & (MTK_STAR_SKB_ALIGNMENT - 1);
+		skb_reserve(skb, MTK_STAR_SKB_ALIGNMENT - offset);
+	}
+
+	/* Ensure 16-byte alignment of the skb pointer: eth_type_trans() will
+	 * extract the Ethernet header (14 bytes) so we need two more bytes.
+	 */
+	skb_reserve(skb, MTK_STAR_IP_ALIGN);
+
+	return skb;
+}
+
+static int mtk_star_prepare_rx_skbs(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct mtk_star_ring *ring = &priv->rx_ring;
+	struct device *dev = mtk_star_get_dev(priv);
+	struct mtk_star_ring_desc *desc;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	int i;
+
+	for (i = 0; i < MTK_STAR_NUM_RX_DESCS; i++) {
+		skb = mtk_star_alloc_skb(ndev);
+		if (!skb)
+			return -ENOMEM;
+
+		dma_addr = mtk_star_dma_map_rx(priv, skb);
+		if (dma_mapping_error(dev, dma_addr)) {
+			dev_kfree_skb(skb);
+			return -ENOMEM;
+		}
+
+		desc = &ring->descs[i];
+		desc->data_ptr = dma_addr;
+		desc->status |= skb_tailroom(skb) & MTK_STAR_DESC_MSK_LEN;
+		desc->status &= ~MTK_STAR_DESC_BIT_COWN;
+		ring->skbs[i] = skb;
+		ring->dma_addrs[i] = dma_addr;
+	}
+
+	return 0;
+}
+
+static void
+mtk_star_ring_free_skbs(struct mtk_star_priv *priv, struct mtk_star_ring *ring,
+			void (*unmap_func)(struct mtk_star_priv *,
+					   struct mtk_star_ring_desc_data *))
+{
+	struct mtk_star_ring_desc_data desc_data;
+	struct mtk_star_ring_desc *desc;
+	int i;
+
+	for (i = 0; i < MTK_STAR_RING_NUM_DESCS; i++) {
+		if (!ring->dma_addrs[i])
+			continue;
+
+		desc = &ring->descs[i];
+
+		desc_data.dma_addr = ring->dma_addrs[i];
+		desc_data.skb = ring->skbs[i];
+
+		unmap_func(priv, &desc_data);
+		dev_kfree_skb(desc_data.skb);
+	}
+}
+
+static void mtk_star_free_rx_skbs(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring *ring = &priv->rx_ring;
+
+	mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_rx);
+}
+
+static void mtk_star_free_tx_skbs(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring *ring = &priv->tx_ring;
+
+	mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_tx);
+}
+
+/* All processing for TX and RX happens in the napi poll callback. */
+static irqreturn_t mtk_star_handle_irq(int irq, void *data)
+{
+	struct mtk_star_priv *priv;
+	struct net_device *ndev;
+	bool need_napi = false;
+	unsigned int status;
+
+	ndev = data;
+	priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		status = mtk_star_intr_read(priv);
+
+		if (status & MTK_STAR_BIT_INT_STS_TNTC) {
+			mtk_star_intr_disable_tx(priv);
+			need_napi = true;
+		}
+
+		if (status & MTK_STAR_BIT_INT_STS_FNRC) {
+			mtk_star_intr_disable_rx(priv);
+			need_napi = true;
+		}
+
+		if (need_napi)
+			napi_schedule(&priv->napi);
+
+		/* One of the counters reached 0x8000000 - update stats and
+		 * reset all counters.
+		 */
+		if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) {
+			mtk_star_intr_disable_stats(priv);
+			schedule_work(&priv->stats_work);
+		}
+
+		mtk_star_intr_ack_all(priv);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* Wait for the completion of any previous command - CMD_START bit must be
+ * cleared by hardware.
+ */
+static int mtk_star_hash_wait_cmd_start(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	return regmap_read_poll_timeout_atomic(priv->regs,
+				MTK_STAR_REG_HASH_CTRL, val,
+				!(val & MTK_STAR_BIT_HASH_CTRL_CMD_START),
+				10, MTK_STAR_WAIT_TIMEOUT);
+}
+
+static int mtk_star_hash_wait_ok(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+	int ret;
+
+	/* Wait for BIST_DONE bit. */
+	ret = regmap_read_poll_timeout_atomic(priv->regs,
+					MTK_STAR_REG_HASH_CTRL, val,
+					val & MTK_STAR_BIT_HASH_CTRL_BIST_DONE,
+					10, MTK_STAR_WAIT_TIMEOUT);
+	if (ret)
+		return ret;
+
+	/* Check the BIST_OK bit. */
+	regmap_read(priv->regs, MTK_STAR_REG_HASH_CTRL, &val);
+	if (!(val & MTK_STAR_BIT_HASH_CTRL_BIST_OK))
+		return -EIO;
+
+	return 0;
+}
+
+static int mtk_star_set_hashbit(struct mtk_star_priv *priv,
+				unsigned int hash_addr)
+{
+	unsigned int val;
+	int ret;
+
+	ret = mtk_star_hash_wait_cmd_start(priv);
+	if (ret)
+		return ret;
+
+	val = hash_addr & MTK_STAR_MSK_HASH_CTRL_HASH_BIT_ADDR;
+	val |= MTK_STAR_BIT_HASH_CTRL_ACC_CMD;
+	val |= MTK_STAR_BIT_HASH_CTRL_CMD_START;
+	val |= MTK_STAR_BIT_HASH_CTRL_BIST_EN;
+	val |= MTK_STAR_BIT_HASH_CTRL_HASH_BIT_DATA;
+	regmap_write(priv->regs, MTK_STAR_REG_HASH_CTRL, val);
+
+	return mtk_star_hash_wait_ok(priv);
+}
+
+static int mtk_star_reset_hash_table(struct mtk_star_priv *priv)
+{
+	int ret;
+
+	ret = mtk_star_hash_wait_cmd_start(priv);
+	if (ret)
+		return ret;
+
+	regmap_update_bits(priv->regs, MTK_STAR_REG_HASH_CTRL,
+			   MTK_STAR_BIT_HASH_CTRL_BIST_EN,
+			   MTK_STAR_BIT_HASH_CTRL_BIST_EN);
+	regmap_update_bits(priv->regs, MTK_STAR_REG_TEST1,
+			   MTK_STAR_BIT_TEST1_RST_HASH_MBIST,
+			   MTK_STAR_BIT_TEST1_RST_HASH_MBIST);
+
+	return mtk_star_hash_wait_ok(priv);
+}
+
+static void mtk_star_phy_config(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	if (priv->speed == SPEED_1000)
+		val = MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_1000M;
+	else if (priv->speed == SPEED_100)
+		val = MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_100M;
+	else
+		val = MTK_STAR_VAL_PHY_CTRL1_FORCE_SPD_10M;
+	val <<= MTK_STAR_OFF_PHY_CTRL1_FORCE_SPD;
+
+	val |= MTK_STAR_BIT_PHY_CTRL1_AN_EN;
+	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_RX;
+	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_FC_TX;
+	/* Only full-duplex supported for now. */
+	val |= MTK_STAR_BIT_PHY_CTRL1_FORCE_DPX;
+
+	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL1, val);
+
+	if (priv->pause) {
+		val = MTK_STAR_VAL_FC_CFG_SEND_PAUSE_TH_2K;
+		val <<= MTK_STAR_OFF_FC_CFG_SEND_PAUSE_TH;
+		val |= MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR;
+	} else {
+		val = 0;
+	}
+
+	regmap_update_bits(priv->regs, MTK_STAR_REG_FC_CFG,
+			   MTK_STAR_MSK_FC_CFG_SEND_PAUSE_TH |
+			   MTK_STAR_BIT_FC_CFG_UC_PAUSE_DIR, val);
+
+	if (priv->pause) {
+		val = MTK_STAR_VAL_EXT_CFG_SND_PAUSE_RLS_1K;
+		val <<= MTK_STAR_OFF_EXT_CFG_SND_PAUSE_RLS;
+	} else {
+		val = 0;
+	}
+
+	regmap_update_bits(priv->regs, MTK_STAR_REG_EXT_CFG,
+			   MTK_STAR_MSK_EXT_CFG_SND_PAUSE_RLS, val);
+}
+
+static void mtk_star_adjust_link(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct phy_device *phydev = priv->phydev;
+	bool new_state = false;
+
+	if (phydev->link) {
+		if (!priv->link) {
+			priv->link = phydev->link;
+			new_state = true;
+		}
+
+		if (priv->speed != phydev->speed) {
+			priv->speed = phydev->speed;
+			new_state = true;
+		}
+
+		if (priv->pause != phydev->pause) {
+			priv->pause = phydev->pause;
+			new_state = true;
+		}
+	} else {
+		if (priv->link) {
+			priv->link = phydev->link;
+			new_state = true;
+		}
+	}
+
+	if (new_state) {
+		if (phydev->link)
+			mtk_star_phy_config(priv);
+
+		phy_print_status(ndev->phydev);
+	}
+}
+
+static void mtk_star_init_config(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	val = (MTK_STAR_BIT_MII_PAD_OUT_ENABLE |
+	       MTK_STAR_BIT_EXT_MDC_MODE |
+	       MTK_STAR_BIT_SWC_MII_MODE);
+
+	regmap_write(priv->regs, MTK_STAR_REG_SYS_CONF, val);
+	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CLK_CONF,
+			   MTK_STAR_MSK_MAC_CLK_CONF,
+			   MTK_STAR_BIT_CLK_DIV_10);
+}
+
+static void mtk_star_set_mode_rmii(struct mtk_star_priv *priv)
+{
+	regmap_update_bits(priv->pericfg, MTK_PERICFG_REG_NIC_CFG_CON,
+			   MTK_PERICFG_MSK_NIC_CFG_CON_CFG_MII,
+			   MTK_PERICFG_BIT_NIC_CFG_CON_RMII);
+}
+
+static int mtk_star_enable(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	unsigned int val;
+	int ret;
+
+	mtk_star_nic_disable_pd(priv);
+	mtk_star_intr_disable(priv);
+	mtk_star_dma_stop(priv);
+
+	mtk_star_set_mac_addr(ndev);
+
+	/* Configure the MAC */
+	val = MTK_STAR_VAL_MAC_CFG_IPG_96BIT;
+	val <<= MTK_STAR_OFF_MAC_CFG_IPG;
+	val |= MTK_STAR_BIT_MAC_CFG_MAXLEN_1522;
+	val |= MTK_STAR_BIT_MAC_CFG_AUTO_PAD;
+	val |= MTK_STAR_BIT_MAC_CFG_CRC_STRIP;
+	regmap_write(priv->regs, MTK_STAR_REG_MAC_CFG, val);
+
+	/* Enable Hash Table BIST and reset it */
+	ret = mtk_star_reset_hash_table(priv);
+	if (ret)
+		return ret;
+
+	/* Setup the hashing algorithm */
+	regmap_update_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
+			   MTK_STAR_BIT_ARL_CFG_HASH_ALG |
+			   MTK_STAR_BIT_ARL_CFG_MISC_MODE, 0);
+
+	/* Don't strip VLAN tags */
+	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
+			   MTK_STAR_BIT_MAC_CFG_VLAN_STRIP, 0);
+
+	/* Setup DMA */
+	mtk_star_dma_init(priv);
+
+	ret = mtk_star_prepare_rx_skbs(ndev);
+	if (ret)
+		goto err_out;
+
+	/* Request the interrupt */
+	ret = request_irq(ndev->irq, mtk_star_handle_irq,
+			  IRQF_TRIGGER_FALLING, ndev->name, ndev);
+	if (ret)
+		goto err_free_skbs;
+
+	napi_enable(&priv->napi);
+
+	mtk_star_intr_ack_all(priv);
+	mtk_star_intr_enable(priv);
+
+	/* Connect to and start PHY */
+	priv->phydev = of_phy_connect(ndev, priv->phy_node,
+				      mtk_star_adjust_link, 0, priv->phy_intf);
+	if (!priv->phydev) {
+		netdev_err(ndev, "failed to connect to PHY\n");
+		goto err_free_irq;
+	}
+
+	mtk_star_dma_start(priv);
+	phy_start(priv->phydev);
+	netif_start_queue(ndev);
+
+	return 0;
+
+err_free_irq:
+	free_irq(ndev->irq, ndev);
+err_free_skbs:
+	mtk_star_free_rx_skbs(priv);
+err_out:
+	return ret;
+}
+
+static void mtk_star_disable(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	napi_disable(&priv->napi);
+	mtk_star_intr_disable(priv);
+	mtk_star_dma_disable(priv);
+	mtk_star_intr_ack_all(priv);
+	phy_stop(priv->phydev);
+	phy_disconnect(priv->phydev);
+	free_irq(ndev->irq, ndev);
+	mtk_star_free_rx_skbs(priv);
+	mtk_star_free_tx_skbs(priv);
+}
+
+static int mtk_star_netdev_open(struct net_device *ndev)
+{
+	return mtk_star_enable(ndev);
+}
+
+static int mtk_star_netdev_stop(struct net_device *ndev)
+{
+	mtk_star_disable(ndev);
+
+	return 0;
+}
+
+static int mtk_star_netdev_ioctl(struct net_device *ndev,
+				 struct ifreq *req, int cmd)
+{
+	if (!netif_running(ndev))
+		return -EINVAL;
+
+	return phy_mii_ioctl(ndev->phydev, req, cmd);
+}
+
+static int mtk_star_netdev_start_xmit(struct sk_buff *skb,
+				      struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct mtk_star_ring *ring = &priv->tx_ring;
+	struct device *dev = mtk_star_get_dev(priv);
+	struct mtk_star_ring_desc_data desc_data;
+
+	desc_data.dma_addr = mtk_star_dma_map_tx(priv, skb);
+	if (dma_mapping_error(dev, desc_data.dma_addr))
+		goto err_drop_packet;
+
+	desc_data.skb = skb;
+	desc_data.len = skb->len;
+
+	spin_lock_bh(&priv->lock);
+
+	mtk_star_ring_push_head_tx(ring, &desc_data);
+
+	netdev_sent_queue(ndev, skb->len);
+
+	if (mtk_star_ring_full(ring))
+		netif_stop_queue(ndev);
+
+	spin_unlock_bh(&priv->lock);
+
+	mtk_star_dma_resume_tx(priv);
+
+	return NETDEV_TX_OK;
+
+err_drop_packet:
+	dev_kfree_skb(skb);
+	ndev->stats.tx_dropped++;
+	return NETDEV_TX_BUSY;
+}
+
+/* Returns the number of bytes sent or a negative number on the first
+ * descriptor owned by DMA.
+ */
+static int mtk_star_tx_complete_one(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring *ring = &priv->tx_ring;
+	struct mtk_star_ring_desc_data desc_data;
+	int ret;
+
+	ret = mtk_star_ring_pop_tail(ring, &desc_data);
+	if (ret)
+		return ret;
+
+	mtk_star_dma_unmap_tx(priv, &desc_data);
+	ret = desc_data.skb->len;
+	dev_kfree_skb_irq(desc_data.skb);
+
+	return ret;
+}
+
+static void mtk_star_tx_complete_all(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring *ring = &priv->tx_ring;
+	struct net_device *ndev = priv->ndev;
+	int ret, pkts_compl, bytes_compl;
+	bool wake = false;
+
+	spin_lock(&priv->lock);
+
+	for (pkts_compl = 0, bytes_compl = 0;;
+	     pkts_compl++, bytes_compl += ret, wake = true) {
+		if (!mtk_star_ring_descs_available(ring))
+			break;
+
+		ret = mtk_star_tx_complete_one(priv);
+		if (ret < 0)
+			break;
+	}
+
+	netdev_completed_queue(ndev, pkts_compl, bytes_compl);
+
+	if (wake && netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+
+	mtk_star_intr_enable_tx(priv);
+
+	spin_unlock(&priv->lock);
+}
+
+static void mtk_star_netdev_get_stats64(struct net_device *ndev,
+					struct rtnl_link_stats64 *stats)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+
+	mtk_star_update_stats(priv);
+
+	memcpy(stats, &priv->stats, sizeof(*stats));
+}
+
+static void mtk_star_set_rx_mode(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct netdev_hw_addr *hw_addr;
+	unsigned int hash_addr, i;
+	int ret;
+
+	if (ndev->flags & IFF_PROMISC) {
+		regmap_update_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
+				   MTK_STAR_BIT_ARL_CFG_MISC_MODE,
+				   MTK_STAR_BIT_ARL_CFG_MISC_MODE);
+	} else if (netdev_mc_count(ndev) > MTK_STAR_HASHTABLE_MC_LIMIT ||
+		   ndev->flags & IFF_ALLMULTI) {
+		for (i = 0; i < MTK_STAR_HASHTABLE_SIZE_MAX; i++) {
+			ret = mtk_star_set_hashbit(priv, i);
+			if (ret)
+				goto hash_fail;
+		}
+	} else {
+		/* Clear previous settings. */
+		ret = mtk_star_reset_hash_table(priv);
+		if (ret)
+			goto hash_fail;
+
+		netdev_for_each_mc_addr(hw_addr, ndev) {
+			hash_addr = (hw_addr->addr[0] & 0x01) << 8;
+			hash_addr += hw_addr->addr[5];
+			ret = mtk_star_set_hashbit(priv, hash_addr);
+			if (ret)
+				goto hash_fail;
+		}
+	}
+
+	return;
+
+hash_fail:
+	if (ret == -ETIMEDOUT)
+		netdev_err(ndev, "setting hash bit timed out\n");
+	else
+		/* Should be -EIO */
+		netdev_err(ndev, "unable to set hash bit");
+}
+
+static const struct net_device_ops mtk_star_netdev_ops = {
+	.ndo_open		= mtk_star_netdev_open,
+	.ndo_stop		= mtk_star_netdev_stop,
+	.ndo_start_xmit		= mtk_star_netdev_start_xmit,
+	.ndo_get_stats64	= mtk_star_netdev_get_stats64,
+	.ndo_set_rx_mode	= mtk_star_set_rx_mode,
+	.ndo_do_ioctl		= mtk_star_netdev_ioctl,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+static void mtk_star_get_drvinfo(struct net_device *dev,
+				 struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, MTK_STAR_DRVNAME, sizeof(info->driver));
+}
+
+/* TODO Add ethtool stats. */
+static const struct ethtool_ops mtk_star_ethtool_ops = {
+	.get_drvinfo		= mtk_star_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+};
+
+static int mtk_star_receive_packet(struct mtk_star_priv *priv)
+{
+	struct mtk_star_ring *ring = &priv->rx_ring;
+	struct device *dev = mtk_star_get_dev(priv);
+	struct mtk_star_ring_desc_data desc_data;
+	struct net_device *ndev = priv->ndev;
+	struct sk_buff *curr_skb, *new_skb;
+	dma_addr_t new_dma_addr;
+	int ret;
+
+	spin_lock(&priv->lock);
+	ret = mtk_star_ring_pop_tail(ring, &desc_data);
+	spin_unlock(&priv->lock);
+	if (ret)
+		return -1;
+
+	curr_skb = desc_data.skb;
+
+	if ((desc_data.flags & MTK_STAR_DESC_BIT_RX_CRCE) ||
+	    (desc_data.flags & MTK_STAR_DESC_BIT_RX_OSIZE)) {
+		/* Error packet -> drop and reuse skb. */
+		new_skb = curr_skb;
+		goto push_new_skb;
+	}
+
+	/* Prepare new skb before receiving the current one. Reuse the current
+	 * skb if we fail at any point.
+	 */
+	new_skb = mtk_star_alloc_skb(ndev);
+	if (!new_skb) {
+		ndev->stats.rx_dropped++;
+		new_skb = curr_skb;
+		goto push_new_skb;
+	}
+
+	new_dma_addr = mtk_star_dma_map_rx(priv, new_skb);
+	if (dma_mapping_error(dev, new_dma_addr)) {
+		ndev->stats.rx_dropped++;
+		dev_kfree_skb(new_skb);
+		new_skb = curr_skb;
+		netdev_err(ndev, "DMA mapping error of RX descriptor\n");
+		goto push_new_skb;
+	}
+
+	/* We can't fail anymore at this point: it's safe to unmap the skb. */
+	mtk_star_dma_unmap_rx(priv, &desc_data);
+
+	skb_put(desc_data.skb, desc_data.len);
+	desc_data.skb->ip_summed = CHECKSUM_NONE;
+	desc_data.skb->protocol = eth_type_trans(desc_data.skb, ndev);
+	desc_data.skb->dev = ndev;
+	netif_receive_skb(desc_data.skb);
+
+push_new_skb:
+	desc_data.dma_addr = new_dma_addr;
+	desc_data.len = skb_tailroom(new_skb);
+	desc_data.skb = new_skb;
+
+	spin_lock(&priv->lock);
+	mtk_star_ring_push_head_rx(ring, &desc_data);
+	spin_unlock(&priv->lock);
+
+	return 0;
+}
+
+static int mtk_star_process_rx(struct mtk_star_priv *priv, int budget)
+{
+	int received, ret;
+
+	for (received = 0, ret = 0; received < budget && ret == 0; received++)
+		ret = mtk_star_receive_packet(priv);
+
+	mtk_star_dma_resume_rx(priv);
+
+	return received;
+}
+
+static int mtk_star_poll(struct napi_struct *napi, int budget)
+{
+	struct mtk_star_priv *priv;
+	int received = 0;
+
+	priv = container_of(napi, struct mtk_star_priv, napi);
+
+	/* Clean-up all TX descriptors. */
+	mtk_star_tx_complete_all(priv);
+	/* Receive up to $budget packets. */
+	received = mtk_star_process_rx(priv, budget);
+
+	if (received < budget) {
+		napi_complete_done(napi, received);
+		mtk_star_intr_enable_rx(priv);
+	}
+
+	return received;
+}
+
+static void mtk_star_mdio_rwok_clear(struct mtk_star_priv *priv)
+{
+	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL0,
+		     MTK_STAR_BIT_PHY_CTRL0_RWOK);
+}
+
+static int mtk_star_mdio_rwok_wait(struct mtk_star_priv *priv)
+{
+	unsigned int val;
+
+	return regmap_read_poll_timeout(priv->regs, MTK_STAR_REG_PHY_CTRL0,
+					val, val & MTK_STAR_BIT_PHY_CTRL0_RWOK,
+					10, MTK_STAR_WAIT_TIMEOUT);
+}
+
+static int mtk_star_mdio_read(struct mii_bus *mii, int phy_id, int regnum)
+{
+	struct mtk_star_priv *priv = mii->priv;
+	unsigned int val, data;
+	int ret;
+
+	if (regnum & MII_ADDR_C45)
+		return -EOPNOTSUPP;
+
+	mtk_star_mdio_rwok_clear(priv);
+
+	val = (regnum << MTK_STAR_OFF_PHY_CTRL0_PREG);
+	val &= MTK_STAR_MSK_PHY_CTRL0_PREG;
+	val |= MTK_STAR_BIT_PHY_CTRL0_RDCMD;
+
+	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL0, val);
+
+	ret = mtk_star_mdio_rwok_wait(priv);
+	if (ret)
+		return ret;
+
+	regmap_read(priv->regs, MTK_STAR_REG_PHY_CTRL0, &data);
+
+	data &= MTK_STAR_MSK_PHY_CTRL0_RWDATA;
+	data >>= MTK_STAR_OFF_PHY_CTRL0_RWDATA;
+
+	return data;
+}
+
+static int mtk_star_mdio_write(struct mii_bus *mii, int phy_id,
+			       int regnum, u16 data)
+{
+	struct mtk_star_priv *priv = mii->priv;
+	unsigned int val;
+
+	if (regnum & MII_ADDR_C45)
+		return -EOPNOTSUPP;
+
+	mtk_star_mdio_rwok_clear(priv);
+
+	val = data;
+	val <<= MTK_STAR_OFF_PHY_CTRL0_RWDATA;
+	val &= MTK_STAR_MSK_PHY_CTRL0_RWDATA;
+	regnum <<= MTK_STAR_OFF_PHY_CTRL0_PREG;
+	regnum &= MTK_STAR_MSK_PHY_CTRL0_PREG;
+	val |= regnum;
+	val |= MTK_STAR_BIT_PHY_CTRL0_WTCMD;
+
+	regmap_write(priv->regs, MTK_STAR_REG_PHY_CTRL0, val);
+
+	return mtk_star_mdio_rwok_wait(priv);
+}
+
+static int mtk_star_mdio_init(struct net_device *ndev)
+{
+	struct mtk_star_priv *priv = netdev_priv(ndev);
+	struct device *dev = mtk_star_get_dev(priv);
+	struct device_node *of_node, *mdio_node;
+	int ret;
+
+	of_node = dev->of_node;
+
+	mdio_node = of_get_child_by_name(of_node, "mdio");
+	if (!mdio_node)
+		return -ENODEV;
+
+	if (!of_device_is_available(mdio_node)) {
+		ret = -ENODEV;
+		goto out_put_node;
+	}
+
+	priv->mii = devm_mdiobus_alloc(dev);
+	if (!priv->mii) {
+		ret = -ENOMEM;
+		goto out_put_node;
+	}
+
+	snprintf(priv->mii->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+	priv->mii->name = "mtk-mac-mdio";
+	priv->mii->parent = dev;
+	priv->mii->read = mtk_star_mdio_read;
+	priv->mii->write = mtk_star_mdio_write;
+	priv->mii->priv = priv;
+
+	ret = of_mdiobus_register(priv->mii, mdio_node);
+
+out_put_node:
+	of_node_put(mdio_node);
+	return ret;
+}
+
+static int mtk_star_suspend(struct device *dev)
+{
+	struct mtk_star_priv *priv;
+	struct net_device *ndev;
+
+	ndev = dev_get_drvdata(dev);
+	priv = netdev_priv(ndev);
+
+	if (netif_running(ndev))
+		mtk_star_disable(ndev);
+
+	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
+
+	return 0;
+}
+
+static int mtk_star_resume(struct device *dev)
+{
+	struct mtk_star_priv *priv;
+	struct net_device *ndev;
+	int ret;
+
+	ndev = dev_get_drvdata(dev);
+	priv = netdev_priv(ndev);
+
+	ret = clk_bulk_prepare_enable(MTK_STAR_NCLKS, priv->clks);
+	if (ret)
+		return ret;
+
+	if (netif_running(ndev)) {
+		ret = mtk_star_enable(ndev);
+		if (ret)
+			clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
+	}
+
+	return ret;
+}
+
+static void mtk_star_clk_disable_unprepare(void *data)
+{
+	struct mtk_star_priv *priv = data;
+
+	clk_bulk_disable_unprepare(MTK_STAR_NCLKS, priv->clks);
+}
+
+static void mtk_star_mdiobus_unregister(void *data)
+{
+	struct mtk_star_priv *priv = data;
+
+	mdiobus_unregister(priv->mii);
+}
+
+static void mtk_star_unregister_netdev(void *data)
+{
+	struct net_device *ndev = data;
+
+	unregister_netdev(ndev);
+}
+
+static int mtk_star_probe(struct platform_device *pdev)
+{
+	struct device_node *of_node;
+	struct mtk_star_priv *priv;
+	struct net_device *ndev;
+	struct device *dev;
+	void __iomem *base;
+	int ret, i;
+
+	dev = &pdev->dev;
+	of_node = dev->of_node;
+
+	ndev = devm_alloc_etherdev(dev, sizeof(*priv));
+	if (!ndev)
+		return -ENOMEM;
+
+	priv = netdev_priv(ndev);
+	priv->ndev = ndev;
+	SET_NETDEV_DEV(ndev, dev);
+	platform_set_drvdata(pdev, ndev);
+
+	ndev->min_mtu = ETH_ZLEN;
+	ndev->max_mtu = MTK_STAR_MAX_FRAME_SIZE;
+
+	spin_lock_init(&priv->lock);
+	INIT_WORK(&priv->stats_work, mtk_star_update_stats_work);
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	/* We won't be checking the return values of regmap read & write
+	 * functions. They can only fail for mmio if there's a clock attached
+	 * to regmap which is not the case here.
+	 */
+	priv->regs = devm_regmap_init_mmio(dev, base,
+					   &mtk_star_regmap_config);
+	if (IS_ERR(priv->regs))
+		return PTR_ERR(priv->regs);
+
+	priv->pericfg = syscon_regmap_lookup_by_phandle(of_node,
+							"mediatek,pericfg");
+	if (IS_ERR(priv->pericfg)) {
+		dev_err(dev, "Failed to lookup the PERICFG syscon\n");
+		return PTR_ERR(priv->pericfg);
+	}
+
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0)
+		return ndev->irq;
+
+	for (i = 0; i < MTK_STAR_NCLKS; i++)
+		priv->clks[i].id = mtk_star_clk_names[i];
+	ret = devm_clk_bulk_get(dev, MTK_STAR_NCLKS, priv->clks);
+	if (ret)
+		return ret;
+
+	ret = clk_bulk_prepare_enable(MTK_STAR_NCLKS, priv->clks);
+	if (ret)
+		return ret;
+
+	ret = devm_add_action_or_reset(dev,
+				       mtk_star_clk_disable_unprepare, priv);
+	if (ret)
+		return ret;
+
+	ret = of_get_phy_mode(of_node, &priv->phy_intf);
+	if (ret) {
+		return ret;
+	} else if (priv->phy_intf != PHY_INTERFACE_MODE_RMII) {
+		dev_err(dev, "unsupported phy mode: %s\n",
+			phy_modes(priv->phy_intf));
+		return -EINVAL;
+	}
+
+	priv->phy_node = of_parse_phandle(of_node, "phy-handle", 0);
+	if (!priv->phy_node) {
+		dev_err(dev, "failed to retrieve the phy handle from device tree\n");
+		return -ENODEV;
+	}
+
+	mtk_star_set_mode_rmii(priv);
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "unsupported DMA mask\n");
+		return ret;
+	}
+
+	priv->ring_base = dmam_alloc_coherent(dev, MTK_STAR_DMA_SIZE,
+					      &priv->dma_addr,
+					      GFP_KERNEL | GFP_DMA);
+	if (!priv->ring_base)
+		return -ENOMEM;
+
+	mtk_star_nic_disable_pd(priv);
+	mtk_star_init_config(priv);
+
+	ret = mtk_star_mdio_init(ndev);
+	if (ret)
+		return ret;
+
+	ret = devm_add_action_or_reset(dev, mtk_star_mdiobus_unregister, priv);
+	if (ret)
+		return ret;
+
+	ret = eth_platform_get_mac_address(dev, ndev->dev_addr);
+	if (ret || !is_valid_ether_addr(ndev->dev_addr))
+		eth_hw_addr_random(ndev);
+
+	ndev->netdev_ops = &mtk_star_netdev_ops;
+	ndev->ethtool_ops = &mtk_star_ethtool_ops;
+
+	netif_napi_add(ndev, &priv->napi, mtk_star_poll, MTK_STAR_NAPI_WEIGHT);
+
+	ret = register_netdev(ndev);
+	if (ret)
+		return ret;
+
+	ret = devm_add_action_or_reset(dev, mtk_star_unregister_netdev, ndev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct of_device_id mtk_star_of_match[] = {
+	{ .compatible = "mediatek,mt8516-eth", },
+	{ .compatible = "mediatek,mt8518-eth", },
+	{ .compatible = "mediatek,mt8175-eth", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mtk_star_of_match);
+
+static SIMPLE_DEV_PM_OPS(mtk_star_pm_ops,
+			 mtk_star_suspend, mtk_star_resume);
+
+static struct platform_driver mtk_star_driver = {
+	.driver = {
+		.name = MTK_STAR_DRVNAME,
+		.pm = &mtk_star_pm_ops,
+		.of_match_table = of_match_ptr(mtk_star_of_match),
+	},
+	.probe = mtk_star_probe,
+};
+module_platform_driver(mtk_star_driver);
+
+MODULE_AUTHOR("Bartosz Golaszewski <bgolaszewski@baylibre.com>");
+MODULE_DESCRIPTION("Mediatek STAR Ethernet MAC Driver");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 060b6381efe58478e1d7dfff7a1e76a73a6377db Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Wed, 20 May 2020 19:18:10 +0100
Subject: net: flow_offload: simplify hw stats check handling

Make FLOW_ACTION_HW_STATS_DONT_CARE be all bits, rather than none, so that
 drivers and __flow_action_hw_stats_check can use simple bitwise checks.

Pre-fill all actions with DONT_CARE in flow_rule_alloc(), rather than
 relying on implicit semantics of zero from kzalloc, so that callers which
 don't configure action stats themselves (i.e. netfilter) get the correct
 behaviour by default.

Only the kernel's internal API semantics change; the TC uAPI is unaffected.

v4: move DONT_CARE setting to flow_rule_alloc() for robustness and simplicity.

v3: set DONT_CARE in nft and ct offload.

v2: rebased on net-next, removed RFC tags.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c |  8 ++++----
 include/net/flow_offload.h                            | 11 +++++++----
 net/core/flow_offload.c                               |  6 ++++++
 3 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index b286fe158820..51e1b3930c56 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -30,14 +30,14 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		return -EOPNOTSUPP;
 
 	act = flow_action_first_entry_get(flow_action);
-	if (act->hw_stats == FLOW_ACTION_HW_STATS_ANY ||
-	    act->hw_stats == FLOW_ACTION_HW_STATS_IMMEDIATE) {
+	if (act->hw_stats & FLOW_ACTION_HW_STATS_DISABLED) {
+		/* Nothing to do */
+	} else if (act->hw_stats & FLOW_ACTION_HW_STATS_IMMEDIATE) {
 		/* Count action is inserted first */
 		err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
 		if (err)
 			return err;
-	} else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED &&
-		   act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) {
+	} else {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type");
 		return -EOPNOTSUPP;
 	}
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 4001ffb04f0d..95d633785ef9 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -168,10 +168,11 @@ enum flow_action_hw_stats_bit {
 	FLOW_ACTION_HW_STATS_IMMEDIATE_BIT,
 	FLOW_ACTION_HW_STATS_DELAYED_BIT,
 	FLOW_ACTION_HW_STATS_DISABLED_BIT,
+
+	FLOW_ACTION_HW_STATS_NUM_BITS
 };
 
 enum flow_action_hw_stats {
-	FLOW_ACTION_HW_STATS_DONT_CARE = 0,
 	FLOW_ACTION_HW_STATS_IMMEDIATE =
 		BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT),
 	FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT),
@@ -179,6 +180,7 @@ enum flow_action_hw_stats {
 				   FLOW_ACTION_HW_STATS_DELAYED,
 	FLOW_ACTION_HW_STATS_DISABLED =
 		BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT),
+	FLOW_ACTION_HW_STATS_DONT_CARE = BIT(FLOW_ACTION_HW_STATS_NUM_BITS) - 1,
 };
 
 typedef void (*action_destr)(void *priv);
@@ -340,11 +342,12 @@ __flow_action_hw_stats_check(const struct flow_action *action,
 		return false;
 
 	action_entry = flow_action_first_entry_get(action);
-	if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE)
-		return true;
+
+	/* Zero is not a legal value for hw_stats, catch anyone passing it */
+	WARN_ON_ONCE(!action_entry->hw_stats);
 
 	if (!check_allow_bit &&
-	    action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) {
+	    ~action_entry->hw_stats & FLOW_ACTION_HW_STATS_ANY) {
 		NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\"");
 		return false;
 	} else if (check_allow_bit &&
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index e951b743bed3..e64941c526b1 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -8,6 +8,7 @@
 struct flow_rule *flow_rule_alloc(unsigned int num_actions)
 {
 	struct flow_rule *rule;
+	int i;
 
 	rule = kzalloc(struct_size(rule, action.entries, num_actions),
 		       GFP_KERNEL);
@@ -15,6 +16,11 @@ struct flow_rule *flow_rule_alloc(unsigned int num_actions)
 		return NULL;
 
 	rule->action.num_entries = num_actions;
+	/* Pre-fill each action hw_stats with DONT_CARE.
+	 * Caller can override this if it wants stats for a given action.
+	 */
+	for (i = 0; i < num_actions; i++)
+		rule->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE;
 
 	return rule;
 }
-- 
cgit v1.2.3


From 93a09e74574b2b75319938ef4155fe841335e436 Mon Sep 17 00:00:00 2001
From: Potnuri Bharat Teja <bharat@chelsio.com>
Date: Thu, 21 May 2020 16:04:29 +0530
Subject: cxgb4: add adapter hotplug support for ULDs

Upon adapter hotplug, cxgb4 registers ULD devices for all the ULDs that
are already loaded, ensuring that ULD's can enumerate the hotplugged
adapter without reloading the ULD.

Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h      |   8 ++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |   8 +-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c  | 138 +++++++++++++++---------
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h  |   2 +
 4 files changed, 100 insertions(+), 56 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index fc1405a8ed74..5a41801acb6a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -60,6 +60,7 @@
 
 #define CH_WARN(adap, fmt, ...) dev_warn(adap->pdev_dev, fmt, ## __VA_ARGS__)
 extern struct list_head adapter_list;
+extern struct list_head uld_list;
 extern struct mutex uld_mutex;
 
 /* Suspend an Ethernet Tx queue with fewer available descriptors than this.
@@ -822,6 +823,13 @@ struct sge_uld_txq_info {
 	u16 ntxq;		/* # of egress uld queues */
 };
 
+/* struct to maintain ULD list to reallocate ULD resources on hotplug */
+struct cxgb4_uld_list {
+	struct cxgb4_uld_info uld_info;
+	struct list_head list_node;
+	enum cxgb4_uld uld_type;
+};
+
 enum sge_eosw_state {
 	CXGB4_EO_STATE_CLOSED = 0, /* Not ready to accept traffic */
 	CXGB4_EO_STATE_FLOWC_OPEN_SEND, /* Send FLOWC open request */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index d05c2371d8c7..7a0414f379be 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -180,6 +180,7 @@ static struct dentry *cxgb4_debugfs_root;
 
 LIST_HEAD(adapter_list);
 DEFINE_MUTEX(uld_mutex);
+LIST_HEAD(uld_list);
 
 static int cfg_queues(struct adapter *adap);
 
@@ -6519,11 +6520,8 @@ fw_attach_fail:
 	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
 	pdev->needs_freset = 1;
 
-	if (is_uld(adapter)) {
-		mutex_lock(&uld_mutex);
-		list_add_tail(&adapter->list_node, &adapter_list);
-		mutex_unlock(&uld_mutex);
-	}
+	if (is_uld(adapter))
+		cxgb4_uld_enable(adapter);
 
 	if (!is_t4(adapter->params.chip))
 		cxgb4_ptp_init(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index e65b52375dd8..6b1d3df4b9ba 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -681,6 +681,74 @@ static void cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 }
 #endif
 
+static void cxgb4_uld_alloc_resources(struct adapter *adap,
+				      enum cxgb4_uld type,
+				      const struct cxgb4_uld_info *p)
+{
+	int ret = 0;
+
+	if ((type == CXGB4_ULD_CRYPTO && !is_pci_uld(adap)) ||
+	    (type != CXGB4_ULD_CRYPTO && !is_offload(adap)))
+		return;
+	if (type == CXGB4_ULD_ISCSIT && is_t4(adap->params.chip))
+		return;
+	ret = cfg_queues_uld(adap, type, p);
+	if (ret)
+		goto out;
+	ret = setup_sge_queues_uld(adap, type, p->lro);
+	if (ret)
+		goto free_queues;
+	if (adap->flags & CXGB4_USING_MSIX) {
+		ret = request_msix_queue_irqs_uld(adap, type);
+		if (ret)
+			goto free_rxq;
+	}
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
+		enable_rx_uld(adap, type);
+#ifdef CONFIG_CHELSIO_TLS_DEVICE
+	/* send mbox to enable ktls related settings. */
+	if (type == CXGB4_ULD_CRYPTO &&
+	    (adap->params.crypto & FW_CAPS_CONFIG_TX_TLS_HW))
+		cxgb4_set_ktls_feature(adap, 1);
+#endif
+	if (adap->uld[type].add)
+		goto free_irq;
+	ret = setup_sge_txq_uld(adap, type, p);
+	if (ret)
+		goto free_irq;
+	adap->uld[type] = *p;
+	ret = uld_attach(adap, type);
+	if (ret)
+		goto free_txq;
+	return;
+free_txq:
+	release_sge_txq_uld(adap, type);
+free_irq:
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
+		quiesce_rx_uld(adap, type);
+	if (adap->flags & CXGB4_USING_MSIX)
+		free_msix_queue_irqs_uld(adap, type);
+free_rxq:
+	free_sge_queues_uld(adap, type);
+free_queues:
+	free_queues_uld(adap, type);
+out:
+	dev_warn(adap->pdev_dev,
+		 "ULD registration failed for uld type %d\n", type);
+}
+
+void cxgb4_uld_enable(struct adapter *adap)
+{
+	struct cxgb4_uld_list *uld_entry;
+
+	mutex_lock(&uld_mutex);
+	list_add_tail(&adap->list_node, &adapter_list);
+	list_for_each_entry(uld_entry, &uld_list, list_node)
+		cxgb4_uld_alloc_resources(adap, uld_entry->uld_type,
+					  &uld_entry->uld_info);
+	mutex_unlock(&uld_mutex);
+}
+
 /* cxgb4_register_uld - register an upper-layer driver
  * @type: the ULD type
  * @p: the ULD methods
@@ -691,63 +759,23 @@ static void cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 void cxgb4_register_uld(enum cxgb4_uld type,
 			const struct cxgb4_uld_info *p)
 {
+	struct cxgb4_uld_list *uld_entry;
 	struct adapter *adap;
-	int ret = 0;
 
 	if (type >= CXGB4_ULD_MAX)
 		return;
 
+	uld_entry = kzalloc(sizeof(*uld_entry), GFP_KERNEL);
+	if (!uld_entry)
+		return;
+
+	memcpy(&uld_entry->uld_info, p, sizeof(struct cxgb4_uld_info));
 	mutex_lock(&uld_mutex);
-	list_for_each_entry(adap, &adapter_list, list_node) {
-		if ((type == CXGB4_ULD_CRYPTO && !is_pci_uld(adap)) ||
-		    (type != CXGB4_ULD_CRYPTO && !is_offload(adap)))
-			continue;
-		if (type == CXGB4_ULD_ISCSIT && is_t4(adap->params.chip))
-			continue;
-		ret = cfg_queues_uld(adap, type, p);
-		if (ret)
-			goto out;
-		ret = setup_sge_queues_uld(adap, type, p->lro);
-		if (ret)
-			goto free_queues;
-		if (adap->flags & CXGB4_USING_MSIX) {
-			ret = request_msix_queue_irqs_uld(adap, type);
-			if (ret)
-				goto free_rxq;
-		}
-		if (adap->flags & CXGB4_FULL_INIT_DONE)
-			enable_rx_uld(adap, type);
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-		/* send mbox to enable ktls related settings. */
-		if (type == CXGB4_ULD_CRYPTO &&
-		    (adap->params.crypto & FW_CAPS_CONFIG_TX_TLS_HW))
-			cxgb4_set_ktls_feature(adap, 1);
-#endif
-		if (adap->uld[type].add)
-			goto free_irq;
-		ret = setup_sge_txq_uld(adap, type, p);
-		if (ret)
-			goto free_irq;
-		adap->uld[type] = *p;
-		ret = uld_attach(adap, type);
-		if (ret)
-			goto free_txq;
-		continue;
-free_txq:
-		release_sge_txq_uld(adap, type);
-free_irq:
-		if (adap->flags & CXGB4_FULL_INIT_DONE)
-			quiesce_rx_uld(adap, type);
-		if (adap->flags & CXGB4_USING_MSIX)
-			free_msix_queue_irqs_uld(adap, type);
-free_rxq:
-		free_sge_queues_uld(adap, type);
-free_queues:
-		free_queues_uld(adap, type);
-out:
-		dev_warn(adap->pdev_dev,
-			 "ULD registration failed for uld type %d\n", type);
-	}
+	list_for_each_entry(adap, &adapter_list, list_node)
+		cxgb4_uld_alloc_resources(adap, type, p);
+
+	uld_entry->uld_type = type;
+	list_add_tail(&uld_entry->list_node, &uld_list);
 	mutex_unlock(&uld_mutex);
 	return;
 }
@@ -761,6 +789,7 @@ EXPORT_SYMBOL(cxgb4_register_uld);
  */
 int cxgb4_unregister_uld(enum cxgb4_uld type)
 {
+	struct cxgb4_uld_list *uld_entry, *tmp;
 	struct adapter *adap;
 
 	if (type >= CXGB4_ULD_MAX)
@@ -783,6 +812,13 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 			cxgb4_set_ktls_feature(adap, 0);
 #endif
 	}
+
+	list_for_each_entry_safe(uld_entry, tmp, &uld_list, list_node) {
+		if (uld_entry->uld_type == type) {
+			list_del(&uld_entry->list_node);
+			kfree(uld_entry);
+		}
+	}
 	mutex_unlock(&uld_mutex);
 
 	return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 16796785eea3..085fa1424f9a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -327,6 +327,7 @@ enum cxgb4_control {
 	CXGB4_CONTROL_DB_DROP,
 };
 
+struct adapter;
 struct pci_dev;
 struct l2t_data;
 struct net_device;
@@ -465,6 +466,7 @@ struct cxgb4_uld_info {
 	int (*tx_handler)(struct sk_buff *skb, struct net_device *dev);
 };
 
+void cxgb4_uld_enable(struct adapter *adap);
 void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
 int cxgb4_unregister_uld(enum cxgb4_uld type);
 int cxgb4_ofld_send(struct net_device *dev, struct sk_buff *skb);
-- 
cgit v1.2.3


From 593532668f635d19d207510e0fbb5c2250f56b6f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 22 May 2020 16:09:42 -0700
Subject: Revert "net: mvneta: speed down the PHY, if WoL used, to save energy"

This reverts commit 5e3768a436bb70c9c3e27aaba6b73f8ef8f5dcf3.

On request from Russell King, this is a layering violation.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 41d2a0eac5fa..37947949345c 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3566,10 +3566,6 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 		    MVNETA_CAUSE_LINK_CHANGE);
 
 	phylink_start(pp->phylink);
-
-	/* We may have called phy_speed_down before */
-	phy_speed_up(pp->dev->phydev);
-
 	netif_tx_start_all_queues(pp->dev);
 }
 
@@ -3577,9 +3573,6 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
-	if (device_may_wakeup(&pp->dev->dev))
-		phy_speed_down(pp->dev->phydev, false);
-
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
@@ -4052,10 +4045,6 @@ static int mvneta_mdio_probe(struct mvneta_port *pp)
 	phylink_ethtool_get_wol(pp->phylink, &wol);
 	device_set_wakeup_capable(&pp->dev->dev, !!wol.supported);
 
-	/* PHY WoL may be enabled but device wakeup disabled */
-	if (wol.supported)
-		device_set_wakeup_enable(&pp->dev->dev, !!wol.wolopts);
-
 	return err;
 }
 
-- 
cgit v1.2.3


From 2639324a8fb69e1db88ef985e7def18a6bc106d1 Mon Sep 17 00:00:00 2001
From: Tang Bin <tangbin@cmss.chinamobile.com>
Date: Sat, 16 May 2020 07:06:33 +0800
Subject: net/mlx5e: Use IS_ERR() to check and simplify code

Use IS_ERR() and PTR_ERR() instead of PTR_ERR_OR_ZERO() to
simplify code, avoid redundant judgements.

Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index b45c3f46570b..9f50a1d3c5cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -96,9 +96,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	}
 
 	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
-	ret = PTR_ERR_OR_ZERO(rt);
-	if (ret)
-		return ret;
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
 
 	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) {
 		ip_rt_put(rt);
-- 
cgit v1.2.3


From 768c3667e6f36bc9db0dac854aa198651b27412f Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 12 May 2020 16:41:41 +0300
Subject: net/mlx5e: Extract TC-specific code from en_rep.c to rep/tc.c

As a preparation for introducing new kconfig option that controls
compilation of all TC offloads code in mlx5, extract TC-specific code from
en_rep.c to standalone file. This allows easily compiling out the code by
only including new source in make file when corresponding kconfig is
enabled instead of adding multiple ifdef blocks to en_rep.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   3 +-
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c    | 710 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.h    |  45 ++
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   | 543 +---------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |  13 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 170 +----
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |  35 +-
 9 files changed, 821 insertions(+), 708 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d3c7dbd7f1d5..c21453970dbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -33,7 +33,8 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/rep/tc.o en/tc_tun.o lib/port_tun.o \
+					lag_mp.o \
 					lib/geneve.o en/mapping.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
 					en/tc_tun_geneve.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
new file mode 100644
index 000000000000..edc574582135
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -0,0 +1,710 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#include <net/dst_metadata.h>
+#include <linux/netdevice.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rtnetlink.h>
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include "tc.h"
+#include "en_rep.h"
+#include "eswitch.h"
+#include "esw/chains.h"
+#include "en/tc_ct.h"
+#include "en/mapping.h"
+#include "en/tc_tun.h"
+#include "lib/port_tun.h"
+
+struct mlx5e_rep_indr_block_priv {
+	struct net_device *netdev;
+	struct mlx5e_rep_priv *rpriv;
+
+	struct list_head list;
+};
+
+int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
+	struct mlx5e_neigh_hash_entry *nhe;
+	int err;
+
+	err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type);
+	if (err)
+		return err;
+
+	mutex_lock(&rpriv->neigh_update.encap_lock);
+	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
+	if (!nhe) {
+		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
+		if (err) {
+			mutex_unlock(&rpriv->neigh_update.encap_lock);
+			mlx5_tun_entropy_refcount_dec(tun_entropy,
+						      e->reformat_type);
+			return err;
+		}
+	}
+
+	e->nhe = nhe;
+	spin_lock(&nhe->encap_list_lock);
+	list_add_rcu(&e->encap_list, &nhe->encap_list);
+	spin_unlock(&nhe->encap_list_lock);
+
+	mutex_unlock(&rpriv->neigh_update.encap_lock);
+
+	return 0;
+}
+
+void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
+				  struct mlx5e_encap_entry *e)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
+
+	if (!e->nhe)
+		return;
+
+	spin_lock(&e->nhe->encap_list_lock);
+	list_del_rcu(&e->encap_list);
+	spin_unlock(&e->nhe->encap_list_lock);
+
+	mlx5e_rep_neigh_entry_release(e->nhe);
+	e->nhe = NULL;
+	mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type);
+}
+
+void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
+			    struct mlx5e_encap_entry *e,
+			    bool neigh_connected,
+			    unsigned char ha[ETH_ALEN])
+{
+	struct ethhdr *eth = (struct ethhdr *)e->encap_header;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	bool encap_connected;
+	LIST_HEAD(flow_list);
+
+	ASSERT_RTNL();
+
+	/* wait for encap to be fully initialized */
+	wait_for_completion(&e->res_ready);
+
+	mutex_lock(&esw->offloads.encap_tbl_lock);
+	encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
+	if (e->compl_result < 0 || (encap_connected == neigh_connected &&
+				    ether_addr_equal(e->h_dest, ha)))
+		goto unlock;
+
+	mlx5e_take_all_encap_flows(e, &flow_list);
+
+	if ((e->flags & MLX5_ENCAP_ENTRY_VALID) &&
+	    (!neigh_connected || !ether_addr_equal(e->h_dest, ha)))
+		mlx5e_tc_encap_flows_del(priv, e, &flow_list);
+
+	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+		ether_addr_copy(e->h_dest, ha);
+		ether_addr_copy(eth->h_dest, ha);
+		/* Update the encap source mac, in case that we delete
+		 * the flows when encap source mac changed.
+		 */
+		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
+
+		mlx5e_tc_encap_flows_add(priv, e, &flow_list);
+	}
+unlock:
+	mutex_unlock(&esw->offloads.encap_tbl_lock);
+	mlx5e_put_encap_flow_list(priv, &flow_list);
+}
+
+static int
+mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
+			      struct flow_cls_offload *cls_flower, int flags)
+{
+	switch (cls_flower->command) {
+	case FLOW_CLS_REPLACE:
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
+	case FLOW_CLS_DESTROY:
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
+	case FLOW_CLS_STATS:
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static
+int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
+				    struct tc_cls_matchall_offload *ma)
+{
+	switch (ma->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return mlx5e_tc_configure_matchall(priv, ma);
+	case TC_CLSMATCHALL_DESTROY:
+		return mlx5e_tc_delete_matchall(priv, ma);
+	case TC_CLSMATCHALL_STATS:
+		mlx5e_tc_stats_matchall(priv, ma);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv)
+{
+	unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD);
+	struct mlx5e_priv *priv = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags);
+	case TC_SETUP_CLSMATCHALL:
+		return mlx5e_rep_setup_tc_cls_matchall(priv, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv)
+{
+	struct flow_cls_offload tmp, *f = type_data;
+	struct mlx5e_priv *priv = cb_priv;
+	struct mlx5_eswitch *esw;
+	unsigned long flags;
+	int err;
+
+	flags = MLX5_TC_FLAG(INGRESS) |
+		MLX5_TC_FLAG(ESW_OFFLOAD) |
+		MLX5_TC_FLAG(FT_OFFLOAD);
+	esw = priv->mdev->priv.eswitch;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		memcpy(&tmp, f, sizeof(*f));
+
+		if (!mlx5_esw_chains_prios_supported(esw))
+			return -EOPNOTSUPP;
+
+		/* Re-use tc offload path by moving the ft flow to the
+		 * reserved ft chain.
+		 *
+		 * FT offload can use prio range [0, INT_MAX], so we normalize
+		 * it to range [1, mlx5_esw_chains_get_prio_range(esw)]
+		 * as with tc, where prio 0 isn't supported.
+		 *
+		 * We only support chain 0 of FT offload.
+		 */
+		if (tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw))
+			return -EOPNOTSUPP;
+		if (tmp.common.chain_index != 0)
+			return -EOPNOTSUPP;
+
+		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.prio++;
+		err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags);
+		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
+		return err;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static LIST_HEAD(mlx5e_rep_block_tc_cb_list);
+static LIST_HEAD(mlx5e_rep_block_ft_cb_list);
+int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		       void *type_data)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct flow_block_offload *f = type_data;
+
+	f->unlocked_driver_cb = true;
+
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_rep_block_tc_cb_list,
+						  mlx5e_rep_setup_tc_cb,
+						  priv, priv, true);
+	case TC_SETUP_FT:
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_rep_block_ft_cb_list,
+						  mlx5e_rep_setup_ft_cb,
+						  priv, priv, true);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	int err;
+
+	mutex_init(&uplink_priv->unready_flows_lock);
+	INIT_LIST_HEAD(&uplink_priv->unready_flows);
+
+	/* init shared tc flow table */
+	err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+	return err;
+}
+
+void mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv)
+{
+	/* delete shared tc flow table */
+	mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
+	mutex_destroy(&rpriv->uplink_priv.unready_flows_lock);
+}
+
+void mlx5e_rep_tc_enable(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
+		  mlx5e_tc_reoffload_flows_work);
+}
+
+void mlx5e_rep_tc_disable(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
+}
+
+int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work);
+
+	return NOTIFY_OK;
+}
+
+static struct mlx5e_rep_indr_block_priv *
+mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
+				 struct net_device *netdev)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv;
+
+	/* All callback list access should be protected by RTNL. */
+	ASSERT_RTNL();
+
+	list_for_each_entry(cb_priv,
+			    &rpriv->uplink_priv.tc_indr_block_priv_list,
+			    list)
+		if (cb_priv->netdev == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
+					    struct net_device *netdev);
+
+void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv, *temp;
+	struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list;
+
+	list_for_each_entry_safe(cb_priv, temp, head, list) {
+		mlx5e_rep_indr_unregister_block(rpriv, cb_priv->netdev);
+		kfree(cb_priv);
+	}
+}
+
+static int
+mlx5e_rep_indr_offload(struct net_device *netdev,
+		       struct flow_cls_offload *flower,
+		       struct mlx5e_rep_indr_block_priv *indr_priv,
+		       unsigned long flags)
+{
+	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
+	int err = 0;
+
+	switch (flower->command) {
+	case FLOW_CLS_REPLACE:
+		err = mlx5e_configure_flower(netdev, priv, flower, flags);
+		break;
+	case FLOW_CLS_DESTROY:
+		err = mlx5e_delete_flower(netdev, priv, flower, flags);
+		break;
+	case FLOW_CLS_STATS:
+		err = mlx5e_stats_flower(netdev, priv, flower, flags);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int mlx5e_rep_indr_setup_tc_cb(enum tc_setup_type type,
+				      void *type_data, void *indr_priv)
+{
+	unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD);
+	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_indr_offload(priv->netdev, type_data, priv,
+					      flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_indr_setup_ft_cb(enum tc_setup_type type,
+				      void *type_data, void *indr_priv)
+{
+	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
+	struct flow_cls_offload *f = type_data;
+	struct flow_cls_offload tmp;
+	struct mlx5e_priv *mpriv;
+	struct mlx5_eswitch *esw;
+	unsigned long flags;
+	int err;
+
+	mpriv = netdev_priv(priv->rpriv->netdev);
+	esw = mpriv->mdev->priv.eswitch;
+
+	flags = MLX5_TC_FLAG(EGRESS) |
+		MLX5_TC_FLAG(ESW_OFFLOAD) |
+		MLX5_TC_FLAG(FT_OFFLOAD);
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		memcpy(&tmp, f, sizeof(*f));
+
+		/* Re-use tc offload path by moving the ft flow to the
+		 * reserved ft chain.
+		 *
+		 * FT offload can use prio range [0, INT_MAX], so we normalize
+		 * it to range [1, mlx5_esw_chains_get_prio_range(esw)]
+		 * as with tc, where prio 0 isn't supported.
+		 *
+		 * We only support chain 0 of FT offload.
+		 */
+		if (!mlx5_esw_chains_prios_supported(esw) ||
+		    tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw) ||
+		    tmp.common.chain_index)
+			return -EOPNOTSUPP;
+
+		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.prio++;
+		err = mlx5e_rep_indr_offload(priv->netdev, &tmp, priv, flags);
+		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
+		return err;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void mlx5e_rep_indr_block_unbind(void *cb_priv)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv = cb_priv;
+
+	list_del(&indr_priv->list);
+	kfree(indr_priv);
+}
+
+static LIST_HEAD(mlx5e_block_cb_list);
+
+static int
+mlx5e_rep_indr_setup_block(struct net_device *netdev,
+			   struct mlx5e_rep_priv *rpriv,
+			   struct flow_block_offload *f,
+			   flow_setup_cb_t *setup_cb)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv;
+	struct flow_block_cb *block_cb;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->unlocked_driver_cb = true;
+	f->driver_block_list = &mlx5e_block_cb_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (indr_priv)
+			return -EEXIST;
+
+		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
+		if (!indr_priv)
+			return -ENOMEM;
+
+		indr_priv->netdev = netdev;
+		indr_priv->rpriv = rpriv;
+		list_add(&indr_priv->list,
+			 &rpriv->uplink_priv.tc_indr_block_priv_list);
+
+		block_cb = flow_block_cb_alloc(setup_cb, indr_priv, indr_priv,
+					       mlx5e_rep_indr_block_unbind);
+		if (IS_ERR(block_cb)) {
+			list_del(&indr_priv->list);
+			kfree(indr_priv);
+			return PTR_ERR(block_cb);
+		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlx5e_block_cb_list);
+
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (!indr_priv)
+			return -ENOENT;
+
+		block_cb = flow_block_cb_lookup(f->block, setup_cb, indr_priv);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static
+int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv,
+			    enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
+						  mlx5e_rep_indr_setup_tc_cb);
+	case TC_SETUP_FT:
+		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
+						  mlx5e_rep_indr_setup_ft_cb);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
+					 struct net_device *netdev)
+{
+	int err;
+
+	err = __flow_indr_block_cb_register(netdev, rpriv,
+					    mlx5e_rep_indr_setup_cb,
+					    rpriv);
+	if (err) {
+		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+		mlx5_core_err(priv->mdev, "Failed to register remote block notifier for %s err=%d\n",
+			      netdev_name(netdev), err);
+	}
+	return err;
+}
+
+static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
+					    struct net_device *netdev)
+{
+	__flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_cb,
+					rpriv);
+}
+
+static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
+						     uplink_priv.netdevice_nb);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
+	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev))
+		return NOTIFY_OK;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		mlx5e_rep_indr_register_block(rpriv, netdev);
+		break;
+	case NETDEV_UNREGISTER:
+		mlx5e_rep_indr_unregister_block(rpriv, netdev);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	int err;
+
+	/* init indirect block notifications */
+	INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
+
+	uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
+	err = register_netdevice_notifier_dev_net(rpriv->netdev,
+						  &uplink_priv->netdevice_nb,
+						  &uplink_priv->netdevice_nn);
+	return err;
+}
+
+void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+
+	/* clean indirect TC block notifications */
+	unregister_netdevice_notifier_dev_net(rpriv->netdev,
+					      &uplink_priv->netdevice_nb,
+					      &uplink_priv->netdevice_nn);
+}
+
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
+				 struct mlx5e_tc_update_priv *tc_priv,
+				 u32 tunnel_id)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct tunnel_match_enc_opts enc_opts = {};
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct metadata_dst *tun_dst;
+	struct tunnel_match_key key;
+	u32 tun_id, enc_opts_id;
+	struct net_device *dev;
+	int err;
+
+	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
+	tun_id = tunnel_id >> ENC_OPTS_BITS;
+
+	if (!tun_id)
+		return true;
+
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &uplink_rpriv->uplink_priv;
+
+	err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key);
+	if (err) {
+		WARN_ON_ONCE(true);
+		netdev_dbg(priv->netdev,
+			   "Couldn't find tunnel for tun_id: %d, err: %d\n",
+			   tun_id, err);
+		return false;
+	}
+
+	if (enc_opts_id) {
+		err = mapping_find(uplink_priv->tunnel_enc_opts_mapping,
+				   enc_opts_id, &enc_opts);
+		if (err) {
+			netdev_dbg(priv->netdev,
+				   "Couldn't find tunnel (opts) for tun_id: %d, err: %d\n",
+				   enc_opts_id, err);
+			return false;
+		}
+	}
+
+	tun_dst = tun_rx_dst(enc_opts.key.len);
+	if (!tun_dst) {
+		WARN_ON_ONCE(true);
+		return false;
+	}
+
+	ip_tunnel_key_init(&tun_dst->u.tun_info.key,
+			   key.enc_ipv4.src, key.enc_ipv4.dst,
+			   key.enc_ip.tos, key.enc_ip.ttl,
+			   0, /* label */
+			   key.enc_tp.src, key.enc_tp.dst,
+			   key32_to_tunnel_id(key.enc_key_id.keyid),
+			   TUNNEL_KEY);
+
+	if (enc_opts.key.len)
+		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
+					enc_opts.key.data,
+					enc_opts.key.len,
+					enc_opts.key.dst_opt_type);
+
+	skb_dst_set(skb, (struct dst_entry *)tun_dst);
+	dev = dev_get_by_index(&init_net, key.filter_ifindex);
+	if (!dev) {
+		netdev_dbg(priv->netdev,
+			   "Couldn't find tunnel device with ifindex: %d\n",
+			   key.filter_ifindex);
+		return false;
+	}
+
+	/* Set tun_dev so we do dev_put() after datapath */
+	tc_priv->tun_dev = dev;
+
+	skb->dev = dev;
+
+	return true;
+}
+#endif /* CONFIG_NET_TC_SKB_EXT */
+
+bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
+			     struct sk_buff *skb,
+			     struct mlx5e_tc_update_priv *tc_priv)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	u32 chain = 0, reg_c0, reg_c1, tunnel_id, tuple_id;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct tc_skb_ext *tc_skb_ext;
+	struct mlx5_eswitch *esw;
+	struct mlx5e_priv *priv;
+	int tunnel_moffset;
+	int err;
+
+	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
+	if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
+		reg_c0 = 0;
+	reg_c1 = be32_to_cpu(cqe->ft_metadata);
+
+	if (!reg_c0)
+		return true;
+
+	priv = netdev_priv(skb->dev);
+	esw = priv->mdev->priv.eswitch;
+
+	err = mlx5_eswitch_get_chain_for_tag(esw, reg_c0, &chain);
+	if (err) {
+		netdev_dbg(priv->netdev,
+			   "Couldn't find chain for chain tag: %d, err: %d\n",
+			   reg_c0, err);
+		return false;
+	}
+
+	if (chain) {
+		tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+		if (!tc_skb_ext) {
+			WARN_ON(1);
+			return false;
+		}
+
+		tc_skb_ext->chain = chain;
+
+		tuple_id = reg_c1 & TUPLE_ID_MAX;
+
+		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+		uplink_priv = &uplink_rpriv->uplink_priv;
+		if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb, tuple_id))
+			return false;
+	}
+
+	tunnel_moffset = mlx5e_tc_attr_to_reg_mappings[TUNNEL_TO_REG].moffset;
+	tunnel_id = reg_c1 >> (8 * tunnel_moffset);
+	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
+#endif /* CONFIG_NET_TC_SKB_EXT */
+
+	return true;
+}
+
+void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv)
+{
+	if (tc_priv->tun_dev)
+		dev_put(tc_priv->tun_dev);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
new file mode 100644
index 000000000000..90da00626b97
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_REP_TC_H__
+#define __MLX5_EN_REP_TC_H__
+
+#include <linux/skbuff.h>
+#include "en.h"
+#include "en_tc.h"
+#include "en_rep.h"
+
+struct mlx5e_rep_priv;
+int mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv);
+void mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv);
+
+int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv);
+void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv);
+
+void mlx5e_rep_tc_enable(struct mlx5e_priv *priv);
+void mlx5e_rep_tc_disable(struct mlx5e_priv *priv);
+
+int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv);
+
+struct mlx5e_encap_entry;
+void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
+			    struct mlx5e_encap_entry *e,
+			    bool neigh_connected,
+			    unsigned char ha[ETH_ALEN]);
+
+int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e);
+void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
+				  struct mlx5e_encap_entry *e);
+
+int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		       void *type_data);
+void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv);
+
+struct mlx5e_tc_update_priv;
+bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
+			     struct sk_buff *skb,
+			     struct mlx5e_tc_update_priv *tc_priv);
+void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv);
+
+#endif /* __MLX5_EN_REP_TC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 9f50a1d3c5cc..9fdd79afa6e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -6,6 +6,7 @@
 #include <net/geneve.h>
 #include "en/tc_tun.h"
 #include "en_tc.h"
+#include "rep/tc.h"
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 52351c105627..c84f0d9b516e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -45,9 +45,8 @@
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
-#include "en/tc_tun.h"
+#include "en/rep/tc.h"
 #include "fs_core.h"
-#include "lib/port_tun.h"
 #include "lib/mlx5.h"
 #define CREATE_TRACE_POINTS
 #include "diag/en_rep_tracepoint.h"
@@ -58,16 +57,6 @@
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
-struct mlx5e_rep_indr_block_priv {
-	struct net_device *netdev;
-	struct mlx5e_rep_priv *rpriv;
-
-	struct list_head list;
-};
-
-static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
-					    struct net_device *netdev);
-
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
@@ -521,7 +510,7 @@ static bool mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
 
 static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe);
 
-static void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
+void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
 {
 	if (refcount_dec_and_test(&nhe->refcnt)) {
 		mlx5e_rep_neigh_entry_remove(nhe);
@@ -579,48 +568,6 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
-static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
-				   struct mlx5e_encap_entry *e,
-				   bool neigh_connected,
-				   unsigned char ha[ETH_ALEN])
-{
-	struct ethhdr *eth = (struct ethhdr *)e->encap_header;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	bool encap_connected;
-	LIST_HEAD(flow_list);
-
-	ASSERT_RTNL();
-
-	/* wait for encap to be fully initialized */
-	wait_for_completion(&e->res_ready);
-
-	mutex_lock(&esw->offloads.encap_tbl_lock);
-	encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
-	if (e->compl_result < 0 || (encap_connected == neigh_connected &&
-				    ether_addr_equal(e->h_dest, ha)))
-		goto unlock;
-
-	mlx5e_take_all_encap_flows(e, &flow_list);
-
-	if ((e->flags & MLX5_ENCAP_ENTRY_VALID) &&
-	    (!neigh_connected || !ether_addr_equal(e->h_dest, ha)))
-		mlx5e_tc_encap_flows_del(priv, e, &flow_list);
-
-	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
-		ether_addr_copy(e->h_dest, ha);
-		ether_addr_copy(eth->h_dest, ha);
-		/* Update the encap source mac, in case that we delete
-		 * the flows when encap source mac changed.
-		 */
-		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
-
-		mlx5e_tc_encap_flows_add(priv, e, &flow_list);
-	}
-unlock:
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
-	mlx5e_put_encap_flow_list(priv, &flow_list);
-}
-
 static void mlx5e_rep_neigh_update(struct work_struct *work)
 {
 	struct mlx5e_neigh_hash_entry *nhe =
@@ -662,254 +609,6 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
 	neigh_release(n);
 }
 
-static struct mlx5e_rep_indr_block_priv *
-mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
-				 struct net_device *netdev)
-{
-	struct mlx5e_rep_indr_block_priv *cb_priv;
-
-	/* All callback list access should be protected by RTNL. */
-	ASSERT_RTNL();
-
-	list_for_each_entry(cb_priv,
-			    &rpriv->uplink_priv.tc_indr_block_priv_list,
-			    list)
-		if (cb_priv->netdev == netdev)
-			return cb_priv;
-
-	return NULL;
-}
-
-static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
-{
-	struct mlx5e_rep_indr_block_priv *cb_priv, *temp;
-	struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list;
-
-	list_for_each_entry_safe(cb_priv, temp, head, list) {
-		mlx5e_rep_indr_unregister_block(rpriv, cb_priv->netdev);
-		kfree(cb_priv);
-	}
-}
-
-static int
-mlx5e_rep_indr_offload(struct net_device *netdev,
-		       struct flow_cls_offload *flower,
-		       struct mlx5e_rep_indr_block_priv *indr_priv,
-		       unsigned long flags)
-{
-	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
-	int err = 0;
-
-	switch (flower->command) {
-	case FLOW_CLS_REPLACE:
-		err = mlx5e_configure_flower(netdev, priv, flower, flags);
-		break;
-	case FLOW_CLS_DESTROY:
-		err = mlx5e_delete_flower(netdev, priv, flower, flags);
-		break;
-	case FLOW_CLS_STATS:
-		err = mlx5e_stats_flower(netdev, priv, flower, flags);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-	}
-
-	return err;
-}
-
-static int mlx5e_rep_indr_setup_tc_cb(enum tc_setup_type type,
-				      void *type_data, void *indr_priv)
-{
-	unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD);
-	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_indr_offload(priv->netdev, type_data, priv,
-					      flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_rep_indr_setup_ft_cb(enum tc_setup_type type,
-				      void *type_data, void *indr_priv)
-{
-	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
-	struct flow_cls_offload *f = type_data;
-	struct flow_cls_offload tmp;
-	struct mlx5e_priv *mpriv;
-	struct mlx5_eswitch *esw;
-	unsigned long flags;
-	int err;
-
-	mpriv = netdev_priv(priv->rpriv->netdev);
-	esw = mpriv->mdev->priv.eswitch;
-
-	flags = MLX5_TC_FLAG(EGRESS) |
-		MLX5_TC_FLAG(ESW_OFFLOAD) |
-		MLX5_TC_FLAG(FT_OFFLOAD);
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		memcpy(&tmp, f, sizeof(*f));
-
-		/* Re-use tc offload path by moving the ft flow to the
-		 * reserved ft chain.
-		 *
-		 * FT offload can use prio range [0, INT_MAX], so we normalize
-		 * it to range [1, mlx5_esw_chains_get_prio_range(esw)]
-		 * as with tc, where prio 0 isn't supported.
-		 *
-		 * We only support chain 0 of FT offload.
-		 */
-		if (!mlx5_esw_chains_prios_supported(esw) ||
-		    tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw) ||
-		    tmp.common.chain_index)
-			return -EOPNOTSUPP;
-
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
-		tmp.common.prio++;
-		err = mlx5e_rep_indr_offload(priv->netdev, &tmp, priv, flags);
-		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
-		return err;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void mlx5e_rep_indr_block_unbind(void *cb_priv)
-{
-	struct mlx5e_rep_indr_block_priv *indr_priv = cb_priv;
-
-	list_del(&indr_priv->list);
-	kfree(indr_priv);
-}
-
-static LIST_HEAD(mlx5e_block_cb_list);
-
-static int
-mlx5e_rep_indr_setup_block(struct net_device *netdev,
-			   struct mlx5e_rep_priv *rpriv,
-			   struct flow_block_offload *f,
-			   flow_setup_cb_t *setup_cb)
-{
-	struct mlx5e_rep_indr_block_priv *indr_priv;
-	struct flow_block_cb *block_cb;
-
-	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	f->unlocked_driver_cb = true;
-	f->driver_block_list = &mlx5e_block_cb_list;
-
-	switch (f->command) {
-	case FLOW_BLOCK_BIND:
-		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
-		if (indr_priv)
-			return -EEXIST;
-
-		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
-		if (!indr_priv)
-			return -ENOMEM;
-
-		indr_priv->netdev = netdev;
-		indr_priv->rpriv = rpriv;
-		list_add(&indr_priv->list,
-			 &rpriv->uplink_priv.tc_indr_block_priv_list);
-
-		block_cb = flow_block_cb_alloc(setup_cb, indr_priv, indr_priv,
-					       mlx5e_rep_indr_block_unbind);
-		if (IS_ERR(block_cb)) {
-			list_del(&indr_priv->list);
-			kfree(indr_priv);
-			return PTR_ERR(block_cb);
-		}
-		flow_block_cb_add(block_cb, f);
-		list_add_tail(&block_cb->driver_list, &mlx5e_block_cb_list);
-
-		return 0;
-	case FLOW_BLOCK_UNBIND:
-		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
-		if (!indr_priv)
-			return -ENOENT;
-
-		block_cb = flow_block_cb_lookup(f->block, setup_cb, indr_priv);
-		if (!block_cb)
-			return -ENOENT;
-
-		flow_block_cb_remove(block_cb, f);
-		list_del(&block_cb->driver_list);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static
-int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv,
-			    enum tc_setup_type type, void *type_data)
-{
-	switch (type) {
-	case TC_SETUP_BLOCK:
-		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
-						  mlx5e_rep_indr_setup_tc_cb);
-	case TC_SETUP_FT:
-		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
-						  mlx5e_rep_indr_setup_ft_cb);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
-					 struct net_device *netdev)
-{
-	int err;
-
-	err = __flow_indr_block_cb_register(netdev, rpriv,
-					    mlx5e_rep_indr_setup_cb,
-					    rpriv);
-	if (err) {
-		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-
-		mlx5_core_err(priv->mdev, "Failed to register remote block notifier for %s err=%d\n",
-			      netdev_name(netdev), err);
-	}
-	return err;
-}
-
-static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
-					    struct net_device *netdev)
-{
-	__flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_cb,
-					rpriv);
-}
-
-static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
-					 unsigned long event, void *ptr)
-{
-	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
-						     uplink_priv.netdevice_nb);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-
-	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
-	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev))
-		return NOTIFY_OK;
-
-	switch (event) {
-	case NETDEV_REGISTER:
-		mlx5e_rep_indr_register_block(rpriv, netdev);
-		break;
-	case NETDEV_UNREGISTER:
-		mlx5e_rep_indr_unregister_block(rpriv, netdev);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 static void
 mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
 				  struct mlx5e_neigh_hash_entry *nhe,
@@ -932,10 +631,6 @@ mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
 	}
 }
 
-static struct mlx5e_neigh_hash_entry *
-mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
-			     struct mlx5e_neigh *m_neigh);
-
 static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
@@ -1091,7 +786,7 @@ static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe)
 /* This function must only be called under the representor's encap_lock or
  * inside rcu read lock section.
  */
-static struct mlx5e_neigh_hash_entry *
+struct mlx5e_neigh_hash_entry *
 mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
 			     struct mlx5e_neigh *m_neigh)
 {
@@ -1104,9 +799,9 @@ mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
 	return nhe && mlx5e_rep_neigh_entry_hold(nhe) ? nhe : NULL;
 }
 
-static int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
-					struct mlx5e_encap_entry *e,
-					struct mlx5e_neigh_hash_entry **nhe)
+int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct mlx5e_neigh_hash_entry **nhe)
 {
 	int err;
 
@@ -1131,60 +826,6 @@ out_free:
 	return err;
 }
 
-int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
-				 struct mlx5e_encap_entry *e)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
-	struct mlx5e_neigh_hash_entry *nhe;
-	int err;
-
-	err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type);
-	if (err)
-		return err;
-
-	mutex_lock(&rpriv->neigh_update.encap_lock);
-	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
-	if (!nhe) {
-		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
-		if (err) {
-			mutex_unlock(&rpriv->neigh_update.encap_lock);
-			mlx5_tun_entropy_refcount_dec(tun_entropy,
-						      e->reformat_type);
-			return err;
-		}
-	}
-
-	e->nhe = nhe;
-	spin_lock(&nhe->encap_list_lock);
-	list_add_rcu(&e->encap_list, &nhe->encap_list);
-	spin_unlock(&nhe->encap_list_lock);
-
-	mutex_unlock(&rpriv->neigh_update.encap_lock);
-
-	return 0;
-}
-
-void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
-				  struct mlx5e_encap_entry *e)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
-
-	if (!e->nhe)
-		return;
-
-	spin_lock(&e->nhe->encap_list_lock);
-	list_del_rcu(&e->encap_list);
-	spin_unlock(&e->nhe->encap_list_lock);
-
-	mlx5e_rep_neigh_entry_release(e->nhe);
-	e->nhe = NULL;
-	mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type);
-}
-
 static int mlx5e_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
@@ -1225,129 +866,6 @@ static int mlx5e_rep_close(struct net_device *dev)
 	return ret;
 }
 
-static int
-mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
-			      struct flow_cls_offload *cls_flower, int flags)
-{
-	switch (cls_flower->command) {
-	case FLOW_CLS_REPLACE:
-		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
-					      flags);
-	case FLOW_CLS_DESTROY:
-		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
-					   flags);
-	case FLOW_CLS_STATS:
-		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
-					  flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static
-int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
-				    struct tc_cls_matchall_offload *ma)
-{
-	switch (ma->command) {
-	case TC_CLSMATCHALL_REPLACE:
-		return mlx5e_tc_configure_matchall(priv, ma);
-	case TC_CLSMATCHALL_DESTROY:
-		return mlx5e_tc_delete_matchall(priv, ma);
-	case TC_CLSMATCHALL_STATS:
-		mlx5e_tc_stats_matchall(priv, ma);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
-				 void *cb_priv)
-{
-	unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD);
-	struct mlx5e_priv *priv = cb_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags);
-	case TC_SETUP_CLSMATCHALL:
-		return mlx5e_rep_setup_tc_cls_matchall(priv, type_data);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
-				 void *cb_priv)
-{
-	struct flow_cls_offload tmp, *f = type_data;
-	struct mlx5e_priv *priv = cb_priv;
-	struct mlx5_eswitch *esw;
-	unsigned long flags;
-	int err;
-
-	flags = MLX5_TC_FLAG(INGRESS) |
-		MLX5_TC_FLAG(ESW_OFFLOAD) |
-		MLX5_TC_FLAG(FT_OFFLOAD);
-	esw = priv->mdev->priv.eswitch;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		memcpy(&tmp, f, sizeof(*f));
-
-		if (!mlx5_esw_chains_prios_supported(esw))
-			return -EOPNOTSUPP;
-
-		/* Re-use tc offload path by moving the ft flow to the
-		 * reserved ft chain.
-		 *
-		 * FT offload can use prio range [0, INT_MAX], so we normalize
-		 * it to range [1, mlx5_esw_chains_get_prio_range(esw)]
-		 * as with tc, where prio 0 isn't supported.
-		 *
-		 * We only support chain 0 of FT offload.
-		 */
-		if (tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw))
-			return -EOPNOTSUPP;
-		if (tmp.common.chain_index != 0)
-			return -EOPNOTSUPP;
-
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
-		tmp.common.prio++;
-		err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags);
-		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
-		return err;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static LIST_HEAD(mlx5e_rep_block_tc_cb_list);
-static LIST_HEAD(mlx5e_rep_block_ft_cb_list);
-static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
-			      void *type_data)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct flow_block_offload *f = type_data;
-
-	f->unlocked_driver_cb = true;
-
-	switch (type) {
-	case TC_SETUP_BLOCK:
-		return flow_block_cb_setup_simple(type_data,
-						  &mlx5e_rep_block_tc_cb_list,
-						  mlx5e_rep_setup_tc_cb,
-						  priv, priv, true);
-	case TC_SETUP_FT:
-		return flow_block_cb_setup_simple(type_data,
-						  &mlx5e_rep_block_ft_cb_list,
-						  mlx5e_rep_setup_ft_cb,
-						  priv, priv, true);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1791,31 +1309,23 @@ static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
 	priv = netdev_priv(netdev);
 	uplink_priv = &rpriv->uplink_priv;
 
-	mutex_init(&uplink_priv->unready_flows_lock);
-	INIT_LIST_HEAD(&uplink_priv->unready_flows);
-
-	/* init shared tc flow table */
-	err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+	err = mlx5e_rep_tc_init(rpriv);
 	if (err)
 		return err;
 
 	mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
 
-	/* init indirect block notifications */
-	INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
-	uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
-	err = register_netdevice_notifier_dev_net(rpriv->netdev,
-						  &uplink_priv->netdevice_nb,
-						  &uplink_priv->netdevice_nn);
+	err = mlx5e_rep_tc_netdevice_event_register(rpriv);
 	if (err) {
-		mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
-		goto tc_esw_cleanup;
+		mlx5_core_err(priv->mdev, "Failed to register netdev notifier, err: %d\n",
+			      err);
+		goto tc_rep_cleanup;
 	}
 
 	return 0;
 
-tc_esw_cleanup:
-	mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
+tc_rep_cleanup:
+	mlx5e_rep_tc_cleanup(rpriv);
 	return err;
 }
 
@@ -1845,17 +1355,10 @@ destroy_tises:
 
 static void mlx5e_cleanup_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
 {
-	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-
-	/* clean indirect TC block notifications */
-	unregister_netdevice_notifier_dev_net(rpriv->netdev,
-					      &uplink_priv->netdevice_nb,
-					      &uplink_priv->netdevice_nn);
+	mlx5e_rep_tc_netdevice_event_unregister(rpriv);
 	mlx5e_rep_indr_clean_block_privs(rpriv);
 
-	/* delete shared tc flow table */
-	mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
-	mutex_destroy(&rpriv->uplink_priv.unready_flows_lock);
+	mlx5e_rep_tc_cleanup(rpriv);
 }
 
 static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
@@ -1897,13 +1400,8 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event
 		return NOTIFY_OK;
 	}
 
-	if (event == MLX5_DEV_EVENT_PORT_AFFINITY) {
-		struct mlx5e_rep_priv *rpriv = priv->ppriv;
-
-		queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work);
-
-		return NOTIFY_OK;
-	}
+	if (event == MLX5_DEV_EVENT_PORT_AFFINITY)
+		return mlx5e_rep_tc_event_port_affinity(priv);
 
 	return NOTIFY_DONE;
 }
@@ -1912,7 +1410,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	u16 max_mtu;
 
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -1920,8 +1417,7 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 	mlx5e_set_dev_port_mtu(priv);
 
-	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
-		  mlx5e_tc_reoffload_flows_work);
+	mlx5e_rep_tc_enable(priv);
 
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
@@ -1933,11 +1429,10 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
 	mlx5e_dcbnl_delete_app(priv);
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
-	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
+	mlx5e_rep_tc_disable(priv);
 	mlx5_lag_remove(mdev);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 6a2337900420..74d46e9a201a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -203,16 +203,19 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
 				   struct mlx5_cqe64 *cqe);
 
-int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
-				 struct mlx5e_encap_entry *e);
-void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
-				  struct mlx5e_encap_entry *e);
-
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 
 bool mlx5e_eswitch_rep(struct net_device *netdev);
 bool mlx5e_eswitch_uplink_rep(struct net_device *netdev);
 
+struct mlx5e_neigh_hash_entry *
+mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
+			     struct mlx5e_neigh *m_neigh);
+int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct mlx5e_neigh_hash_entry **nhe);
+void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a514685fb560..1b60aeebab48 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -42,6 +42,7 @@
 #include "en_tc.h"
 #include "eswitch.h"
 #include "en_rep.h"
+#include "en/rep/tc.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
@@ -1216,12 +1217,12 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	if (rep->vlan && skb_vlan_tag_present(skb))
 		skb_vlan_pop(skb);
 
-	if (!mlx5e_tc_rep_update_skb(cqe, skb, &tc_priv))
+	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))
 		goto free_wqe;
 
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5_tc_rep_post_napi_receive(&tc_priv);
+	mlx5_rep_tc_post_napi_receive(&tc_priv);
 
 free_wqe:
 	mlx5e_free_rx_wqe(rq, wi, true);
@@ -1272,12 +1273,12 @@ void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 
-	if (!mlx5e_tc_rep_update_skb(cqe, skb, &tc_priv))
+	if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))
 		goto mpwrq_cqe_out;
 
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5_tc_rep_post_napi_receive(&tc_priv);
+	mlx5_rep_tc_post_napi_receive(&tc_priv);
 
 mpwrq_cqe_out:
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a050808f2128..251975ccbdf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -49,6 +49,7 @@
 #include <net/ipv6_stubs.h>
 #include "en.h"
 #include "en_rep.h"
+#include "en/rep/tc.h"
 #include "en_tc.h"
 #include "eswitch.h"
 #include "esw/chains.h"
@@ -158,35 +159,6 @@ struct mlx5e_tc_flow_parse_attr {
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16)
 
-struct tunnel_match_key {
-	struct flow_dissector_key_control enc_control;
-	struct flow_dissector_key_keyid enc_key_id;
-	struct flow_dissector_key_ports enc_tp;
-	struct flow_dissector_key_ip enc_ip;
-	union {
-		struct flow_dissector_key_ipv4_addrs enc_ipv4;
-		struct flow_dissector_key_ipv6_addrs enc_ipv6;
-	};
-
-	int filter_ifindex;
-};
-
-struct tunnel_match_enc_opts {
-	struct flow_dissector_key_enc_opts key;
-	struct flow_dissector_key_enc_opts mask;
-};
-
-/* Tunnel_id mapping is TUNNEL_INFO_BITS + ENC_OPTS_BITS.
- * Upper TUNNEL_INFO_BITS for general tunnel info.
- * Lower ENC_OPTS_BITS bits for enc_opts.
- */
-#define TUNNEL_INFO_BITS 6
-#define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0)
-#define ENC_OPTS_BITS 2
-#define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0)
-#define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS)
-#define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0)
-
 struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[CHAIN_TO_REG] = {
 		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0,
@@ -4806,146 +4778,6 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
 	mutex_unlock(&rpriv->unready_flows_lock);
 }
 
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb,
-				 struct mlx5e_tc_update_priv *tc_priv,
-				 u32 tunnel_id)
-{
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct tunnel_match_enc_opts enc_opts = {};
-	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct metadata_dst *tun_dst;
-	struct tunnel_match_key key;
-	u32 tun_id, enc_opts_id;
-	struct net_device *dev;
-	int err;
-
-	enc_opts_id = tunnel_id & ENC_OPTS_BITS_MASK;
-	tun_id = tunnel_id >> ENC_OPTS_BITS;
-
-	if (!tun_id)
-		return true;
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	uplink_priv = &uplink_rpriv->uplink_priv;
-
-	err = mapping_find(uplink_priv->tunnel_mapping, tun_id, &key);
-	if (err) {
-		WARN_ON_ONCE(true);
-		netdev_dbg(priv->netdev,
-			   "Couldn't find tunnel for tun_id: %d, err: %d\n",
-			   tun_id, err);
-		return false;
-	}
-
-	if (enc_opts_id) {
-		err = mapping_find(uplink_priv->tunnel_enc_opts_mapping,
-				   enc_opts_id, &enc_opts);
-		if (err) {
-			netdev_dbg(priv->netdev,
-				   "Couldn't find tunnel (opts) for tun_id: %d, err: %d\n",
-				   enc_opts_id, err);
-			return false;
-		}
-	}
-
-	tun_dst = tun_rx_dst(enc_opts.key.len);
-	if (!tun_dst) {
-		WARN_ON_ONCE(true);
-		return false;
-	}
-
-	ip_tunnel_key_init(&tun_dst->u.tun_info.key,
-			   key.enc_ipv4.src, key.enc_ipv4.dst,
-			   key.enc_ip.tos, key.enc_ip.ttl,
-			   0, /* label */
-			   key.enc_tp.src, key.enc_tp.dst,
-			   key32_to_tunnel_id(key.enc_key_id.keyid),
-			   TUNNEL_KEY);
-
-	if (enc_opts.key.len)
-		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
-					enc_opts.key.data,
-					enc_opts.key.len,
-					enc_opts.key.dst_opt_type);
-
-	skb_dst_set(skb, (struct dst_entry *)tun_dst);
-	dev = dev_get_by_index(&init_net, key.filter_ifindex);
-	if (!dev) {
-		netdev_dbg(priv->netdev,
-			   "Couldn't find tunnel device with ifindex: %d\n",
-			   key.filter_ifindex);
-		return false;
-	}
-
-	/* Set tun_dev so we do dev_put() after datapath */
-	tc_priv->tun_dev = dev;
-
-	skb->dev = dev;
-
-	return true;
-}
-#endif /* CONFIG_NET_TC_SKB_EXT */
-
-bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe,
-			     struct sk_buff *skb,
-			     struct mlx5e_tc_update_priv *tc_priv)
-{
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-	u32 chain = 0, reg_c0, reg_c1, tunnel_id, tuple_id;
-	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct tc_skb_ext *tc_skb_ext;
-	struct mlx5_eswitch *esw;
-	struct mlx5e_priv *priv;
-	int tunnel_moffset;
-	int err;
-
-	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
-	if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
-		reg_c0 = 0;
-	reg_c1 = be32_to_cpu(cqe->ft_metadata);
-
-	if (!reg_c0)
-		return true;
-
-	priv = netdev_priv(skb->dev);
-	esw = priv->mdev->priv.eswitch;
-
-	err = mlx5_eswitch_get_chain_for_tag(esw, reg_c0, &chain);
-	if (err) {
-		netdev_dbg(priv->netdev,
-			   "Couldn't find chain for chain tag: %d, err: %d\n",
-			   reg_c0, err);
-		return false;
-	}
-
-	if (chain) {
-		tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
-		if (!tc_skb_ext) {
-			WARN_ON(1);
-			return false;
-		}
-
-		tc_skb_ext->chain = chain;
-
-		tuple_id = reg_c1 & TUPLE_ID_MAX;
-
-		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		uplink_priv = &uplink_rpriv->uplink_priv;
-		if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb, tuple_id))
-			return false;
-	}
-
-	tunnel_moffset = mlx5e_tc_attr_to_reg_mappings[TUNNEL_TO_REG].moffset;
-	tunnel_id = reg_c1 >> (8 * tunnel_moffset);
-	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
-#endif /* CONFIG_NET_TC_SKB_EXT */
-
-	return true;
-}
-
 void mlx5_tc_rep_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv)
 {
 	if (tc_priv->tun_dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index abdcfa4c4e0e..1d8d85b842fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -34,11 +34,41 @@
 #define __MLX5_EN_TC_H__
 
 #include <net/pkt_cls.h>
+#include "en.h"
 
 #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff
 
 #ifdef CONFIG_MLX5_ESWITCH
 
+struct tunnel_match_key {
+	struct flow_dissector_key_control enc_control;
+	struct flow_dissector_key_keyid enc_key_id;
+	struct flow_dissector_key_ports enc_tp;
+	struct flow_dissector_key_ip enc_ip;
+	union {
+		struct flow_dissector_key_ipv4_addrs enc_ipv4;
+		struct flow_dissector_key_ipv6_addrs enc_ipv6;
+	};
+
+	int filter_ifindex;
+};
+
+struct tunnel_match_enc_opts {
+	struct flow_dissector_key_enc_opts key;
+	struct flow_dissector_key_enc_opts mask;
+};
+
+/* Tunnel_id mapping is TUNNEL_INFO_BITS + ENC_OPTS_BITS.
+ * Upper TUNNEL_INFO_BITS for general tunnel info.
+ * Lower ENC_OPTS_BITS bits for enc_opts.
+ */
+#define TUNNEL_INFO_BITS 6
+#define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0)
+#define ENC_OPTS_BITS 2
+#define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0)
+#define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS)
+#define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0)
+
 enum {
 	MLX5E_TC_FLAG_INGRESS_BIT,
 	MLX5E_TC_FLAG_EGRESS_BIT,
@@ -119,11 +149,6 @@ struct mlx5e_tc_update_priv {
 	struct net_device *tun_dev;
 };
 
-bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb,
-			     struct mlx5e_tc_update_priv *tc_priv);
-
-void mlx5_tc_rep_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv);
-
 struct mlx5e_tc_mod_hdr_acts {
 	int num_actions;
 	int max_actions;
-- 
cgit v1.2.3


From 549c243e4e010067a075e248f4d72e8dda844e12 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 12 May 2020 17:29:22 +0300
Subject: net/mlx5e: Extract neigh-specific code from en_rep.c to rep/neigh.c

As a preparation for introducing new kconfig option that controls
compilation of all TC offloads code in mlx5, extract neigh-specific code
from en_rep.c to standalone file. This allows easily compiling out the code
by only including new source in make file when corresponding kconfig is
enabled instead of adding multiple ifdef blocks to en_rep.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/rep/neigh.c | 368 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/rep/neigh.h |  23 ++
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c    |   1 +
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   | 354 +-------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |   8 -
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |   6 -
 8 files changed, 395 insertions(+), 368 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index c21453970dbb..3c9d78e6695c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -33,7 +33,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/rep/tc.o en/tc_tun.o lib/port_tun.o \
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/rep/tc.o en/rep/neigh.o en/tc_tun.o lib/port_tun.o \
 					lag_mp.o \
 					lib/geneve.o en/mapping.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
 					en/tc_tun_geneve.o diag/en_tc_tracepoint.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
new file mode 100644
index 000000000000..baa162432e75
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rtnetlink.h>
+#include <linux/workqueue.h>
+#include <linux/rwlock.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <net/netevent.h>
+#include "neigh.h"
+#include "tc.h"
+#include "en_rep.h"
+#include "fs_core.h"
+#include "diag/en_rep_tracepoint.h"
+
+static unsigned long mlx5e_rep_ipv6_interval(void)
+{
+	if (IS_ENABLED(CONFIG_IPV6) && ipv6_stub->nd_tbl)
+		return NEIGH_VAR(&ipv6_stub->nd_tbl->parms, DELAY_PROBE_TIME);
+
+	return ~0UL;
+}
+
+static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
+{
+	unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME);
+	unsigned long ipv6_interval = mlx5e_rep_ipv6_interval();
+	struct net_device *netdev = rpriv->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
+	mlx5_fc_update_sampling_interval(priv->mdev, rpriv->neigh_update.min_interval);
+}
+
+void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+
+	mlx5_fc_queue_stats_work(priv->mdev,
+				 &neigh_update->neigh_stats_work,
+				 neigh_update->min_interval);
+}
+
+static bool mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
+{
+	return refcount_inc_not_zero(&nhe->refcnt);
+}
+
+static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe);
+
+void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
+{
+	if (refcount_dec_and_test(&nhe->refcnt)) {
+		mlx5e_rep_neigh_entry_remove(nhe);
+		kfree_rcu(nhe, rcu);
+	}
+}
+
+static struct mlx5e_neigh_hash_entry *
+mlx5e_get_next_nhe(struct mlx5e_rep_priv *rpriv,
+		   struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_neigh_hash_entry *next = NULL;
+
+	rcu_read_lock();
+
+	for (next = nhe ?
+		     list_next_or_null_rcu(&rpriv->neigh_update.neigh_list,
+					   &nhe->neigh_list,
+					   struct mlx5e_neigh_hash_entry,
+					   neigh_list) :
+		     list_first_or_null_rcu(&rpriv->neigh_update.neigh_list,
+					    struct mlx5e_neigh_hash_entry,
+					    neigh_list);
+	     next;
+	     next = list_next_or_null_rcu(&rpriv->neigh_update.neigh_list,
+					  &next->neigh_list,
+					  struct mlx5e_neigh_hash_entry,
+					  neigh_list))
+		if (mlx5e_rep_neigh_entry_hold(next))
+			break;
+
+	rcu_read_unlock();
+
+	if (nhe)
+		mlx5e_rep_neigh_entry_release(nhe);
+
+	return next;
+}
+
+static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
+						    neigh_update.neigh_stats_work.work);
+	struct net_device *netdev = rpriv->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_neigh_hash_entry *nhe = NULL;
+
+	rtnl_lock();
+	if (!list_empty(&rpriv->neigh_update.neigh_list))
+		mlx5e_rep_queue_neigh_stats_work(priv);
+
+	while ((nhe = mlx5e_get_next_nhe(rpriv, nhe)) != NULL)
+		mlx5e_tc_update_neigh_used_value(nhe);
+
+	rtnl_unlock();
+}
+
+static void mlx5e_rep_neigh_update(struct work_struct *work)
+{
+	struct mlx5e_neigh_hash_entry *nhe =
+		container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
+	struct neighbour *n = nhe->n;
+	struct mlx5e_encap_entry *e;
+	unsigned char ha[ETH_ALEN];
+	struct mlx5e_priv *priv;
+	bool neigh_connected;
+	u8 nud_state, dead;
+
+	rtnl_lock();
+
+	/* If these parameters are changed after we release the lock,
+	 * we'll receive another event letting us know about it.
+	 * We use this lock to avoid inconsistency between the neigh validity
+	 * and it's hw address.
+	 */
+	read_lock_bh(&n->lock);
+	memcpy(ha, n->ha, ETH_ALEN);
+	nud_state = n->nud_state;
+	dead = n->dead;
+	read_unlock_bh(&n->lock);
+
+	neigh_connected = (nud_state & NUD_VALID) && !dead;
+
+	trace_mlx5e_rep_neigh_update(nhe, ha, neigh_connected);
+
+	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		if (!mlx5e_encap_take(e))
+			continue;
+
+		priv = netdev_priv(e->out_dev);
+		mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
+		mlx5e_encap_put(priv, e);
+	}
+	mlx5e_rep_neigh_entry_release(nhe);
+	rtnl_unlock();
+	neigh_release(n);
+}
+
+static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
+					      struct mlx5e_neigh_hash_entry *nhe,
+					      struct neighbour *n)
+{
+	/* Take a reference to ensure the neighbour and mlx5 encap
+	 * entry won't be destructed until we drop the reference in
+	 * delayed work.
+	 */
+	neigh_hold(n);
+
+	/* This assignment is valid as long as the the neigh reference
+	 * is taken
+	 */
+	nhe->n = n;
+
+	if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
+		mlx5e_rep_neigh_entry_release(nhe);
+		neigh_release(n);
+	}
+}
+
+static int mlx5e_rep_netevent_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
+						    neigh_update.netevent_nb);
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	struct net_device *netdev = rpriv->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_neigh_hash_entry *nhe = NULL;
+	struct mlx5e_neigh m_neigh = {};
+	struct neigh_parms *p;
+	struct neighbour *n;
+	bool found = false;
+
+	switch (event) {
+	case NETEVENT_NEIGH_UPDATE:
+		n = ptr;
+#if IS_ENABLED(CONFIG_IPV6)
+		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+#else
+		if (n->tbl != &arp_tbl)
+#endif
+			return NOTIFY_DONE;
+
+		m_neigh.dev = n->dev;
+		m_neigh.family = n->ops->family;
+		memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+
+		rcu_read_lock();
+		nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
+		rcu_read_unlock();
+		if (!nhe)
+			return NOTIFY_DONE;
+
+		mlx5e_rep_queue_neigh_update_work(priv, nhe, n);
+		break;
+
+	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
+		p = ptr;
+
+		/* We check the device is present since we don't care about
+		 * changes in the default table, we only care about changes
+		 * done per device delay prob time parameter.
+		 */
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
+#else
+		if (!p->dev || p->tbl != &arp_tbl)
+#endif
+			return NOTIFY_DONE;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(nhe, &neigh_update->neigh_list,
+					neigh_list) {
+			if (p->dev == nhe->m_neigh.dev) {
+				found = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+		if (!found)
+			return NOTIFY_DONE;
+
+		neigh_update->min_interval = min_t(unsigned long,
+						   NEIGH_VAR(p, DELAY_PROBE_TIME),
+						   neigh_update->min_interval);
+		mlx5_fc_update_sampling_interval(priv->mdev,
+						 neigh_update->min_interval);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static const struct rhashtable_params mlx5e_neigh_ht_params = {
+	.head_offset = offsetof(struct mlx5e_neigh_hash_entry, rhash_node),
+	.key_offset = offsetof(struct mlx5e_neigh_hash_entry, m_neigh),
+	.key_len = sizeof(struct mlx5e_neigh),
+	.automatic_shrinking = true,
+};
+
+int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	int err;
+
+	err = rhashtable_init(&neigh_update->neigh_ht, &mlx5e_neigh_ht_params);
+	if (err)
+		return err;
+
+	INIT_LIST_HEAD(&neigh_update->neigh_list);
+	mutex_init(&neigh_update->encap_lock);
+	INIT_DELAYED_WORK(&neigh_update->neigh_stats_work,
+			  mlx5e_rep_neigh_stats_work);
+	mlx5e_rep_neigh_update_init_interval(rpriv);
+
+	rpriv->neigh_update.netevent_nb.notifier_call = mlx5e_rep_netevent_event;
+	err = register_netevent_notifier(&rpriv->neigh_update.netevent_nb);
+	if (err)
+		goto out_err;
+	return 0;
+
+out_err:
+	rhashtable_destroy(&neigh_update->neigh_ht);
+	return err;
+}
+
+void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+	unregister_netevent_notifier(&neigh_update->netevent_nb);
+
+	flush_workqueue(priv->wq); /* flush neigh update works */
+
+	cancel_delayed_work_sync(&rpriv->neigh_update.neigh_stats_work);
+
+	mutex_destroy(&neigh_update->encap_lock);
+	rhashtable_destroy(&neigh_update->neigh_ht);
+}
+
+static int mlx5e_rep_neigh_entry_insert(struct mlx5e_priv *priv,
+					struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	int err;
+
+	err = rhashtable_insert_fast(&rpriv->neigh_update.neigh_ht,
+				     &nhe->rhash_node,
+				     mlx5e_neigh_ht_params);
+	if (err)
+		return err;
+
+	list_add_rcu(&nhe->neigh_list, &rpriv->neigh_update.neigh_list);
+
+	return err;
+}
+
+static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe)
+{
+	struct mlx5e_rep_priv *rpriv = nhe->priv->ppriv;
+
+	mutex_lock(&rpriv->neigh_update.encap_lock);
+
+	list_del_rcu(&nhe->neigh_list);
+
+	rhashtable_remove_fast(&rpriv->neigh_update.neigh_ht,
+			       &nhe->rhash_node,
+			       mlx5e_neigh_ht_params);
+	mutex_unlock(&rpriv->neigh_update.encap_lock);
+}
+
+/* This function must only be called under the representor's encap_lock or
+ * inside rcu read lock section.
+ */
+struct mlx5e_neigh_hash_entry *
+mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
+			     struct mlx5e_neigh *m_neigh)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
+	struct mlx5e_neigh_hash_entry *nhe;
+
+	nhe = rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh,
+				     mlx5e_neigh_ht_params);
+	return nhe && mlx5e_rep_neigh_entry_hold(nhe) ? nhe : NULL;
+}
+
+int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct mlx5e_neigh_hash_entry **nhe)
+{
+	int err;
+
+	*nhe = kzalloc(sizeof(**nhe), GFP_KERNEL);
+	if (!*nhe)
+		return -ENOMEM;
+
+	(*nhe)->priv = priv;
+	memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
+	INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
+	spin_lock_init(&(*nhe)->encap_list_lock);
+	INIT_LIST_HEAD(&(*nhe)->encap_list);
+	refcount_set(&(*nhe)->refcnt, 1);
+
+	err = mlx5e_rep_neigh_entry_insert(priv, *nhe);
+	if (err)
+		goto out_free;
+	return 0;
+
+out_free:
+	kfree(*nhe);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h
new file mode 100644
index 000000000000..8eddb3ac0d74
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_REP_NEIGH__
+#define __MLX5_EN_REP_NEIGH__
+
+#include "en.h"
+#include "en_rep.h"
+
+int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv);
+void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv);
+
+struct mlx5e_neigh_hash_entry *
+mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
+			     struct mlx5e_neigh *m_neigh);
+int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct mlx5e_neigh_hash_entry **nhe);
+void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe);
+
+void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
+
+#endif /* __MLX5_EN_REP_NEIGH__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index edc574582135..c609a5e50ebc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -9,6 +9,7 @@
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include "tc.h"
+#include "neigh.h"
 #include "en_rep.h"
 #include "eswitch.h"
 #include "esw/chains.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 9fdd79afa6e4..9be1fcc269b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -7,6 +7,7 @@
 #include "en/tc_tun.h"
 #include "en_tc.h"
 #include "rep/tc.h"
+#include "rep/neigh.h"
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c84f0d9b516e..a46405c6d560 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -35,7 +35,6 @@
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/act_api.h>
-#include <net/netevent.h>
 #include <net/arp.h>
 #include <net/devlink.h>
 #include <net/ipv6_stubs.h>
@@ -46,6 +45,7 @@
 #include "en_rep.h"
 #include "en_tc.h"
 #include "en/rep/tc.h"
+#include "en/rep/neigh.h"
 #include "fs_core.h"
 #include "lib/mlx5.h"
 #define CREATE_TRACE_POINTS
@@ -474,358 +474,6 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 	mlx5e_sqs2vport_stop(esw, rep);
 }
 
-static unsigned long mlx5e_rep_ipv6_interval(void)
-{
-	if (IS_ENABLED(CONFIG_IPV6) && ipv6_stub->nd_tbl)
-		return NEIGH_VAR(&ipv6_stub->nd_tbl->parms, DELAY_PROBE_TIME);
-
-	return ~0UL;
-}
-
-static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
-{
-	unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME);
-	unsigned long ipv6_interval = mlx5e_rep_ipv6_interval();
-	struct net_device *netdev = rpriv->netdev;
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-
-	rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
-	mlx5_fc_update_sampling_interval(priv->mdev, rpriv->neigh_update.min_interval);
-}
-
-void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-
-	mlx5_fc_queue_stats_work(priv->mdev,
-				 &neigh_update->neigh_stats_work,
-				 neigh_update->min_interval);
-}
-
-static bool mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe)
-{
-	return refcount_inc_not_zero(&nhe->refcnt);
-}
-
-static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe);
-
-void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe)
-{
-	if (refcount_dec_and_test(&nhe->refcnt)) {
-		mlx5e_rep_neigh_entry_remove(nhe);
-		kfree_rcu(nhe, rcu);
-	}
-}
-
-static struct mlx5e_neigh_hash_entry *
-mlx5e_get_next_nhe(struct mlx5e_rep_priv *rpriv,
-		   struct mlx5e_neigh_hash_entry *nhe)
-{
-	struct mlx5e_neigh_hash_entry *next = NULL;
-
-	rcu_read_lock();
-
-	for (next = nhe ?
-		     list_next_or_null_rcu(&rpriv->neigh_update.neigh_list,
-					   &nhe->neigh_list,
-					   struct mlx5e_neigh_hash_entry,
-					   neigh_list) :
-		     list_first_or_null_rcu(&rpriv->neigh_update.neigh_list,
-					    struct mlx5e_neigh_hash_entry,
-					    neigh_list);
-	     next;
-	     next = list_next_or_null_rcu(&rpriv->neigh_update.neigh_list,
-					  &next->neigh_list,
-					  struct mlx5e_neigh_hash_entry,
-					  neigh_list))
-		if (mlx5e_rep_neigh_entry_hold(next))
-			break;
-
-	rcu_read_unlock();
-
-	if (nhe)
-		mlx5e_rep_neigh_entry_release(nhe);
-
-	return next;
-}
-
-static void mlx5e_rep_neigh_stats_work(struct work_struct *work)
-{
-	struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
-						    neigh_update.neigh_stats_work.work);
-	struct net_device *netdev = rpriv->netdev;
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_neigh_hash_entry *nhe = NULL;
-
-	rtnl_lock();
-	if (!list_empty(&rpriv->neigh_update.neigh_list))
-		mlx5e_rep_queue_neigh_stats_work(priv);
-
-	while ((nhe = mlx5e_get_next_nhe(rpriv, nhe)) != NULL)
-		mlx5e_tc_update_neigh_used_value(nhe);
-
-	rtnl_unlock();
-}
-
-static void mlx5e_rep_neigh_update(struct work_struct *work)
-{
-	struct mlx5e_neigh_hash_entry *nhe =
-		container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work);
-	struct neighbour *n = nhe->n;
-	struct mlx5e_encap_entry *e;
-	unsigned char ha[ETH_ALEN];
-	struct mlx5e_priv *priv;
-	bool neigh_connected;
-	u8 nud_state, dead;
-
-	rtnl_lock();
-
-	/* If these parameters are changed after we release the lock,
-	 * we'll receive another event letting us know about it.
-	 * We use this lock to avoid inconsistency between the neigh validity
-	 * and it's hw address.
-	 */
-	read_lock_bh(&n->lock);
-	memcpy(ha, n->ha, ETH_ALEN);
-	nud_state = n->nud_state;
-	dead = n->dead;
-	read_unlock_bh(&n->lock);
-
-	neigh_connected = (nud_state & NUD_VALID) && !dead;
-
-	trace_mlx5e_rep_neigh_update(nhe, ha, neigh_connected);
-
-	list_for_each_entry(e, &nhe->encap_list, encap_list) {
-		if (!mlx5e_encap_take(e))
-			continue;
-
-		priv = netdev_priv(e->out_dev);
-		mlx5e_rep_update_flows(priv, e, neigh_connected, ha);
-		mlx5e_encap_put(priv, e);
-	}
-	mlx5e_rep_neigh_entry_release(nhe);
-	rtnl_unlock();
-	neigh_release(n);
-}
-
-static void
-mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv,
-				  struct mlx5e_neigh_hash_entry *nhe,
-				  struct neighbour *n)
-{
-	/* Take a reference to ensure the neighbour and mlx5 encap
-	 * entry won't be destructed until we drop the reference in
-	 * delayed work.
-	 */
-	neigh_hold(n);
-
-	/* This assignment is valid as long as the the neigh reference
-	 * is taken
-	 */
-	nhe->n = n;
-
-	if (!queue_work(priv->wq, &nhe->neigh_update_work)) {
-		mlx5e_rep_neigh_entry_release(nhe);
-		neigh_release(n);
-	}
-}
-
-static int mlx5e_rep_netevent_event(struct notifier_block *nb,
-				    unsigned long event, void *ptr)
-{
-	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
-						    neigh_update.netevent_nb);
-	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	struct net_device *netdev = rpriv->netdev;
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_neigh_hash_entry *nhe = NULL;
-	struct mlx5e_neigh m_neigh = {};
-	struct neigh_parms *p;
-	struct neighbour *n;
-	bool found = false;
-
-	switch (event) {
-	case NETEVENT_NEIGH_UPDATE:
-		n = ptr;
-#if IS_ENABLED(CONFIG_IPV6)
-		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
-#else
-		if (n->tbl != &arp_tbl)
-#endif
-			return NOTIFY_DONE;
-
-		m_neigh.dev = n->dev;
-		m_neigh.family = n->ops->family;
-		memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-
-		rcu_read_lock();
-		nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh);
-		rcu_read_unlock();
-		if (!nhe)
-			return NOTIFY_DONE;
-
-		mlx5e_rep_queue_neigh_update_work(priv, nhe, n);
-		break;
-
-	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
-		p = ptr;
-
-		/* We check the device is present since we don't care about
-		 * changes in the default table, we only care about changes
-		 * done per device delay prob time parameter.
-		 */
-#if IS_ENABLED(CONFIG_IPV6)
-		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
-#else
-		if (!p->dev || p->tbl != &arp_tbl)
-#endif
-			return NOTIFY_DONE;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu(nhe, &neigh_update->neigh_list,
-					neigh_list) {
-			if (p->dev == nhe->m_neigh.dev) {
-				found = true;
-				break;
-			}
-		}
-		rcu_read_unlock();
-		if (!found)
-			return NOTIFY_DONE;
-
-		neigh_update->min_interval = min_t(unsigned long,
-						   NEIGH_VAR(p, DELAY_PROBE_TIME),
-						   neigh_update->min_interval);
-		mlx5_fc_update_sampling_interval(priv->mdev,
-						 neigh_update->min_interval);
-		break;
-	}
-	return NOTIFY_DONE;
-}
-
-static const struct rhashtable_params mlx5e_neigh_ht_params = {
-	.head_offset = offsetof(struct mlx5e_neigh_hash_entry, rhash_node),
-	.key_offset = offsetof(struct mlx5e_neigh_hash_entry, m_neigh),
-	.key_len = sizeof(struct mlx5e_neigh),
-	.automatic_shrinking = true,
-};
-
-static int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv)
-{
-	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	int err;
-
-	err = rhashtable_init(&neigh_update->neigh_ht, &mlx5e_neigh_ht_params);
-	if (err)
-		return err;
-
-	INIT_LIST_HEAD(&neigh_update->neigh_list);
-	mutex_init(&neigh_update->encap_lock);
-	INIT_DELAYED_WORK(&neigh_update->neigh_stats_work,
-			  mlx5e_rep_neigh_stats_work);
-	mlx5e_rep_neigh_update_init_interval(rpriv);
-
-	rpriv->neigh_update.netevent_nb.notifier_call = mlx5e_rep_netevent_event;
-	err = register_netevent_notifier(&rpriv->neigh_update.netevent_nb);
-	if (err)
-		goto out_err;
-	return 0;
-
-out_err:
-	rhashtable_destroy(&neigh_update->neigh_ht);
-	return err;
-}
-
-static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
-{
-	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-
-	unregister_netevent_notifier(&neigh_update->netevent_nb);
-
-	flush_workqueue(priv->wq); /* flush neigh update works */
-
-	cancel_delayed_work_sync(&rpriv->neigh_update.neigh_stats_work);
-
-	mutex_destroy(&neigh_update->encap_lock);
-	rhashtable_destroy(&neigh_update->neigh_ht);
-}
-
-static int mlx5e_rep_neigh_entry_insert(struct mlx5e_priv *priv,
-					struct mlx5e_neigh_hash_entry *nhe)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	int err;
-
-	err = rhashtable_insert_fast(&rpriv->neigh_update.neigh_ht,
-				     &nhe->rhash_node,
-				     mlx5e_neigh_ht_params);
-	if (err)
-		return err;
-
-	list_add_rcu(&nhe->neigh_list, &rpriv->neigh_update.neigh_list);
-
-	return err;
-}
-
-static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe)
-{
-	struct mlx5e_rep_priv *rpriv = nhe->priv->ppriv;
-
-	mutex_lock(&rpriv->neigh_update.encap_lock);
-
-	list_del_rcu(&nhe->neigh_list);
-
-	rhashtable_remove_fast(&rpriv->neigh_update.neigh_ht,
-			       &nhe->rhash_node,
-			       mlx5e_neigh_ht_params);
-	mutex_unlock(&rpriv->neigh_update.encap_lock);
-}
-
-/* This function must only be called under the representor's encap_lock or
- * inside rcu read lock section.
- */
-struct mlx5e_neigh_hash_entry *
-mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
-			     struct mlx5e_neigh *m_neigh)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
-	struct mlx5e_neigh_hash_entry *nhe;
-
-	nhe = rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh,
-				     mlx5e_neigh_ht_params);
-	return nhe && mlx5e_rep_neigh_entry_hold(nhe) ? nhe : NULL;
-}
-
-int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
-				 struct mlx5e_encap_entry *e,
-				 struct mlx5e_neigh_hash_entry **nhe)
-{
-	int err;
-
-	*nhe = kzalloc(sizeof(**nhe), GFP_KERNEL);
-	if (!*nhe)
-		return -ENOMEM;
-
-	(*nhe)->priv = priv;
-	memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh));
-	INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update);
-	spin_lock_init(&(*nhe)->encap_list_lock);
-	INIT_LIST_HEAD(&(*nhe)->encap_list);
-	refcount_set(&(*nhe)->refcnt, 1);
-
-	err = mlx5e_rep_neigh_entry_insert(priv, *nhe);
-	if (err)
-		goto out_free;
-	return 0;
-
-out_free:
-	kfree(*nhe);
-	return err;
-}
-
 static int mlx5e_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 74d46e9a201a..81ed06e58fea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -208,14 +208,6 @@ void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 bool mlx5e_eswitch_rep(struct net_device *netdev);
 bool mlx5e_eswitch_uplink_rep(struct net_device *netdev);
 
-struct mlx5e_neigh_hash_entry *
-mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
-			     struct mlx5e_neigh *m_neigh);
-int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv,
-				 struct mlx5e_encap_entry *e,
-				 struct mlx5e_neigh_hash_entry **nhe);
-void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe);
-
 #else /* CONFIG_MLX5_ESWITCH */
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 251975ccbdf7..749390dc7aaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4777,9 +4777,3 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
 	}
 	mutex_unlock(&rpriv->unready_flows_lock);
 }
-
-void mlx5_tc_rep_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv)
-{
-	if (tc_priv->tun_dev)
-		dev_put(tc_priv->tun_dev);
-}
-- 
cgit v1.2.3


From e2394a61d243d74ec7d0bfd4c6e25171fba54caa Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 12 May 2020 18:08:41 +0300
Subject: net/mlx5e: Move TC-specific code from en_main.c to en_tc.c

As a preparation for introducing new kconfig option that controls
compilation of all TC offloads code in mlx5, extract TC-specific code from
en_main.c to en_tc.c. This allows easily compiling out the code by
only including new source in make file when corresponding kconfig is
enabled instead of adding multiple ifdef blocks to en_main.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 37 -----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   | 35 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h   |  7 +++++
 3 files changed, 42 insertions(+), 37 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 07823abe5557..3829dfd39800 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3539,41 +3539,6 @@ out:
 	return err;
 }
 
-#ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct flow_cls_offload *cls_flower,
-				     unsigned long flags)
-{
-	switch (cls_flower->command) {
-	case FLOW_CLS_REPLACE:
-		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
-					      flags);
-	case FLOW_CLS_DESTROY:
-		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
-					   flags);
-	case FLOW_CLS_STATS:
-		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
-					  flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-				   void *cb_priv)
-{
-	unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(NIC_OFFLOAD);
-	struct mlx5e_priv *priv = cb_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data, flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-#endif
-
 static LIST_HEAD(mlx5e_block_cb_list);
 
 static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -3582,7 +3547,6 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
 	switch (type) {
-#ifdef CONFIG_MLX5_ESWITCH
 	case TC_SETUP_BLOCK: {
 		struct flow_block_offload *f = type_data;
 
@@ -3592,7 +3556,6 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 						  mlx5e_setup_tc_block_cb,
 						  priv, priv, true);
 	}
-#endif
 	case TC_SETUP_QDISC_MQPRIO:
 		return mlx5e_setup_tc_mqprio(priv, type_data);
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 749390dc7aaa..1614b077a477 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -31,6 +31,7 @@
  */
 
 #include <net/flow_dissector.h>
+#include <net/flow_offload.h>
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
@@ -50,6 +51,7 @@
 #include "en.h"
 #include "en_rep.h"
 #include "en/rep/tc.h"
+#include "en/rep/neigh.h"
 #include "en_tc.h"
 #include "eswitch.h"
 #include "esw/chains.h"
@@ -4777,3 +4779,36 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
 	}
 	mutex_unlock(&rpriv->unready_flows_lock);
 }
+
+static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
+				     struct flow_cls_offload *cls_flower,
+				     unsigned long flags)
+{
+	switch (cls_flower->command) {
+	case FLOW_CLS_REPLACE:
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
+	case FLOW_CLS_DESTROY:
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
+	case FLOW_CLS_STATS:
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv)
+{
+	unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(NIC_OFFLOAD);
+	struct mlx5e_priv *priv = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_setup_tc_cls_flower(priv, type_data, flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 1d8d85b842fe..9c59b7fe258a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -173,6 +173,9 @@ void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 struct mlx5e_tc_flow;
 u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
 
+int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+			    void *cb_priv);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
@@ -181,6 +184,10 @@ static inline int  mlx5e_tc_num_filters(struct mlx5e_priv *priv,
 {
 	return 0;
 }
+
+static inline int
+mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{ return -EOPNOTSUPP; }
 #endif
 
 #endif /* __MLX5_EN_TC_H__ */
-- 
cgit v1.2.3


From d956873f908cff46dd55976dbd9442a027e9d9d1 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 12 May 2020 18:24:11 +0300
Subject: net/mlx5e: Introduce kconfig var for TC support

In order to improve code maintainability and readability, introduce new
CONFIG_MLX5_CLS_ACT kconfig variable to control compilation of TC hardware
offloads implementation. This allows distinguishing between features that
require TC support (MPLSoUDP, etc.) and features that just rely on
representor functionality (rep_bond for live migration, etc.).

Modify rep_tc.h, rep_neigh.h, en_tc.h and chains.h files to provide stubs
for functions that are called from generic code.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    | 17 ++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   | 11 +++---
 .../net/ethernet/mellanox/mlx5/core/en/rep/neigh.h | 11 ++++++
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.h    | 44 ++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    | 16 ++++++--
 .../net/ethernet/mellanox/mlx5/core/esw/chains.h   | 19 ++++++++++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |  2 +
 8 files changed, 109 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 7d69a3061f17..4256d59eca2b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -78,9 +78,24 @@ config MLX5_ESWITCH
 	        Legacy SRIOV mode (L2 mac vlan steering based).
 	        Switchdev mode (eswitch offloads).
 
+config MLX5_CLS_ACT
+	bool "MLX5 TC classifier action support"
+	depends on MLX5_ESWITCH && NET_CLS_ACT
+	default y
+	help
+	  mlx5 ConnectX offloads support for TC classifier action (NET_CLS_ACT),
+	  works in both native NIC mdoe and Switchdev SRIOV mode.
+	  Actions get attached to a Hardware offloaded classifiers and are
+	  invoked after a successful classification. Actions are used to
+	  overwrite the classification result, instantly drop or redirect and/or
+	  reformat packets in wire speeds without involving the host cpu.
+
+	  If set to N, TC offloads in both NIC and switchdev modes will be disabled.
+	  If unsure, set to Y
+
 config MLX5_TC_CT
 	bool "MLX5 TC connection tracking offload support"
-	depends on MLX5_CORE_EN && NET_SWITCHDEV && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT
+	depends on MLX5_CLS_ACT && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT
 	default y
 	help
 	  Say Y here if you want to support offloading connection tracking rules
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 3c9d78e6695c..3c1f12c7175f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -33,18 +33,19 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/rep/tc.o en/rep/neigh.o en/tc_tun.o lib/port_tun.o \
-					lag_mp.o \
-					lib/geneve.o en/mapping.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
-					en/tc_tun_geneve.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o lib/geneve.o lib/port_tun.o lag_mp.o
+mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
+					en/mapping.o esw/chains.o en/tc_tun.o \
+					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
+					diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
 
 #
 # Core extra
 #
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
-				      ecpf.o rdma.o esw/chains.o
+				      ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h
index 8eddb3ac0d74..32b239189c95 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.h
@@ -7,6 +7,8 @@
 #include "en.h"
 #include "en_rep.h"
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
 int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv);
 void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv);
 
@@ -20,4 +22,13 @@ void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe);
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline int
+mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv) { return 0; }
+static inline void
+mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv) {}
+
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __MLX5_EN_REP_NEIGH__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
index 90da00626b97..86f92abf2fdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -5,11 +5,11 @@
 #define __MLX5_EN_REP_TC_H__
 
 #include <linux/skbuff.h>
-#include "en.h"
 #include "en_tc.h"
 #include "en_rep.h"
 
-struct mlx5e_rep_priv;
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
 int mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv);
 void mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv);
 
@@ -21,7 +21,6 @@ void mlx5e_rep_tc_disable(struct mlx5e_priv *priv);
 
 int mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv);
 
-struct mlx5e_encap_entry;
 void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 			    struct mlx5e_encap_entry *e,
 			    bool neigh_connected,
@@ -36,10 +35,47 @@ int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		       void *type_data);
 void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv);
 
-struct mlx5e_tc_update_priv;
 bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 			     struct sk_buff *skb,
 			     struct mlx5e_tc_update_priv *tc_priv);
 void mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv);
 
+#else /* CONFIG_MLX5_CLS_ACT */
+
+struct mlx5e_rep_priv;
+static inline int
+mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv) { return 0; }
+static inline void
+mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv) {}
+
+static inline int
+mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv) { return 0; }
+static inline void
+mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv) {}
+
+static inline void
+mlx5e_rep_tc_enable(struct mlx5e_priv *priv) {}
+static inline void
+mlx5e_rep_tc_disable(struct mlx5e_priv *priv) {}
+
+static inline int
+mlx5e_rep_tc_event_port_affinity(struct mlx5e_priv *priv) { return NOTIFY_DONE; }
+
+static inline int
+mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		   void *type_data) { return -EOPNOTSUPP; }
+
+static inline void
+mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv) {}
+
+struct mlx5e_tc_update_priv;
+static inline bool
+mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
+			struct sk_buff *skb,
+			struct mlx5e_tc_update_priv *tc_priv) { return true; }
+static inline void
+mlx5_rep_tc_post_napi_receive(struct mlx5e_tc_update_priv *tc_priv) {}
+
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __MLX5_EN_REP_TC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3829dfd39800..803f1066ac08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3728,7 +3728,7 @@ static int set_feature_cvlan_filter(struct net_device *netdev, bool enable)
 	return 0;
 }
 
-#ifdef CONFIG_MLX5_ESWITCH
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3839,7 +3839,7 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
 				    set_feature_cvlan_filter);
-#ifdef CONFIG_MLX5_ESWITCH
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_tc_num_filters);
 #endif
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 9c59b7fe258a..037aa73bf9ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -80,9 +80,6 @@ enum {
 
 #define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT)
 
-int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
-void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
-
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
 
@@ -173,9 +170,22 @@ void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 struct mlx5e_tc_flow;
 u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
+void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
+
 int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 			    void *cb_priv);
 
+#else /* CONFIG_MLX5_CLS_ACT */
+static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
+static inline int
+mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{ return -EOPNOTSUPP; }
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h
index f8c4239846ea..7679ac359e31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h
@@ -6,6 +6,8 @@
 
 #include "eswitch.h"
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
 bool
 mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw);
 bool
@@ -46,4 +48,21 @@ void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw);
 int
 mlx5_eswitch_get_chain_for_tag(struct mlx5_eswitch *esw, u32 tag, u32 *chain);
 
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline struct mlx5_flow_table *
+mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+			  u32 level) { return ERR_PTR(-EOPNOTSUPP); }
+static inline void
+mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
+			  u32 level) {}
+
+static inline struct mlx5_flow_table *
+mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw) { return ERR_PTR(-EOPNOTSUPP); }
+
+static inline int mlx5_esw_chains_create(struct mlx5_eswitch *esw) { return 0; }
+static inline void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw) {}
+
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __ML5_ESW_CHAINS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 57ac2ef52e80..1c9be19ee025 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1727,7 +1727,9 @@ static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
 
 static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 {
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	mlx5e_tc_clean_fdb_peer_flows(esw);
+#endif
 	esw_del_fdb_peer_miss_rules(esw);
 }
 
-- 
cgit v1.2.3


From f828ca6a2fb6f6c861e5113d3c91d3bca68db28e Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Sun, 17 Nov 2019 15:32:24 +0200
Subject: net/mlx5e: Add support for hw encapsulation of MPLS over UDP

MPLS over UDP is supported by adding a rule on a representor net device
which does tunnel_key set, push mpls and forward to a baredup device. At
the hardware level we use a packet_reformat_context object to do the
encapsulation of the packet.

The resulting packet looks as follows (left side transmitted first):
outer L2 | outer IP | UDP | MPLS | inner L3 and data |

Example usage:
  tc filter add dev $rep0 protocol ip prio 1 root flower skip_sw  \
     action tunnel_key set src_ip 8.8.8.21 dst_ip 8.8.8.24 id 555 \
     dst_port 6635 tos 4 ttl 6 csum action mpls push protocol 0x8847 \
     label 555 tc 3 action mirred egress redirect dev bareudp0

This is how the filter is shown with tc filter show:
tc filter show dev enp59s0f0_0 ingress
filter protocol ip pref 1 flower chain 0
filter protocol ip pref 1 flower chain 0 handle 0x1
  eth_type ipv4
  skip_sw
  in_hw in_hw_count 1
        action order 1: tunnel_key  set
        src_ip 8.8.8.21
        dst_ip 8.8.8.24
        key_id 555
        dst_port 6635
        csum
        tos 0x4
        ttl 6 pipe
         index 1 ref 1 bind 1

        action order 2: mpls  push protocol mpls_uc label 555 tc 3 ttl 255 pipe
         index 1 ref 1 bind 1

        action order 3: mirred (Egress Redirect to device bareudp0) stolen
        index 1 ref 1 bind 1

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |  3 +
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.h    |  2 +
 .../mellanox/mlx5/core/en/tc_tun_mplsoudp.c        | 88 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 18 +++++
 .../net/ethernet/mellanox/mlx5/core/lib/port_tun.c |  4 +-
 6 files changed, 114 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 3c1f12c7175f..e5ee9103fefb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -38,7 +38,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o lib/geneve.o lib/port_tun.o lag
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					en/mapping.o esw/chains.o en/tc_tun.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
-					diag/en_tc_tracepoint.o
+					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 9be1fcc269b2..e99382f58807 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -4,6 +4,7 @@
 #include <net/vxlan.h>
 #include <net/gre.h>
 #include <net/geneve.h>
+#include <net/bareudp.h>
 #include "en/tc_tun.h"
 #include "en_tc.h"
 #include "rep/tc.h"
@@ -18,6 +19,8 @@ struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
 	else if (netif_is_gretap(tunnel_dev) ||
 		 netif_is_ip6gretap(tunnel_dev))
 		return &gre_tunnel;
+	else if (netif_is_bareudp(tunnel_dev))
+		return &mplsoudp_tunnel;
 	else
 		return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 1630f0ec3ad7..704359df6095 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -16,6 +16,7 @@ enum {
 	MLX5E_TC_TUNNEL_TYPE_VXLAN,
 	MLX5E_TC_TUNNEL_TYPE_GENEVE,
 	MLX5E_TC_TUNNEL_TYPE_GRETAP,
+	MLX5E_TC_TUNNEL_TYPE_MPLSOUDP,
 };
 
 struct mlx5e_tc_tunnel {
@@ -46,6 +47,7 @@ struct mlx5e_tc_tunnel {
 extern struct mlx5e_tc_tunnel vxlan_tunnel;
 extern struct mlx5e_tc_tunnel geneve_tunnel;
 extern struct mlx5e_tc_tunnel gre_tunnel;
+extern struct mlx5e_tc_tunnel mplsoudp_tunnel;
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
new file mode 100644
index 000000000000..ff296c0a32c4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/bareudp.h>
+#include <net/mpls.h>
+#include "en/tc_tun.h"
+
+static bool can_offload(struct mlx5e_priv *priv)
+{
+	return MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, reformat_l3_tunnel_to_l2);
+}
+
+static int calc_hlen(struct mlx5e_encap_entry *e)
+{
+	return sizeof(struct udphdr) + MPLS_HLEN;
+}
+
+static int init_encap_attr(struct net_device *tunnel_dev,
+			   struct mlx5e_priv *priv,
+			   struct mlx5e_encap_entry *e,
+			   struct netlink_ext_ack *extack)
+{
+	e->tunnel = &mplsoudp_tunnel;
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL;
+	return 0;
+}
+
+static inline __be32 mpls_label_id_field(__be32 label, u8 tos, u8 ttl)
+{
+	u32 res;
+
+	/* mpls label is 32 bits long and construction as follows:
+	 * 20 bits label
+	 * 3 bits tos
+	 * 1 bit bottom of stack. Since we support only one label, this bit is
+	 *       always set.
+	 * 8 bits TTL
+	 */
+	res = be32_to_cpu(label) << 12 | 1 << 8 | (tos & 7) <<  9 | ttl;
+	return cpu_to_be32(res);
+}
+
+static int generate_ip_tun_hdr(char buf[],
+			       __u8 *ip_proto,
+			       struct mlx5e_encap_entry *r)
+{
+	const struct ip_tunnel_key *tun_key = &r->tun_info->key;
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct mpls_shim_hdr *mpls;
+
+	mpls = (struct mpls_shim_hdr *)(udp + 1);
+	*ip_proto = IPPROTO_UDP;
+
+	udp->dest = tun_key->tp_dst;
+	mpls->label_stack_entry = mpls_label_id_field(tun_id, tun_key->tos, tun_key->ttl);
+
+	return 0;
+}
+
+static int parse_udp_ports(struct mlx5e_priv *priv,
+			   struct mlx5_flow_spec *spec,
+			   struct flow_cls_offload *f,
+			   void *headers_c,
+			   void *headers_v)
+{
+	return mlx5e_tc_tun_parse_udp_ports(priv, spec, f, headers_c, headers_v);
+}
+
+static int parse_tunnel(struct mlx5e_priv *priv,
+			struct mlx5_flow_spec *spec,
+			struct flow_cls_offload *f,
+			void *headers_c,
+			void *headers_v)
+{
+	return 0;
+}
+
+struct mlx5e_tc_tunnel mplsoudp_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_MPLSOUDP,
+	.match_level          = MLX5_MATCH_L4,
+	.can_offload          = can_offload,
+	.calc_hlen            = calc_hlen,
+	.init_encap_attr      = init_encap_attr,
+	.generate_ip_tun_hdr  = generate_ip_tun_hdr,
+	.parse_udp_ports      = parse_udp_ports,
+	.parse_tunnel         = parse_tunnel,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1614b077a477..2cebbd03bc57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -48,6 +48,7 @@
 #include <net/tc_act/tc_csum.h>
 #include <net/arp.h>
 #include <net/ipv6_stubs.h>
+#include <net/bareudp.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en/rep/tc.h"
@@ -3685,6 +3686,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	bool encap = false, decap = false;
 	u32 action = attr->action;
 	int err, i, if_count = 0;
+	bool mpls_push = false;
 
 	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
@@ -3699,6 +3701,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			break;
+		case FLOW_ACTION_MPLS_PUSH:
+			if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+							reformat_l2_to_l3_tunnel) ||
+			    act->mpls_push.proto != htons(ETH_P_MPLS_UC)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "mpls push is supported only for mpls_uc protocol");
+				return -EOPNOTSUPP;
+			}
+			mpls_push = true;
+			break;
 		case FLOW_ACTION_MANGLE:
 		case FLOW_ACTION_ADD:
 			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB,
@@ -3729,6 +3741,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				return -EINVAL;
 			}
 
+			if (mpls_push && !netif_is_bareudp(out_dev)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "mpls is supported only through a bareudp device");
+				return -EOPNOTSUPP;
+			}
+
 			if (ft_flow && out_dev == priv->netdev) {
 				/* Ignore forward to self rules generated
 				 * by adding both mlx5 devs to the flow table
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
index 8809a65ecefb..e042e0924079 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -144,11 +144,11 @@ static int mlx5_set_entropy(struct mlx5_tun_entropy *tun_entropy,
 int mlx5_tun_entropy_refcount_inc(struct mlx5_tun_entropy *tun_entropy,
 				  int reformat_type)
 {
-	/* the default is error for unknown (non VXLAN/GRE tunnel types) */
 	int err = -EOPNOTSUPP;
 
 	mutex_lock(&tun_entropy->lock);
-	if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN &&
+	if ((reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN ||
+	     reformat_type == MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL) &&
 	    tun_entropy->enabled) {
 		/* in case entropy calculation is enabled for all tunneling
 		 * types, it is ok for VXLAN, so approve.
-- 
cgit v1.2.3


From 72046a91d13469ef35885323a84938dce35ade94 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 29 Jan 2020 16:21:16 +0200
Subject: net/mlx5e: Allow to match on mpls parameters

Support matching on MPLS over UDP parameters using misc2 section of
match parameters.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en/tc_tun_mplsoudp.c        | 49 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 20 ++++++++-
 2 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
index ff296c0a32c4..98ee62e427d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
@@ -73,6 +73,55 @@ static int parse_tunnel(struct mlx5e_priv *priv,
 			void *headers_c,
 			void *headers_v)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_match_enc_keyid enc_keyid;
+	struct flow_match_mpls match;
+	void *misc2_c;
+	void *misc2_v;
+
+	misc2_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			       misc_parameters_2);
+	misc2_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			       misc_parameters_2);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS))
+		return 0;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
+		return 0;
+
+	flow_rule_match_enc_keyid(rule, &enc_keyid);
+
+	if (!enc_keyid.mask->keyid)
+		return 0;
+
+	if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) &
+	      MLX5_FLEX_PROTO_CW_MPLS_UDP))
+		return -EOPNOTSUPP;
+
+	flow_rule_match_mpls(rule, &match);
+
+	MLX5_SET(fte_match_set_misc2, misc2_c,
+		 outer_first_mpls_over_udp.mpls_label, match.mask->mpls_label);
+	MLX5_SET(fte_match_set_misc2, misc2_v,
+		 outer_first_mpls_over_udp.mpls_label, match.key->mpls_label);
+
+	MLX5_SET(fte_match_set_misc2, misc2_c,
+		 outer_first_mpls_over_udp.mpls_exp, match.mask->mpls_tc);
+	MLX5_SET(fte_match_set_misc2, misc2_v,
+		 outer_first_mpls_over_udp.mpls_exp, match.key->mpls_tc);
+
+	MLX5_SET(fte_match_set_misc2, misc2_c,
+		 outer_first_mpls_over_udp.mpls_s_bos, match.mask->mpls_bos);
+	MLX5_SET(fte_match_set_misc2, misc2_v,
+		 outer_first_mpls_over_udp.mpls_s_bos, match.key->mpls_bos);
+
+	MLX5_SET(fte_match_set_misc2, misc2_c,
+		 outer_first_mpls_over_udp.mpls_ttl, match.mask->mpls_ttl);
+	MLX5_SET(fte_match_set_misc2, misc2_v,
+		 outer_first_mpls_over_udp.mpls_ttl, match.key->mpls_ttl);
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 2cebbd03bc57..801fcd1b5f85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2073,6 +2073,20 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 	return 0;
 }
 
+static bool skip_key_basic(struct net_device *filter_dev,
+			   struct flow_cls_offload *f)
+{
+	/* When doing mpls over udp decap, the user needs to provide
+	 * MPLS_UC as the protocol in order to be able to match on mpls
+	 * label fields.  However, the actual ethertype is IP so we want to
+	 * avoid matching on this, otherwise we'll fail the match.
+	 */
+	if (netif_is_bareudp(filter_dev) && f->common.chain_index == 0)
+		return true;
+
+	return false;
+}
+
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow,
 			      struct mlx5_flow_spec *spec,
@@ -2117,7 +2131,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_IP)  |
 	      BIT(FLOW_DISSECTOR_KEY_CT) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS))) {
+	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) |
+	      BIT(FLOW_DISSECTOR_KEY_MPLS))) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported key");
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
 			    dissector->used_keys);
@@ -2147,7 +2162,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC) &&
+	    !skip_key_basic(filter_dev, f)) {
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
-- 
cgit v1.2.3


From 14e6b038afa014ac2288a2f3d692697f708ba344 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Mon, 3 Feb 2020 13:44:14 +0200
Subject: net/mlx5e: Add support for hw decapsulation of MPLS over UDP

MPLS over UDP is supported in hardware by using a packet reformat object
with reformat type equal L3_TUNNEL_TO_L2 which both decapsulates the
outer L3, L4 and MPLS headers, and allows for setting the L2 headers of
the resulting decapsulated packet. For the hardware to operate
correctly, the configuration of the firmware must have
FLEX_PARSER_PROFILE_ENABLE = 1.

Example tc rule:
  tc filter add dev bareudp0 protocol all prio 1 root flower enc_dst_port \
      6635 enc_src_ip 8.8.8.23 action mpls pop protocol ip pipe \
      action pedit ex munge eth dst set 00:11:22:33:44:21 pipe action \
      mirred egress redirect dev enp59s0f0_0

We use pedit to set the correct destination MAC.

For MPLS over UDP decapsulation to take place, the driver logic requires
the following:

1. flower filter added on bareudp device.
2. action mpls pop
3. zero or more pedit munge actions
4. one redirect action

Current implementation supports only IPv4 and no VLAN.

tc filter show output looks like this:
   filter protocol all pref 1 flower chain 0
   filter protocol all pref 1 flower chain 0 handle 0x1
     enc_src_ip 8.8.8.24
     enc_dst_port 6635
     in_hw in_hw_count 1
            action order 1: mpls  pop protocol ip pipe
             index 2 ref 1 bind 1

            action order 2:  pedit action pipe keys 2
             index 1 ref 1 bind 1
             key #0  at eth+0: val 00112233 mask 00000000
             key #1  at eth+4: val 44210000 mask 0000ffff

            action order 3: mirred (Egress Redirect to device enp59s0f0_0) stolen
            index 2 ref 1 bind 1

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |  16 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 217 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |   3 +
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |   4 +
 5 files changed, 238 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 81ed06e58fea..93e911baacad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -158,6 +158,22 @@ struct mlx5e_neigh_hash_entry {
 enum {
 	/* set when the encap entry is successfully offloaded into HW */
 	MLX5_ENCAP_ENTRY_VALID     = BIT(0),
+	MLX5_REFORMAT_DECAP        = BIT(1),
+};
+
+struct mlx5e_decap_key {
+	struct ethhdr key;
+};
+
+struct mlx5e_decap_entry {
+	struct mlx5e_decap_key key;
+	struct list_head flows;
+	struct hlist_node hlist;
+	refcount_t refcnt;
+	struct completion res_ready;
+	int compl_result;
+	struct mlx5_pkt_reformat *pkt_reformat;
+	struct rcu_head rcu;
 };
 
 struct mlx5e_encap_entry {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 801fcd1b5f85..a6b18f0444e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -46,6 +46,7 @@
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
+#include <net/tc_act/tc_mpls.h>
 #include <net/arp.h>
 #include <net/ipv6_stubs.h>
 #include <net/bareudp.h>
@@ -93,6 +94,7 @@ enum {
 	MLX5E_TC_FLOW_FLAG_NOT_READY	= MLX5E_TC_FLOW_BASE + 5,
 	MLX5E_TC_FLOW_FLAG_DELETED	= MLX5E_TC_FLOW_BASE + 6,
 	MLX5E_TC_FLOW_FLAG_CT		= MLX5E_TC_FLOW_BASE + 7,
+	MLX5E_TC_FLOW_FLAG_L3_TO_L2_DECAP = MLX5E_TC_FLOW_BASE + 8,
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
@@ -126,6 +128,11 @@ struct mlx5e_tc_flow {
 	u64			cookie;
 	unsigned long		flags;
 	struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1];
+
+	/* flows sharing the same reformat object - currently mpls decap */
+	struct list_head l3_to_l2_reformat;
+	struct mlx5e_decap_entry *decap_reformat;
+
 	/* Flow can be associated with multiple encap IDs.
 	 * The number of encaps is bounded by the number of supported
 	 * destinations.
@@ -157,6 +164,7 @@ struct mlx5e_tc_flow_parse_attr {
 	struct mlx5_flow_spec spec;
 	struct mlx5e_tc_mod_hdr_acts mod_hdr_acts;
 	int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS];
+	struct ethhdr eth;
 };
 
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
@@ -1124,6 +1132,11 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct netlink_ext_ack *extack,
 			      struct net_device **encap_dev,
 			      bool *encap_valid);
+static int mlx5e_attach_decap(struct mlx5e_priv *priv,
+			      struct mlx5e_tc_flow *flow,
+			      struct netlink_ext_ack *extack);
+static void mlx5e_detach_decap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow);
 
 static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
@@ -1299,6 +1312,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	if (flow_flag_test(flow, L3_TO_L2_DECAP)) {
+		err = mlx5e_attach_decap(priv, flow, extack);
+		if (err)
+			return err;
+	}
+
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
 		int mirred_ifindex;
 
@@ -1408,6 +1427,9 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
 		mlx5_fc_destroy(attr->counter_dev, attr->counter);
+
+	if (flow_flag_test(flow, L3_TO_L2_DECAP))
+		mlx5e_detach_decap(priv, flow);
 }
 
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
@@ -1684,6 +1706,17 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr
 	kfree_rcu(e, rcu);
 }
 
+static void mlx5e_decap_dealloc(struct mlx5e_priv *priv,
+				struct mlx5e_decap_entry *d)
+{
+	WARN_ON(!list_empty(&d->flows));
+
+	if (!d->compl_result)
+		mlx5_packet_reformat_dealloc(priv->mdev, d->pkt_reformat);
+
+	kfree_rcu(d, rcu);
+}
+
 void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -1696,6 +1729,18 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
 	mlx5e_encap_dealloc(priv, e);
 }
 
+static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	if (!refcount_dec_and_mutex_lock(&d->refcnt, &esw->offloads.decap_tbl_lock))
+		return;
+	hash_del_rcu(&d->hlist);
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+
+	mlx5e_decap_dealloc(priv, d);
+}
+
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow, int out_index)
 {
@@ -1719,6 +1764,29 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 	mlx5e_encap_dealloc(priv, e);
 }
 
+static void mlx5e_detach_decap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_decap_entry *d = flow->decap_reformat;
+
+	if (!d)
+		return;
+
+	mutex_lock(&esw->offloads.decap_tbl_lock);
+	list_del(&flow->l3_to_l2_reformat);
+	flow->decap_reformat = NULL;
+
+	if (!refcount_dec_and_test(&d->refcnt)) {
+		mutex_unlock(&esw->offloads.decap_tbl_lock);
+		return;
+	}
+	hash_del_rcu(&d->hlist);
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+
+	mlx5e_decap_dealloc(priv, d);
+}
+
 static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch;
@@ -1990,7 +2058,11 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			return err;
 		}
 
-		flow->esw_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+		/* With mpls over udp we decapsulate using packet reformat
+		 * object
+		 */
+		if (!netif_is_bareudp(filter_dev))
+			flow->esw_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
 	}
 
 	if (!needs_mapping && !sets_mapping)
@@ -3285,12 +3357,22 @@ static inline int cmp_encap_info(struct encap_key *a,
 	       a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type;
 }
 
+static inline int cmp_decap_info(struct mlx5e_decap_key *a,
+				 struct mlx5e_decap_key *b)
+{
+	return memcmp(&a->key, &b->key, sizeof(b->key));
+}
+
 static inline int hash_encap_info(struct encap_key *key)
 {
 	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
 		     key->tc_tunnel->tunnel_type);
 }
 
+static inline int hash_decap_info(struct mlx5e_decap_key *key)
+{
+	return jhash(&key->key, sizeof(key->key), 0);
+}
 
 static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 				  struct net_device *peer_netdev)
@@ -3305,13 +3387,16 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 		same_hw_devs(priv, peer_priv));
 }
 
-
-
 bool mlx5e_encap_take(struct mlx5e_encap_entry *e)
 {
 	return refcount_inc_not_zero(&e->refcnt);
 }
 
+static bool mlx5e_decap_take(struct mlx5e_decap_entry *e)
+{
+	return refcount_inc_not_zero(&e->refcnt);
+}
+
 static struct mlx5e_encap_entry *
 mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
 		uintptr_t hash_key)
@@ -3332,6 +3417,24 @@ mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
 	return NULL;
 }
 
+static struct mlx5e_decap_entry *
+mlx5e_decap_get(struct mlx5e_priv *priv, struct mlx5e_decap_key *key,
+		uintptr_t hash_key)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5e_decap_key r_key;
+	struct mlx5e_decap_entry *e;
+
+	hash_for_each_possible_rcu(esw->offloads.decap_tbl, e,
+				   hlist, hash_key) {
+		r_key = e->key;
+		if (!cmp_decap_info(&r_key, key) &&
+		    mlx5e_decap_take(e))
+			return e;
+	}
+	return NULL;
+}
+
 static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info)
 {
 	size_t tun_size = sizeof(*tun_info) + tun_info->options_len;
@@ -3477,6 +3580,84 @@ out_err_init:
 	return err;
 }
 
+static int mlx5e_attach_decap(struct mlx5e_priv *priv,
+			      struct mlx5e_tc_flow *flow,
+			      struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5e_decap_entry *d;
+	struct mlx5e_decap_key key;
+	uintptr_t hash_key;
+	int err;
+
+	parse_attr = attr->parse_attr;
+	if (sizeof(parse_attr->eth) > MLX5_CAP_ESW(priv->mdev, max_encap_header_size)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "encap header larger than max supported");
+		return -EOPNOTSUPP;
+	}
+
+	key.key = parse_attr->eth;
+	hash_key = hash_decap_info(&key);
+	mutex_lock(&esw->offloads.decap_tbl_lock);
+	d = mlx5e_decap_get(priv, &key, hash_key);
+	if (d) {
+		mutex_unlock(&esw->offloads.decap_tbl_lock);
+		wait_for_completion(&d->res_ready);
+		mutex_lock(&esw->offloads.decap_tbl_lock);
+		if (d->compl_result) {
+			err = -EREMOTEIO;
+			goto out_free;
+		}
+		goto found;
+	}
+
+	d = kzalloc(sizeof(*d), GFP_KERNEL);
+	if (!d) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	d->key = key;
+	refcount_set(&d->refcnt, 1);
+	init_completion(&d->res_ready);
+	INIT_LIST_HEAD(&d->flows);
+	hash_add_rcu(esw->offloads.decap_tbl, &d->hlist, hash_key);
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+
+	d->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
+						     MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2,
+						     sizeof(parse_attr->eth),
+						     &parse_attr->eth,
+						     MLX5_FLOW_NAMESPACE_FDB);
+	if (IS_ERR(d->pkt_reformat)) {
+		err = PTR_ERR(d->pkt_reformat);
+		d->compl_result = err;
+	}
+	mutex_lock(&esw->offloads.decap_tbl_lock);
+	complete_all(&d->res_ready);
+	if (err)
+		goto out_free;
+
+found:
+	flow->decap_reformat = d;
+	attr->decap_pkt_reformat = d->pkt_reformat;
+	list_add(&flow->l3_to_l2_reformat, &d->flows);
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+	return 0;
+
+out_free:
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+	mlx5e_decap_put(priv, d);
+	return err;
+
+out_err:
+	mutex_unlock(&esw->offloads.decap_tbl_lock);
+	return err;
+}
+
 static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 				const struct flow_action_entry *act,
 				struct mlx5_esw_flow_attr *attr,
@@ -3688,7 +3869,8 @@ static int verify_uplink_forwarding(struct mlx5e_priv *priv,
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				struct flow_action *flow_action,
 				struct mlx5e_tc_flow *flow,
-				struct netlink_ext_ack *extack)
+				struct netlink_ext_ack *extack,
+				struct net_device *filter_dev)
 {
 	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -3727,8 +3909,32 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			}
 			mpls_push = true;
 			break;
+		case FLOW_ACTION_MPLS_POP:
+			/* we only support mpls pop if it is the first action
+			 * and the filter net device is bareudp. Subsequent
+			 * actions can be pedit and the last can be mirred
+			 * egress redirect.
+			 */
+			if (i) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "mpls pop supported only as first action");
+				return -EOPNOTSUPP;
+			}
+			if (!netif_is_bareudp(filter_dev)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "mpls pop supported only on bareudp devices");
+				return -EOPNOTSUPP;
+			}
+
+			parse_attr->eth.h_proto = act->mpls_pop.proto;
+			action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+			flow_flag_set(flow, L3_TO_L2_DECAP);
+			break;
 		case FLOW_ACTION_MANGLE:
 		case FLOW_ACTION_ADD:
+			if (flow_flag_test(flow, L3_TO_L2_DECAP))
+				return -EOPNOTSUPP;
+
 			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB,
 						    hdrs, extack);
 			if (err)
@@ -4093,6 +4299,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 		INIT_LIST_HEAD(&flow->encaps[out_index].list);
 	INIT_LIST_HEAD(&flow->mod_hdr);
 	INIT_LIST_HEAD(&flow->hairpin);
+	INIT_LIST_HEAD(&flow->l3_to_l2_reformat);
 	refcount_set(&flow->refcnt, 1);
 	init_completion(&flow->init_done);
 
@@ -4162,7 +4369,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
+	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev);
 	if (err)
 		goto err_free;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c5eb4e7754a9..ac79b7c9aeb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2262,6 +2262,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	hash_init(esw->offloads.encap_tbl);
 	mutex_init(&esw->offloads.mod_hdr.lock);
 	hash_init(esw->offloads.mod_hdr.hlist);
+	mutex_init(&esw->offloads.decap_tbl_lock);
+	hash_init(esw->offloads.decap_tbl);
 	atomic64_set(&esw->offloads.num_flows, 0);
 	mutex_init(&esw->state_lock);
 	mutex_init(&esw->mode_lock);
@@ -2303,6 +2305,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	mutex_destroy(&esw->state_lock);
 	mutex_destroy(&esw->offloads.mod_hdr.lock);
 	mutex_destroy(&esw->offloads.encap_tbl_lock);
+	mutex_destroy(&esw->offloads.decap_tbl_lock);
 	kfree(esw->vports);
 	kfree(esw);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4a1c6c78bb14..ccbbea3e0505 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -209,6 +209,8 @@ struct mlx5_esw_offload {
 	struct mutex peer_mutex;
 	struct mutex encap_tbl_lock; /* protects encap_tbl */
 	DECLARE_HASHTABLE(encap_tbl, 8);
+	struct mutex decap_tbl_lock; /* protects decap_tbl */
+	DECLARE_HASHTABLE(decap_tbl, 8);
 	struct mod_hdr_tbl mod_hdr;
 	DECLARE_HASHTABLE(termtbl_tbl, 8);
 	struct mutex termtbl_mutex; /* protects termtbl hash */
@@ -432,6 +434,7 @@ struct mlx5_esw_flow_attr {
 	struct mlx5_flow_table *fdb;
 	struct mlx5_flow_table *dest_ft;
 	struct mlx5_ct_attr ct_attr;
+	struct mlx5_pkt_reformat *decap_pkt_reformat;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1c9be19ee025..554fc64d8ef6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -366,6 +366,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 			}
 		}
 	}
+
+	if (attr->decap_pkt_reformat)
+		flow_act.pkt_reformat = attr->decap_pkt_reformat;
+
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 		dest[i].counter_id = mlx5_fc_id(attr->counter);
-- 
cgit v1.2.3


From 582234b465edfa12835b20477c0aa2bc91a02e18 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 8 Apr 2020 09:01:33 +0300
Subject: net/mlx5e: Support pedit on mpls over UDP decap

Allow to modify ethernet headers while decapsulating mpls over UDP
packets. This is implemented using the same reformat object used for
decapsulation.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 65 ++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a6b18f0444e7..cc669ea450ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2900,10 +2900,12 @@ void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
 
 static const struct pedit_headers zero_masks = {};
 
-static int parse_tc_pedit_action(struct mlx5e_priv *priv,
-				 const struct flow_action_entry *act, int namespace,
-				 struct pedit_headers_action *hdrs,
-				 struct netlink_ext_ack *extack)
+static int
+parse_pedit_to_modify_hdr(struct mlx5e_priv *priv,
+			  const struct flow_action_entry *act, int namespace,
+			  struct mlx5e_tc_flow_parse_attr *parse_attr,
+			  struct pedit_headers_action *hdrs,
+			  struct netlink_ext_ack *extack)
 {
 	u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1;
 	int err = -EOPNOTSUPP;
@@ -2939,6 +2941,46 @@ out_err:
 	return err;
 }
 
+static int
+parse_pedit_to_reformat(struct mlx5e_priv *priv,
+			const struct flow_action_entry *act,
+			struct mlx5e_tc_flow_parse_attr *parse_attr,
+			struct netlink_ext_ack *extack)
+{
+	u32 mask, val, offset;
+	u32 *p;
+
+	if (act->id != FLOW_ACTION_MANGLE)
+		return -EOPNOTSUPP;
+
+	if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) {
+		NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported");
+		return -EOPNOTSUPP;
+	}
+
+	mask = ~act->mangle.mask;
+	val = act->mangle.val;
+	offset = act->mangle.offset;
+	p = (u32 *)&parse_attr->eth;
+	*(p + (offset >> 2)) |= (val & mask);
+
+	return 0;
+}
+
+static int parse_tc_pedit_action(struct mlx5e_priv *priv,
+				 const struct flow_action_entry *act, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
+				 struct mlx5e_tc_flow *flow,
+				 struct netlink_ext_ack *extack)
+{
+	if (flow && flow_flag_test(flow, L3_TO_L2_DECAP))
+		return parse_pedit_to_reformat(priv, act, parse_attr, extack);
+
+	return parse_pedit_to_modify_hdr(priv, act, namespace,
+					 parse_attr, hdrs, extack);
+}
+
 static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr,
 				 struct pedit_headers_action *hdrs,
@@ -3197,7 +3239,7 @@ static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace,
 		return -EOPNOTSUPP;
 	}
 
-	err = parse_tc_pedit_action(priv, &pedit_act, namespace, hdrs, NULL);
+	err = parse_tc_pedit_action(priv, &pedit_act, namespace, parse_attr, hdrs, NULL, extack);
 	*action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 
 	return err;
@@ -3263,7 +3305,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 		case FLOW_ACTION_MANGLE:
 		case FLOW_ACTION_ADD:
 			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL,
-						    hdrs, extack);
+						    parse_attr, hdrs, NULL, extack);
 			if (err)
 				return err;
 
@@ -3932,16 +3974,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			break;
 		case FLOW_ACTION_MANGLE:
 		case FLOW_ACTION_ADD:
-			if (flow_flag_test(flow, L3_TO_L2_DECAP))
-				return -EOPNOTSUPP;
-
 			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB,
-						    hdrs, extack);
+						    parse_attr, hdrs, flow, extack);
 			if (err)
 				return err;
 
-			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			attr->split_count = attr->out_count;
+			if (!flow_flag_test(flow, L3_TO_L2_DECAP)) {
+				action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+				attr->split_count = attr->out_count;
+			}
 			break;
 		case FLOW_ACTION_CSUM:
 			if (csum_offload_supported(priv, action,
-- 
cgit v1.2.3


From 16fdc16c6bff6764fc8c9a5f10640dfdb7ce201a Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:12 -0700
Subject: igc: Refactor igc_ethtool_add_nfc_rule()

Current implementation of igc_ethtool_add_nfc_rule() is quite long and a
bit convoluted so this patch does a code refactoring to improve the
code.

Code related to NFC rule object initialization is refactored out to the
local helper function igc_ethtool_init_nfc_rule(). Likewise, code
related to NFC rule validation is refactored out to another local
helper, igc_ethtool_is_nfc_rule_valid().

RX_CLS_FLOW_DISC check is removed since it is redundant. The macro is
defined as the max value fsp->ring_cookie can have, so checking if
fsp->ring_cookie >= adapter->num_rx_queues is already sufficient.

Finally, some log messages are improved or added, and obvious comments
are removed.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 150 ++++++++++++++++-----------
 1 file changed, 92 insertions(+), 58 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 66e0760a8f9e..1145c88a8e44 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1271,9 +1271,6 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 	if (!input)
 		return err;
 
-	/* initialize node */
-	INIT_HLIST_NODE(&input->nfc_node);
-
 	/* add filter to the list */
 	if (parent)
 		hlist_add_behind(&input->nfc_node, &parent->nfc_node);
@@ -1286,41 +1283,19 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
-				    struct ethtool_rxnfc *cmd)
+static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
+				      const struct ethtool_rx_flow_spec *fsp)
 {
-	struct net_device *netdev = adapter->netdev;
-	struct ethtool_rx_flow_spec *fsp =
-		(struct ethtool_rx_flow_spec *)&cmd->fs;
-	struct igc_nfc_rule *rule, *tmp;
-	int err = 0;
-
-	if (!(netdev->hw_features & NETIF_F_NTUPLE))
-		return -EOPNOTSUPP;
+	INIT_HLIST_NODE(&rule->nfc_node);
 
-	/* Don't allow programming if the action is a queue greater than
-	 * the number of online Rx queues.
-	 */
-	if (fsp->ring_cookie == RX_CLS_FLOW_DISC ||
-	    fsp->ring_cookie >= adapter->num_rx_queues) {
-		netdev_err(netdev,
-			   "ethtool -N: The specified action is invalid\n");
-		return -EINVAL;
-	}
+	rule->action = fsp->ring_cookie;
+	rule->sw_idx = fsp->location;
 
-	/* Don't allow indexes to exist outside of available space */
-	if (fsp->location >= IGC_MAX_RXNFC_RULES) {
-		netdev_err(netdev, "Location out of range\n");
-		return -EINVAL;
+	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
+		rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci);
+		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
 	}
 
-	if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
-		return -EINVAL;
-
-	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
-	if (!rule)
-		return -ENOMEM;
-
 	if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) {
 		rule->filter.etype = ntohs(fsp->h_u.ether_spec.h_proto);
 		rule->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
@@ -1340,51 +1315,110 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 		ether_addr_copy(rule->filter.dst_addr,
 				fsp->h_u.ether_spec.h_dest);
 	}
+}
 
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
-	    rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-		netdev_dbg(netdev, "Filters with both dst and src are not supported\n");
-		err = -EOPNOTSUPP;
-		goto err_out;
-	}
+/**
+ * igc_ethtool_check_nfc_rule() - Check if NFC rule is valid
+ * @adapter: Pointer to adapter
+ * @rule: Rule under evaluation
+ *
+ * Rules with both destination and source MAC addresses are considered invalid
+ * since the driver doesn't support them.
+ *
+ * Also, if there is already another rule with the same filter, @rule is
+ * considered invalid.
+ *
+ * Context: Expects adapter->nfc_rule_lock to be held by caller.
+ *
+ * Return: 0 in case of success, negative errno code otherwise.
+ */
+static int igc_ethtool_check_nfc_rule(struct igc_adapter *adapter,
+				      struct igc_nfc_rule *rule)
+{
+	struct net_device *dev = adapter->netdev;
+	u8 flags = rule->filter.match_flags;
+	struct igc_nfc_rule *tmp;
 
-	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
-		if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
-			netdev_dbg(netdev, "VLAN mask not supported\n");
-			err = -EOPNOTSUPP;
-			goto err_out;
-		}
-		rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci);
-		rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
+	if (!flags) {
+		netdev_dbg(dev, "Rule with no match\n");
+		return -EINVAL;
 	}
 
-	rule->action = fsp->ring_cookie;
-	rule->sw_idx = fsp->location;
-
-	spin_lock(&adapter->nfc_rule_lock);
+	if (flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
+	    flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		netdev_dbg(dev, "Filters with both dst and src are not supported\n");
+		return -EOPNOTSUPP;
+	}
 
 	hlist_for_each_entry(tmp, &adapter->nfc_rule_list, nfc_node) {
 		if (!memcmp(&rule->filter, &tmp->filter,
 			    sizeof(rule->filter))) {
-			err = -EEXIST;
-			netdev_err(netdev,
-				   "ethtool: this filter is already set\n");
-			goto err_out_w_lock;
+			netdev_dbg(dev, "Rule already exists\n");
+			return -EEXIST;
 		}
 	}
 
+	return 0;
+}
+
+static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
+				    struct ethtool_rxnfc *cmd)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct igc_nfc_rule *rule;
+	int err;
+
+	if (!(netdev->hw_features & NETIF_F_NTUPLE)) {
+		netdev_dbg(netdev, "N-tuple filters disabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW) {
+		netdev_dbg(netdev, "Only ethernet flow type is supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if ((fsp->flow_type & FLOW_EXT) &&
+	    fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
+		netdev_dbg(netdev, "VLAN mask not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (fsp->ring_cookie >= adapter->num_rx_queues) {
+		netdev_dbg(netdev, "Invalid action\n");
+		return -EINVAL;
+	}
+
+	if (fsp->location >= IGC_MAX_RXNFC_RULES) {
+		netdev_dbg(netdev, "Invalid location\n");
+		return -EINVAL;
+	}
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
+	igc_ethtool_init_nfc_rule(rule, fsp);
+
+	spin_lock(&adapter->nfc_rule_lock);
+
+	err = igc_ethtool_check_nfc_rule(adapter, rule);
+	if (err)
+		goto err;
+
 	err = igc_enable_nfc_rule(adapter, rule);
 	if (err)
-		goto err_out_w_lock;
+		goto err;
 
 	igc_ethtool_update_nfc_rule(adapter, rule, rule->sw_idx);
 
 	spin_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
-err_out_w_lock:
+err:
 	spin_unlock(&adapter->nfc_rule_lock);
-err_out:
 	kfree(rule);
 	return err;
 }
-- 
cgit v1.2.3


From d3ba9e6f6157e6fa047d853936dabb981e315080 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:13 -0700
Subject: igc: Fix 'sw_idx' type in struct igc_nfc_rule

The 'sw_idx' field from 'struct igc_nfc_rule' is u16 type but it is
assigned an u32 value in igc_ethtool_init_nfc_rule(). This patch changes
'sw_idx' type to u32 so they match. Also, it makes more sense to call
this field 'location' since it holds the NFC rule location.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  2 +-
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 16 ++++++++--------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index fcc6261d7f67..ae7d48070ee2 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -463,7 +463,7 @@ struct igc_nfc_filter {
 struct igc_nfc_rule {
 	struct hlist_node nfc_node;
 	struct igc_nfc_filter filter;
-	u16 sw_idx;
+	u32 location;
 	u16 action;
 };
 
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 1145c88a8e44..24aa321f64b5 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -940,11 +940,11 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 	cmd->data = IGC_MAX_RXNFC_RULES;
 
 	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
-		if (fsp->location <= rule->sw_idx)
+		if (fsp->location <= rule->location)
 			break;
 	}
 
-	if (!rule || fsp->location != rule->sw_idx)
+	if (!rule || fsp->location != rule->location)
 		return -EINVAL;
 
 	if (!rule->filter.match_flags)
@@ -991,7 +991,7 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
 	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		if (cnt == cmd->rule_cnt)
 			return -EMSGSIZE;
-		rule_locs[cnt] = rule->sw_idx;
+		rule_locs[cnt] = rule->location;
 		cnt++;
 	}
 
@@ -1240,7 +1240,7 @@ int igc_disable_nfc_rule(struct igc_adapter *adapter,
 
 static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 				       struct igc_nfc_rule *input,
-				       u16 sw_idx)
+				       u32 location)
 {
 	struct igc_nfc_rule *rule, *parent;
 	int err = -EINVAL;
@@ -1250,13 +1250,13 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 
 	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		/* hash found, or no matching entry */
-		if (rule->sw_idx >= sw_idx)
+		if (rule->location >= location)
 			break;
 		parent = rule;
 	}
 
 	/* if there is an old rule occupying our place remove it */
-	if (rule && rule->sw_idx == sw_idx) {
+	if (rule && rule->location == location) {
 		if (!input)
 			err = igc_disable_nfc_rule(adapter, rule);
 
@@ -1289,7 +1289,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 	INIT_HLIST_NODE(&rule->nfc_node);
 
 	rule->action = fsp->ring_cookie;
-	rule->sw_idx = fsp->location;
+	rule->location = fsp->location;
 
 	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
 		rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci);
@@ -1412,7 +1412,7 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 	if (err)
 		goto err;
 
-	igc_ethtool_update_nfc_rule(adapter, rule, rule->sw_idx);
+	igc_ethtool_update_nfc_rule(adapter, rule, rule->location);
 
 	spin_unlock(&adapter->nfc_rule_lock);
 	return 0;
-- 
cgit v1.2.3


From b500350a36ae6e83a03931723b787b771f411817 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:14 -0700
Subject: igc: Fix locking issue when retrieving NFC rules

Access to NFC rules stored in adapter->nfc_rule_list is protect by
adapter->nfc_rule_lock. The functions igc_ethtool_get_nfc_rule()
and igc_ethtool_get_nfc_rules() are missing to hold the lock while
accessing rule objects.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 24aa321f64b5..decd29fbfbe2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -939,16 +939,18 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 
 	cmd->data = IGC_MAX_RXNFC_RULES;
 
+	spin_lock(&adapter->nfc_rule_lock);
+
 	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
 		if (fsp->location <= rule->location)
 			break;
 	}
 
 	if (!rule || fsp->location != rule->location)
-		return -EINVAL;
+		goto out;
 
 	if (!rule->filter.match_flags)
-		return -EINVAL;
+		goto out;
 
 	fsp->flow_type = ETHER_FLOW;
 	fsp->ring_cookie = rule->action;
@@ -976,7 +978,12 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 		eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
 	}
 
+	spin_unlock(&adapter->nfc_rule_lock);
 	return 0;
+
+out:
+	spin_unlock(&adapter->nfc_rule_lock);
+	return -EINVAL;
 }
 
 static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
@@ -988,13 +995,19 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
 
 	cmd->data = IGC_MAX_RXNFC_RULES;
 
+	spin_lock(&adapter->nfc_rule_lock);
+
 	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
-		if (cnt == cmd->rule_cnt)
+		if (cnt == cmd->rule_cnt) {
+			spin_unlock(&adapter->nfc_rule_lock);
 			return -EMSGSIZE;
+		}
 		rule_locs[cnt] = rule->location;
 		cnt++;
 	}
 
+	spin_unlock(&adapter->nfc_rule_lock);
+
 	cmd->rule_cnt = cnt;
 
 	return 0;
-- 
cgit v1.2.3


From 4bdf89e85ed3881e8c40510ebad918dded9e5831 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:15 -0700
Subject: igc: Fix NFC rule overwrite cases

When the 'loc' argument is passed in ethtool, the input rule overwrites
any rule present in that location. In this situation we must disable the
old rule otherwise it is left enabled in hardware. This patch fixes
the issue by always calling igc_disable_nfc_rule() when deleting the
old rule, no matter the value of 'input' argument.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index decd29fbfbe2..f01a7ec0c1c2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1270,8 +1270,7 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 
 	/* if there is an old rule occupying our place remove it */
 	if (rule && rule->location == location) {
-		if (!input)
-			err = igc_disable_nfc_rule(adapter, rule);
+		err = igc_disable_nfc_rule(adapter, rule);
 
 		hlist_del(&rule->nfc_node);
 		kfree(rule);
-- 
cgit v1.2.3


From 39707c16e6b34fb70b3f170d5733245256d768e5 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:16 -0700
Subject: igc: Fix NFC rules with multicast addresses

Multicast MAC addresses are valid address for NFC rules but
igc_add_mac_filter() is currently rejecting them. In fact, the I225
controller doesn't impose any constraint on the address value so this
patch gets rid of the address validation check in MAC filter APIs.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f48d6127a220..acb8dfdf275f 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2249,9 +2249,6 @@ int igc_add_mac_filter(struct igc_adapter *adapter,
 	struct net_device *dev = adapter->netdev;
 	int index;
 
-	if (!is_valid_ether_addr(addr))
-		return -EINVAL;
-
 	index = igc_find_mac_filter(adapter, type, addr);
 	if (index >= 0)
 		goto update_filter;
@@ -2283,9 +2280,6 @@ int igc_del_mac_filter(struct igc_adapter *adapter,
 	struct net_device *dev = adapter->netdev;
 	int index;
 
-	if (!is_valid_ether_addr(addr))
-		return -EINVAL;
-
 	index = igc_find_mac_filter(adapter, type, addr);
 	if (index < 0)
 		return -ENOENT;
-- 
cgit v1.2.3


From d957c6010a907d86d41d1bee024a9827e385c4fa Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:17 -0700
Subject: igc: Fix NFC rules restoration

When network interface is brought up, the driver re-enables the NFC
rules previously configured. However, this is done in reverse order
the rules were added and hardware filters are configured differently.

For example, consider the following rules:

$ ethtool -N eth0 flow-type ether dst 00:00:00:00:00:AA queue 0
$ ethtool -N eth0 flow-type ether dst 00:00:00:00:00:BB queue 1
$ ethtool -N eth0 flow-type ether dst 00:00:00:00:00:CC queue 2
$ ethtool -N eth0 flow-type ether dst 00:00:00:00:00:DD queue 3

RAL/RAH registers are configure so filter index 1 has address ending
with AA, filter index 2 has address ending in BB, and so on.

If we bring the interface down and up again, RAL/RAH registers are
configured so filter index 1 has address ending in DD, filter index 2
has CC, and so on. IOW, in reverse order we had before bringing the
interface down.

This issue can be fixed by traversing adapter->nfc_rule_list in
backwards when restoring the rules. Since hlist doesn't support
backwards traversal, this patch replaces it by list_head and fixes
igc_restore_nfc_rules() accordingly.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  4 ++--
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 19 ++++++++-----------
 drivers/net/ethernet/intel/igc/igc_main.c    | 16 +++++++++-------
 3 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index ae7d48070ee2..76bc3a51ad70 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -191,7 +191,7 @@ struct igc_adapter {
 	 * nfc_rule_lock.
 	 */
 	spinlock_t nfc_rule_lock;
-	struct hlist_head nfc_rule_list;
+	struct list_head nfc_rule_list;
 	unsigned int nfc_rule_count;
 
 	u8 rss_indir_tbl[IGC_RETA_SIZE];
@@ -461,7 +461,7 @@ struct igc_nfc_filter {
 };
 
 struct igc_nfc_rule {
-	struct hlist_node nfc_node;
+	struct list_head list;
 	struct igc_nfc_filter filter;
 	u32 location;
 	u16 action;
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index f01a7ec0c1c2..a90493fee0d2 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -941,7 +941,7 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 
 	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
 		if (fsp->location <= rule->location)
 			break;
 	}
@@ -997,7 +997,7 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
 
 	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
 		if (cnt == cmd->rule_cnt) {
 			spin_unlock(&adapter->nfc_rule_lock);
 			return -EMSGSIZE;
@@ -1261,7 +1261,7 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 	parent = NULL;
 	rule = NULL;
 
-	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node) {
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
 		/* hash found, or no matching entry */
 		if (rule->location >= location)
 			break;
@@ -1272,7 +1272,7 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 	if (rule && rule->location == location) {
 		err = igc_disable_nfc_rule(adapter, rule);
 
-		hlist_del(&rule->nfc_node);
+		list_del(&rule->list);
 		kfree(rule);
 		adapter->nfc_rule_count--;
 	}
@@ -1283,11 +1283,8 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 	if (!input)
 		return err;
 
-	/* add filter to the list */
-	if (parent)
-		hlist_add_behind(&input->nfc_node, &parent->nfc_node);
-	else
-		hlist_add_head(&input->nfc_node, &adapter->nfc_rule_list);
+	list_add(&input->list, parent ? &parent->list :
+					&adapter->nfc_rule_list);
 
 	/* update counts */
 	adapter->nfc_rule_count++;
@@ -1298,7 +1295,7 @@ static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
 static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 				      const struct ethtool_rx_flow_spec *fsp)
 {
-	INIT_HLIST_NODE(&rule->nfc_node);
+	INIT_LIST_HEAD(&rule->list);
 
 	rule->action = fsp->ring_cookie;
 	rule->location = fsp->location;
@@ -1362,7 +1359,7 @@ static int igc_ethtool_check_nfc_rule(struct igc_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
-	hlist_for_each_entry(tmp, &adapter->nfc_rule_list, nfc_node) {
+	list_for_each_entry(tmp, &adapter->nfc_rule_list, list) {
 		if (!memcmp(&rule->filter, &tmp->filter,
 			    sizeof(rule->filter))) {
 			netdev_dbg(dev, "Rule already exists\n");
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index acb8dfdf275f..cf76e2c1f9b1 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2180,7 +2180,7 @@ static void igc_restore_nfc_rules(struct igc_adapter *adapter)
 
 	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node)
+	list_for_each_entry_reverse(rule, &adapter->nfc_rule_list, list)
 		igc_enable_nfc_rule(adapter, rule);
 
 	spin_unlock(&adapter->nfc_rule_lock);
@@ -3419,6 +3419,9 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
 	spin_lock_init(&adapter->nfc_rule_lock);
+	INIT_LIST_HEAD(&adapter->nfc_rule_list);
+	adapter->nfc_rule_count = 0;
+
 	spin_lock_init(&adapter->stats64_lock);
 	/* Assume MSI-X interrupts, will be checked during IRQ allocation */
 	adapter->flags |= IGC_FLAG_HAS_MSIX;
@@ -3651,7 +3654,7 @@ static void igc_nfc_rule_exit(struct igc_adapter *adapter)
 
 	spin_lock(&adapter->nfc_rule_lock);
 
-	hlist_for_each_entry(rule, &adapter->nfc_rule_list, nfc_node)
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list)
 		igc_disable_nfc_rule(adapter, rule);
 
 	spin_unlock(&adapter->nfc_rule_lock);
@@ -3826,14 +3829,13 @@ static int igc_set_features(struct net_device *netdev,
 		return 0;
 
 	if (!(features & NETIF_F_NTUPLE)) {
-		struct hlist_node *node2;
-		struct igc_nfc_rule *rule;
+		struct igc_nfc_rule *rule, *tmp;
 
 		spin_lock(&adapter->nfc_rule_lock);
-		hlist_for_each_entry_safe(rule, node2,
-					  &adapter->nfc_rule_list, nfc_node) {
+		list_for_each_entry_safe(rule, tmp,
+					 &adapter->nfc_rule_list, list) {
 			igc_disable_nfc_rule(adapter, rule);
-			hlist_del(&rule->nfc_node);
+			list_del(&rule->list);
 			kfree(rule);
 		}
 		spin_unlock(&adapter->nfc_rule_lock);
-- 
cgit v1.2.3


From 36fa21520f33317fe51bf80bc154873e922c2a26 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:18 -0700
Subject: igc: Refactor igc_ethtool_update_nfc_rule()

Current implementation of igc_ethtool_update_nfc_rule() is a bit
convoluted since it handles too many things: rule lookup, deletion
and addition. This patch breaks it into three functions so we simplify
the code and improve code reuse.

Code related to rule lookup is refactored out to a new function called
igc_get_nfc_rule().

Code related to rule addition is refactored out to a new function called
igc_add_nfc_rule(). This function enables the rule in hardware and adds
it to the adapter's list.

Code related to rule deletion is refactored out to a new function called
igc_del_nfc_rule(). This function disables the rule in hardware, removes
it from adapter's list, and deletes it.

As a byproduct of this refactoring, igc_enable_nfc_rule() and
igc_disable_nfc_rule() are moved to igc_main.c since they are not used
in igc_ethtool.c anymore, and igc_restore_nfc_rules() and igc_nfc_rule_
exit() are moved around to avoid forward declaration.

Also, since this patch already touches igc_ethtool_get_nfc_rule(), it
takes the opportunity to remove the 'match_flags' check. Empty flags
are not allowed to be added so no need to check that.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  18 +--
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 138 +++---------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 205 ++++++++++++++++++++++-----
 3 files changed, 195 insertions(+), 166 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 76bc3a51ad70..a484b328268b 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -232,16 +232,6 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
 bool igc_has_link(struct igc_adapter *adapter);
 void igc_reset(struct igc_adapter *adapter);
 int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
-int igc_add_mac_filter(struct igc_adapter *adapter,
-		       enum igc_mac_filter_type type, const u8 *addr,
-		       int queue);
-int igc_del_mac_filter(struct igc_adapter *adapter,
-		       enum igc_mac_filter_type type, const u8 *addr);
-int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
-			     int queue);
-void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio);
-int igc_add_etype_filter(struct igc_adapter *adapter, u16 etype, int queue);
-int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype);
 void igc_update_stats(struct igc_adapter *adapter);
 
 /* igc_dump declarations */
@@ -544,10 +534,10 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
 }
 
 void igc_reinit_locked(struct igc_adapter *);
-int igc_enable_nfc_rule(struct igc_adapter *adapter,
-			const struct igc_nfc_rule *rule);
-int igc_disable_nfc_rule(struct igc_adapter *adapter,
-			 const struct igc_nfc_rule *rule);
+struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter,
+				      u32 location);
+int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
+void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule);
 
 void igc_ptp_init(struct igc_adapter *adapter);
 void igc_ptp_reset(struct igc_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index a90493fee0d2..43dff09a8f86 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -941,15 +941,8 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 
 	spin_lock(&adapter->nfc_rule_lock);
 
-	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
-		if (fsp->location <= rule->location)
-			break;
-	}
-
-	if (!rule || fsp->location != rule->location)
-		goto out;
-
-	if (!rule->filter.match_flags)
+	rule = igc_get_nfc_rule(adapter, fsp->location);
+	if (!rule)
 		goto out;
 
 	fsp->flow_type = ETHER_FLOW;
@@ -1190,108 +1183,6 @@ static int igc_ethtool_set_rss_hash_opt(struct igc_adapter *adapter,
 	return 0;
 }
 
-int igc_enable_nfc_rule(struct igc_adapter *adapter,
-			const struct igc_nfc_rule *rule)
-{
-	int err = -EINVAL;
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
-		err = igc_add_etype_filter(adapter, rule->filter.etype,
-					   rule->action);
-		if (err)
-			return err;
-	}
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
-					 rule->filter.src_addr, rule->action);
-		if (err)
-			return err;
-	}
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
-		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
-					 rule->filter.dst_addr, rule->action);
-		if (err)
-			return err;
-	}
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
-			   VLAN_PRIO_SHIFT;
-
-		err = igc_add_vlan_prio_filter(adapter, prio, rule->action);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-int igc_disable_nfc_rule(struct igc_adapter *adapter,
-			 const struct igc_nfc_rule *rule)
-{
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
-		igc_del_etype_filter(adapter, rule->filter.etype);
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
-		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
-			   VLAN_PRIO_SHIFT;
-		igc_del_vlan_prio_filter(adapter, prio);
-	}
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
-		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
-				   rule->filter.src_addr);
-
-	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
-		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
-				   rule->filter.dst_addr);
-
-	return 0;
-}
-
-static int igc_ethtool_update_nfc_rule(struct igc_adapter *adapter,
-				       struct igc_nfc_rule *input,
-				       u32 location)
-{
-	struct igc_nfc_rule *rule, *parent;
-	int err = -EINVAL;
-
-	parent = NULL;
-	rule = NULL;
-
-	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
-		/* hash found, or no matching entry */
-		if (rule->location >= location)
-			break;
-		parent = rule;
-	}
-
-	/* if there is an old rule occupying our place remove it */
-	if (rule && rule->location == location) {
-		err = igc_disable_nfc_rule(adapter, rule);
-
-		list_del(&rule->list);
-		kfree(rule);
-		adapter->nfc_rule_count--;
-	}
-
-	/* If no input this was a delete, err should be 0 if a rule was
-	 * successfully found and removed from the list else -EINVAL
-	 */
-	if (!input)
-		return err;
-
-	list_add(&input->list, parent ? &parent->list :
-					&adapter->nfc_rule_list);
-
-	/* update counts */
-	adapter->nfc_rule_count++;
-
-	return 0;
-}
-
 static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
 				      const struct ethtool_rx_flow_spec *fsp)
 {
@@ -1376,7 +1267,7 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 	struct net_device *netdev = adapter->netdev;
 	struct ethtool_rx_flow_spec *fsp =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
-	struct igc_nfc_rule *rule;
+	struct igc_nfc_rule *rule, *old_rule;
 	int err;
 
 	if (!(netdev->hw_features & NETIF_F_NTUPLE)) {
@@ -1417,12 +1308,14 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 	if (err)
 		goto err;
 
-	err = igc_enable_nfc_rule(adapter, rule);
+	old_rule = igc_get_nfc_rule(adapter, fsp->location);
+	if (old_rule)
+		igc_del_nfc_rule(adapter, old_rule);
+
+	err = igc_add_nfc_rule(adapter, rule);
 	if (err)
 		goto err;
 
-	igc_ethtool_update_nfc_rule(adapter, rule, rule->location);
-
 	spin_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
@@ -1437,13 +1330,20 @@ static int igc_ethtool_del_nfc_rule(struct igc_adapter *adapter,
 {
 	struct ethtool_rx_flow_spec *fsp =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
-	int err;
+	struct igc_nfc_rule *rule;
 
 	spin_lock(&adapter->nfc_rule_lock);
-	err = igc_ethtool_update_nfc_rule(adapter, NULL, fsp->location);
-	spin_unlock(&adapter->nfc_rule_lock);
 
-	return err;
+	rule = igc_get_nfc_rule(adapter, fsp->location);
+	if (!rule) {
+		spin_unlock(&adapter->nfc_rule_lock);
+		return -EINVAL;
+	}
+
+	igc_del_nfc_rule(adapter, rule);
+
+	spin_unlock(&adapter->nfc_rule_lock);
+	return 0;
 }
 
 static int igc_ethtool_set_rxnfc(struct net_device *dev,
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index cf76e2c1f9b1..ad9217335a64 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2174,18 +2174,6 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 	return !!budget;
 }
 
-static void igc_restore_nfc_rules(struct igc_adapter *adapter)
-{
-	struct igc_nfc_rule *rule;
-
-	spin_lock(&adapter->nfc_rule_lock);
-
-	list_for_each_entry_reverse(rule, &adapter->nfc_rule_list, list)
-		igc_enable_nfc_rule(adapter, rule);
-
-	spin_unlock(&adapter->nfc_rule_lock);
-}
-
 static int igc_find_mac_filter(struct igc_adapter *adapter,
 			       enum igc_mac_filter_type type, const u8 *addr)
 {
@@ -2242,9 +2230,9 @@ static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter)
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_add_mac_filter(struct igc_adapter *adapter,
-		       enum igc_mac_filter_type type, const u8 *addr,
-		       int queue)
+static int igc_add_mac_filter(struct igc_adapter *adapter,
+			      enum igc_mac_filter_type type, const u8 *addr,
+			      int queue)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
@@ -2274,8 +2262,8 @@ update_filter:
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_del_mac_filter(struct igc_adapter *adapter,
-		       enum igc_mac_filter_type type, const u8 *addr)
+static int igc_del_mac_filter(struct igc_adapter *adapter,
+			      enum igc_mac_filter_type type, const u8 *addr)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
@@ -2312,7 +2300,8 @@ int igc_del_mac_filter(struct igc_adapter *adapter,
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio, int queue)
+static int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio,
+				    int queue)
 {
 	struct net_device *dev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
@@ -2340,7 +2329,7 @@ int igc_add_vlan_prio_filter(struct igc_adapter *adapter, int prio, int queue)
  * @adapter: Pointer to adapter where the filter should be deleted from
  * @prio: VLAN priority value
  */
-void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio)
+static void igc_del_vlan_prio_filter(struct igc_adapter *adapter, int prio)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 vlanpqf;
@@ -2381,7 +2370,8 @@ static int igc_get_avail_etype_filter_slot(struct igc_adapter *adapter)
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_add_etype_filter(struct igc_adapter *adapter, u16 etype, int queue)
+static int igc_add_etype_filter(struct igc_adapter *adapter, u16 etype,
+				int queue)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int index;
@@ -2433,7 +2423,7 @@ static int igc_find_etype_filter(struct igc_adapter *adapter, u16 etype)
  *
  * Return: 0 in case of success, negative errno code otherwise.
  */
-int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
+static int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int index;
@@ -2449,6 +2439,167 @@ int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
 	return 0;
 }
 
+static int igc_enable_nfc_rule(struct igc_adapter *adapter,
+			       const struct igc_nfc_rule *rule)
+{
+	int err;
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		err = igc_add_etype_filter(adapter, rule->filter.etype,
+					   rule->action);
+		if (err)
+			return err;
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
+					 rule->filter.src_addr, rule->action);
+		if (err)
+			return err;
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+		err = igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
+					 rule->filter.dst_addr, rule->action);
+		if (err)
+			return err;
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
+			   VLAN_PRIO_SHIFT;
+
+		err = igc_add_vlan_prio_filter(adapter, prio, rule->action);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int igc_disable_nfc_rule(struct igc_adapter *adapter,
+				const struct igc_nfc_rule *rule)
+{
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
+		igc_del_etype_filter(adapter, rule->filter.etype);
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+		int prio = (rule->filter.vlan_tci & VLAN_PRIO_MASK) >>
+			   VLAN_PRIO_SHIFT;
+
+		igc_del_vlan_prio_filter(adapter, prio);
+	}
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_SRC,
+				   rule->filter.src_addr);
+
+	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
+		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
+				   rule->filter.dst_addr);
+
+	return 0;
+}
+
+/**
+ * igc_get_nfc_rule() - Get NFC rule
+ * @adapter: Pointer to adapter
+ * @location: Rule location
+ *
+ * Context: Expects adapter->nfc_rule_lock to be held by caller.
+ *
+ * Return: Pointer to NFC rule at @location. If not found, NULL.
+ */
+struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter,
+				      u32 location)
+{
+	struct igc_nfc_rule *rule;
+
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
+		if (rule->location == location)
+			return rule;
+		if (rule->location > location)
+			break;
+	}
+
+	return NULL;
+}
+
+/**
+ * igc_del_nfc_rule() - Delete NFC rule
+ * @adapter: Pointer to adapter
+ * @rule: Pointer to rule to be deleted
+ *
+ * Disable NFC rule in hardware and delete it from adapter.
+ *
+ * Context: Expects adapter->nfc_rule_lock to be held by caller.
+ */
+void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule)
+{
+	igc_disable_nfc_rule(adapter, rule);
+
+	list_del(&rule->list);
+	adapter->nfc_rule_count--;
+
+	kfree(rule);
+}
+
+/**
+ * igc_add_nfc_rule() - Add NFC rule
+ * @adapter: Pointer to adapter
+ * @rule: Pointer to rule to be added
+ *
+ * Enable NFC rule in hardware and add it to adapter.
+ *
+ * Context: Expects adapter->nfc_rule_lock to be held by caller.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule)
+{
+	struct igc_nfc_rule *pred, *cur;
+	int err;
+
+	err = igc_enable_nfc_rule(adapter, rule);
+	if (err)
+		return err;
+
+	pred = NULL;
+	list_for_each_entry(cur, &adapter->nfc_rule_list, list) {
+		if (cur->location >= rule->location)
+			break;
+		pred = cur;
+	}
+
+	list_add(&rule->list, pred ? &pred->list : &adapter->nfc_rule_list);
+	adapter->nfc_rule_count++;
+	return 0;
+}
+
+static void igc_restore_nfc_rules(struct igc_adapter *adapter)
+{
+	struct igc_nfc_rule *rule;
+
+	spin_lock(&adapter->nfc_rule_lock);
+
+	list_for_each_entry_reverse(rule, &adapter->nfc_rule_list, list)
+		igc_enable_nfc_rule(adapter, rule);
+
+	spin_unlock(&adapter->nfc_rule_lock);
+}
+
+static void igc_nfc_rule_exit(struct igc_adapter *adapter)
+{
+	struct igc_nfc_rule *rule;
+
+	spin_lock(&adapter->nfc_rule_lock);
+
+	list_for_each_entry(rule, &adapter->nfc_rule_list, list)
+		igc_disable_nfc_rule(adapter, rule);
+
+	spin_unlock(&adapter->nfc_rule_lock);
+}
+
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
@@ -3648,18 +3799,6 @@ void igc_update_stats(struct igc_adapter *adapter)
 	adapter->stats.mgpdc += rd32(IGC_MGTPDC);
 }
 
-static void igc_nfc_rule_exit(struct igc_adapter *adapter)
-{
-	struct igc_nfc_rule *rule;
-
-	spin_lock(&adapter->nfc_rule_lock);
-
-	list_for_each_entry(rule, &adapter->nfc_rule_list, list)
-		igc_disable_nfc_rule(adapter, rule);
-
-	spin_unlock(&adapter->nfc_rule_lock);
-}
-
 /**
  * igc_down - Close the interface
  * @adapter: board private structure
-- 
cgit v1.2.3


From e256ec83fabd5803a576c46e03289e519d087fda Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:19 -0700
Subject: igc: Fix NFC rules leak when driver is unloaded

If we have RFC rules in adapter->nfc_rule_list when the IGC driver
is unloaded, all rules are leaked. This patch fixes the issue by
introducing the helper igc_flush_nfc_rules() and calling it in
igc_remove(). It also updates igc_set_features() so is reuses the
new helper instead of re-implementing it.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ad9217335a64..0a6f880e3538 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2544,6 +2544,18 @@ void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule)
 	kfree(rule);
 }
 
+static void igc_flush_nfc_rules(struct igc_adapter *adapter)
+{
+	struct igc_nfc_rule *rule, *tmp;
+
+	spin_lock(&adapter->nfc_rule_lock);
+
+	list_for_each_entry_safe(rule, tmp, &adapter->nfc_rule_list, list)
+		igc_del_nfc_rule(adapter, rule);
+
+	spin_unlock(&adapter->nfc_rule_lock);
+}
+
 /**
  * igc_add_nfc_rule() - Add NFC rule
  * @adapter: Pointer to adapter
@@ -3967,19 +3979,8 @@ static int igc_set_features(struct net_device *netdev,
 	if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE)))
 		return 0;
 
-	if (!(features & NETIF_F_NTUPLE)) {
-		struct igc_nfc_rule *rule, *tmp;
-
-		spin_lock(&adapter->nfc_rule_lock);
-		list_for_each_entry_safe(rule, tmp,
-					 &adapter->nfc_rule_list, list) {
-			igc_disable_nfc_rule(adapter, rule);
-			list_del(&rule->list);
-			kfree(rule);
-		}
-		spin_unlock(&adapter->nfc_rule_lock);
-		adapter->nfc_rule_count = 0;
-	}
+	if (!(features & NETIF_F_NTUPLE))
+		igc_flush_nfc_rules(adapter);
 
 	netdev->features = features;
 
@@ -5246,6 +5247,8 @@ static void igc_remove(struct pci_dev *pdev)
 
 	pm_runtime_get_noresume(&pdev->dev);
 
+	igc_flush_nfc_rules(adapter);
+
 	igc_ptp_stop(adapter);
 
 	set_bit(__IGC_DOWN, &adapter->state);
-- 
cgit v1.2.3


From 1894df0ccb6ac7ba8b2c799e7d74b5db1180c518 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:20 -0700
Subject: igc: Fix NFC rule validation

If we try to overwrite an existing rule with the same filter but
different action, we get EEXIST error as shown below.

$ ethtool -N eth0 flow-type ether dst <MACADDR> action 1 loc 10
$ ethtool -N eth0 flow-type ether dst <MACADDR> action 2 loc 10
rmgr: Cannot insert RX class rule: File exists

The second command is expected to overwrite the previous rule in location
10 and succeed.

This patch fixes igc_ethtool_check_nfc_rule() so it also checks the
rules location. In case they match, the rule under evaluation should not
be considered invalid.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 43dff09a8f86..d14c46dce053 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1225,8 +1225,8 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
  * Rules with both destination and source MAC addresses are considered invalid
  * since the driver doesn't support them.
  *
- * Also, if there is already another rule with the same filter, @rule is
- * considered invalid.
+ * Also, if there is already another rule with the same filter in a different
+ * location, @rule is considered invalid.
  *
  * Context: Expects adapter->nfc_rule_lock to be held by caller.
  *
@@ -1252,7 +1252,8 @@ static int igc_ethtool_check_nfc_rule(struct igc_adapter *adapter,
 
 	list_for_each_entry(tmp, &adapter->nfc_rule_list, list) {
 		if (!memcmp(&rule->filter, &tmp->filter,
-			    sizeof(rule->filter))) {
+			    sizeof(rule->filter)) &&
+		    tmp->location != rule->location) {
 			netdev_dbg(dev, "Rule already exists\n");
 			return -EEXIST;
 		}
-- 
cgit v1.2.3


From acda576f72b8a2eed44aa3840561daa0ce837744 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:21 -0700
Subject: igc: Change return type from igc_disable_nfc_rule()

None of igc_disable_nfc_rule() callers actually check its returning
value. A closer look at why this function would fail shows that the
only situation is when we try to delete an Ethertype or MAC filter that
doesn't exist.

That situation is very unlikely so we can change igc_del_etype_filter()
and igc_del_mac_filter() logic to "if the filter doesn't exist, we are
done", and keep the logic in igc_disable_nfc_rule() callers simple.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 0a6f880e3538..9338209cedf2 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2259,18 +2259,16 @@ update_filter:
  * @adapter: Pointer to adapter where the filter should be deleted from
  * @type: MAC address filter type (source or destination)
  * @addr: MAC address
- *
- * Return: 0 in case of success, negative errno code otherwise.
  */
-static int igc_del_mac_filter(struct igc_adapter *adapter,
-			      enum igc_mac_filter_type type, const u8 *addr)
+static void igc_del_mac_filter(struct igc_adapter *adapter,
+			       enum igc_mac_filter_type type, const u8 *addr)
 {
 	struct net_device *dev = adapter->netdev;
 	int index;
 
 	index = igc_find_mac_filter(adapter, type, addr);
 	if (index < 0)
-		return -ENOENT;
+		return;
 
 	if (index == 0) {
 		/* If this is the default filter, we don't actually delete it.
@@ -2288,8 +2286,6 @@ static int igc_del_mac_filter(struct igc_adapter *adapter,
 
 		igc_clear_mac_filter_hw(adapter, index);
 	}
-
-	return 0;
 }
 
 /**
@@ -2420,23 +2416,20 @@ static int igc_find_etype_filter(struct igc_adapter *adapter, u16 etype)
  * igc_del_etype_filter() - Delete ethertype filter
  * @adapter: Pointer to adapter where the filter should be deleted from
  * @etype: Ethertype value
- *
- * Return: 0 in case of success, negative errno code otherwise.
  */
-static int igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
+static void igc_del_etype_filter(struct igc_adapter *adapter, u16 etype)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int index;
 
 	index = igc_find_etype_filter(adapter, etype);
 	if (index < 0)
-		return -ENOENT;
+		return;
 
 	wr32(IGC_ETQF(index), 0);
 
 	netdev_dbg(adapter->netdev, "Delete ethertype filter: etype %04x\n",
 		   etype);
-	return 0;
 }
 
 static int igc_enable_nfc_rule(struct igc_adapter *adapter,
@@ -2477,8 +2470,8 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter,
 	return 0;
 }
 
-static int igc_disable_nfc_rule(struct igc_adapter *adapter,
-				const struct igc_nfc_rule *rule)
+static void igc_disable_nfc_rule(struct igc_adapter *adapter,
+				 const struct igc_nfc_rule *rule)
 {
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
 		igc_del_etype_filter(adapter, rule->filter.etype);
@@ -2497,8 +2490,6 @@ static int igc_disable_nfc_rule(struct igc_adapter *adapter,
 	if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
 		igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
 				   rule->filter.dst_addr);
-
-	return 0;
 }
 
 /**
@@ -2623,7 +2614,8 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	return igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, addr);
+	igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, addr);
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 42fc5dc042796a825d9e2db8ee4cd977b12f73d1 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:22 -0700
Subject: igc: Change adapter->nfc_rule_lock to mutex

This patch changes adapter->nfc_rule_lock type from spin_lock to mutex
so we avoid unnecessary busy waiting on lock contention.

A closer look at the execution context of NFC rule API users shows that
all of them run in process context. The API users are: ethtool ops,
igc_configure(), called when interface is brought up by user or reset
workequeue thread, igc_down(), called when interface is brought down,
and igc_remove(), called when driver is unloaded.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         |  2 +-
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 24 ++++++++++++------------
 drivers/net/ethernet/intel/igc/igc_main.c    | 14 +++++++-------
 3 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index a484b328268b..14f9edaaaf83 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -190,7 +190,7 @@ struct igc_adapter {
 	/* Any access to elements in nfc_rule_list is protected by the
 	 * nfc_rule_lock.
 	 */
-	spinlock_t nfc_rule_lock;
+	struct mutex nfc_rule_lock;
 	struct list_head nfc_rule_list;
 	unsigned int nfc_rule_count;
 
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index d14c46dce053..946e775e34ae 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -939,7 +939,7 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 
 	cmd->data = IGC_MAX_RXNFC_RULES;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	rule = igc_get_nfc_rule(adapter, fsp->location);
 	if (!rule)
@@ -971,11 +971,11 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter,
 		eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
 	}
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
 out:
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 	return -EINVAL;
 }
 
@@ -988,18 +988,18 @@ static int igc_ethtool_get_nfc_rules(struct igc_adapter *adapter,
 
 	cmd->data = IGC_MAX_RXNFC_RULES;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	list_for_each_entry(rule, &adapter->nfc_rule_list, list) {
 		if (cnt == cmd->rule_cnt) {
-			spin_unlock(&adapter->nfc_rule_lock);
+			mutex_unlock(&adapter->nfc_rule_lock);
 			return -EMSGSIZE;
 		}
 		rule_locs[cnt] = rule->location;
 		cnt++;
 	}
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 
 	cmd->rule_cnt = cnt;
 
@@ -1303,7 +1303,7 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 
 	igc_ethtool_init_nfc_rule(rule, fsp);
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	err = igc_ethtool_check_nfc_rule(adapter, rule);
 	if (err)
@@ -1317,11 +1317,11 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter,
 	if (err)
 		goto err;
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 	return 0;
 
 err:
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 	kfree(rule);
 	return err;
 }
@@ -1333,17 +1333,17 @@ static int igc_ethtool_del_nfc_rule(struct igc_adapter *adapter,
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
 	struct igc_nfc_rule *rule;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	rule = igc_get_nfc_rule(adapter, fsp->location);
 	if (!rule) {
-		spin_unlock(&adapter->nfc_rule_lock);
+		mutex_unlock(&adapter->nfc_rule_lock);
 		return -EINVAL;
 	}
 
 	igc_del_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9338209cedf2..165263ae8add 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2539,12 +2539,12 @@ static void igc_flush_nfc_rules(struct igc_adapter *adapter)
 {
 	struct igc_nfc_rule *rule, *tmp;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	list_for_each_entry_safe(rule, tmp, &adapter->nfc_rule_list, list)
 		igc_del_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 }
 
 /**
@@ -2583,24 +2583,24 @@ static void igc_restore_nfc_rules(struct igc_adapter *adapter)
 {
 	struct igc_nfc_rule *rule;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	list_for_each_entry_reverse(rule, &adapter->nfc_rule_list, list)
 		igc_enable_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 }
 
 static void igc_nfc_rule_exit(struct igc_adapter *adapter)
 {
 	struct igc_nfc_rule *rule;
 
-	spin_lock(&adapter->nfc_rule_lock);
+	mutex_lock(&adapter->nfc_rule_lock);
 
 	list_for_each_entry(rule, &adapter->nfc_rule_list, list)
 		igc_disable_nfc_rule(adapter, rule);
 
-	spin_unlock(&adapter->nfc_rule_lock);
+	mutex_unlock(&adapter->nfc_rule_lock);
 }
 
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
@@ -3573,7 +3573,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 				VLAN_HLEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
-	spin_lock_init(&adapter->nfc_rule_lock);
+	mutex_init(&adapter->nfc_rule_lock);
 	INIT_LIST_HEAD(&adapter->nfc_rule_list);
 	adapter->nfc_rule_count = 0;
 
-- 
cgit v1.2.3


From 5c739e77ca338a37765370290e02cb270651380b Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Fri, 24 Apr 2020 13:16:23 -0700
Subject: igc: Remove igc_nfc_rule_exit()

During igc_down(), we call igc_nfc_rule_exit() which traverse the NFC
rule list disabling filters one by one. Later on in igc_down() flow
we issue an hardware reset which also clear all filters.  Since we
already reset the hardware, we don't actually need to disable each
filter manually. In order to simplify the code, this patch removes
igc_nfc_rule() altogether.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 165263ae8add..97d26991c87e 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2591,18 +2591,6 @@ static void igc_restore_nfc_rules(struct igc_adapter *adapter)
 	mutex_unlock(&adapter->nfc_rule_lock);
 }
 
-static void igc_nfc_rule_exit(struct igc_adapter *adapter)
-{
-	struct igc_nfc_rule *rule;
-
-	mutex_lock(&adapter->nfc_rule_lock);
-
-	list_for_each_entry(rule, &adapter->nfc_rule_list, list)
-		igc_disable_nfc_rule(adapter, rule);
-
-	mutex_unlock(&adapter->nfc_rule_lock);
-}
-
 static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
@@ -3821,8 +3809,6 @@ void igc_down(struct igc_adapter *adapter)
 	wr32(IGC_RCTL, rctl & ~IGC_RCTL_EN);
 	/* flush and sleep below */
 
-	igc_nfc_rule_exit(adapter);
-
 	/* set trans_start so we don't get spurious watchdogs during reset */
 	netif_trans_update(netdev);
 
-- 
cgit v1.2.3


From 14ec06b02e260b2e78785741d0e734f4b04db1fe Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Mon, 4 May 2020 09:29:25 +0300
Subject: igc: Remove unused descriptor's flags

Enable Tidv register, Report Packet Sent, Report Status and
Ethernet CRC flags not in use.
This patch comes to clean up these flags.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 45b567587ca9..3d8d40d6fa3f 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -265,13 +265,9 @@
 #define IGC_TXD_POPTS_IXSM	0x01       /* Insert IP checksum */
 #define IGC_TXD_POPTS_TXSM	0x02       /* Insert TCP/UDP checksum */
 #define IGC_TXD_CMD_EOP		0x01000000 /* End of Packet */
-#define IGC_TXD_CMD_IFCS	0x02000000 /* Insert FCS (Ethernet CRC) */
 #define IGC_TXD_CMD_IC		0x04000000 /* Insert Checksum */
-#define IGC_TXD_CMD_RS		0x08000000 /* Report Status */
-#define IGC_TXD_CMD_RPS		0x10000000 /* Report Packet Sent */
 #define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
 #define IGC_TXD_CMD_VLE		0x40000000 /* Add VLAN tag */
-#define IGC_TXD_CMD_IDE		0x80000000 /* Enable Tidv register */
 #define IGC_TXD_STAT_DD		0x00000001 /* Descriptor Done */
 #define IGC_TXD_STAT_EC		0x00000002 /* Excess Collisions */
 #define IGC_TXD_STAT_LC		0x00000004 /* Late Collisions */
-- 
cgit v1.2.3


From 165ae7a8feb53dc47fb041357e4b253bfc927cf9 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 5 May 2020 12:01:54 +0800
Subject: igb: Report speed and duplex as unknown when device is runtime
 suspended

igb device gets runtime suspended when there's no link partner. We can't
get correct speed under that state:
$ cat /sys/class/net/enp3s0/speed
1000

In addition to that, an error can also be spotted in dmesg:
[  385.991957] igb 0000:03:00.0 enp3s0: PCIe link lost

Since device can only be runtime suspended when there's no link partner,
we can skip reading register and let the following logic set speed and
duplex with correct status.

The more generic approach will be wrap get_link_ksettings() with begin()
and complete() callbacks. However, for this particular issue, begin()
calls igb_runtime_resume() , which tries to rtnl_lock() while the lock
is already hold by upper ethtool layer.

So let's take this approach until the igb_runtime_resume() no longer
needs to hold rtnl_lock.

CC: stable <stable@vger.kernel.org>
Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_ethtool.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 39d3b76a6f5d..2cd003c5ad43 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -143,7 +143,8 @@ static int igb_get_link_ksettings(struct net_device *netdev,
 	u32 speed;
 	u32 supported, advertising;
 
-	status = rd32(E1000_STATUS);
+	status = pm_runtime_suspended(&adapter->pdev->dev) ?
+		 0 : rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
 		supported = (SUPPORTED_10baseT_Half |
-- 
cgit v1.2.3


From 0c80cdbf33207c7aea1aec9027ad8011bd6178ad Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 7 May 2020 14:25:45 +0800
Subject: e1000e: Warn if disabling ULP failed

The hardware may stop working if driver failed to disable ULP mode.

Take the return value of e1000_disable_ulp_lpt_lp() into account, and
pass up the error if it fails.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 735bf25952fc..f999cca37a8a 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -300,7 +300,11 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	 * so forcibly disable it.
 	 */
 	hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown;
-	e1000_disable_ulp_lpt_lp(hw, true);
+	ret_val = e1000_disable_ulp_lpt_lp(hw, true);
+	if (ret_val) {
+		e_warn("Failed to disable ULP\n");
+		goto out;
+	}
 
 	ret_val = hw->phy.ops.acquire(hw);
 	if (ret_val) {
-- 
cgit v1.2.3


From f29801030ac67bf98b7a65d3aea67b30769d4f7c Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 7 May 2020 22:21:07 +0800
Subject: e1000e: Disable TSO for buffer overrun workaround

Commit b10effb92e27 ("e1000e: fix buffer overrun while the I219 is
processing DMA transactions") imposes roughly 30% performance penalty.

The commit log states that "Disabling TSO eliminates performance loss
for TCP traffic without a noticeable impact on CPU performance", so
let's disable TSO by default to regain the loss.

CC: stable <stable@vger.kernel.org>
Fixes: b10effb92e27 ("e1000e: fix buffer overrun while the I219 is processing DMA transactions")
BugLink: https://bugs.launchpad.net/bugs/1802691
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index e0b074820b47..66609cf689de 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5294,6 +5294,10 @@ static void e1000_watchdog_task(struct work_struct *work)
 					/* oops */
 					break;
 				}
+				if (hw->mac.type == e1000_pch_spt) {
+					netdev->features &= ~NETIF_F_TSO;
+					netdev->features &= ~NETIF_F_TSO6;
+				}
 			}
 
 			/* enable transmits in the hardware, need to do this
-- 
cgit v1.2.3


From e086ba2fccda4c196b84a167493f67f089d0ebdc Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Thu, 7 May 2020 20:14:06 +0300
Subject: e1000e: disable s0ix entry and exit flows for ME systems

Since ME systems do not support SLP_S0 in S0ix state, and S0ix entry
and exit flows may cause errors on them it is best to avoid using
e1000e_s0ix_entry_flow and e1000e_s0ix_exit_flow functions.

This was done by creating a struct of all devices that comes with ME
and by checking if the current device has ME.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 45 ++++++++++++++++++++++++++++--
 1 file changed, 43 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 66609cf689de..32f23a15ff64 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -107,6 +107,45 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = {
 	{0, NULL}
 };
 
+struct e1000e_me_supported {
+	u16 device_id;		/* supported device ID */
+};
+
+static const struct e1000e_me_supported me_supported[] = {
+	{E1000_DEV_ID_PCH_LPT_I217_LM},
+	{E1000_DEV_ID_PCH_LPTLP_I218_LM},
+	{E1000_DEV_ID_PCH_I218_LM2},
+	{E1000_DEV_ID_PCH_I218_LM3},
+	{E1000_DEV_ID_PCH_SPT_I219_LM},
+	{E1000_DEV_ID_PCH_SPT_I219_LM2},
+	{E1000_DEV_ID_PCH_LBG_I219_LM3},
+	{E1000_DEV_ID_PCH_SPT_I219_LM4},
+	{E1000_DEV_ID_PCH_SPT_I219_LM5},
+	{E1000_DEV_ID_PCH_CNP_I219_LM6},
+	{E1000_DEV_ID_PCH_CNP_I219_LM7},
+	{E1000_DEV_ID_PCH_ICP_I219_LM8},
+	{E1000_DEV_ID_PCH_ICP_I219_LM9},
+	{E1000_DEV_ID_PCH_CMP_I219_LM10},
+	{E1000_DEV_ID_PCH_CMP_I219_LM11},
+	{E1000_DEV_ID_PCH_CMP_I219_LM12},
+	{E1000_DEV_ID_PCH_TGP_I219_LM13},
+	{E1000_DEV_ID_PCH_TGP_I219_LM14},
+	{E1000_DEV_ID_PCH_TGP_I219_LM15},
+	{0}
+};
+
+static bool e1000e_check_me(u16 device_id)
+{
+	struct e1000e_me_supported *id;
+
+	for (id = (struct e1000e_me_supported *)me_supported;
+	     id->device_id; id++)
+		if (device_id == id->device_id)
+			return true;
+
+	return false;
+}
+
 /**
  * __ew32_prepare - prepare to write to MAC CSR register on certain parts
  * @hw: pointer to the HW structure
@@ -6916,7 +6955,8 @@ static int e1000e_pm_suspend(struct device *dev)
 		e1000e_pm_thaw(dev);
 
 	/* Introduce S0ix implementation */
-	if (hw->mac.type >= e1000_pch_cnp)
+	if (hw->mac.type >= e1000_pch_cnp &&
+	    !e1000e_check_me(hw->adapter->pdev->device))
 		e1000e_s0ix_entry_flow(adapter);
 
 	return rc;
@@ -6931,7 +6971,8 @@ static int e1000e_pm_resume(struct device *dev)
 	int rc;
 
 	/* Introduce S0ix implementation */
-	if (hw->mac.type >= e1000_pch_cnp)
+	if (hw->mac.type >= e1000_pch_cnp &&
+	    !e1000e_check_me(hw->adapter->pdev->device))
 		e1000e_s0ix_exit_flow(adapter);
 
 	rc = __e1000_resume(pdev);
-- 
cgit v1.2.3


From 148beb612031255156d68b342170140524afb36e Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:40 -0700
Subject: ice: Initialize Flow Director resources

Flow Director allows for redirection based on ntuple rules. Rules are
programmed using the ethtool set-ntuple interface. Supported actions are
redirect to queue and drop.

Setup the initial framework to process Flow Director filters. Create and
allocate resources to manage and program filters to the hardware. Filters
are processed via a sideband interface; a control VSI is created to manage
communication and process requests through the sideband. Upon allocation of
resources, update the hardware tables to accept perfect filters.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile            |   2 +
 drivers/net/ethernet/intel/ice/ice.h               |  24 ++
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h    |   9 +
 drivers/net/ethernet/intel/ice/ice_base.c          |   1 +
 drivers/net/ethernet/intel/ice/ice_common.c        |  36 ++
 drivers/net/ethernet/intel/ice/ice_ethtool.c       |  11 +-
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c  | 399 +++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_fdir.c          |  54 +++
 drivers/net/ethernet/intel/ice/ice_fdir.h          |  12 +
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c     | 224 ++++++++++++
 drivers/net/ethernet/intel/ice/ice_flow.c          | 169 ++++++++-
 drivers/net/ethernet/intel/ice/ice_flow.h          |  32 +-
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h    |  11 +
 drivers/net/ethernet/intel/ice/ice_lib.c           | 210 +++++++++--
 drivers/net/ethernet/intel/ice/ice_lib.h           |   2 +
 drivers/net/ethernet/intel/ice/ice_main.c          | 160 ++++++++-
 drivers/net/ethernet/intel/ice/ice_protocol_type.h |   1 +
 drivers/net/ethernet/intel/ice/ice_switch.c        |  75 ++++
 drivers/net/ethernet/intel/ice/ice_switch.h        |   7 +
 drivers/net/ethernet/intel/ice/ice_txrx.c          | 100 +++++-
 drivers/net/ethernet/intel/ice/ice_txrx.h          |   7 +-
 drivers/net/ethernet/intel/ice/ice_type.h          |  45 ++-
 22 files changed, 1553 insertions(+), 38 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_fdir.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_fdir.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 2055e61eaf24..9ffa2e366766 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -18,6 +18,8 @@ ice-y := ice_main.o	\
 	 ice_txrx_lib.o	\
 	 ice_txrx.o	\
 	 ice_fltr.o	\
+	 ice_fdir.o	\
+	 ice_ethtool_fdir.o \
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
 	 ice_devlink.o	\
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 58d0d6436c7f..ffd11bc2e5f0 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -50,6 +50,7 @@
 #include "ice_sched.h"
 #include "ice_virtchnl_pf.h"
 #include "ice_sriov.h"
+#include "ice_fdir.h"
 #include "ice_xsk.h"
 
 extern const char ice_drv_ver[];
@@ -66,6 +67,7 @@ extern const char ice_drv_ver[];
 #define ICE_AQ_LEN		64
 #define ICE_MBXSQ_LEN		64
 #define ICE_MIN_MSIX		2
+#define ICE_FDIR_MSIX		1
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -257,6 +259,8 @@ struct ice_vsi {
 	s16 vf_id;			/* VF ID for SR-IOV VSIs */
 
 	u16 ethtype;			/* Ethernet protocol for pause frame */
+	u16 num_gfltr;
+	u16 num_bfltr;
 
 	/* RSS config */
 	u16 rss_table_size;	/* HW RSS table size */
@@ -339,6 +343,7 @@ enum ice_pf_flags {
 	ICE_FLAG_SRIOV_CAPABLE,
 	ICE_FLAG_DCB_CAPABLE,
 	ICE_FLAG_DCB_ENA,
+	ICE_FLAG_FD_ENA,
 	ICE_FLAG_ADV_FEATURES,
 	ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
 	ICE_FLAG_NO_MEDIA,
@@ -367,6 +372,8 @@ struct ice_pf {
 	 */
 	u16 sriov_base_vector;
 
+	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
+
 	struct ice_vsi **vsi;		/* VSIs created by the driver */
 	struct ice_sw *first_sw;	/* first switch created by firmware */
 	/* Virtchnl/SR-IOV config info */
@@ -505,8 +512,22 @@ static inline struct ice_vsi *ice_get_main_vsi(struct ice_pf *pf)
 	return NULL;
 }
 
+/**
+ * ice_get_ctrl_vsi - Get the control VSI
+ * @pf: PF instance
+ */
+static inline struct ice_vsi *ice_get_ctrl_vsi(struct ice_pf *pf)
+{
+	/* if pf->ctrl_vsi_idx is ICE_NO_VSI, control VSI was not set up */
+	if (!pf->vsi || pf->ctrl_vsi_idx == ICE_NO_VSI)
+		return NULL;
+
+	return pf->vsi[pf->ctrl_vsi_idx];
+}
+
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
+int ice_vsi_open_ctrl(struct ice_vsi *vsi);
 void ice_set_ethtool_ops(struct net_device *netdev);
 void ice_set_ethtool_safe_mode_ops(struct net_device *netdev);
 u16 ice_get_avail_txq_count(struct ice_pf *pf);
@@ -530,6 +551,9 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
+void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena);
+void ice_fdir_release_flows(struct ice_hw *hw);
+int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 int ice_open(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 979e9c6254af..deada2e3d7c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -107,6 +107,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_RXQS				0x0041
 #define ICE_AQC_CAPS_TXQS				0x0042
 #define ICE_AQC_CAPS_MSIX				0x0043
+#define ICE_AQC_CAPS_FD					0x0045
 #define ICE_AQC_CAPS_MAX_MTU				0x0047
 
 	u8 major_ver;
@@ -232,6 +233,11 @@ struct ice_aqc_get_sw_cfg_resp {
  */
 #define ICE_AQC_RES_TYPE_VSI_LIST_REP			0x03
 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE			0x04
+#define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK		0x21
+#define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES	0x22
+#define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES		0x23
+#define ICE_AQC_RES_TYPE_FD_PROF_BLDR_PROFID		0x58
+#define ICE_AQC_RES_TYPE_FD_PROF_BLDR_TCAM		0x59
 #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID		0x60
 #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM		0x61
 
@@ -240,6 +246,9 @@ struct ice_aqc_get_sw_cfg_resp {
 
 #define ICE_AQC_RES_TYPE_FLAG_DEDICATED			0x00
 
+#define ICE_AQC_RES_TYPE_S	0
+#define ICE_AQC_RES_TYPE_M	(0x07F << ICE_AQC_RES_TYPE_S)
+
 /* Allocate Resources command (indirect 0x0208)
  * Free Resources command (indirect 0x0209)
  */
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 4c835c144907..00c072f61a32 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -246,6 +246,7 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	 */
 	switch (vsi->type) {
 	case ICE_VSI_LB:
+	case ICE_VSI_CTRL:
 	case ICE_VSI_PF:
 		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 1a613199d6cb..3a4c14150107 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -653,6 +653,10 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_cqinit;
 
+	/* Set bit to enable Flow Director filters */
+	wr32(hw, PFQF_FD_ENA, PFQF_FD_ENA_FD_ENA_M);
+	INIT_LIST_HEAD(&hw->fdir_list_head);
+
 	ice_clear_pxe_mode(hw);
 
 	status = ice_init_nvm(hw);
@@ -741,6 +745,10 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	status = ice_aq_manage_mac_read(hw, mac_buf, mac_buf_len, NULL);
 	devm_kfree(ice_hw_to_dev(hw), mac_buf);
 
+	if (status)
+		goto err_unroll_fltr_mgmt_struct;
+	/* Obtain counter base index which would be used by flow director */
+	status = ice_alloc_fd_res_cntr(hw, &hw->fd_ctr_base);
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
 	status = ice_init_hw_tbls(hw);
@@ -770,6 +778,7 @@ err_unroll_cqinit:
  */
 void ice_deinit_hw(struct ice_hw *hw)
 {
+	ice_free_fd_res_cntr(hw, hw->fd_ctr_base);
 	ice_cleanup_fltr_mgmt_struct(hw);
 
 	ice_sched_cleanup_all(hw);
@@ -1680,6 +1689,33 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 				  "%s: msix_vector_first_id = %d\n", prefix,
 				  caps->msix_vector_first_id);
 			break;
+		case ICE_AQC_CAPS_FD:
+			if (dev_p) {
+				dev_p->num_flow_director_fltr = number;
+				ice_debug(hw, ICE_DBG_INIT,
+					  "%s: num_flow_director_fltr = %d\n",
+					  prefix,
+					  dev_p->num_flow_director_fltr);
+			}
+			if (func_p) {
+				u32 reg_val, val;
+
+				reg_val = rd32(hw, GLQF_FD_SIZE);
+				val = (reg_val & GLQF_FD_SIZE_FD_GSIZE_M) >>
+				      GLQF_FD_SIZE_FD_GSIZE_S;
+				func_p->fd_fltr_guar =
+				      ice_get_num_per_func(hw, val);
+				val = (reg_val & GLQF_FD_SIZE_FD_BSIZE_M) >>
+				      GLQF_FD_SIZE_FD_BSIZE_S;
+				func_p->fd_fltr_best_effort = val;
+				ice_debug(hw, ICE_DBG_INIT,
+					  "%s: fd_fltr_guar = %d\n",
+					  prefix, func_p->fd_fltr_guar);
+				ice_debug(hw, ICE_DBG_INIT,
+					  "%s: fd_fltr_best_effort = %d\n",
+					  prefix, func_p->fd_fltr_best_effort);
+			}
+			break;
 		case ICE_AQC_CAPS_MAX_MTU:
 			caps->max_mtu = number;
 			ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 9fb82c993df9..d11960b21474 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3184,6 +3184,10 @@ ice_get_channels(struct net_device *dev, struct ethtool_channels *ch)
 	ch->combined_count = ice_get_combined_cnt(vsi);
 	ch->rx_count = vsi->num_rxq - ch->combined_count;
 	ch->tx_count = vsi->num_txq - ch->combined_count;
+
+	/* report other queues */
+	ch->other_count = test_bit(ICE_FLAG_FD_ENA, pf->flags) ? 1 : 0;
+	ch->max_other = ch->other_count;
 }
 
 /**
@@ -3256,9 +3260,14 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 		return -EOPNOTSUPP;
 	}
 	/* do not support changing other_count */
-	if (ch->other_count)
+	if (ch->other_count != (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? 1U : 0U))
 		return -EINVAL;
 
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags) && pf->hw.fdir_active_fltr) {
+		netdev_err(dev, "Cannot set channels when Flow Director filters are active\n");
+		return -EOPNOTSUPP;
+	}
+
 	curr_combined = ice_get_combined_cnt(vsi);
 
 	/* these checks are for cases where user didn't specify a particular
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
new file mode 100644
index 000000000000..425bf6f00db1
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+/* flow director ethtool support for ice */
+
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_flow.h"
+
+/* calls to ice_flow_add_prof require the number of segments in the array
+ * for segs_cnt. In this code that is one more than the index.
+ */
+#define TNL_SEG_CNT(_TNL_) ((_TNL_) + 1)
+
+/**
+ * ice_fdir_get_hw_prof - return the ice_fd_hw_proc associated with a flow
+ * @hw: hardware structure containing the filter list
+ * @blk: hardware block
+ * @flow: FDir flow type to release
+ */
+static struct ice_fd_hw_prof *
+ice_fdir_get_hw_prof(struct ice_hw *hw, enum ice_block blk, int flow)
+{
+	if (blk == ICE_BLK_FD && hw->fdir_prof)
+		return hw->fdir_prof[flow];
+
+	return NULL;
+}
+
+/**
+ * ice_fdir_erase_flow_from_hw - remove a flow from the HW profile tables
+ * @hw: hardware structure containing the filter list
+ * @blk: hardware block
+ * @flow: FDir flow type to release
+ */
+static void
+ice_fdir_erase_flow_from_hw(struct ice_hw *hw, enum ice_block blk, int flow)
+{
+	struct ice_fd_hw_prof *prof = ice_fdir_get_hw_prof(hw, blk, flow);
+	int tun;
+
+	if (!prof)
+		return;
+
+	for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
+		u64 prof_id;
+		int j;
+
+		prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
+		for (j = 0; j < prof->cnt; j++) {
+			u16 vsi_num;
+
+			if (!prof->entry_h[j][tun] || !prof->vsi_h[j])
+				continue;
+			vsi_num = ice_get_hw_vsi_num(hw, prof->vsi_h[j]);
+			ice_rem_prof_id_flow(hw, blk, vsi_num, prof_id);
+			ice_flow_rem_entry(hw, blk, prof->entry_h[j][tun]);
+			prof->entry_h[j][tun] = 0;
+		}
+		ice_flow_rem_prof(hw, blk, prof_id);
+	}
+}
+
+/**
+ * ice_fdir_rem_flow - release the ice_flow structures for a filter type
+ * @hw: hardware structure containing the filter list
+ * @blk: hardware block
+ * @flow_type: FDir flow type to release
+ */
+static void
+ice_fdir_rem_flow(struct ice_hw *hw, enum ice_block blk,
+		  enum ice_fltr_ptype flow_type)
+{
+	int flow = (int)flow_type & ~FLOW_EXT;
+	struct ice_fd_hw_prof *prof;
+	int tun, i;
+
+	prof = ice_fdir_get_hw_prof(hw, blk, flow);
+	if (!prof)
+		return;
+
+	ice_fdir_erase_flow_from_hw(hw, blk, flow);
+	for (i = 0; i < prof->cnt; i++)
+		prof->vsi_h[i] = 0;
+	for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
+		if (!prof->fdir_seg[tun])
+			continue;
+		devm_kfree(ice_hw_to_dev(hw), prof->fdir_seg[tun]);
+		prof->fdir_seg[tun] = NULL;
+	}
+	prof->cnt = 0;
+}
+
+/**
+ * ice_fdir_release_flows - release all flows in use for later replay
+ * @hw: pointer to HW instance
+ */
+void ice_fdir_release_flows(struct ice_hw *hw)
+{
+	int flow;
+
+	/* release Flow Director HW table entries */
+	for (flow = 0; flow < ICE_FLTR_PTYPE_MAX; flow++)
+		ice_fdir_erase_flow_from_hw(hw, ICE_BLK_FD, flow);
+}
+
+/**
+ * ice_fdir_alloc_flow_prof - allocate FDir flow profile structure(s)
+ * @hw: HW structure containing the FDir flow profile structure(s)
+ * @flow: flow type to allocate the flow profile for
+ *
+ * Allocate the fdir_prof and fdir_prof[flow] if not already created. Return 0
+ * on success and negative on error.
+ */
+static int
+ice_fdir_alloc_flow_prof(struct ice_hw *hw, enum ice_fltr_ptype flow)
+{
+	if (!hw)
+		return -EINVAL;
+
+	if (!hw->fdir_prof) {
+		hw->fdir_prof = devm_kcalloc(ice_hw_to_dev(hw),
+					     ICE_FLTR_PTYPE_MAX,
+					     sizeof(*hw->fdir_prof),
+					     GFP_KERNEL);
+		if (!hw->fdir_prof)
+			return -ENOMEM;
+	}
+
+	if (!hw->fdir_prof[flow]) {
+		hw->fdir_prof[flow] = devm_kzalloc(ice_hw_to_dev(hw),
+						   sizeof(**hw->fdir_prof),
+						   GFP_KERNEL);
+		if (!hw->fdir_prof[flow])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_fdir_set_hw_fltr_rule - Configure HW tables to generate a FDir rule
+ * @pf: pointer to the PF structure
+ * @seg: protocol header description pointer
+ * @flow: filter enum
+ * @tun: FDir segment to program
+ */
+static int
+ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
+			  enum ice_fltr_ptype flow, enum ice_fd_hw_seg tun)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_vsi *main_vsi, *ctrl_vsi;
+	struct ice_flow_seg_info *old_seg;
+	struct ice_flow_prof *prof = NULL;
+	struct ice_fd_hw_prof *hw_prof;
+	struct ice_hw *hw = &pf->hw;
+	enum ice_status status;
+	u64 entry1_h = 0;
+	u64 entry2_h = 0;
+	u64 prof_id;
+	int err;
+
+	main_vsi = ice_get_main_vsi(pf);
+	if (!main_vsi)
+		return -EINVAL;
+
+	ctrl_vsi = ice_get_ctrl_vsi(pf);
+	if (!ctrl_vsi)
+		return -EINVAL;
+
+	err = ice_fdir_alloc_flow_prof(hw, flow);
+	if (err)
+		return err;
+
+	hw_prof = hw->fdir_prof[flow];
+	old_seg = hw_prof->fdir_seg[tun];
+	if (old_seg) {
+		/* This flow_type already has a changed input set.
+		 * If it matches the requested input set then we are
+		 * done. Or, if it's different then it's an error.
+		 */
+		if (!memcmp(old_seg, seg, sizeof(*seg)))
+			return -EEXIST;
+
+		/* remove HW filter definition */
+		ice_fdir_rem_flow(hw, ICE_BLK_FD, flow);
+	}
+
+	/* Adding a profile, but there is only one header supported.
+	 * That is the final parameters are 1 header (segment), no
+	 * actions (NULL) and zero actions 0.
+	 */
+	prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
+	status = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg,
+				   TNL_SEG_CNT(tun), &prof);
+	if (status)
+		return ice_status_to_errno(status);
+	status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx,
+				    main_vsi->idx, ICE_FLOW_PRIO_NORMAL,
+				    seg, &entry1_h);
+	if (status) {
+		err = ice_status_to_errno(status);
+		goto err_prof;
+	}
+	status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx,
+				    ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL,
+				    seg, &entry2_h);
+	if (status) {
+		err = ice_status_to_errno(status);
+		goto err_entry;
+	}
+
+	hw_prof->fdir_seg[tun] = seg;
+	hw_prof->entry_h[0][tun] = entry1_h;
+	hw_prof->entry_h[1][tun] = entry2_h;
+	hw_prof->vsi_h[0] = main_vsi->idx;
+	hw_prof->vsi_h[1] = ctrl_vsi->idx;
+	if (!hw_prof->cnt)
+		hw_prof->cnt = 2;
+
+	return 0;
+
+err_entry:
+	ice_rem_prof_id_flow(hw, ICE_BLK_FD,
+			     ice_get_hw_vsi_num(hw, main_vsi->idx), prof_id);
+	ice_flow_rem_entry(hw, ICE_BLK_FD, entry1_h);
+err_prof:
+	ice_flow_rem_prof(hw, ICE_BLK_FD, prof_id);
+	dev_err(dev, "Failed to add filter.  Flow director filters on each port must have the same input set.\n");
+
+	return err;
+}
+
+/**
+ * ice_set_init_fdir_seg
+ * @seg: flow segment for programming
+ * @l4_proto: ICE_FLOW_SEG_HDR_TCP or ICE_FLOW_SEG_HDR_UDP
+ *
+ * Set the configuration for perfect filters to the provided flow segment for
+ * programming the HW filter. This is to be called only when initializing
+ * filters as this function it assumes no filters exist.
+ */
+static int
+ice_set_init_fdir_seg(struct ice_flow_seg_info *seg,
+		      enum ice_flow_seg_hdr l4_proto)
+{
+	enum ice_flow_field src_port, dst_port;
+
+	if (!seg)
+		return -EINVAL;
+
+	if (l4_proto == ICE_FLOW_SEG_HDR_TCP) {
+		src_port = ICE_FLOW_FIELD_IDX_TCP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_TCP_DST_PORT;
+	} else if (l4_proto == ICE_FLOW_SEG_HDR_UDP) {
+		src_port = ICE_FLOW_FIELD_IDX_UDP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_UDP_DST_PORT;
+	} else {
+		return -EINVAL;
+	}
+
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV4 | l4_proto);
+
+	/* IP source address */
+	ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_SA,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, false);
+
+	/* IP destination address */
+	ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_DA,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, false);
+
+	/* Layer 4 source port */
+	ice_flow_set_fld(seg, src_port, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, false);
+
+	/* Layer 4 destination port */
+	ice_flow_set_fld(seg, dst_port, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, false);
+
+	return 0;
+}
+
+/**
+ * ice_create_init_fdir_rule
+ * @pf: PF structure
+ * @flow: filter enum
+ *
+ * Return error value or 0 on success.
+ */
+static int
+ice_create_init_fdir_rule(struct ice_pf *pf, enum ice_fltr_ptype flow)
+{
+	struct ice_flow_seg_info *seg, *tun_seg;
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	int ret;
+
+	/* if there is already a filter rule for kind return -EINVAL */
+	if (hw->fdir_prof && hw->fdir_prof[flow] &&
+	    hw->fdir_prof[flow]->fdir_seg[0])
+		return -EINVAL;
+
+	seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL);
+	if (!seg)
+		return -ENOMEM;
+
+	tun_seg = devm_kzalloc(dev, sizeof(*seg) * ICE_FD_HW_SEG_MAX,
+			       GFP_KERNEL);
+	if (!tun_seg) {
+		devm_kfree(dev, seg);
+		return -ENOMEM;
+	}
+
+	if (flow == ICE_FLTR_PTYPE_NONF_IPV4_TCP)
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_TCP);
+	else if (flow == ICE_FLTR_PTYPE_NONF_IPV4_UDP)
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_UDP);
+	else
+		ret = -EINVAL;
+	if (ret)
+		goto err_exit;
+
+	/* add filter for outer headers */
+	ret = ice_fdir_set_hw_fltr_rule(pf, seg, flow, ICE_FD_HW_SEG_NON_TUN);
+	if (ret)
+		/* could not write filter, free memory */
+		goto err_exit;
+
+	/* make tunneled filter HW entries if possible */
+	memcpy(&tun_seg[1], seg, sizeof(*seg));
+	ret = ice_fdir_set_hw_fltr_rule(pf, tun_seg, flow, ICE_FD_HW_SEG_TUN);
+	if (ret)
+		/* could not write tunnel filter, but outer header filter
+		 * exists
+		 */
+		devm_kfree(dev, tun_seg);
+
+	set_bit(flow, hw->fdir_perfect_fltr);
+	return ret;
+err_exit:
+	devm_kfree(dev, tun_seg);
+	devm_kfree(dev, seg);
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ice_fdir_create_dflt_rules - create default perfect filters
+ * @pf: PF data structure
+ *
+ * Returns 0 for success or error.
+ */
+int ice_fdir_create_dflt_rules(struct ice_pf *pf)
+{
+	int err;
+
+	/* Create perfect TCP and UDP rules in hardware. */
+	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP);
+	if (err)
+		return err;
+
+	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP);
+
+	return err;
+}
+
+/**
+ * ice_vsi_manage_fdir - turn on/off flow director
+ * @vsi: the VSI being changed
+ * @ena: boolean value indicating if this is an enable or disable request
+ */
+void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	enum ice_fltr_ptype flow;
+
+	if (ena) {
+		set_bit(ICE_FLAG_FD_ENA, pf->flags);
+		ice_fdir_create_dflt_rules(pf);
+		return;
+	}
+
+	mutex_lock(&hw->fdir_fltr_lock);
+	if (!test_and_clear_bit(ICE_FLAG_FD_ENA, pf->flags))
+		goto release_lock;
+
+	if (hw->fdir_prof)
+		for (flow = ICE_FLTR_PTYPE_NONF_NONE; flow < ICE_FLTR_PTYPE_MAX;
+		     flow++)
+			if (hw->fdir_prof[flow])
+				ice_fdir_rem_flow(hw, ICE_BLK_FD, flow);
+
+release_lock:
+	mutex_unlock(&hw->fdir_fltr_lock);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
new file mode 100644
index 000000000000..878fa4df9453
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#include "ice_common.h"
+
+/**
+ * ice_alloc_fd_res_cntr - obtain counter resource for FD type
+ * @hw: pointer to the hardware structure
+ * @cntr_id: returns counter index
+ */
+enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id)
+{
+	return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK,
+				  ICE_AQC_RES_TYPE_FLAG_DEDICATED, 1, cntr_id);
+}
+
+/**
+ * ice_free_fd_res_cntr - Free counter resource for FD type
+ * @hw: pointer to the hardware structure
+ * @cntr_id: counter index to be freed
+ */
+enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id)
+{
+	return ice_free_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK,
+				 ICE_AQC_RES_TYPE_FLAG_DEDICATED, 1, cntr_id);
+}
+
+/**
+ * ice_alloc_fd_guar_item - allocate resource for FD guaranteed entries
+ * @hw: pointer to the hardware structure
+ * @cntr_id: returns counter index
+ * @num_fltr: number of filter entries to be allocated
+ */
+enum ice_status
+ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr)
+{
+	return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES,
+				  ICE_AQC_RES_TYPE_FLAG_DEDICATED, num_fltr,
+				  cntr_id);
+}
+
+/**
+ * ice_alloc_fd_shrd_item - allocate resource for flow director shared entries
+ * @hw: pointer to the hardware structure
+ * @cntr_id: returns counter index
+ * @num_fltr: number of filter entries to be allocated
+ */
+enum ice_status
+ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr)
+{
+	return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES,
+				  ICE_AQC_RES_TYPE_FLAG_DEDICATED, num_fltr,
+				  cntr_id);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
new file mode 100644
index 000000000000..feac47adde6e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#ifndef _ICE_FDIR_H_
+#define _ICE_FDIR_H_
+enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
+enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
+enum ice_status
+ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
+enum ice_status
+ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
+#endif /* _ICE_FDIR_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 38c37f506257..fe2f04f706e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -2353,6 +2353,9 @@ ice_find_prof_id(struct ice_hw *hw, enum ice_block blk,
 static bool ice_prof_id_rsrc_type(enum ice_block blk, u16 *rsrc_type)
 {
 	switch (blk) {
+	case ICE_BLK_FD:
+		*rsrc_type = ICE_AQC_RES_TYPE_FD_PROF_BLDR_PROFID;
+		break;
 	case ICE_BLK_RSS:
 		*rsrc_type = ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID;
 		break;
@@ -2370,6 +2373,9 @@ static bool ice_prof_id_rsrc_type(enum ice_block blk, u16 *rsrc_type)
 static bool ice_tcam_ent_rsrc_type(enum ice_block blk, u16 *rsrc_type)
 {
 	switch (blk) {
+	case ICE_BLK_FD:
+		*rsrc_type = ICE_AQC_RES_TYPE_FD_PROF_BLDR_TCAM;
+		break;
 	case ICE_BLK_RSS:
 		*rsrc_type = ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM;
 		break;
@@ -2813,6 +2819,12 @@ static void ice_free_flow_profs(struct ice_hw *hw, u8 blk_idx)
 
 	mutex_lock(&hw->fl_profs_locks[blk_idx]);
 	list_for_each_entry_safe(p, tmp, &hw->fl_profs[blk_idx], l_entry) {
+		struct ice_flow_entry *e, *t;
+
+		list_for_each_entry_safe(e, t, &p->entries, l_entry)
+			ice_flow_rem_entry(hw, (enum ice_block)blk_idx,
+					   ICE_FLOW_ENTRY_HNDL(e));
+
 		list_del(&p->l_entry);
 		devm_kfree(ice_hw_to_dev(hw), p);
 	}
@@ -3441,6 +3453,206 @@ error_tmp:
 	return status;
 }
 
+/**
+ * ice_update_fd_mask - set Flow Director Field Vector mask for a profile
+ * @hw: pointer to the HW struct
+ * @prof_id: profile ID
+ * @mask_sel: mask select
+ *
+ * This function enable any of the masks selected by the mask select parameter
+ * for the profile specified.
+ */
+static void ice_update_fd_mask(struct ice_hw *hw, u16 prof_id, u32 mask_sel)
+{
+	wr32(hw, GLQF_FDMASK_SEL(prof_id), mask_sel);
+
+	ice_debug(hw, ICE_DBG_INIT, "fd mask(%d): %x = %x\n", prof_id,
+		  GLQF_FDMASK_SEL(prof_id), mask_sel);
+}
+
+struct ice_fd_src_dst_pair {
+	u8 prot_id;
+	u8 count;
+	u16 off;
+};
+
+static const struct ice_fd_src_dst_pair ice_fd_pairs[] = {
+	/* These are defined in pairs */
+	{ ICE_PROT_IPV4_OF_OR_S, 2, 12 },
+	{ ICE_PROT_IPV4_OF_OR_S, 2, 16 },
+
+	{ ICE_PROT_IPV4_IL, 2, 12 },
+	{ ICE_PROT_IPV4_IL, 2, 16 },
+
+	{ ICE_PROT_TCP_IL, 1, 0 },
+	{ ICE_PROT_TCP_IL, 1, 2 },
+
+	{ ICE_PROT_UDP_OF, 1, 0 },
+	{ ICE_PROT_UDP_OF, 1, 2 },
+
+	{ ICE_PROT_UDP_IL_OR_S, 1, 0 },
+	{ ICE_PROT_UDP_IL_OR_S, 1, 2 },
+
+	{ ICE_PROT_SCTP_IL, 1, 0 },
+	{ ICE_PROT_SCTP_IL, 1, 2 }
+};
+
+#define ICE_FD_SRC_DST_PAIR_COUNT	ARRAY_SIZE(ice_fd_pairs)
+
+/**
+ * ice_update_fd_swap - set register appropriately for a FD FV extraction
+ * @hw: pointer to the HW struct
+ * @prof_id: profile ID
+ * @es: extraction sequence (length of array is determined by the block)
+ */
+static enum ice_status
+ice_update_fd_swap(struct ice_hw *hw, u16 prof_id, struct ice_fv_word *es)
+{
+	DECLARE_BITMAP(pair_list, ICE_FD_SRC_DST_PAIR_COUNT);
+	u8 pair_start[ICE_FD_SRC_DST_PAIR_COUNT] = { 0 };
+#define ICE_FD_FV_NOT_FOUND (-2)
+	s8 first_free = ICE_FD_FV_NOT_FOUND;
+	u8 used[ICE_MAX_FV_WORDS] = { 0 };
+	s8 orig_free, si;
+	u32 mask_sel = 0;
+	u8 i, j, k;
+
+	bitmap_zero(pair_list, ICE_FD_SRC_DST_PAIR_COUNT);
+
+	/* This code assumes that the Flow Director field vectors are assigned
+	 * from the end of the FV indexes working towards the zero index, that
+	 * only complete fields will be included and will be consecutive, and
+	 * that there are no gaps between valid indexes.
+	 */
+
+	/* Determine swap fields present */
+	for (i = 0; i < hw->blk[ICE_BLK_FD].es.fvw; i++) {
+		/* Find the first free entry, assuming right to left population.
+		 * This is where we can start adding additional pairs if needed.
+		 */
+		if (first_free == ICE_FD_FV_NOT_FOUND && es[i].prot_id !=
+		    ICE_PROT_INVALID)
+			first_free = i - 1;
+
+		for (j = 0; j < ICE_FD_SRC_DST_PAIR_COUNT; j++)
+			if (es[i].prot_id == ice_fd_pairs[j].prot_id &&
+			    es[i].off == ice_fd_pairs[j].off) {
+				set_bit(j, pair_list);
+				pair_start[j] = i;
+			}
+	}
+
+	orig_free = first_free;
+
+	/* determine missing swap fields that need to be added */
+	for (i = 0; i < ICE_FD_SRC_DST_PAIR_COUNT; i += 2) {
+		u8 bit1 = test_bit(i + 1, pair_list);
+		u8 bit0 = test_bit(i, pair_list);
+
+		if (bit0 ^ bit1) {
+			u8 index;
+
+			/* add the appropriate 'paired' entry */
+			if (!bit0)
+				index = i;
+			else
+				index = i + 1;
+
+			/* check for room */
+			if (first_free + 1 < (s8)ice_fd_pairs[index].count)
+				return ICE_ERR_MAX_LIMIT;
+
+			/* place in extraction sequence */
+			for (k = 0; k < ice_fd_pairs[index].count; k++) {
+				es[first_free - k].prot_id =
+					ice_fd_pairs[index].prot_id;
+				es[first_free - k].off =
+					ice_fd_pairs[index].off + (k * 2);
+
+				if (k > first_free)
+					return ICE_ERR_OUT_OF_RANGE;
+
+				/* keep track of non-relevant fields */
+				mask_sel |= BIT(first_free - k);
+			}
+
+			pair_start[index] = first_free;
+			first_free -= ice_fd_pairs[index].count;
+		}
+	}
+
+	/* fill in the swap array */
+	si = hw->blk[ICE_BLK_FD].es.fvw - 1;
+	while (si >= 0) {
+		u8 indexes_used = 1;
+
+		/* assume flat at this index */
+#define ICE_SWAP_VALID	0x80
+		used[si] = si | ICE_SWAP_VALID;
+
+		if (orig_free == ICE_FD_FV_NOT_FOUND || si <= orig_free) {
+			si -= indexes_used;
+			continue;
+		}
+
+		/* check for a swap location */
+		for (j = 0; j < ICE_FD_SRC_DST_PAIR_COUNT; j++)
+			if (es[si].prot_id == ice_fd_pairs[j].prot_id &&
+			    es[si].off == ice_fd_pairs[j].off) {
+				u8 idx;
+
+				/* determine the appropriate matching field */
+				idx = j + ((j % 2) ? -1 : 1);
+
+				indexes_used = ice_fd_pairs[idx].count;
+				for (k = 0; k < indexes_used; k++) {
+					used[si - k] = (pair_start[idx] - k) |
+						ICE_SWAP_VALID;
+				}
+
+				break;
+			}
+
+		si -= indexes_used;
+	}
+
+	/* for each set of 4 swap and 4 inset indexes, write the appropriate
+	 * register
+	 */
+	for (j = 0; j < hw->blk[ICE_BLK_FD].es.fvw / 4; j++) {
+		u32 raw_swap = 0;
+		u32 raw_in = 0;
+
+		for (k = 0; k < 4; k++) {
+			u8 idx;
+
+			idx = (j * 4) + k;
+			if (used[idx] && !(mask_sel & BIT(idx))) {
+				raw_swap |= used[idx] << (k * BITS_PER_BYTE);
+#define ICE_INSET_DFLT 0x9f
+				raw_in |= ICE_INSET_DFLT << (k * BITS_PER_BYTE);
+			}
+		}
+
+		/* write the appropriate swap register set */
+		wr32(hw, GLQF_FDSWAP(prof_id, j), raw_swap);
+
+		ice_debug(hw, ICE_DBG_INIT, "swap wr(%d, %d): %x = %08x\n",
+			  prof_id, j, GLQF_FDSWAP(prof_id, j), raw_swap);
+
+		/* write the appropriate inset register set */
+		wr32(hw, GLQF_FDINSET(prof_id, j), raw_in);
+
+		ice_debug(hw, ICE_DBG_INIT, "inset wr(%d, %d): %x = %08x\n",
+			  prof_id, j, GLQF_FDINSET(prof_id, j), raw_in);
+	}
+
+	/* initially clear the mask select for this profile */
+	ice_update_fd_mask(hw, prof_id, 0);
+
+	return 0;
+}
+
 /**
  * ice_add_prof - add profile
  * @hw: pointer to the HW struct
@@ -3476,6 +3688,18 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 		status = ice_alloc_prof_id(hw, blk, &prof_id);
 		if (status)
 			goto err_ice_add_prof;
+		if (blk == ICE_BLK_FD) {
+			/* For Flow Director block, the extraction sequence may
+			 * need to be altered in the case where there are paired
+			 * fields that have no match. This is necessary because
+			 * for Flow Director, src and dest fields need to paired
+			 * for filter programming and these values are swapped
+			 * during Tx.
+			 */
+			status = ice_update_fd_swap(hw, prof_id, es);
+			if (status)
+				goto err_ice_add_prof;
+		}
 
 		/* and write new es */
 		ice_write_es(hw, blk, prof_id, es);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index 07875db08c3f..f4b6c3933564 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -397,10 +397,8 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params)
 		return status;
 
 	switch (params->blk) {
+	case ICE_BLK_FD:
 	case ICE_BLK_RSS:
-		/* Only header information is provided for RSS configuration.
-		 * No further processing is needed.
-		 */
 		status = 0;
 		break;
 	default:
@@ -481,6 +479,43 @@ ice_flow_find_prof_id(struct ice_hw *hw, enum ice_block blk, u64 prof_id)
 	return NULL;
 }
 
+/**
+ * ice_dealloc_flow_entry - Deallocate flow entry memory
+ * @hw: pointer to the HW struct
+ * @entry: flow entry to be removed
+ */
+static void
+ice_dealloc_flow_entry(struct ice_hw *hw, struct ice_flow_entry *entry)
+{
+	if (!entry)
+		return;
+
+	if (entry->entry)
+		devm_kfree(ice_hw_to_dev(hw), entry->entry);
+
+	devm_kfree(ice_hw_to_dev(hw), entry);
+}
+
+/**
+ * ice_flow_rem_entry_sync - Remove a flow entry
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @entry: flow entry to be removed
+ */
+static enum ice_status
+ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk,
+			struct ice_flow_entry *entry)
+{
+	if (!entry)
+		return ICE_ERR_BAD_PTR;
+
+	list_del(&entry->l_entry);
+
+	ice_dealloc_flow_entry(hw, entry);
+
+	return 0;
+}
+
 /**
  * ice_flow_add_prof_sync - Add a flow profile for packet segments and fields
  * @hw: pointer to the HW struct
@@ -568,6 +603,21 @@ ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk,
 {
 	enum ice_status status;
 
+	/* Remove all remaining flow entries before removing the flow profile */
+	if (!list_empty(&prof->entries)) {
+		struct ice_flow_entry *e, *t;
+
+		mutex_lock(&prof->entries_lock);
+
+		list_for_each_entry_safe(e, t, &prof->entries, l_entry) {
+			status = ice_flow_rem_entry_sync(hw, blk, e);
+			if (status)
+				break;
+		}
+
+		mutex_unlock(&prof->entries_lock);
+	}
+
 	/* Remove all hardware profiles associated with this flow profile */
 	status = ice_rem_prof(hw, blk, prof->id);
 	if (!status) {
@@ -653,7 +703,7 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk,
  * @segs_cnt: number of packet segments provided
  * @prof: stores the returned flow profile added
  */
-static enum ice_status
+enum ice_status
 ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
 		  u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt,
 		  struct ice_flow_prof **prof)
@@ -691,7 +741,7 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
  * @blk: the block for which the flow profile is to be removed
  * @prof_id: unique ID of the flow profile to be removed
  */
-static enum ice_status
+enum ice_status
 ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id)
 {
 	struct ice_flow_prof *prof;
@@ -714,6 +764,113 @@ out:
 	return status;
 }
 
+/**
+ * ice_flow_add_entry - Add a flow entry
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @prof_id: ID of the profile to add a new flow entry to
+ * @entry_id: unique ID to identify this flow entry
+ * @vsi_handle: software VSI handle for the flow entry
+ * @prio: priority of the flow entry
+ * @data: pointer to a data buffer containing flow entry's match values/masks
+ * @entry_h: pointer to buffer that receives the new flow entry's handle
+ */
+enum ice_status
+ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id,
+		   u64 entry_id, u16 vsi_handle, enum ice_flow_priority prio,
+		   void *data, u64 *entry_h)
+{
+	struct ice_flow_entry *e = NULL;
+	struct ice_flow_prof *prof;
+	enum ice_status status;
+
+	/* No flow entry data is expected for RSS */
+	if (!entry_h || (!data && blk != ICE_BLK_RSS))
+		return ICE_ERR_BAD_PTR;
+
+	if (!ice_is_vsi_valid(hw, vsi_handle))
+		return ICE_ERR_PARAM;
+
+	mutex_lock(&hw->fl_profs_locks[blk]);
+
+	prof = ice_flow_find_prof_id(hw, blk, prof_id);
+	if (!prof) {
+		status = ICE_ERR_DOES_NOT_EXIST;
+	} else {
+		/* Allocate memory for the entry being added and associate
+		 * the VSI to the found flow profile
+		 */
+		e = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*e), GFP_KERNEL);
+		if (!e)
+			status = ICE_ERR_NO_MEMORY;
+		else
+			status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle);
+	}
+
+	mutex_unlock(&hw->fl_profs_locks[blk]);
+	if (status)
+		goto out;
+
+	e->id = entry_id;
+	e->vsi_handle = vsi_handle;
+	e->prof = prof;
+	e->priority = prio;
+
+	switch (blk) {
+	case ICE_BLK_FD:
+	case ICE_BLK_RSS:
+		break;
+	default:
+		status = ICE_ERR_NOT_IMPL;
+		goto out;
+	}
+
+	mutex_lock(&prof->entries_lock);
+	list_add(&e->l_entry, &prof->entries);
+	mutex_unlock(&prof->entries_lock);
+
+	*entry_h = ICE_FLOW_ENTRY_HNDL(e);
+
+out:
+	if (status && e) {
+		if (e->entry)
+			devm_kfree(ice_hw_to_dev(hw), e->entry);
+		devm_kfree(ice_hw_to_dev(hw), e);
+	}
+
+	return status;
+}
+
+/**
+ * ice_flow_rem_entry - Remove a flow entry
+ * @hw: pointer to the HW struct
+ * @blk: classification stage
+ * @entry_h: handle to the flow entry to be removed
+ */
+enum ice_status ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk,
+				   u64 entry_h)
+{
+	struct ice_flow_entry *entry;
+	struct ice_flow_prof *prof;
+	enum ice_status status = 0;
+
+	if (entry_h == ICE_FLOW_ENTRY_HANDLE_INVAL)
+		return ICE_ERR_PARAM;
+
+	entry = ICE_FLOW_ENTRY_PTR(entry_h);
+
+	/* Retain the pointer to the flow profile as the entry will be freed */
+	prof = entry->prof;
+
+	if (prof) {
+		mutex_lock(&prof->entries_lock);
+		status = ice_flow_rem_entry_sync(hw, blk, entry);
+		mutex_unlock(&prof->entries_lock);
+	}
+
+	return status;
+}
+
 /**
  * ice_flow_set_fld_ext - specifies locations of field from entry's input buffer
  * @seg: packet segment the field being set belongs to
@@ -776,7 +933,7 @@ ice_flow_set_fld_ext(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
  * create the content of a match entry. This function should only be used for
  * fixed-size data structures.
  */
-static void
+void
 ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
 		 u16 val_loc, u16 mask_loc, u16 last_loc, bool range)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 00f2b7a9feed..3c784c3b5db2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -172,6 +172,22 @@ struct ice_flow_seg_info {
 	struct ice_flow_fld_info fields[ICE_FLOW_FIELD_IDX_MAX];
 };
 
+/* This structure describes a flow entry, and is tracked only in this file */
+struct ice_flow_entry {
+	struct list_head l_entry;
+
+	u64 id;
+	struct ice_flow_prof *prof;
+	/* Flow entry's content */
+	void *entry;
+	enum ice_flow_priority priority;
+	u16 vsi_handle;
+	u16 entry_sz;
+};
+
+#define ICE_FLOW_ENTRY_HNDL(e)	((u64)e)
+#define ICE_FLOW_ENTRY_PTR(h)	((struct ice_flow_entry *)(h))
+
 struct ice_flow_prof {
 	struct list_head l_entry;
 
@@ -197,7 +213,21 @@ struct ice_rss_cfg {
 	u32 packet_hdr;
 };
 
-enum ice_status ice_flow_rem_entry(struct ice_hw *hw, u64 entry_h);
+enum ice_status
+ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
+		  u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt,
+		  struct ice_flow_prof **prof);
+enum ice_status
+ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id);
+enum ice_status
+ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id,
+		   u64 entry_id, u16 vsi, enum ice_flow_priority prio,
+		   void *data, u64 *entry_h);
+enum ice_status
+ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, u64 entry_h);
+void
+ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
+		 u16 val_loc, u16 mask_loc, u16 last_loc, bool range);
 void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle);
 enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index bc48eda67c81..3c61b2a04fc4 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -290,6 +290,17 @@
 #define GL_PWR_MODE_CTL				0x000B820C
 #define GL_PWR_MODE_CTL_CAR_MAX_BW_S		30
 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M		ICE_M(0x3, 30)
+#define GLQF_FD_SIZE				0x00460010
+#define GLQF_FD_SIZE_FD_GSIZE_S			0
+#define GLQF_FD_SIZE_FD_GSIZE_M			ICE_M(0x7FFF, 0)
+#define GLQF_FD_SIZE_FD_BSIZE_S			16
+#define GLQF_FD_SIZE_FD_BSIZE_M			ICE_M(0x7FFF, 16)
+#define GLQF_FDINSET(_i, _j)			(0x00412000 + ((_i) * 4 + (_j) * 512))
+#define GLQF_FDMASK_SEL(_i)			(0x00410400 + ((_i) * 4))
+#define GLQF_FDSWAP(_i, _j)			(0x00413000 + ((_i) * 4 + (_j) * 512))
+#define PFQF_FD_ENA				0x0043A000
+#define PFQF_FD_ENA_FD_ENA_M			BIT(0)
+#define PFQF_FD_SIZE				0x00460100
 #define GLDCB_RTCTQ_RXQNUM_S			0
 #define GLDCB_RTCTQ_RXQNUM_M			ICE_M(0x7FF, 0)
 #define GLPRT_BPRCL(_i)				(0x00381380 + ((_i) * 8))
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index c73c977f6967..43c949e0a760 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -19,6 +19,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type)
 		return "ICE_VSI_PF";
 	case ICE_VSI_VF:
 		return "ICE_VSI_VF";
+	case ICE_VSI_CTRL:
+		return "ICE_VSI_CTRL";
 	case ICE_VSI_LB:
 		return "ICE_VSI_LB";
 	default:
@@ -123,6 +125,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 {
 	switch (vsi->type) {
 	case ICE_VSI_PF:
+	case ICE_VSI_CTRL:
 	case ICE_VSI_LB:
 		vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC;
 		vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC;
@@ -187,6 +190,11 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		 */
 		vsi->num_q_vectors = pf->num_msix_per_vf - ICE_NONQ_VECS_VF;
 		break;
+	case ICE_VSI_CTRL:
+		vsi->alloc_txq = 1;
+		vsi->alloc_rxq = 1;
+		vsi->num_q_vectors = 1;
+		break;
 	case ICE_VSI_LB:
 		vsi->alloc_txq = 1;
 		vsi->alloc_rxq = 1;
@@ -322,7 +330,7 @@ int ice_vsi_clear(struct ice_vsi *vsi)
 	/* updates the PF for this cleared VSI */
 
 	pf->vsi[vsi->idx] = NULL;
-	if (vsi->idx < pf->next_vsi)
+	if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL)
 		pf->next_vsi = vsi->idx;
 
 	ice_vsi_free_arrays(vsi);
@@ -332,6 +340,25 @@ int ice_vsi_clear(struct ice_vsi *vsi)
 	return 0;
 }
 
+/**
+ * ice_msix_clean_ctrl_vsi - MSIX mode interrupt handler for ctrl VSI
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_msix_clean_ctrl_vsi(int __always_unused irq, void *data)
+{
+	struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
+
+	if (!q_vector->tx.ring)
+		return IRQ_HANDLED;
+
+#define FDIR_RX_DESC_CLEAN_BUDGET 64
+	ice_clean_rx_irq(q_vector->rx.ring, FDIR_RX_DESC_CLEAN_BUDGET);
+	ice_clean_ctrl_tx_irq(q_vector->tx.ring);
+
+	return IRQ_HANDLED;
+}
+
 /**
  * ice_msix_clean_rings - MSIX mode Interrupt Handler
  * @irq: interrupt number
@@ -383,8 +410,6 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id)
 	vsi->back = pf;
 	set_bit(__ICE_DOWN, vsi->state);
 
-	vsi->idx = pf->next_vsi;
-
 	if (vsi_type == ICE_VSI_VF)
 		ice_vsi_set_num_qs(vsi, vf_id);
 	else
@@ -398,6 +423,13 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id)
 		/* Setup default MSIX irq handler for VSI */
 		vsi->irq_handler = ice_msix_clean_rings;
 		break;
+	case ICE_VSI_CTRL:
+		if (ice_vsi_alloc_arrays(vsi))
+			goto err_rings;
+
+		/* Setup ctrl VSI MSIX irq handler */
+		vsi->irq_handler = ice_msix_clean_ctrl_vsi;
+		break;
 	case ICE_VSI_VF:
 		if (ice_vsi_alloc_arrays(vsi))
 			goto err_rings;
@@ -411,12 +443,20 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id)
 		goto unlock_pf;
 	}
 
-	/* fill VSI slot in the PF struct */
-	pf->vsi[pf->next_vsi] = vsi;
+	if (vsi->type == ICE_VSI_CTRL) {
+		/* Use the last VSI slot as the index for the control VSI */
+		vsi->idx = pf->num_alloc_vsi - 1;
+		pf->ctrl_vsi_idx = vsi->idx;
+		pf->vsi[vsi->idx] = vsi;
+	} else {
+		/* fill slot and make note of the index */
+		vsi->idx = pf->next_vsi;
+		pf->vsi[pf->next_vsi] = vsi;
 
-	/* prepare pf->next_vsi for next use */
-	pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
-					 pf->next_vsi);
+		/* prepare pf->next_vsi for next use */
+		pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
+						 pf->next_vsi);
+	}
 	goto unlock_pf;
 
 err_rings:
@@ -427,6 +467,48 @@ unlock_pf:
 	return vsi;
 }
 
+/**
+ * ice_alloc_fd_res - Allocate FD resource for a VSI
+ * @vsi: pointer to the ice_vsi
+ *
+ * This allocates the FD resources
+ *
+ * Returns 0 on success, -EPERM on no-op or -EIO on failure
+ */
+static int ice_alloc_fd_res(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	u32 g_val, b_val;
+
+	/* Flow Director filters are only allocated/assigned to the PF VSI which
+	 * passes the traffic. The CTRL VSI is only used to add/delete filters
+	 * so we don't allocate resources to it
+	 */
+
+	/* FD filters from guaranteed pool per VSI */
+	g_val = pf->hw.func_caps.fd_fltr_guar;
+	if (!g_val)
+		return -EPERM;
+
+	/* FD filters from best effort pool */
+	b_val = pf->hw.func_caps.fd_fltr_best_effort;
+	if (!b_val)
+		return -EPERM;
+
+	if (vsi->type != ICE_VSI_PF)
+		return -EPERM;
+
+	if (!test_bit(ICE_FLAG_FD_ENA, pf->flags))
+		return -EPERM;
+
+	vsi->num_gfltr = g_val / pf->num_alloc_vsi;
+
+	/* each VSI gets same "best_effort" quota */
+	vsi->num_bfltr = b_val;
+
+	return 0;
+}
+
 /**
  * ice_vsi_get_qs - Assign queues from PF to VSI
  * @vsi: the VSI to assign queues to
@@ -583,8 +665,8 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 	case ICE_VSI_LB:
 		break;
 	default:
-		dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n",
-			 vsi->type);
+		dev_dbg(ice_pf_to_dev(pf), "Unsupported VSI type %s\n",
+			ice_vsi_type_str(vsi->type));
 		break;
 	}
 }
@@ -753,6 +835,51 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	ctxt->info.q_mapping[1] = cpu_to_le16(vsi->num_rxq);
 }
 
+/**
+ * ice_set_fd_vsi_ctx - Set FD VSI context before adding a VSI
+ * @ctxt: the VSI context being set
+ * @vsi: the VSI being configured
+ */
+static void ice_set_fd_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
+{
+	u8 dflt_q_group, dflt_q_prio;
+	u16 dflt_q, report_q, val;
+
+	if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_CTRL)
+		return;
+
+	val = ICE_AQ_VSI_PROP_FLOW_DIR_VALID;
+	ctxt->info.valid_sections |= cpu_to_le16(val);
+	dflt_q = 0;
+	dflt_q_group = 0;
+	report_q = 0;
+	dflt_q_prio = 0;
+
+	/* enable flow director filtering/programming */
+	val = ICE_AQ_VSI_FD_ENABLE | ICE_AQ_VSI_FD_PROG_ENABLE;
+	ctxt->info.fd_options = cpu_to_le16(val);
+	/* max of allocated flow director filters */
+	ctxt->info.max_fd_fltr_dedicated =
+			cpu_to_le16(vsi->num_gfltr);
+	/* max of shared flow director filters any VSI may program */
+	ctxt->info.max_fd_fltr_shared =
+			cpu_to_le16(vsi->num_bfltr);
+	/* default queue index within the VSI of the default FD */
+	val = ((dflt_q << ICE_AQ_VSI_FD_DEF_Q_S) &
+	       ICE_AQ_VSI_FD_DEF_Q_M);
+	/* target queue or queue group to the FD filter */
+	val |= ((dflt_q_group << ICE_AQ_VSI_FD_DEF_GRP_S) &
+		ICE_AQ_VSI_FD_DEF_GRP_M);
+	ctxt->info.fd_def_q = cpu_to_le16(val);
+	/* queue index on which FD filter completion is reported */
+	val = ((report_q << ICE_AQ_VSI_FD_REPORT_Q_S) &
+	       ICE_AQ_VSI_FD_REPORT_Q_M);
+	/* priority of the default qindex action */
+	val |= ((dflt_q_prio << ICE_AQ_VSI_FD_DEF_PRIORITY_S) &
+		ICE_AQ_VSI_FD_DEF_PRIORITY_M);
+	ctxt->info.fd_report_opt = cpu_to_le16(val);
+}
+
 /**
  * ice_set_rss_vsi_ctx - Set RSS VSI context before adding a VSI
  * @ctxt: the VSI context being set
@@ -778,13 +905,10 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
 		hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
 		break;
-	case ICE_VSI_LB:
+	default:
 		dev_dbg(dev, "Unsupported VSI type %s\n",
 			ice_vsi_type_str(vsi->type));
 		return;
-	default:
-		dev_warn(dev, "Unknown VSI type %d\n", vsi->type);
-		return;
 	}
 
 	ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
@@ -816,6 +940,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 
 	ctxt->info = vsi->info;
 	switch (vsi->type) {
+	case ICE_VSI_CTRL:
 	case ICE_VSI_LB:
 	case ICE_VSI_PF:
 		ctxt->flags = ICE_AQ_VSI_TYPE_PF;
@@ -831,12 +956,15 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 	}
 
 	ice_set_dflt_vsi_ctx(ctxt);
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags))
+		ice_set_fd_vsi_ctx(ctxt, vsi);
 	/* if the switch is in VEB mode, allow VSI loopback */
 	if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
 		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
 
 	/* Set LUT type and HASH type if RSS is enabled */
-	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags) &&
+	    vsi->type != ICE_VSI_CTRL) {
 		ice_set_rss_vsi_ctx(ctxt, vsi);
 		/* if updating VSI context, make sure to set valid_section:
 		 * to indicate which section of VSI context being updated
@@ -1986,10 +2114,12 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	if (vsi->type == ICE_VSI_VF)
 		vsi->vf_id = vf_id;
 
+	ice_alloc_fd_res(vsi);
+
 	if (ice_vsi_get_qs(vsi)) {
 		dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n",
 			vsi->idx);
-		goto unroll_get_qs;
+		goto unroll_vsi_alloc;
 	}
 
 	/* set RSS capabilities */
@@ -2004,6 +2134,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		goto unroll_get_qs;
 
 	switch (vsi->type) {
+	case ICE_VSI_CTRL:
 	case ICE_VSI_PF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
@@ -2034,14 +2165,16 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 
 		ice_vsi_map_rings_to_vectors(vsi);
 
-		/* Do not exit if configuring RSS had an issue, at least
-		 * receive traffic on first queue. Hence no need to capture
-		 * return value
-		 */
-		if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
-			ice_vsi_cfg_rss_lut_key(vsi);
-			ice_vsi_set_rss_flow_fld(vsi);
-		}
+		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
+		if (vsi->type != ICE_VSI_CTRL)
+			/* Do not exit if configuring RSS had an issue, at
+			 * least receive traffic on first queue. Hence no
+			 * need to capture return value
+			 */
+			if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
+				ice_vsi_cfg_rss_lut_key(vsi);
+				ice_vsi_set_rss_flow_fld(vsi);
+			}
 		break;
 	case ICE_VSI_VF:
 		/* VF driver will take care of creating netdev for this type and
@@ -2122,6 +2255,7 @@ unroll_vsi_init:
 	ice_vsi_delete(vsi);
 unroll_get_qs:
 	ice_vsi_put_qs(vsi);
+unroll_vsi_alloc:
 	ice_vsi_clear(vsi);
 
 	return NULL;
@@ -2274,6 +2408,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
 			if (!locked)
 				rtnl_unlock();
 		}
+	} else if (vsi->type == ICE_VSI_CTRL) {
+		err = ice_vsi_open_ctrl(vsi);
 	}
 
 	return err;
@@ -2303,6 +2439,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 		} else {
 			ice_vsi_close(vsi);
 		}
+	} else if (vsi->type == ICE_VSI_CTRL) {
+		ice_vsi_close(vsi);
 	}
 }
 
@@ -2848,6 +2986,30 @@ void ice_update_rx_ring_stats(struct ice_ring *rx_ring, u64 pkts, u64 bytes)
 	u64_stats_update_end(&rx_ring->syncp);
 }
 
+/**
+ * ice_status_to_errno - convert from enum ice_status to Linux errno
+ * @err: ice_status value to convert
+ */
+int ice_status_to_errno(enum ice_status err)
+{
+	switch (err) {
+	case ICE_SUCCESS:
+		return 0;
+	case ICE_ERR_DOES_NOT_EXIST:
+		return -ENOENT;
+	case ICE_ERR_OUT_OF_RANGE:
+		return -ENOTTY;
+	case ICE_ERR_PARAM:
+		return -EINVAL;
+	case ICE_ERR_NO_MEMORY:
+		return -ENOMEM;
+	case ICE_ERR_MAX_LIMIT:
+		return -EAGAIN;
+	default:
+		return -EINVAL;
+	}
+}
+
 /**
  * ice_is_dflt_vsi_in_use - check if the default forwarding VSI is being used
  * @sw: switch to check if its default forwarding VSI is free
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 9746de9b25fe..076e635e0c9f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -92,6 +92,8 @@ void ice_update_rx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes);
 
 void ice_vsi_cfg_frame_size(struct ice_vsi *vsi);
 
+int ice_status_to_errno(enum ice_status err);
+
 u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran);
 
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c3e5c4334e26..2cc1f345c845 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2319,6 +2319,7 @@ static void ice_set_netdev_features(struct net_device *netdev)
 
 	dflt_features = NETIF_F_SG	|
 			NETIF_F_HIGHDMA	|
+			NETIF_F_NTUPLE	|
 			NETIF_F_RXHASH;
 
 	csumo_features = NETIF_F_RXCSUM	  |
@@ -2458,6 +2459,20 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 	return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID);
 }
 
+/**
+ * ice_ctrl_vsi_setup - Set up a control VSI
+ * @pf: board private structure
+ * @pi: pointer to the port_info instance
+ *
+ * Returns pointer to the successfully allocated VSI software struct
+ * on success, otherwise returns NULL on failure.
+ */
+static struct ice_vsi *
+ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
+{
+	return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, ICE_INVAL_VFID);
+}
+
 /**
  * ice_lb_vsi_setup - Set up a loopback VSI
  * @pf: board private structure
@@ -2706,6 +2721,23 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 	if (func_caps->common_cap.rss_table_size)
 		set_bit(ICE_FLAG_RSS_ENA, pf->flags);
 
+	clear_bit(ICE_FLAG_FD_ENA, pf->flags);
+	if (func_caps->fd_fltr_guar > 0 || func_caps->fd_fltr_best_effort > 0) {
+		u16 unused;
+
+		/* ctrl_vsi_idx will be set to a valid value when flow director
+		 * is setup by ice_init_fdir
+		 */
+		pf->ctrl_vsi_idx = ICE_NO_VSI;
+		set_bit(ICE_FLAG_FD_ENA, pf->flags);
+		/* force guaranteed filter pool for PF */
+		ice_alloc_fd_guar_item(&pf->hw, &unused,
+				       func_caps->fd_fltr_guar);
+		/* force shared filter pool for PF */
+		ice_alloc_fd_shrd_item(&pf->hw, &unused,
+				       func_caps->fd_fltr_best_effort);
+	}
+
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
 	pf->max_pf_rxqs = func_caps->common_cap.num_rxq;
 }
@@ -2772,6 +2804,15 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	v_budget += needed;
 	v_left -= needed;
 
+	/* reserve one vector for flow director */
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) {
+		needed = ICE_FDIR_MSIX;
+		if (v_left < needed)
+			goto no_hw_vecs_left_err;
+		v_budget += needed;
+		v_left -= needed;
+	}
+
 	pf->msix_entries = devm_kcalloc(dev, v_budget,
 					sizeof(*pf->msix_entries), GFP_KERNEL);
 
@@ -2796,8 +2837,10 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	if (v_actual < v_budget) {
 		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
 			 v_budget, v_actual);
-/* 2 vectors for LAN (traffic + OICR) */
+/* 2 vectors each for LAN and RDMA (traffic + OICR), one for flow director */
 #define ICE_MIN_LAN_VECS 2
+#define ICE_MIN_RDMA_VECS 2
+#define ICE_MIN_VECS (ICE_MIN_LAN_VECS + ICE_MIN_RDMA_VECS + 1)
 
 		if (v_actual < ICE_MIN_LAN_VECS) {
 			/* error if we can't get minimum vectors */
@@ -3102,6 +3145,53 @@ static enum ice_status ice_send_version(struct ice_pf *pf)
 	return ice_aq_send_driver_ver(&pf->hw, &dv, NULL);
 }
 
+/**
+ * ice_init_fdir - Initialize flow director VSI and configuration
+ * @pf: pointer to the PF instance
+ *
+ * returns 0 on success, negative on error
+ */
+static int ice_init_fdir(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_vsi *ctrl_vsi;
+	int err;
+
+	/* Side Band Flow Director needs to have a control VSI.
+	 * Allocate it and store it in the PF.
+	 */
+	ctrl_vsi = ice_ctrl_vsi_setup(pf, pf->hw.port_info);
+	if (!ctrl_vsi) {
+		dev_dbg(dev, "could not create control VSI\n");
+		return -ENOMEM;
+	}
+
+	err = ice_vsi_open_ctrl(ctrl_vsi);
+	if (err) {
+		dev_dbg(dev, "could not open control VSI\n");
+		goto err_vsi_open;
+	}
+
+	mutex_init(&pf->hw.fdir_fltr_lock);
+
+	err = ice_fdir_create_dflt_rules(pf);
+	if (err)
+		goto err_fdir_rule;
+
+	return 0;
+
+err_fdir_rule:
+	ice_fdir_release_flows(&pf->hw);
+	ice_vsi_close(ctrl_vsi);
+err_vsi_open:
+	ice_vsi_release(ctrl_vsi);
+	if (pf->ctrl_vsi_idx != ICE_NO_VSI) {
+		pf->vsi[pf->ctrl_vsi_idx] = NULL;
+		pf->ctrl_vsi_idx = ICE_NO_VSI;
+	}
+	return err;
+}
+
 /**
  * ice_get_opt_fw_name - return optional firmware file name or NULL
  * @pf: pointer to the PF instance
@@ -3362,6 +3452,10 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	/* initialize DDP driven features */
 
+	/* Note: Flow director init failure is non-fatal to load */
+	if (ice_init_fdir(pf))
+		dev_err(dev, "could not initialize flow director\n");
+
 	/* Note: DCB init failure is non-fatal to load */
 	if (ice_init_pf_dcb(pf, false)) {
 		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
@@ -3424,6 +3518,7 @@ static void ice_remove(struct pci_dev *pdev)
 	set_bit(__ICE_DOWN, pf->state);
 	ice_service_task_stop(pf);
 
+	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
 	ice_devlink_destroy_port(pf);
 	ice_vsi_release_all(pf);
 	ice_free_irq_msix_misc(pf);
@@ -3940,6 +4035,13 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 		 (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
 		ret = ice_cfg_vlan_pruning(vsi, false, false);
 
+	if ((features & NETIF_F_NTUPLE) &&
+	    !(netdev->features & NETIF_F_NTUPLE))
+		ice_vsi_manage_fdir(vsi, true);
+	else if (!(features & NETIF_F_NTUPLE) &&
+		 (netdev->features & NETIF_F_NTUPLE))
+		ice_vsi_manage_fdir(vsi, false);
+
 	return ret;
 }
 
@@ -4494,6 +4596,62 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
 	return err;
 }
 
+/**
+ * ice_vsi_open_ctrl - open control VSI for use
+ * @vsi: the VSI to open
+ *
+ * Initialization of the Control VSI
+ *
+ * Returns 0 on success, negative value on error
+ */
+int ice_vsi_open_ctrl(struct ice_vsi *vsi)
+{
+	char int_name[ICE_INT_NAME_STR_LEN];
+	struct ice_pf *pf = vsi->back;
+	struct device *dev;
+	int err;
+
+	dev = ice_pf_to_dev(pf);
+	/* allocate descriptors */
+	err = ice_vsi_setup_tx_rings(vsi);
+	if (err)
+		goto err_setup_tx;
+
+	err = ice_vsi_setup_rx_rings(vsi);
+	if (err)
+		goto err_setup_rx;
+
+	err = ice_vsi_cfg(vsi);
+	if (err)
+		goto err_setup_rx;
+
+	snprintf(int_name, sizeof(int_name) - 1, "%s-%s:ctrl",
+		 dev_driver_string(dev), dev_name(dev));
+	err = ice_vsi_req_irq_msix(vsi, int_name);
+	if (err)
+		goto err_setup_rx;
+
+	ice_vsi_cfg_msix(vsi);
+
+	err = ice_vsi_start_all_rx_rings(vsi);
+	if (err)
+		goto err_up_complete;
+
+	clear_bit(__ICE_DOWN, vsi->state);
+	ice_vsi_ena_irq(vsi);
+
+	return 0;
+
+err_up_complete:
+	ice_down(vsi);
+err_setup_rx:
+	ice_vsi_free_rx_rings(vsi);
+err_setup_tx:
+	ice_vsi_free_tx_rings(vsi);
+
+	return err;
+}
+
 /**
  * ice_vsi_open - Called when a network interface is made active
  * @vsi: the VSI to open
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index 678db6bf7f57..babe4a485fd6 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -17,6 +17,7 @@ enum ice_prot_id {
 	ICE_PROT_IPV6_OF_OR_S	= 40,
 	ICE_PROT_IPV6_IL	= 41,
 	ICE_PROT_TCP_IL		= 49,
+	ICE_PROT_UDP_OF		= 52,
 	ICE_PROT_UDP_IL_OR_S	= 53,
 	ICE_PROT_GRE_OF		= 64,
 	ICE_PROT_SCTP_IL	= 96,
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 7d88944de31a..0156b73df1b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -2677,6 +2677,81 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle)
 	ice_remove_vsi_lkup_fltr(hw, vsi_handle, ICE_SW_LKUP_PROMISC_VLAN);
 }
 
+/**
+ * ice_alloc_res_cntr - allocating resource counter
+ * @hw: pointer to the hardware structure
+ * @type: type of resource
+ * @alloc_shared: if set it is shared else dedicated
+ * @num_items: number of entries requested for FD resource type
+ * @counter_id: counter index returned by AQ call
+ */
+enum ice_status
+ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
+		   u16 *counter_id)
+{
+	struct ice_aqc_alloc_free_res_elem *buf;
+	enum ice_status status;
+	u16 buf_len;
+
+	/* Allocate resource */
+	buf_len = sizeof(*buf);
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return ICE_ERR_NO_MEMORY;
+
+	buf->num_elems = cpu_to_le16(num_items);
+	buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
+				      ICE_AQC_RES_TYPE_M) | alloc_shared);
+
+	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
+				       ice_aqc_opc_alloc_res, NULL);
+	if (status)
+		goto exit;
+
+	*counter_id = le16_to_cpu(buf->elem[0].e.sw_resp);
+
+exit:
+	kfree(buf);
+	return status;
+}
+
+/**
+ * ice_free_res_cntr - free resource counter
+ * @hw: pointer to the hardware structure
+ * @type: type of resource
+ * @alloc_shared: if set it is shared else dedicated
+ * @num_items: number of entries to be freed for FD resource type
+ * @counter_id: counter ID resource which needs to be freed
+ */
+enum ice_status
+ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
+		  u16 counter_id)
+{
+	struct ice_aqc_alloc_free_res_elem *buf;
+	enum ice_status status;
+	u16 buf_len;
+
+	/* Free resource */
+	buf_len = sizeof(*buf);
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return ICE_ERR_NO_MEMORY;
+
+	buf->num_elems = cpu_to_le16(num_items);
+	buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) &
+				      ICE_AQC_RES_TYPE_M) | alloc_shared);
+	buf->elem[0].e.sw_resp = cpu_to_le16(counter_id);
+
+	status = ice_aq_alloc_free_res(hw, 1, buf, buf_len,
+				       ice_aqc_opc_free_res, NULL);
+	if (status)
+		ice_debug(hw, ICE_DBG_SW,
+			  "counter resource could not be freed\n");
+
+	kfree(buf);
+	return status;
+}
+
 /**
  * ice_replay_vsi_fltr - Replay filters for requested VSI
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index fa14b9545dab..8b4f9d35c860 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -208,6 +208,13 @@ void ice_clear_all_vsi_ctx(struct ice_hw *hw);
 /* Switch config */
 enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw);
 
+enum ice_status
+ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
+		   u16 *counter_id);
+enum ice_status
+ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items,
+		  u16 counter_id);
+
 /* Switch/bridge related commands */
 enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw);
 enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 0d90e32efab9..173a167c96d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -15,6 +15,8 @@
 
 #define ICE_RX_HDR_SIZE		256
 
+#define FDIR_DESC_RXDID 0x40
+
 /**
  * ice_unmap_and_free_tx_buf - Release a Tx buffer
  * @ring: the ring that owns the buffer
@@ -24,7 +26,9 @@ static void
 ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf)
 {
 	if (tx_buf->skb) {
-		if (ice_ring_is_xdp(ring))
+		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
+			devm_kfree(ring->dev, tx_buf->raw_buf);
+		else if (ice_ring_is_xdp(ring))
 			page_frag_free(tx_buf->raw_buf);
 		else
 			dev_kfree_skb_any(tx_buf->skb);
@@ -599,7 +603,8 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 	struct ice_rx_buf *bi;
 
 	/* do nothing if no valid netdev defined */
-	if (!rx_ring->netdev || !cleaned_count)
+	if ((!rx_ring->netdev && rx_ring->vsi->type != ICE_VSI_CTRL) ||
+	    !cleaned_count)
 		return false;
 
 	/* get the Rx descriptor and buffer based on next_to_use */
@@ -997,7 +1002,7 @@ ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
  *
  * Returns amount of work completed
  */
-static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
+int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
@@ -1040,6 +1045,12 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
+			ice_put_rx_buf(rx_ring, NULL);
+			cleaned_count++;
+			continue;
+		}
+
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 			ICE_RX_FLX_DESC_PKT_LEN_M;
 
@@ -2378,3 +2389,86 @@ netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	return ice_xmit_frame_ring(skb, tx_ring);
 }
+
+/**
+ * ice_clean_ctrl_tx_irq - interrupt handler for flow director Tx queue
+ * @tx_ring: tx_ring to clean
+ */
+void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring)
+{
+	struct ice_vsi *vsi = tx_ring->vsi;
+	s16 i = tx_ring->next_to_clean;
+	int budget = ICE_DFLT_IRQ_WORK;
+	struct ice_tx_desc *tx_desc;
+	struct ice_tx_buf *tx_buf;
+
+	tx_buf = &tx_ring->tx_buf[i];
+	tx_desc = ICE_TX_DESC(tx_ring, i);
+	i -= tx_ring->count;
+
+	do {
+		struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;
+
+		/* if next_to_watch is not set then there is no pending work */
+		if (!eop_desc)
+			break;
+
+		/* prevent any other reads prior to eop_desc */
+		smp_rmb();
+
+		/* if the descriptor isn't done, no work to do */
+		if (!(eop_desc->cmd_type_offset_bsz &
+		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
+			break;
+
+		/* clear next_to_watch to prevent false hangs */
+		tx_buf->next_to_watch = NULL;
+		tx_desc->buf_addr = 0;
+		tx_desc->cmd_type_offset_bsz = 0;
+
+		/* move past filter desc */
+		tx_buf++;
+		tx_desc++;
+		i++;
+		if (unlikely(!i)) {
+			i -= tx_ring->count;
+			tx_buf = tx_ring->tx_buf;
+			tx_desc = ICE_TX_DESC(tx_ring, 0);
+		}
+
+		/* unmap the data header */
+		if (dma_unmap_len(tx_buf, len))
+			dma_unmap_single(tx_ring->dev,
+					 dma_unmap_addr(tx_buf, dma),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
+		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
+			devm_kfree(tx_ring->dev, tx_buf->raw_buf);
+
+		/* clear next_to_watch to prevent false hangs */
+		tx_buf->raw_buf = NULL;
+		tx_buf->tx_flags = 0;
+		tx_buf->next_to_watch = NULL;
+		dma_unmap_len_set(tx_buf, len, 0);
+		tx_desc->buf_addr = 0;
+		tx_desc->cmd_type_offset_bsz = 0;
+
+		/* move past eop_desc for start of next FD desc */
+		tx_buf++;
+		tx_desc++;
+		i++;
+		if (unlikely(!i)) {
+			i -= tx_ring->count;
+			tx_buf = tx_ring->tx_buf;
+			tx_desc = ICE_TX_DESC(tx_ring, 0);
+		}
+
+		budget--;
+	} while (likely(budget));
+
+	i += tx_ring->count;
+	tx_ring->next_to_clean = i;
+
+	/* re-enable interrupt if needed */
+	ice_irq_dynamic_ena(&vsi->back->hw, vsi, vsi->q_vectors[0]);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 025dd642cf28..2209583c993e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -113,6 +113,10 @@ static inline int ice_skb_pad(void)
 #define ICE_TX_FLAGS_TSO	BIT(0)
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
 #define ICE_TX_FLAGS_SW_VLAN	BIT(2)
+/* ICE_TX_FLAGS_DUMMY_PKT is used to mark dummy packets that should be
+ * freed instead of returned like skb packets.
+ */
+#define ICE_TX_FLAGS_DUMMY_PKT	BIT(3)
 #define ICE_TX_FLAGS_IPV4	BIT(5)
 #define ICE_TX_FLAGS_IPV6	BIT(6)
 #define ICE_TX_FLAGS_TUNNEL	BIT(7)
@@ -376,5 +380,6 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring);
 void ice_free_tx_ring(struct ice_ring *tx_ring);
 void ice_free_rx_ring(struct ice_ring *rx_ring);
 int ice_napi_poll(struct napi_struct *napi, int budget);
-
+int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget);
+void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring);
 #endif /* _ICE_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 9f6578eb4672..74bdc00e869c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -118,7 +118,8 @@ enum ice_media_type {
 
 enum ice_vsi_type {
 	ICE_VSI_PF = 0,
-	ICE_VSI_VF,
+	ICE_VSI_VF = 1,
+	ICE_VSI_CTRL = 3,	/* equates to ICE_VSI_PF with 1 queue pair */
 	ICE_VSI_LB = 6,
 };
 
@@ -161,6 +162,34 @@ struct ice_phy_info {
 	u8 get_link_info;
 };
 
+/* protocol enumeration for filters */
+enum ice_fltr_ptype {
+	/* NONE - used for undef/error */
+	ICE_FLTR_PTYPE_NONF_NONE = 0,
+	ICE_FLTR_PTYPE_NONF_IPV4_UDP,
+	ICE_FLTR_PTYPE_NONF_IPV4_TCP,
+	ICE_FLTR_PTYPE_NONF_IPV4_SCTP,
+	ICE_FLTR_PTYPE_NONF_IPV4_OTHER,
+	ICE_FLTR_PTYPE_FRAG_IPV4,
+	ICE_FLTR_PTYPE_MAX,
+};
+
+enum ice_fd_hw_seg {
+	ICE_FD_HW_SEG_NON_TUN = 0,
+	ICE_FD_HW_SEG_TUN,
+	ICE_FD_HW_SEG_MAX,
+};
+
+/* 2 VSI = 1 ICE_VSI_PF + 1 ICE_VSI_CTRL */
+#define ICE_MAX_FDIR_VSI_PER_FILTER	2
+
+struct ice_fd_hw_prof {
+	struct ice_flow_seg_info *fdir_seg[ICE_FD_HW_SEG_MAX];
+	int cnt;
+	u64 entry_h[ICE_MAX_FDIR_VSI_PER_FILTER][ICE_FD_HW_SEG_MAX];
+	u16 vsi_h[ICE_MAX_FDIR_VSI_PER_FILTER];
+};
+
 /* Common HW capabilities for SW use */
 struct ice_hw_common_caps {
 	u32 valid_functions;
@@ -197,6 +226,8 @@ struct ice_hw_func_caps {
 	u32 num_allocd_vfs;		/* Number of allocated VFs */
 	u32 vf_base_id;			/* Logical ID of the first VF */
 	u32 guar_num_vsi;
+	u32 fd_fltr_guar;		/* Number of filters guaranteed */
+	u32 fd_fltr_best_effort;	/* Number of best effort filters */
 };
 
 /* Device wide capabilities */
@@ -204,6 +235,7 @@ struct ice_hw_dev_caps {
 	struct ice_hw_common_caps common_cap;
 	u32 num_vfs_exposed;		/* Total number of VFs exposed */
 	u32 num_vsi_allocd_to_host;	/* Excluding EMP VSI */
+	u32 num_flow_director_fltr;	/* Number of FD filters available */
 	u32 num_funcs;
 };
 
@@ -489,6 +521,8 @@ struct ice_hw {
 	u64 debug_mask;		/* bitmap for debug mask */
 	enum ice_mac_type mac_type;
 
+	u16 fd_ctr_base;	/* FD counter base index */
+
 	/* pci info */
 	u16 device_id;
 	u16 vendor_id;
@@ -587,6 +621,15 @@ struct ice_hw {
 	struct ice_blk_info blk[ICE_BLK_COUNT];
 	struct mutex fl_profs_locks[ICE_BLK_COUNT];	/* lock fltr profiles */
 	struct list_head fl_profs[ICE_BLK_COUNT];
+
+	/* Flow Director filter info */
+	int fdir_active_fltr;
+
+	struct mutex fdir_fltr_lock;	/* protect Flow Director */
+	struct list_head fdir_list_head;
+
+	struct ice_fd_hw_prof **fdir_prof;
+	DECLARE_BITMAP(fdir_perfect_fltr, ICE_FLTR_PTYPE_MAX);
 	struct mutex rss_locks;	/* protect RSS configuration */
 	struct list_head rss_list_head;
 };
-- 
cgit v1.2.3


From 4ab956462f67763be4049b03a414aa7c9b2d4c96 Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:41 -0700
Subject: ice: Support displaying ntuple rules

Add functionality for ethtool --show-ntuple, allowing for filters to be
displayed when set functionality is added. Add statistics related to
Flow Director matches and status.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h              |   9 ++
 drivers/net/ethernet/intel/ice/ice_ethtool.c      |  17 +++
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 161 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_fdir.c         |  33 +++++
 drivers/net/ethernet/intel/ice/ice_fdir.h         |  47 +++++++
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h   |   1 +
 drivers/net/ethernet/intel/ice/ice_main.c         |   9 ++
 drivers/net/ethernet/intel/ice/ice_type.h         |   3 +
 8 files changed, 280 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index ffd11bc2e5f0..e0c9e4a30d82 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -525,6 +525,11 @@ static inline struct ice_vsi *ice_get_ctrl_vsi(struct ice_pf *pf)
 	return pf->vsi[pf->ctrl_vsi_idx];
 }
 
+#define ICE_FD_STAT_CTR_BLOCK_COUNT	256
+#define ICE_FD_STAT_PF_IDX(base_idx) \
+			((base_idx) * ICE_FD_STAT_CTR_BLOCK_COUNT)
+#define ICE_FD_SB_STAT_IDX(base_idx) ICE_FD_STAT_PF_IDX(base_idx)
+
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 int ice_vsi_open_ctrl(struct ice_vsi *vsi);
@@ -552,6 +557,10 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
 void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena);
+int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd);
+int
+ice_get_fdir_fltr_ids(struct ice_hw *hw, struct ethtool_rxnfc *cmd,
+		      u32 *rule_locs);
 void ice_fdir_release_flows(struct ice_hw *hw);
 int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 int ice_open(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index d11960b21474..f77db28e1e4c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -130,6 +130,8 @@ static const struct ice_stats ice_gstrings_pf_stats[] = {
 	ICE_PF_STAT("illegal_bytes.nic", stats.illegal_bytes),
 	ICE_PF_STAT("mac_local_faults.nic", stats.mac_local_faults),
 	ICE_PF_STAT("mac_remote_faults.nic", stats.mac_remote_faults),
+	ICE_PF_STAT("fdir_sb_match.nic", stats.fd_sb_match),
+	ICE_PF_STAT("fdir_sb_status.nic", stats.fd_sb_status),
 };
 
 static const u32 ice_regs_dump_list[] = {
@@ -2558,12 +2560,27 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 	int ret = -EOPNOTSUPP;
+	struct ice_hw *hw;
+
+	hw = &vsi->back->hw;
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
 		cmd->data = vsi->rss_size;
 		ret = 0;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = hw->fdir_active_fltr;
+		/* report total rule count */
+		cmd->data = ice_get_fdir_cnt_all(hw);
+		ret = 0;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = ice_get_ethtool_fdir_entry(hw, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = ice_get_fdir_fltr_ids(hw, cmd, (u32 *)rule_locs);
+		break;
 	case ETHTOOL_GRXFH:
 		ice_get_rss_hash_opt(vsi, cmd);
 		ret = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 425bf6f00db1..9276ebf96d28 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -12,6 +12,167 @@
  */
 #define TNL_SEG_CNT(_TNL_) ((_TNL_) + 1)
 
+/**
+ * ice_fltr_to_ethtool_flow - convert filter type values to ethtool
+ * flow type values
+ * @flow: filter type to be converted
+ *
+ * Returns the corresponding ethtool flow type.
+ */
+static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow)
+{
+	switch (flow) {
+	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
+		return TCP_V4_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
+		return UDP_V4_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV4_SCTP:
+		return SCTP_V4_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV4_OTHER:
+		return IPV4_USER_FLOW;
+	default:
+		/* 0 is undefined ethtool flow */
+		return 0;
+	}
+}
+
+/**
+ * ice_ethtool_flow_to_fltr - convert ethtool flow type to filter enum
+ * @eth: Ethtool flow type to be converted
+ *
+ * Returns flow enum
+ */
+static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth)
+{
+	switch (eth) {
+	case TCP_V4_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV4_TCP;
+	case UDP_V4_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+	case SCTP_V4_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV4_SCTP;
+	case IPV4_USER_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV4_OTHER;
+	default:
+		return ICE_FLTR_PTYPE_NONF_NONE;
+	}
+}
+
+/**
+ * ice_get_ethtool_fdir_entry - fill ethtool structure with fdir filter data
+ * @hw: hardware structure that contains filter list
+ * @cmd: ethtool command data structure to receive the filter data
+ *
+ * Returns 0 on success and -EINVAL on failure
+ */
+int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct ice_fdir_fltr *rule;
+	int ret = 0;
+	u16 idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	mutex_lock(&hw->fdir_fltr_lock);
+
+	rule = ice_fdir_find_fltr_by_idx(hw, fsp->location);
+
+	if (!rule || fsp->location != rule->fltr_id) {
+		ret = -EINVAL;
+		goto release_lock;
+	}
+
+	fsp->flow_type = ice_fltr_to_ethtool_flow(rule->flow_type);
+
+	memset(&fsp->m_u, 0, sizeof(fsp->m_u));
+	memset(&fsp->m_ext, 0, sizeof(fsp->m_ext));
+
+	switch (fsp->flow_type) {
+	case IPV4_USER_FLOW:
+		fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		fsp->h_u.usr_ip4_spec.proto = 0;
+		fsp->h_u.usr_ip4_spec.l4_4_bytes = rule->ip.l4_header;
+		fsp->h_u.usr_ip4_spec.tos = rule->ip.tos;
+		fsp->h_u.usr_ip4_spec.ip4src = rule->ip.src_ip;
+		fsp->h_u.usr_ip4_spec.ip4dst = rule->ip.dst_ip;
+		fsp->m_u.usr_ip4_spec.ip4src = rule->mask.src_ip;
+		fsp->m_u.usr_ip4_spec.ip4dst = rule->mask.dst_ip;
+		fsp->m_u.usr_ip4_spec.ip_ver = 0xFF;
+		fsp->m_u.usr_ip4_spec.proto = 0;
+		fsp->m_u.usr_ip4_spec.l4_4_bytes = rule->mask.l4_header;
+		fsp->m_u.usr_ip4_spec.tos = rule->mask.tos;
+		break;
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		fsp->h_u.tcp_ip4_spec.psrc = rule->ip.src_port;
+		fsp->h_u.tcp_ip4_spec.pdst = rule->ip.dst_port;
+		fsp->h_u.tcp_ip4_spec.ip4src = rule->ip.src_ip;
+		fsp->h_u.tcp_ip4_spec.ip4dst = rule->ip.dst_ip;
+		fsp->m_u.tcp_ip4_spec.psrc = rule->mask.src_port;
+		fsp->m_u.tcp_ip4_spec.pdst = rule->mask.dst_port;
+		fsp->m_u.tcp_ip4_spec.ip4src = rule->mask.src_ip;
+		fsp->m_u.tcp_ip4_spec.ip4dst = rule->mask.dst_ip;
+		break;
+	default:
+		break;
+	}
+
+	if (rule->dest_ctl == ICE_FLTR_PRGM_DESC_DEST_DROP_PKT)
+		fsp->ring_cookie = RX_CLS_FLOW_DISC;
+	else
+		fsp->ring_cookie = rule->q_index;
+
+	idx = ice_ethtool_flow_to_fltr(fsp->flow_type);
+	if (idx == ICE_FLTR_PTYPE_NONF_NONE) {
+		dev_err(ice_hw_to_dev(hw), "Missing input index for flow_type %d\n",
+			rule->flow_type);
+		ret = -EINVAL;
+	}
+
+release_lock:
+	mutex_unlock(&hw->fdir_fltr_lock);
+	return ret;
+}
+
+/**
+ * ice_get_fdir_fltr_ids - fill buffer with filter IDs of active filters
+ * @hw: hardware structure containing the filter list
+ * @cmd: ethtool command data structure
+ * @rule_locs: ethtool array passed in from OS to receive filter IDs
+ *
+ * Returns 0 as expected for success by ethtool
+ */
+int
+ice_get_fdir_fltr_ids(struct ice_hw *hw, struct ethtool_rxnfc *cmd,
+		      u32 *rule_locs)
+{
+	struct ice_fdir_fltr *f_rule;
+	unsigned int cnt = 0;
+	int val = 0;
+
+	/* report total rule count */
+	cmd->data = ice_get_fdir_cnt_all(hw);
+
+	mutex_lock(&hw->fdir_fltr_lock);
+
+	list_for_each_entry(f_rule, &hw->fdir_list_head, fltr_node) {
+		if (cnt == cmd->rule_cnt) {
+			val = -EMSGSIZE;
+			goto release_lock;
+		}
+		rule_locs[cnt] = f_rule->fltr_id;
+		cnt++;
+	}
+
+release_lock:
+	mutex_unlock(&hw->fdir_fltr_lock);
+	if (!val)
+		cmd->rule_cnt = cnt;
+	return val;
+}
+
 /**
  * ice_fdir_get_hw_prof - return the ice_fd_hw_proc associated with a flow
  * @hw: hardware structure containing the filter list
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 878fa4df9453..1f423e50182c 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -52,3 +52,36 @@ ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr)
 				  ICE_AQC_RES_TYPE_FLAG_DEDICATED, num_fltr,
 				  cntr_id);
 }
+
+/**
+ * ice_get_fdir_cnt_all - get the number of Flow Director filters
+ * @hw: hardware data structure
+ *
+ * Returns the number of filters available on device
+ */
+int ice_get_fdir_cnt_all(struct ice_hw *hw)
+{
+	return hw->func_caps.fd_fltr_guar + hw->func_caps.fd_fltr_best_effort;
+}
+
+/**
+ * ice_fdir_find_by_idx - find filter with idx
+ * @hw: pointer to hardware structure
+ * @fltr_idx: index to find.
+ *
+ * Returns pointer to filter if found or null
+ */
+struct ice_fdir_fltr *
+ice_fdir_find_fltr_by_idx(struct ice_hw *hw, u32 fltr_idx)
+{
+	struct ice_fdir_fltr *rule;
+
+	list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) {
+		/* rule ID found in the list */
+		if (fltr_idx == rule->fltr_id)
+			return rule;
+		if (fltr_idx < rule->fltr_id)
+			break;
+	}
+	return NULL;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index feac47adde6e..1b69249b40c1 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -3,10 +3,57 @@
 
 #ifndef _ICE_FDIR_H_
 #define _ICE_FDIR_H_
+
+enum ice_fltr_prgm_desc_dest {
+	ICE_FLTR_PRGM_DESC_DEST_DROP_PKT,
+	ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX,
+};
+
+struct ice_fdir_v4 {
+	__be32 dst_ip;
+	__be32 src_ip;
+	__be16 dst_port;
+	__be16 src_port;
+	__be32 l4_header;
+	__be32 sec_parm_idx;	/* security parameter index */
+	u8 tos;
+	u8 ip_ver;
+	u8 proto;
+};
+
+struct ice_fdir_extra {
+	u8 dst_mac[ETH_ALEN];	/* dest MAC address */
+	u32 usr_def[2];		/* user data */
+	__be16 vlan_type;	/* VLAN ethertype */
+	__be16 vlan_tag;	/* VLAN tag info */
+};
+
+struct ice_fdir_fltr {
+	struct list_head fltr_node;
+	enum ice_fltr_ptype flow_type;
+
+	struct ice_fdir_v4 ip;
+	struct ice_fdir_v4 mask;
+
+	struct ice_fdir_extra ext_data;
+	struct ice_fdir_extra ext_mask;
+
+	/* filter control */
+	u16 q_index;
+	u16 dest_vsi;
+	u8 dest_ctl;
+	u8 fltr_status;
+	u16 cnt_index;
+	u32 fltr_id;
+};
+
 enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
 enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
 enum ice_status
 ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
 enum ice_status
 ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
+int ice_get_fdir_cnt_all(struct ice_hw *hw);
+struct ice_fdir_fltr *
+ice_fdir_find_fltr_by_idx(struct ice_hw *hw, u32 fltr_idx);
 #endif /* _ICE_FDIR_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 3c61b2a04fc4..3376cdf5667f 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -344,6 +344,7 @@
 #define GLPRT_TDOLD(_i)				(0x00381280 + ((_i) * 8))
 #define GLPRT_UPRCL(_i)				(0x00381300 + ((_i) * 8))
 #define GLPRT_UPTCL(_i)				(0x003811C0 + ((_i) * 8))
+#define GLSTAT_FD_CNT0L(_i)			(0x003A0000 + ((_i) * 8))
 #define GLV_BPRCL(_i)				(0x003B6000 + ((_i) * 8))
 #define GLV_BPTCL(_i)				(0x0030E000 + ((_i) * 8))
 #define GLV_GORCL(_i)				(0x003B0000 + ((_i) * 8))
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2cc1f345c845..fecc3b29a4de 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4281,6 +4281,7 @@ void ice_update_pf_stats(struct ice_pf *pf)
 {
 	struct ice_hw_port_stats *prev_ps, *cur_ps;
 	struct ice_hw *hw = &pf->hw;
+	u16 fd_ctr_base;
 	u8 port;
 
 	port = hw->port_info->lport;
@@ -4369,6 +4370,12 @@ void ice_update_pf_stats(struct ice_pf *pf)
 	ice_stat_update40(hw, GLPRT_PTC9522L(port), pf->stat_prev_loaded,
 			  &prev_ps->tx_size_big, &cur_ps->tx_size_big);
 
+	fd_ctr_base = hw->fd_ctr_base;
+
+	ice_stat_update40(hw,
+			  GLSTAT_FD_CNT0L(ICE_FD_SB_STAT_IDX(fd_ctr_base)),
+			  pf->stat_prev_loaded, &prev_ps->fd_sb_match,
+			  &cur_ps->fd_sb_match);
 	ice_stat_update32(hw, GLPRT_LXONRXC(port), pf->stat_prev_loaded,
 			  &prev_ps->link_xon_rx, &cur_ps->link_xon_rx);
 
@@ -4412,6 +4419,8 @@ void ice_update_pf_stats(struct ice_pf *pf)
 	ice_stat_update32(hw, GLPRT_RJC(port), pf->stat_prev_loaded,
 			  &prev_ps->rx_jabber, &cur_ps->rx_jabber);
 
+	cur_ps->fd_sb_status = test_bit(ICE_FLAG_FD_ENA, pf->flags) ? 1 : 0;
+
 	pf->stat_prev_loaded = true;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 74bdc00e869c..0c14d89f7be9 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -691,6 +691,9 @@ struct ice_hw_port_stats {
 	u64 tx_size_1023;		/* ptc1023 */
 	u64 tx_size_1522;		/* ptc1522 */
 	u64 tx_size_big;		/* ptc9522 */
+	/* flow director stats */
+	u32 fd_sb_status;
+	u64 fd_sb_match;
 };
 
 /* Checksum and Shadow RAM pointers */
-- 
cgit v1.2.3


From cac2a27cd9ab1638e21df11ec583d2bc919a3ae3 Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:42 -0700
Subject: ice: Support IPv4 Flow Director filters

Support the addition and deletion of IPv4 filters.

Supported fields are: src-ip, dst-ip, src-port, and dst-port
Supported flow-types are: tcp4, udp4, sctp4, ip4

Example usage:

ethtool -N eth0 flow-type tcp4 src-ip 192.168.0.55 dst-ip 172.16.0.55 \
src-port 16 dst-port 12 action 32

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h              |   4 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c      |   4 +
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 658 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_fdir.c         | 513 +++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_fdir.h         |  79 +++
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c    |  34 ++
 drivers/net/ethernet/intel/ice/ice_flex_pipe.h    |   3 +
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h   |   6 +
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h    | 101 ++++
 drivers/net/ethernet/intel/ice/ice_txrx.c         |  82 +++
 drivers/net/ethernet/intel/ice/ice_txrx.h         |   3 +
 drivers/net/ethernet/intel/ice/ice_type.h         |   6 +
 12 files changed, 1493 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index e0c9e4a30d82..298a65a3799c 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -96,6 +96,7 @@ extern const char ice_drv_ver[];
 #define ICE_TX_DESC(R, i) (&(((struct ice_tx_desc *)((R)->desc))[i]))
 #define ICE_RX_DESC(R, i) (&(((union ice_32b_rx_flex_desc *)((R)->desc))[i]))
 #define ICE_TX_CTX_DESC(R, i) (&(((struct ice_tx_ctx_desc *)((R)->desc))[i]))
+#define ICE_TX_FDIRDESC(R, i) (&(((struct ice_fltr_desc *)((R)->desc))[i]))
 
 /* Macro for each VSI in a PF */
 #define ice_for_each_vsi(pf, i) \
@@ -216,6 +217,7 @@ enum ice_state {
 	__ICE_CFG_BUSY,
 	__ICE_SERVICE_SCHED,
 	__ICE_SERVICE_DIS,
+	__ICE_FD_FLUSH_REQ,
 	__ICE_OICR_INTR_DIS,		/* Global OICR interrupt disabled */
 	__ICE_MDD_VF_PRINT_PENDING,	/* set when MDD event handle */
 	__ICE_VF_RESETS_DISABLED,	/* disable resets during ice_remove */
@@ -557,6 +559,8 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
 void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena);
+int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd);
+int ice_del_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd);
 int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd);
 int
 ice_get_fdir_fltr_ids(struct ice_hw *hw, struct ethtool_rxnfc *cmd,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index f77db28e1e4c..72105d70cead 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2537,6 +2537,10 @@ static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 	struct ice_vsi *vsi = np->vsi;
 
 	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		return ice_add_fdir_ethtool(vsi, cmd);
+	case ETHTOOL_SRXCLSRLDEL:
+		return ice_del_fdir_ethtool(vsi, cmd);
 	case ETHTOOL_SRXFH:
 		return ice_set_rss_hash_opt(vsi, cmd);
 	default:
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 9276ebf96d28..6badf2ef2255 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -265,6 +265,43 @@ void ice_fdir_release_flows(struct ice_hw *hw)
 		ice_fdir_erase_flow_from_hw(hw, ICE_BLK_FD, flow);
 }
 
+/**
+ * ice_fdir_num_avail_fltr - return the number of unused flow director filters
+ * @hw: pointer to hardware structure
+ * @vsi: software VSI structure
+ *
+ * There are 2 filter pools: guaranteed and best effort(shared). Each VSI can
+ * use filters from either pool. The guaranteed pool is divided between VSIs.
+ * The best effort filter pool is common to all VSIs and is a device shared
+ * resource pool. The number of filters available to this VSI is the sum of
+ * the VSIs guaranteed filter pool and the global available best effort
+ * filter pool.
+ *
+ * Returns the number of available flow director filters to this VSI
+ */
+static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
+{
+	u16 vsi_num = ice_get_hw_vsi_num(hw, vsi->idx);
+	u16 num_guar;
+	u16 num_be;
+
+	/* total guaranteed filters assigned to this VSI */
+	num_guar = vsi->num_gfltr;
+
+	/* minus the guaranteed filters programed by this VSI */
+	num_guar -= (rd32(hw, VSIQF_FD_CNT(vsi_num)) &
+		     VSIQF_FD_CNT_FD_GCNT_M) >> VSIQF_FD_CNT_FD_GCNT_S;
+
+	/* total global best effort filters */
+	num_be = hw->func_caps.fd_fltr_best_effort;
+
+	/* minus the global best effort filters programmed */
+	num_be -= (rd32(hw, GLQF_FD_CNT) & GLQF_FD_CNT_FD_BCNT_M) >>
+		   GLQF_FD_CNT_FD_BCNT_S;
+
+	return num_guar + num_be;
+}
+
 /**
  * ice_fdir_alloc_flow_prof - allocate FDir flow profile structure(s)
  * @hw: HW structure containing the FDir flow profile structure(s)
@@ -344,6 +381,14 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 		if (!memcmp(old_seg, seg, sizeof(*seg)))
 			return -EEXIST;
 
+		/* if there are FDir filters using this flow,
+		 * then return error.
+		 */
+		if (hw->fdir_fltr_cnt[flow]) {
+			dev_err(dev, "Failed to add filter.  Flow director filters on each port must have the same input set.\n");
+			return -EINVAL;
+		}
+
 		/* remove HW filter definition */
 		ice_fdir_rem_flow(hw, ICE_BLK_FD, flow);
 	}
@@ -508,6 +553,347 @@ err_exit:
 	return -EOPNOTSUPP;
 }
 
+/**
+ * ice_set_fdir_ip4_seg
+ * @seg: flow segment for programming
+ * @tcp_ip4_spec: mask data from ethtool
+ * @l4_proto: Layer 4 protocol to program
+ * @perfect_fltr: only valid on success; returns true if perfect filter,
+ *		  false if not
+ *
+ * Set the mask data into the flow segment to be used to program HW
+ * table based on provided L4 protocol for IPv4
+ */
+static int
+ice_set_fdir_ip4_seg(struct ice_flow_seg_info *seg,
+		     struct ethtool_tcpip4_spec *tcp_ip4_spec,
+		     enum ice_flow_seg_hdr l4_proto, bool *perfect_fltr)
+{
+	enum ice_flow_field src_port, dst_port;
+
+	/* make sure we don't have any empty rule */
+	if (!tcp_ip4_spec->psrc && !tcp_ip4_spec->ip4src &&
+	    !tcp_ip4_spec->pdst && !tcp_ip4_spec->ip4dst)
+		return -EINVAL;
+
+	/* filtering on TOS not supported */
+	if (tcp_ip4_spec->tos)
+		return -EOPNOTSUPP;
+
+	if (l4_proto == ICE_FLOW_SEG_HDR_TCP) {
+		src_port = ICE_FLOW_FIELD_IDX_TCP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_TCP_DST_PORT;
+	} else if (l4_proto == ICE_FLOW_SEG_HDR_UDP) {
+		src_port = ICE_FLOW_FIELD_IDX_UDP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_UDP_DST_PORT;
+	} else if (l4_proto == ICE_FLOW_SEG_HDR_SCTP) {
+		src_port = ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_SCTP_DST_PORT;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	*perfect_fltr = true;
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV4 | l4_proto);
+
+	/* IP source address */
+	if (tcp_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_SA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!tcp_ip4_spec->ip4src)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* IP destination address */
+	if (tcp_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_DA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!tcp_ip4_spec->ip4dst)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* Layer 4 source port */
+	if (tcp_ip4_spec->psrc == htons(0xFFFF))
+		ice_flow_set_fld(seg, src_port, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 false);
+	else if (!tcp_ip4_spec->psrc)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* Layer 4 destination port */
+	if (tcp_ip4_spec->pdst == htons(0xFFFF))
+		ice_flow_set_fld(seg, dst_port, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 false);
+	else if (!tcp_ip4_spec->pdst)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/**
+ * ice_set_fdir_ip4_usr_seg
+ * @seg: flow segment for programming
+ * @usr_ip4_spec: ethtool userdef packet offset
+ * @perfect_fltr: only valid on success; returns true if perfect filter,
+ *		  false if not
+ *
+ * Set the offset data into the flow segment to be used to program HW
+ * table for IPv4
+ */
+static int
+ice_set_fdir_ip4_usr_seg(struct ice_flow_seg_info *seg,
+			 struct ethtool_usrip4_spec *usr_ip4_spec,
+			 bool *perfect_fltr)
+{
+	/* first 4 bytes of Layer 4 header */
+	if (usr_ip4_spec->l4_4_bytes)
+		return -EINVAL;
+	if (usr_ip4_spec->tos)
+		return -EINVAL;
+	if (usr_ip4_spec->ip_ver)
+		return -EINVAL;
+	/* Filtering on Layer 4 protocol not supported */
+	if (usr_ip4_spec->proto)
+		return -EOPNOTSUPP;
+	/* empty rules are not valid */
+	if (!usr_ip4_spec->ip4src && !usr_ip4_spec->ip4dst)
+		return -EINVAL;
+
+	*perfect_fltr = true;
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV4);
+
+	/* IP source address */
+	if (usr_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_SA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!usr_ip4_spec->ip4src)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* IP destination address */
+	if (usr_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_DA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!usr_ip4_spec->ip4dst)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/**
+ * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter
+ * @pf: PF structure
+ * @fsp: pointer to ethtool Rx flow specification
+ *
+ * Returns 0 on success.
+ */
+static int
+ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp)
+{
+	struct ice_flow_seg_info *seg, *tun_seg;
+	struct device *dev = ice_pf_to_dev(pf);
+	enum ice_fltr_ptype fltr_idx;
+	struct ice_hw *hw = &pf->hw;
+	bool perfect_filter;
+	int ret;
+
+	seg = devm_kzalloc(dev, sizeof(*seg), GFP_KERNEL);
+	if (!seg)
+		return -ENOMEM;
+
+	tun_seg = devm_kzalloc(dev, sizeof(*seg) * ICE_FD_HW_SEG_MAX,
+			       GFP_KERNEL);
+	if (!tun_seg) {
+		devm_kfree(dev, seg);
+		return -ENOMEM;
+	}
+
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case TCP_V4_FLOW:
+		ret = ice_set_fdir_ip4_seg(seg, &fsp->m_u.tcp_ip4_spec,
+					   ICE_FLOW_SEG_HDR_TCP,
+					   &perfect_filter);
+		break;
+	case UDP_V4_FLOW:
+		ret = ice_set_fdir_ip4_seg(seg, &fsp->m_u.tcp_ip4_spec,
+					   ICE_FLOW_SEG_HDR_UDP,
+					   &perfect_filter);
+		break;
+	case SCTP_V4_FLOW:
+		ret = ice_set_fdir_ip4_seg(seg, &fsp->m_u.tcp_ip4_spec,
+					   ICE_FLOW_SEG_HDR_SCTP,
+					   &perfect_filter);
+		break;
+	case IPV4_USER_FLOW:
+		ret = ice_set_fdir_ip4_usr_seg(seg, &fsp->m_u.usr_ip4_spec,
+					       &perfect_filter);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	if (ret)
+		goto err_exit;
+
+	/* tunnel segments are shifted up one. */
+	memcpy(&tun_seg[1], seg, sizeof(*seg));
+
+	/* add filter for outer headers */
+	fltr_idx = ice_ethtool_flow_to_fltr(fsp->flow_type & ~FLOW_EXT);
+	ret = ice_fdir_set_hw_fltr_rule(pf, seg, fltr_idx,
+					ICE_FD_HW_SEG_NON_TUN);
+	if (ret == -EEXIST)
+		/* Rule already exists, free memory and continue */
+		devm_kfree(dev, seg);
+	else if (ret)
+		/* could not write filter, free memory */
+		goto err_exit;
+
+	/* make tunneled filter HW entries if possible */
+	memcpy(&tun_seg[1], seg, sizeof(*seg));
+	ret = ice_fdir_set_hw_fltr_rule(pf, tun_seg, fltr_idx,
+					ICE_FD_HW_SEG_TUN);
+	if (ret == -EEXIST) {
+		/* Rule already exists, free memory and count as success */
+		devm_kfree(dev, tun_seg);
+		ret = 0;
+	} else if (ret) {
+		/* could not write tunnel filter, but outer filter exists */
+		devm_kfree(dev, tun_seg);
+	}
+
+	if (perfect_filter)
+		set_bit(fltr_idx, hw->fdir_perfect_fltr);
+	else
+		clear_bit(fltr_idx, hw->fdir_perfect_fltr);
+
+	return ret;
+
+err_exit:
+	devm_kfree(dev, tun_seg);
+	devm_kfree(dev, seg);
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ice_fdir_write_fltr - send a flow director filter to the hardware
+ * @pf: PF data structure
+ * @input: filter structure
+ * @add: true adds filter and false removed filter
+ * @is_tun: true adds inner filter on tunnel and false outer headers
+ *
+ * returns 0 on success and negative value on error
+ */
+static int
+ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add,
+		    bool is_tun)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct ice_hw *hw = &pf->hw;
+	struct ice_fltr_desc desc;
+	struct ice_vsi *ctrl_vsi;
+	enum ice_status status;
+	u8 *pkt, *frag_pkt;
+	bool has_frag;
+	int err;
+
+	ctrl_vsi = ice_get_ctrl_vsi(pf);
+	if (!ctrl_vsi)
+		return -EINVAL;
+
+	pkt = devm_kzalloc(dev, ICE_FDIR_MAX_RAW_PKT_SIZE, GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+	frag_pkt = devm_kzalloc(dev, ICE_FDIR_MAX_RAW_PKT_SIZE, GFP_KERNEL);
+	if (!frag_pkt) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	ice_fdir_get_prgm_desc(hw, input, &desc, add);
+	status = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun);
+	if (status) {
+		err = ice_status_to_errno(status);
+		goto err_free_all;
+	}
+	err = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt);
+	if (err)
+		goto err_free_all;
+
+	/* repeat for fragment packet */
+	has_frag = ice_fdir_has_frag(input->flow_type);
+	if (has_frag) {
+		/* does not return error */
+		ice_fdir_get_prgm_desc(hw, input, &desc, add);
+		status = ice_fdir_get_gen_prgm_pkt(hw, input, frag_pkt, true,
+						   is_tun);
+		if (status) {
+			err = ice_status_to_errno(status);
+			goto err_frag;
+		}
+		err = ice_prgm_fdir_fltr(ctrl_vsi, &desc, frag_pkt);
+		if (err)
+			goto err_frag;
+	} else {
+		devm_kfree(dev, frag_pkt);
+	}
+
+	return 0;
+
+err_free_all:
+	devm_kfree(dev, frag_pkt);
+err_free:
+	devm_kfree(dev, pkt);
+	return err;
+
+err_frag:
+	devm_kfree(dev, frag_pkt);
+	return err;
+}
+
+/**
+ * ice_fdir_write_all_fltr - send a flow director filter to the hardware
+ * @pf: PF data structure
+ * @input: filter structure
+ * @add: true adds filter and false removed filter
+ *
+ * returns 0 on success and negative value on error
+ */
+static int
+ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input,
+			bool add)
+{
+	u16 port_num;
+	int tun;
+
+	for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
+		bool is_tun = tun == ICE_FD_HW_SEG_TUN;
+		int err;
+
+		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, TNL_ALL,
+							&port_num))
+			continue;
+		err = ice_fdir_write_fltr(pf, input, add, is_tun);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 /**
  * ice_fdir_create_dflt_rules - create default perfect filters
  * @pf: PF data structure
@@ -535,6 +921,7 @@ int ice_fdir_create_dflt_rules(struct ice_pf *pf)
  */
 void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena)
 {
+	struct ice_fdir_fltr *f_rule, *tmp;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	enum ice_fltr_ptype flow;
@@ -548,6 +935,13 @@ void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena)
 	mutex_lock(&hw->fdir_fltr_lock);
 	if (!test_and_clear_bit(ICE_FLAG_FD_ENA, pf->flags))
 		goto release_lock;
+	list_for_each_entry_safe(f_rule, tmp, &hw->fdir_list_head, fltr_node) {
+		/* ignore return value */
+		ice_fdir_write_all_fltr(pf, f_rule, false);
+		ice_fdir_update_cntrs(hw, f_rule->flow_type, false);
+		list_del(&f_rule->fltr_node);
+		devm_kfree(ice_hw_to_dev(hw), f_rule);
+	}
 
 	if (hw->fdir_prof)
 		for (flow = ICE_FLTR_PTYPE_NONF_NONE; flow < ICE_FLTR_PTYPE_MAX;
@@ -558,3 +952,267 @@ void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena)
 release_lock:
 	mutex_unlock(&hw->fdir_fltr_lock);
 }
+
+/**
+ * ice_fdir_update_list_entry - add or delete a filter from the filter list
+ * @pf: PF structure
+ * @input: filter structure
+ * @fltr_idx: ethtool index of filter to modify
+ *
+ * returns 0 on success and negative on errors
+ */
+static int
+ice_fdir_update_list_entry(struct ice_pf *pf, struct ice_fdir_fltr *input,
+			   int fltr_idx)
+{
+	struct ice_fdir_fltr *old_fltr;
+	struct ice_hw *hw = &pf->hw;
+	int err = -ENOENT;
+
+	/* Do not update filters during reset */
+	if (ice_is_reset_in_progress(pf->state))
+		return -EBUSY;
+
+	old_fltr = ice_fdir_find_fltr_by_idx(hw, fltr_idx);
+	if (old_fltr) {
+		err = ice_fdir_write_all_fltr(pf, old_fltr, false);
+		if (err)
+			return err;
+		ice_fdir_update_cntrs(hw, old_fltr->flow_type, false);
+		if (!input && !hw->fdir_fltr_cnt[old_fltr->flow_type])
+			/* we just deleted the last filter of flow_type so we
+			 * should also delete the HW filter info.
+			 */
+			ice_fdir_rem_flow(hw, ICE_BLK_FD, old_fltr->flow_type);
+		list_del(&old_fltr->fltr_node);
+		devm_kfree(ice_hw_to_dev(hw), old_fltr);
+	}
+	if (!input)
+		return err;
+	ice_fdir_list_add_fltr(hw, input);
+	ice_fdir_update_cntrs(hw, input->flow_type, true);
+	return 0;
+}
+
+/**
+ * ice_del_fdir_ethtool - delete Flow Director filter
+ * @vsi: pointer to target VSI
+ * @cmd: command to add or delete Flow Director filter
+ *
+ * Returns 0 on success and negative values for failure
+ */
+int ice_del_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	int val;
+
+	if (!test_bit(ICE_FLAG_FD_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	/* Do not delete filters during reset */
+	if (ice_is_reset_in_progress(pf->state)) {
+		dev_err(ice_pf_to_dev(pf), "Device is resetting - deleting Flow Director filters not supported during reset\n");
+		return -EBUSY;
+	}
+
+	if (test_bit(__ICE_FD_FLUSH_REQ, pf->state))
+		return -EBUSY;
+
+	mutex_lock(&hw->fdir_fltr_lock);
+	val = ice_fdir_update_list_entry(pf, NULL, fsp->location);
+	mutex_unlock(&hw->fdir_fltr_lock);
+
+	return val;
+}
+
+/**
+ * ice_set_fdir_input_set - Set the input set for Flow Director
+ * @vsi: pointer to target VSI
+ * @fsp: pointer to ethtool Rx flow specification
+ * @input: filter structure
+ */
+static int
+ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp,
+		       struct ice_fdir_fltr *input)
+{
+	u16 dest_vsi, q_index = 0;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int flow_type;
+	u8 dest_ctl;
+
+	if (!vsi || !fsp || !input)
+		return -EINVAL;
+
+	pf = vsi->back;
+	hw = &pf->hw;
+
+	dest_vsi = vsi->idx;
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DROP_PKT;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (vf) {
+			dev_err(ice_pf_to_dev(pf), "Failed to add filter. Flow director filters are not supported on VF queues.\n");
+			return -EINVAL;
+		}
+
+		if (ring >= vsi->num_rxq)
+			return -EINVAL;
+
+		dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX;
+		q_index = ring;
+	}
+
+	input->fltr_id = fsp->location;
+	input->q_index = q_index;
+	flow_type = fsp->flow_type & ~FLOW_EXT;
+
+	input->dest_vsi = dest_vsi;
+	input->dest_ctl = dest_ctl;
+	input->fltr_status = ICE_FLTR_PRGM_DESC_FD_STATUS_FD_ID;
+	input->cnt_index = ICE_FD_SB_STAT_IDX(hw->fd_ctr_base);
+	input->flow_type = ice_ethtool_flow_to_fltr(flow_type);
+
+	if (fsp->flow_type & FLOW_EXT) {
+		memcpy(input->ext_data.usr_def, fsp->h_ext.data,
+		       sizeof(input->ext_data.usr_def));
+		input->ext_data.vlan_type = fsp->h_ext.vlan_etype;
+		input->ext_data.vlan_tag = fsp->h_ext.vlan_tci;
+		memcpy(input->ext_mask.usr_def, fsp->m_ext.data,
+		       sizeof(input->ext_mask.usr_def));
+		input->ext_mask.vlan_type = fsp->m_ext.vlan_etype;
+		input->ext_mask.vlan_tag = fsp->m_ext.vlan_tci;
+	}
+
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		input->ip.dst_port = fsp->h_u.tcp_ip4_spec.pdst;
+		input->ip.src_port = fsp->h_u.tcp_ip4_spec.psrc;
+		input->ip.dst_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+		input->ip.src_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+		input->mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst;
+		input->mask.src_port = fsp->m_u.tcp_ip4_spec.psrc;
+		input->mask.dst_ip = fsp->m_u.tcp_ip4_spec.ip4dst;
+		input->mask.src_ip = fsp->m_u.tcp_ip4_spec.ip4src;
+		break;
+	case IPV4_USER_FLOW:
+		input->ip.dst_ip = fsp->h_u.usr_ip4_spec.ip4dst;
+		input->ip.src_ip = fsp->h_u.usr_ip4_spec.ip4src;
+		input->ip.l4_header = fsp->h_u.usr_ip4_spec.l4_4_bytes;
+		input->ip.proto = fsp->h_u.usr_ip4_spec.proto;
+		input->ip.ip_ver = fsp->h_u.usr_ip4_spec.ip_ver;
+		input->ip.tos = fsp->h_u.usr_ip4_spec.tos;
+		input->mask.dst_ip = fsp->m_u.usr_ip4_spec.ip4dst;
+		input->mask.src_ip = fsp->m_u.usr_ip4_spec.ip4src;
+		input->mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes;
+		input->mask.proto = fsp->m_u.usr_ip4_spec.proto;
+		input->mask.ip_ver = fsp->m_u.usr_ip4_spec.ip_ver;
+		input->mask.tos = fsp->m_u.usr_ip4_spec.tos;
+		break;
+	default:
+		/* not doing un-parsed flow types */
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_add_fdir_ethtool - Add/Remove Flow Director filter
+ * @vsi: pointer to target VSI
+ * @cmd: command to add or delete Flow Director filter
+ *
+ * Returns 0 on success and negative values for failure
+ */
+int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct ice_fdir_fltr *input;
+	struct device *dev;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int fltrs_needed;
+	u16 tunnel_port;
+	int ret;
+
+	if (!vsi)
+		return -EINVAL;
+
+	pf = vsi->back;
+	hw = &pf->hw;
+	dev = ice_pf_to_dev(pf);
+
+	if (!test_bit(ICE_FLAG_FD_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	/* Do not program filters during reset */
+	if (ice_is_reset_in_progress(pf->state)) {
+		dev_err(dev, "Device is resetting - adding Flow Director filters not supported during reset\n");
+		return -EBUSY;
+	}
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->flow_type & FLOW_MAC_EXT)
+		return -EINVAL;
+
+	ret = ice_cfg_fdir_xtrct_seq(pf, fsp);
+	if (ret)
+		return ret;
+
+	if (fsp->location >= ice_get_fdir_cnt_all(hw)) {
+		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
+		return -ENOSPC;
+	}
+
+	/* return error if not an update and no available filters */
+	fltrs_needed = ice_get_open_tunnel_port(hw, TNL_ALL, &tunnel_port) ?
+		2 : 1;
+	if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
+	    ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
+		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
+		return -ENOSPC;
+	}
+
+	input = devm_kzalloc(dev, sizeof(*input), GFP_KERNEL);
+	if (!input)
+		return -ENOMEM;
+
+	ret = ice_set_fdir_input_set(vsi, fsp, input);
+	if (ret)
+		goto free_input;
+
+	mutex_lock(&hw->fdir_fltr_lock);
+	if (ice_fdir_is_dup_fltr(hw, input)) {
+		ret = -EINVAL;
+		goto release_lock;
+	}
+
+	/* input struct is added to the HW filter list */
+	ice_fdir_update_list_entry(pf, input, fsp->location);
+
+	ret = ice_fdir_write_all_fltr(pf, input, true);
+	if (ret)
+		goto remove_sw_rule;
+
+	goto release_lock;
+
+remove_sw_rule:
+	ice_fdir_update_cntrs(hw, input->flow_type, false);
+	list_del(&input->fltr_node);
+release_lock:
+	mutex_unlock(&hw->fdir_fltr_lock);
+free_input:
+	if (ret)
+		devm_kfree(dev, input);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 1f423e50182c..60a824363f06 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -3,6 +3,261 @@
 
 #include "ice_common.h"
 
+/* These are training packet headers used to program flow director filters. */
+static const u8 ice_fdir_tcpv4_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x28, 0x00, 0x01, 0x00, 0x00, 0x40, 0x06,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x00,
+	0x20, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+
+static const u8 ice_fdir_udpv4_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x1C, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00,
+};
+
+static const u8 ice_fdir_sctpv4_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x20, 0x00, 0x00, 0x40, 0x00, 0x40, 0x84,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_ipv4_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x14, 0x00, 0x00, 0x40, 0x00, 0x40, 0x10,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00
+};
+
+static const u8 ice_fdir_tcp4_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x5a, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00,
+	0x45, 0x00, 0x00, 0x28, 0x00, 0x00, 0x40, 0x00,
+	0x40, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x50, 0x00, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_udp4_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x4e, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00,
+	0x45, 0x00, 0x00, 0x1c, 0x00, 0x00, 0x40, 0x00,
+	0x40, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_sctp4_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x52, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00,
+	0x45, 0x00, 0x00, 0x20, 0x00, 0x01, 0x00, 0x00,
+	0x40, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_ip4_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x46, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00,
+	0x45, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x00,
+	0x40, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+};
+
+/* Flow Director no-op training packet table */
+static const struct ice_fdir_base_pkt ice_fdir_pkt[] = {
+	{
+		ICE_FLTR_PTYPE_NONF_IPV4_TCP,
+		sizeof(ice_fdir_tcpv4_pkt), ice_fdir_tcpv4_pkt,
+		sizeof(ice_fdir_tcp4_tun_pkt), ice_fdir_tcp4_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV4_UDP,
+		sizeof(ice_fdir_udpv4_pkt), ice_fdir_udpv4_pkt,
+		sizeof(ice_fdir_udp4_tun_pkt), ice_fdir_udp4_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV4_SCTP,
+		sizeof(ice_fdir_sctpv4_pkt), ice_fdir_sctpv4_pkt,
+		sizeof(ice_fdir_sctp4_tun_pkt), ice_fdir_sctp4_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV4_OTHER,
+		sizeof(ice_fdir_ipv4_pkt), ice_fdir_ipv4_pkt,
+		sizeof(ice_fdir_ip4_tun_pkt), ice_fdir_ip4_tun_pkt,
+	},
+};
+
+#define ICE_FDIR_NUM_PKT ARRAY_SIZE(ice_fdir_pkt)
+
+/**
+ * ice_set_dflt_val_fd_desc
+ * @fd_fltr_ctx: pointer to fd filter descriptor
+ */
+static void ice_set_dflt_val_fd_desc(struct ice_fd_fltr_desc_ctx *fd_fltr_ctx)
+{
+	fd_fltr_ctx->comp_q = ICE_FXD_FLTR_QW0_COMP_Q_ZERO;
+	fd_fltr_ctx->comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL;
+	fd_fltr_ctx->fd_space = ICE_FXD_FLTR_QW0_FD_SPACE_GUAR_BEST;
+	fd_fltr_ctx->cnt_ena = ICE_FXD_FLTR_QW0_STAT_ENA_PKTS;
+	fd_fltr_ctx->evict_ena = ICE_FXD_FLTR_QW0_EVICT_ENA_TRUE;
+	fd_fltr_ctx->toq = ICE_FXD_FLTR_QW0_TO_Q_EQUALS_QINDEX;
+	fd_fltr_ctx->toq_prio = ICE_FXD_FLTR_QW0_TO_Q_PRIO1;
+	fd_fltr_ctx->dpu_recipe = ICE_FXD_FLTR_QW0_DPU_RECIPE_DFLT;
+	fd_fltr_ctx->drop = ICE_FXD_FLTR_QW0_DROP_NO;
+	fd_fltr_ctx->flex_prio = ICE_FXD_FLTR_QW0_FLEX_PRI_NONE;
+	fd_fltr_ctx->flex_mdid = ICE_FXD_FLTR_QW0_FLEX_MDID0;
+	fd_fltr_ctx->flex_val = ICE_FXD_FLTR_QW0_FLEX_VAL0;
+	fd_fltr_ctx->dtype = ICE_TX_DESC_DTYPE_FLTR_PROG;
+	fd_fltr_ctx->desc_prof_prio = ICE_FXD_FLTR_QW1_PROF_PRIO_ZERO;
+	fd_fltr_ctx->desc_prof = ICE_FXD_FLTR_QW1_PROF_ZERO;
+	fd_fltr_ctx->swap = ICE_FXD_FLTR_QW1_SWAP_SET;
+	fd_fltr_ctx->fdid_prio = ICE_FXD_FLTR_QW1_FDID_PRI_ONE;
+	fd_fltr_ctx->fdid_mdid = ICE_FXD_FLTR_QW1_FDID_MDID_FD;
+	fd_fltr_ctx->fdid = ICE_FXD_FLTR_QW1_FDID_ZERO;
+}
+
+/**
+ * ice_set_fd_desc_val
+ * @ctx: pointer to fd filter descriptor context
+ * @fdir_desc: populated with fd filter descriptor values
+ */
+static void
+ice_set_fd_desc_val(struct ice_fd_fltr_desc_ctx *ctx,
+		    struct ice_fltr_desc *fdir_desc)
+{
+	u64 qword;
+
+	/* prep QW0 of FD filter programming desc */
+	qword = ((u64)ctx->qindex << ICE_FXD_FLTR_QW0_QINDEX_S) &
+		ICE_FXD_FLTR_QW0_QINDEX_M;
+	qword |= ((u64)ctx->comp_q << ICE_FXD_FLTR_QW0_COMP_Q_S) &
+		 ICE_FXD_FLTR_QW0_COMP_Q_M;
+	qword |= ((u64)ctx->comp_report << ICE_FXD_FLTR_QW0_COMP_REPORT_S) &
+		 ICE_FXD_FLTR_QW0_COMP_REPORT_M;
+	qword |= ((u64)ctx->fd_space << ICE_FXD_FLTR_QW0_FD_SPACE_S) &
+		 ICE_FXD_FLTR_QW0_FD_SPACE_M;
+	qword |= ((u64)ctx->cnt_index << ICE_FXD_FLTR_QW0_STAT_CNT_S) &
+		 ICE_FXD_FLTR_QW0_STAT_CNT_M;
+	qword |= ((u64)ctx->cnt_ena << ICE_FXD_FLTR_QW0_STAT_ENA_S) &
+		 ICE_FXD_FLTR_QW0_STAT_ENA_M;
+	qword |= ((u64)ctx->evict_ena << ICE_FXD_FLTR_QW0_EVICT_ENA_S) &
+		 ICE_FXD_FLTR_QW0_EVICT_ENA_M;
+	qword |= ((u64)ctx->toq << ICE_FXD_FLTR_QW0_TO_Q_S) &
+		 ICE_FXD_FLTR_QW0_TO_Q_M;
+	qword |= ((u64)ctx->toq_prio << ICE_FXD_FLTR_QW0_TO_Q_PRI_S) &
+		 ICE_FXD_FLTR_QW0_TO_Q_PRI_M;
+	qword |= ((u64)ctx->dpu_recipe << ICE_FXD_FLTR_QW0_DPU_RECIPE_S) &
+		 ICE_FXD_FLTR_QW0_DPU_RECIPE_M;
+	qword |= ((u64)ctx->drop << ICE_FXD_FLTR_QW0_DROP_S) &
+		 ICE_FXD_FLTR_QW0_DROP_M;
+	qword |= ((u64)ctx->flex_prio << ICE_FXD_FLTR_QW0_FLEX_PRI_S) &
+		 ICE_FXD_FLTR_QW0_FLEX_PRI_M;
+	qword |= ((u64)ctx->flex_mdid << ICE_FXD_FLTR_QW0_FLEX_MDID_S) &
+		 ICE_FXD_FLTR_QW0_FLEX_MDID_M;
+	qword |= ((u64)ctx->flex_val << ICE_FXD_FLTR_QW0_FLEX_VAL_S) &
+		 ICE_FXD_FLTR_QW0_FLEX_VAL_M;
+	fdir_desc->qidx_compq_space_stat = cpu_to_le64(qword);
+
+	/* prep QW1 of FD filter programming desc */
+	qword = ((u64)ctx->dtype << ICE_FXD_FLTR_QW1_DTYPE_S) &
+		ICE_FXD_FLTR_QW1_DTYPE_M;
+	qword |= ((u64)ctx->pcmd << ICE_FXD_FLTR_QW1_PCMD_S) &
+		 ICE_FXD_FLTR_QW1_PCMD_M;
+	qword |= ((u64)ctx->desc_prof_prio << ICE_FXD_FLTR_QW1_PROF_PRI_S) &
+		 ICE_FXD_FLTR_QW1_PROF_PRI_M;
+	qword |= ((u64)ctx->desc_prof << ICE_FXD_FLTR_QW1_PROF_S) &
+		 ICE_FXD_FLTR_QW1_PROF_M;
+	qword |= ((u64)ctx->fd_vsi << ICE_FXD_FLTR_QW1_FD_VSI_S) &
+		 ICE_FXD_FLTR_QW1_FD_VSI_M;
+	qword |= ((u64)ctx->swap << ICE_FXD_FLTR_QW1_SWAP_S) &
+		 ICE_FXD_FLTR_QW1_SWAP_M;
+	qword |= ((u64)ctx->fdid_prio << ICE_FXD_FLTR_QW1_FDID_PRI_S) &
+		 ICE_FXD_FLTR_QW1_FDID_PRI_M;
+	qword |= ((u64)ctx->fdid_mdid << ICE_FXD_FLTR_QW1_FDID_MDID_S) &
+		 ICE_FXD_FLTR_QW1_FDID_MDID_M;
+	qword |= ((u64)ctx->fdid << ICE_FXD_FLTR_QW1_FDID_S) &
+		 ICE_FXD_FLTR_QW1_FDID_M;
+	fdir_desc->dtype_cmd_vsi_fdid = cpu_to_le64(qword);
+}
+
+/**
+ * ice_fdir_get_prgm_desc - set a fdir descriptor from a fdir filter struct
+ * @hw: pointer to the hardware structure
+ * @input: filter
+ * @fdesc: filter descriptor
+ * @add: if add is true, this is an add operation, false implies delete
+ */
+void
+ice_fdir_get_prgm_desc(struct ice_hw *hw, struct ice_fdir_fltr *input,
+		       struct ice_fltr_desc *fdesc, bool add)
+{
+	struct ice_fd_fltr_desc_ctx fdir_fltr_ctx = { 0 };
+
+	/* set default context info */
+	ice_set_dflt_val_fd_desc(&fdir_fltr_ctx);
+
+	/* change sideband filtering values */
+	fdir_fltr_ctx.fdid = input->fltr_id;
+	if (input->dest_ctl == ICE_FLTR_PRGM_DESC_DEST_DROP_PKT) {
+		fdir_fltr_ctx.drop = ICE_FXD_FLTR_QW0_DROP_YES;
+		fdir_fltr_ctx.qindex = 0;
+	} else {
+		fdir_fltr_ctx.drop = ICE_FXD_FLTR_QW0_DROP_NO;
+		fdir_fltr_ctx.qindex = input->q_index;
+	}
+	fdir_fltr_ctx.cnt_ena = ICE_FXD_FLTR_QW0_STAT_ENA_PKTS;
+	fdir_fltr_ctx.cnt_index = input->cnt_index;
+	fdir_fltr_ctx.fd_vsi = ice_get_hw_vsi_num(hw, input->dest_vsi);
+	fdir_fltr_ctx.evict_ena = ICE_FXD_FLTR_QW0_EVICT_ENA_FALSE;
+	fdir_fltr_ctx.toq_prio = 3;
+	fdir_fltr_ctx.pcmd = add ? ICE_FXD_FLTR_QW1_PCMD_ADD :
+		ICE_FXD_FLTR_QW1_PCMD_REMOVE;
+	fdir_fltr_ctx.swap = ICE_FXD_FLTR_QW1_SWAP_NOT_SET;
+	fdir_fltr_ctx.comp_q = ICE_FXD_FLTR_QW0_COMP_Q_ZERO;
+	fdir_fltr_ctx.comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL;
+	fdir_fltr_ctx.fdid_prio = 3;
+	fdir_fltr_ctx.desc_prof = 1;
+	fdir_fltr_ctx.desc_prof_prio = 3;
+	ice_set_fd_desc_val(&fdir_fltr_ctx, fdesc);
+}
+
 /**
  * ice_alloc_fd_res_cntr - obtain counter resource for FD type
  * @hw: pointer to the hardware structure
@@ -64,6 +319,150 @@ int ice_get_fdir_cnt_all(struct ice_hw *hw)
 	return hw->func_caps.fd_fltr_guar + hw->func_caps.fd_fltr_best_effort;
 }
 
+/**
+ * ice_pkt_insert_u16 - insert a be16 value into a memory buffer
+ * @pkt: packet buffer
+ * @offset: offset into buffer
+ * @data: 16 bit value to convert and insert into pkt at offset
+ */
+static void ice_pkt_insert_u16(u8 *pkt, int offset, __be16 data)
+{
+	memcpy(pkt + offset, &data, sizeof(data));
+}
+
+/**
+ * ice_pkt_insert_u32 - insert a be32 value into a memory buffer
+ * @pkt: packet buffer
+ * @offset: offset into buffer
+ * @data: 32 bit value to convert and insert into pkt at offset
+ */
+static void ice_pkt_insert_u32(u8 *pkt, int offset, __be32 data)
+{
+	memcpy(pkt + offset, &data, sizeof(data));
+}
+
+/**
+ * ice_fdir_get_gen_prgm_pkt - generate a training packet
+ * @hw: pointer to the hardware structure
+ * @input: flow director filter data structure
+ * @pkt: pointer to return filter packet
+ * @frag: generate a fragment packet
+ * @tun: true implies generate a tunnel packet
+ */
+enum ice_status
+ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
+			  u8 *pkt, bool frag, bool tun)
+{
+	enum ice_fltr_ptype flow;
+	u16 tnl_port;
+	u8 *loc;
+	u16 idx;
+
+	if (input->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
+		switch (input->ip.proto) {
+		case IPPROTO_TCP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV4_TCP;
+			break;
+		case IPPROTO_UDP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+			break;
+		case IPPROTO_SCTP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV4_SCTP;
+			break;
+		case IPPROTO_IP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV4_OTHER;
+			break;
+		default:
+			return ICE_ERR_PARAM;
+		}
+	} else {
+		flow = input->flow_type;
+	}
+
+	for (idx = 0; idx < ICE_FDIR_NUM_PKT; idx++)
+		if (ice_fdir_pkt[idx].flow == flow)
+			break;
+	if (idx == ICE_FDIR_NUM_PKT)
+		return ICE_ERR_PARAM;
+	if (!tun) {
+		memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len);
+		loc = pkt;
+	} else {
+		if (!ice_get_open_tunnel_port(hw, TNL_ALL, &tnl_port))
+			return ICE_ERR_DOES_NOT_EXIST;
+		if (!ice_fdir_pkt[idx].tun_pkt)
+			return ICE_ERR_PARAM;
+		memcpy(pkt, ice_fdir_pkt[idx].tun_pkt,
+		       ice_fdir_pkt[idx].tun_pkt_len);
+		ice_pkt_insert_u16(pkt, ICE_IPV4_UDP_DST_PORT_OFFSET,
+				   htons(tnl_port));
+		loc = &pkt[ICE_FDIR_TUN_PKT_OFF];
+	}
+
+	/* Reverse the src and dst, since the HW expects them to be from Tx
+	 * perspective. The input from user is from Rx filter perspective.
+	 */
+	switch (flow) {
+	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
+		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
+				   input->ip.src_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_TCP_DST_PORT_OFFSET,
+				   input->ip.src_port);
+		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
+				   input->ip.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_TCP_SRC_PORT_OFFSET,
+				   input->ip.dst_port);
+		if (frag)
+			loc[20] = ICE_FDIR_IPV4_PKT_FLAG_DF;
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
+		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
+				   input->ip.src_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_UDP_DST_PORT_OFFSET,
+				   input->ip.src_port);
+		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
+				   input->ip.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_UDP_SRC_PORT_OFFSET,
+				   input->ip.dst_port);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_SCTP:
+		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
+				   input->ip.src_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_SCTP_DST_PORT_OFFSET,
+				   input->ip.src_port);
+		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
+				   input->ip.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_SCTP_SRC_PORT_OFFSET,
+				   input->ip.dst_port);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_OTHER:
+		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
+				   input->ip.src_ip);
+		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
+				   input->ip.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV4_PROTO_OFFSET, 0);
+		break;
+	default:
+		return ICE_ERR_PARAM;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_fdir_has_frag - does flow type have 2 ptypes
+ * @flow: flow ptype
+ *
+ * returns true is there is a fragment packet for this ptype
+ */
+bool ice_fdir_has_frag(enum ice_fltr_ptype flow)
+{
+	if (flow == ICE_FLTR_PTYPE_NONF_IPV4_OTHER)
+		return true;
+	else
+		return false;
+}
+
 /**
  * ice_fdir_find_by_idx - find filter with idx
  * @hw: pointer to hardware structure
@@ -85,3 +484,117 @@ ice_fdir_find_fltr_by_idx(struct ice_hw *hw, u32 fltr_idx)
 	}
 	return NULL;
 }
+
+/**
+ * ice_fdir_list_add_fltr - add a new node to the flow director filter list
+ * @hw: hardware structure
+ * @fltr: filter node to add to structure
+ */
+void ice_fdir_list_add_fltr(struct ice_hw *hw, struct ice_fdir_fltr *fltr)
+{
+	struct ice_fdir_fltr *rule, *parent = NULL;
+
+	list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) {
+		/* rule ID found or pass its spot in the list */
+		if (rule->fltr_id >= fltr->fltr_id)
+			break;
+		parent = rule;
+	}
+
+	if (parent)
+		list_add(&fltr->fltr_node, &parent->fltr_node);
+	else
+		list_add(&fltr->fltr_node, &hw->fdir_list_head);
+}
+
+/**
+ * ice_fdir_update_cntrs - increment / decrement filter counter
+ * @hw: pointer to hardware structure
+ * @flow: filter flow type
+ * @add: true implies filters added
+ */
+void
+ice_fdir_update_cntrs(struct ice_hw *hw, enum ice_fltr_ptype flow, bool add)
+{
+	int incr;
+
+	incr = add ? 1 : -1;
+	hw->fdir_active_fltr += incr;
+
+	if (flow == ICE_FLTR_PTYPE_NONF_NONE || flow >= ICE_FLTR_PTYPE_MAX)
+		ice_debug(hw, ICE_DBG_SW, "Unknown filter type %d\n", flow);
+	else
+		hw->fdir_fltr_cnt[flow] += incr;
+}
+
+/**
+ * ice_fdir_comp_rules - compare 2 filters
+ * @a: a Flow Director filter data structure
+ * @b: a Flow Director filter data structure
+ *
+ * Returns true if the filters match
+ */
+static bool
+ice_fdir_comp_rules(struct ice_fdir_fltr *a,  struct ice_fdir_fltr *b)
+{
+	enum ice_fltr_ptype flow_type = a->flow_type;
+
+	/* The calling function already checks that the two filters have the
+	 * same flow_type.
+	 */
+	if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+	    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
+	    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) {
+		if (a->ip.dst_ip == b->ip.dst_ip &&
+		    a->ip.src_ip == b->ip.src_ip &&
+		    a->ip.dst_port == b->ip.dst_port &&
+		    a->ip.src_port == b->ip.src_port)
+			return true;
+	} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
+		if (a->ip.dst_ip == b->ip.dst_ip &&
+		    a->ip.src_ip == b->ip.src_ip &&
+		    a->ip.l4_header == b->ip.l4_header &&
+		    a->ip.proto == b->ip.proto &&
+		    a->ip.ip_ver == b->ip.ip_ver &&
+		    a->ip.tos == b->ip.tos)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * ice_fdir_is_dup_fltr - test if filter is already in list for PF
+ * @hw: hardware data structure
+ * @input: Flow Director filter data structure
+ *
+ * Returns true if the filter is found in the list
+ */
+bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input)
+{
+	struct ice_fdir_fltr *rule;
+	bool ret = false;
+
+	list_for_each_entry(rule, &hw->fdir_list_head, fltr_node) {
+		enum ice_fltr_ptype flow_type;
+
+		if (rule->flow_type != input->flow_type)
+			continue;
+
+		flow_type = input->flow_type;
+		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER)
+			ret = ice_fdir_comp_rules(rule, input);
+		if (ret) {
+			if (rule->fltr_id == input->fltr_id &&
+			    rule->q_index != input->q_index)
+				ret = false;
+			else
+				break;
+		}
+	}
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 1b69249b40c1..1a13c80e1eac 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -4,11 +4,70 @@
 #ifndef _ICE_FDIR_H_
 #define _ICE_FDIR_H_
 
+#define ICE_FDIR_TUN_PKT_OFF		50
+#define ICE_FDIR_MAX_RAW_PKT_SIZE	(512 + ICE_FDIR_TUN_PKT_OFF)
+
+/* macros for offsets into packets for flow director programming */
+#define ICE_IPV4_SRC_ADDR_OFFSET	26
+#define ICE_IPV4_DST_ADDR_OFFSET	30
+#define ICE_IPV4_TCP_SRC_PORT_OFFSET	34
+#define ICE_IPV4_TCP_DST_PORT_OFFSET	36
+#define ICE_IPV4_UDP_SRC_PORT_OFFSET	34
+#define ICE_IPV4_UDP_DST_PORT_OFFSET	36
+#define ICE_IPV4_SCTP_SRC_PORT_OFFSET	34
+#define ICE_IPV4_SCTP_DST_PORT_OFFSET	36
+#define ICE_IPV4_PROTO_OFFSET		23
+#define ICE_IPV6_SRC_ADDR_OFFSET	22
+#define ICE_IPV6_DST_ADDR_OFFSET	38
+#define ICE_IPV6_TCP_SRC_PORT_OFFSET	54
+#define ICE_IPV6_TCP_DST_PORT_OFFSET	56
+#define ICE_IPV6_UDP_SRC_PORT_OFFSET	54
+#define ICE_IPV6_UDP_DST_PORT_OFFSET	56
+#define ICE_IPV6_SCTP_SRC_PORT_OFFSET	54
+#define ICE_IPV6_SCTP_DST_PORT_OFFSET	56
+/* IP v4 has 2 flag bits that enable fragment processing: DF and MF. DF
+ * requests that the packet not be fragmented. MF indicates that a packet has
+ * been fragmented.
+ */
+#define ICE_FDIR_IPV4_PKT_FLAG_DF		0x20
+
 enum ice_fltr_prgm_desc_dest {
 	ICE_FLTR_PRGM_DESC_DEST_DROP_PKT,
 	ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX,
 };
 
+enum ice_fltr_prgm_desc_fd_status {
+	ICE_FLTR_PRGM_DESC_FD_STATUS_NONE,
+	ICE_FLTR_PRGM_DESC_FD_STATUS_FD_ID,
+};
+
+/* Flow Director (FD) Filter Programming descriptor */
+struct ice_fd_fltr_desc_ctx {
+	u32 fdid;
+	u16 qindex;
+	u16 cnt_index;
+	u16 fd_vsi;
+	u16 flex_val;
+	u8 comp_q;
+	u8 comp_report;
+	u8 fd_space;
+	u8 cnt_ena;
+	u8 evict_ena;
+	u8 toq;
+	u8 toq_prio;
+	u8 dpu_recipe;
+	u8 drop;
+	u8 flex_prio;
+	u8 flex_mdid;
+	u8 dtype;
+	u8 pcmd;
+	u8 desc_prof_prio;
+	u8 desc_prof;
+	u8 swap;
+	u8 fdid_prio;
+	u8 fdid_mdid;
+};
+
 struct ice_fdir_v4 {
 	__be32 dst_ip;
 	__be32 src_ip;
@@ -47,13 +106,33 @@ struct ice_fdir_fltr {
 	u32 fltr_id;
 };
 
+/* Dummy packet filter definition structure */
+struct ice_fdir_base_pkt {
+	enum ice_fltr_ptype flow;
+	u16 pkt_len;
+	const u8 *pkt;
+	u16 tun_pkt_len;
+	const u8 *tun_pkt;
+};
+
 enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
 enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
 enum ice_status
 ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
 enum ice_status
 ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
+void
+ice_fdir_get_prgm_desc(struct ice_hw *hw, struct ice_fdir_fltr *input,
+		       struct ice_fltr_desc *fdesc, bool add);
+enum ice_status
+ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
+			  u8 *pkt, bool frag, bool tun);
 int ice_get_fdir_cnt_all(struct ice_hw *hw);
+bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input);
+bool ice_fdir_has_frag(enum ice_fltr_ptype flow);
 struct ice_fdir_fltr *
 ice_fdir_find_fltr_by_idx(struct ice_hw *hw, u32 fltr_idx);
+void
+ice_fdir_update_cntrs(struct ice_hw *hw, enum ice_fltr_ptype flow, bool add);
+void ice_fdir_list_add_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input);
 #endif /* _ICE_FDIR_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index fe2f04f706e7..16d2f599bd70 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -1632,6 +1632,34 @@ ice_find_free_tunnel_entry(struct ice_hw *hw, enum ice_tunnel_type type,
 	return false;
 }
 
+/**
+ * ice_get_open_tunnel_port - retrieve an open tunnel port
+ * @hw: pointer to the HW structure
+ * @type: tunnel type (TNL_ALL will return any open port)
+ * @port: returns open port
+ */
+bool
+ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
+			 u16 *port)
+{
+	bool res = false;
+	u16 i;
+
+	mutex_lock(&hw->tnl_lock);
+
+	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
+		    (type == TNL_ALL || hw->tnl.tbl[i].type == type)) {
+			*port = hw->tnl.tbl[i].port;
+			res = true;
+			break;
+		}
+
+	mutex_unlock(&hw->tnl_lock);
+
+	return res;
+}
+
 /**
  * ice_create_tunnel
  * @hw: pointer to the HW structure
@@ -2332,6 +2360,12 @@ ice_find_prof_id(struct ice_hw *hw, enum ice_block blk,
 	u16 off;
 	u8 i;
 
+	/* For FD, we don't want to re-use a existed profile with the same
+	 * field vector and mask. This will cause rule interference.
+	 */
+	if (blk == ICE_BLK_FD)
+		return ICE_ERR_DOES_NOT_EXIST;
+
 	for (i = 0; i < (u8)es->count; i++) {
 		off = i * es->fvw;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 70db213c9fe3..568ea519af51 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -18,6 +18,9 @@
 
 #define ICE_PKG_CNT 4
 
+bool
+ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
+			 u16 *port);
 enum ice_status
 ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port);
 enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all);
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 3376cdf5667f..c8b037d25053 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -290,6 +290,9 @@
 #define GL_PWR_MODE_CTL				0x000B820C
 #define GL_PWR_MODE_CTL_CAR_MAX_BW_S		30
 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M		ICE_M(0x3, 30)
+#define GLQF_FD_CNT				0x00460018
+#define GLQF_FD_CNT_FD_BCNT_S			16
+#define GLQF_FD_CNT_FD_BCNT_M			ICE_M(0x7FFF, 16)
 #define GLQF_FD_SIZE				0x00460010
 #define GLQF_FD_SIZE_FD_GSIZE_S			0
 #define GLQF_FD_SIZE_FD_GSIZE_M			ICE_M(0x7FFF, 0)
@@ -355,6 +358,9 @@
 #define GLV_TEPC(_VSI)				(0x00312000 + ((_VSI) * 4))
 #define GLV_UPRCL(_i)				(0x003B2000 + ((_i) * 8))
 #define GLV_UPTCL(_i)				(0x0030A000 + ((_i) * 8))
+#define VSIQF_FD_CNT(_VSI)			(0x00464000 + ((_VSI) * 4))
+#define VSIQF_FD_CNT_FD_GCNT_S			0
+#define VSIQF_FD_CNT_FD_GCNT_M			ICE_M(0x3FFF, 0)
 #define VSIQF_HKEY_MAX_INDEX			12
 #define VSIQF_HLUT_MAX_INDEX			15
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 5d61acdec7ed..bd2cd3435768 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -40,6 +40,104 @@ union ice_32byte_rx_desc {
 	} wb; /* writeback */
 };
 
+struct ice_fltr_desc {
+	__le64 qidx_compq_space_stat;
+	__le64 dtype_cmd_vsi_fdid;
+};
+
+#define ICE_FXD_FLTR_QW0_QINDEX_S	0
+#define ICE_FXD_FLTR_QW0_QINDEX_M	(0x7FFULL << ICE_FXD_FLTR_QW0_QINDEX_S)
+#define ICE_FXD_FLTR_QW0_COMP_Q_S	11
+#define ICE_FXD_FLTR_QW0_COMP_Q_M	BIT_ULL(ICE_FXD_FLTR_QW0_COMP_Q_S)
+#define ICE_FXD_FLTR_QW0_COMP_Q_ZERO	0x0ULL
+
+#define ICE_FXD_FLTR_QW0_COMP_REPORT_S	12
+#define ICE_FXD_FLTR_QW0_COMP_REPORT_M	\
+				(0x3ULL << ICE_FXD_FLTR_QW0_COMP_REPORT_S)
+#define ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL	0x1ULL
+
+#define ICE_FXD_FLTR_QW0_FD_SPACE_S	14
+#define ICE_FXD_FLTR_QW0_FD_SPACE_M	(0x3ULL << ICE_FXD_FLTR_QW0_FD_SPACE_S)
+#define ICE_FXD_FLTR_QW0_FD_SPACE_GUAR_BEST		0x2ULL
+
+#define ICE_FXD_FLTR_QW0_STAT_CNT_S	16
+#define ICE_FXD_FLTR_QW0_STAT_CNT_M	\
+				(0x1FFFULL << ICE_FXD_FLTR_QW0_STAT_CNT_S)
+#define ICE_FXD_FLTR_QW0_STAT_ENA_S	29
+#define ICE_FXD_FLTR_QW0_STAT_ENA_M	(0x3ULL << ICE_FXD_FLTR_QW0_STAT_ENA_S)
+#define ICE_FXD_FLTR_QW0_STAT_ENA_PKTS		0x1ULL
+
+#define ICE_FXD_FLTR_QW0_EVICT_ENA_S	31
+#define ICE_FXD_FLTR_QW0_EVICT_ENA_M	BIT_ULL(ICE_FXD_FLTR_QW0_EVICT_ENA_S)
+#define ICE_FXD_FLTR_QW0_EVICT_ENA_FALSE	0x0ULL
+#define ICE_FXD_FLTR_QW0_EVICT_ENA_TRUE		0x1ULL
+
+#define ICE_FXD_FLTR_QW0_TO_Q_S		32
+#define ICE_FXD_FLTR_QW0_TO_Q_M		(0x7ULL << ICE_FXD_FLTR_QW0_TO_Q_S)
+#define ICE_FXD_FLTR_QW0_TO_Q_EQUALS_QINDEX	0x0ULL
+
+#define ICE_FXD_FLTR_QW0_TO_Q_PRI_S	35
+#define ICE_FXD_FLTR_QW0_TO_Q_PRI_M	(0x7ULL << ICE_FXD_FLTR_QW0_TO_Q_PRI_S)
+#define ICE_FXD_FLTR_QW0_TO_Q_PRIO1	0x1ULL
+
+#define ICE_FXD_FLTR_QW0_DPU_RECIPE_S	38
+#define ICE_FXD_FLTR_QW0_DPU_RECIPE_M	\
+			(0x3ULL << ICE_FXD_FLTR_QW0_DPU_RECIPE_S)
+#define ICE_FXD_FLTR_QW0_DPU_RECIPE_DFLT	0x0ULL
+
+#define ICE_FXD_FLTR_QW0_DROP_S		40
+#define ICE_FXD_FLTR_QW0_DROP_M		BIT_ULL(ICE_FXD_FLTR_QW0_DROP_S)
+#define ICE_FXD_FLTR_QW0_DROP_NO	0x0ULL
+#define ICE_FXD_FLTR_QW0_DROP_YES	0x1ULL
+
+#define ICE_FXD_FLTR_QW0_FLEX_PRI_S	41
+#define ICE_FXD_FLTR_QW0_FLEX_PRI_M	(0x7ULL << ICE_FXD_FLTR_QW0_FLEX_PRI_S)
+#define ICE_FXD_FLTR_QW0_FLEX_PRI_NONE	0x0ULL
+
+#define ICE_FXD_FLTR_QW0_FLEX_MDID_S	44
+#define ICE_FXD_FLTR_QW0_FLEX_MDID_M	(0xFULL << ICE_FXD_FLTR_QW0_FLEX_MDID_S)
+#define ICE_FXD_FLTR_QW0_FLEX_MDID0	0x0ULL
+
+#define ICE_FXD_FLTR_QW0_FLEX_VAL_S	48
+#define ICE_FXD_FLTR_QW0_FLEX_VAL_M	\
+				(0xFFFFULL << ICE_FXD_FLTR_QW0_FLEX_VAL_S)
+#define ICE_FXD_FLTR_QW0_FLEX_VAL0	0x0ULL
+
+#define ICE_FXD_FLTR_QW1_DTYPE_S	0
+#define ICE_FXD_FLTR_QW1_DTYPE_M	(0xFULL << ICE_FXD_FLTR_QW1_DTYPE_S)
+#define ICE_FXD_FLTR_QW1_PCMD_S		4
+#define ICE_FXD_FLTR_QW1_PCMD_M		BIT_ULL(ICE_FXD_FLTR_QW1_PCMD_S)
+#define ICE_FXD_FLTR_QW1_PCMD_ADD	0x0ULL
+#define ICE_FXD_FLTR_QW1_PCMD_REMOVE	0x1ULL
+
+#define ICE_FXD_FLTR_QW1_PROF_PRI_S	5
+#define ICE_FXD_FLTR_QW1_PROF_PRI_M	(0x7ULL << ICE_FXD_FLTR_QW1_PROF_PRI_S)
+#define ICE_FXD_FLTR_QW1_PROF_PRIO_ZERO	0x0ULL
+
+#define ICE_FXD_FLTR_QW1_PROF_S		8
+#define ICE_FXD_FLTR_QW1_PROF_M		(0x3FULL << ICE_FXD_FLTR_QW1_PROF_S)
+#define ICE_FXD_FLTR_QW1_PROF_ZERO	0x0ULL
+
+#define ICE_FXD_FLTR_QW1_FD_VSI_S	14
+#define ICE_FXD_FLTR_QW1_FD_VSI_M	(0x3FFULL << ICE_FXD_FLTR_QW1_FD_VSI_S)
+#define ICE_FXD_FLTR_QW1_SWAP_S		24
+#define ICE_FXD_FLTR_QW1_SWAP_M		BIT_ULL(ICE_FXD_FLTR_QW1_SWAP_S)
+#define ICE_FXD_FLTR_QW1_SWAP_NOT_SET	0x0ULL
+#define ICE_FXD_FLTR_QW1_SWAP_SET	0x1ULL
+
+#define ICE_FXD_FLTR_QW1_FDID_PRI_S	25
+#define ICE_FXD_FLTR_QW1_FDID_PRI_M	(0x7ULL << ICE_FXD_FLTR_QW1_FDID_PRI_S)
+#define ICE_FXD_FLTR_QW1_FDID_PRI_ONE	0x1ULL
+
+#define ICE_FXD_FLTR_QW1_FDID_MDID_S	28
+#define ICE_FXD_FLTR_QW1_FDID_MDID_M	(0xFULL << ICE_FXD_FLTR_QW1_FDID_MDID_S)
+#define ICE_FXD_FLTR_QW1_FDID_MDID_FD	0x05ULL
+
+#define ICE_FXD_FLTR_QW1_FDID_S		32
+#define ICE_FXD_FLTR_QW1_FDID_M		\
+			(0xFFFFFFFFULL << ICE_FXD_FLTR_QW1_FDID_S)
+#define ICE_FXD_FLTR_QW1_FDID_ZERO	0x0ULL
+
 struct ice_rx_ptype_decoded {
 	u32 ptype:10;
 	u32 known:1;
@@ -346,6 +444,7 @@ struct ice_tx_desc {
 enum ice_tx_desc_dtype_value {
 	ICE_TX_DESC_DTYPE_DATA		= 0x0,
 	ICE_TX_DESC_DTYPE_CTX		= 0x1,
+	ICE_TX_DESC_DTYPE_FLTR_PROG	= 0x8,
 	/* DESC_DONE - HW has completed write-back of descriptor */
 	ICE_TX_DESC_DTYPE_DESC_DONE	= 0xF,
 };
@@ -357,12 +456,14 @@ enum ice_tx_desc_cmd_bits {
 	ICE_TX_DESC_CMD_EOP			= 0x0001,
 	ICE_TX_DESC_CMD_RS			= 0x0002,
 	ICE_TX_DESC_CMD_IL2TAG1			= 0x0008,
+	ICE_TX_DESC_CMD_DUMMY			= 0x0010,
 	ICE_TX_DESC_CMD_IIPT_IPV6		= 0x0020,
 	ICE_TX_DESC_CMD_IIPT_IPV4		= 0x0040,
 	ICE_TX_DESC_CMD_IIPT_IPV4_CSUM		= 0x0060,
 	ICE_TX_DESC_CMD_L4T_EOFT_TCP		= 0x0100,
 	ICE_TX_DESC_CMD_L4T_EOFT_SCTP		= 0x0200,
 	ICE_TX_DESC_CMD_L4T_EOFT_UDP		= 0x0300,
+	ICE_TX_DESC_CMD_RE			= 0x0400,
 };
 
 #define ICE_TXD_QW1_OFFSET_S	16
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 173a167c96d9..cda7e05bd8ae 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -16,6 +16,88 @@
 #define ICE_RX_HDR_SIZE		256
 
 #define FDIR_DESC_RXDID 0x40
+#define ICE_FDIR_CLEAN_DELAY 10
+
+/**
+ * ice_prgm_fdir_fltr - Program a Flow Director filter
+ * @vsi: VSI to send dummy packet
+ * @fdir_desc: flow director descriptor
+ * @raw_packet: allocated buffer for flow director
+ */
+int
+ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
+		   u8 *raw_packet)
+{
+	struct ice_tx_buf *tx_buf, *first;
+	struct ice_fltr_desc *f_desc;
+	struct ice_tx_desc *tx_desc;
+	struct ice_ring *tx_ring;
+	struct device *dev;
+	dma_addr_t dma;
+	u32 td_cmd;
+	u16 i;
+
+	/* VSI and Tx ring */
+	if (!vsi)
+		return -ENOENT;
+	tx_ring = vsi->tx_rings[0];
+	if (!tx_ring || !tx_ring->desc)
+		return -ENOENT;
+	dev = tx_ring->dev;
+
+	/* we are using two descriptors to add/del a filter and we can wait */
+	for (i = ICE_FDIR_CLEAN_DELAY; ICE_DESC_UNUSED(tx_ring) < 2; i--) {
+		if (!i)
+			return -EAGAIN;
+		msleep_interruptible(1);
+	}
+
+	dma = dma_map_single(dev, raw_packet, ICE_FDIR_MAX_RAW_PKT_SIZE,
+			     DMA_TO_DEVICE);
+
+	if (dma_mapping_error(dev, dma))
+		return -EINVAL;
+
+	/* grab the next descriptor */
+	i = tx_ring->next_to_use;
+	first = &tx_ring->tx_buf[i];
+	f_desc = ICE_TX_FDIRDESC(tx_ring, i);
+	memcpy(f_desc, fdir_desc, sizeof(*f_desc));
+
+	i++;
+	i = (i < tx_ring->count) ? i : 0;
+	tx_desc = ICE_TX_DESC(tx_ring, i);
+	tx_buf = &tx_ring->tx_buf[i];
+
+	i++;
+	tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
+
+	memset(tx_buf, 0, sizeof(*tx_buf));
+	dma_unmap_len_set(tx_buf, len, ICE_FDIR_MAX_RAW_PKT_SIZE);
+	dma_unmap_addr_set(tx_buf, dma, dma);
+
+	tx_desc->buf_addr = cpu_to_le64(dma);
+	td_cmd = ICE_TXD_LAST_DESC_CMD | ICE_TX_DESC_CMD_DUMMY |
+		 ICE_TX_DESC_CMD_RE;
+
+	tx_buf->tx_flags = ICE_TX_FLAGS_DUMMY_PKT;
+	tx_buf->raw_buf = raw_packet;
+
+	tx_desc->cmd_type_offset_bsz =
+		ice_build_ctob(td_cmd, 0, ICE_FDIR_MAX_RAW_PKT_SIZE, 0);
+
+	/* Force memory write to complete before letting h/w know
+	 * there are new descriptors to fetch.
+	 */
+	wmb();
+
+	/* mark the data descriptor to be watched */
+	first->next_to_watch = tx_desc;
+
+	writel(tx_ring->next_to_use, tx_ring->tail);
+
+	return 0;
+}
 
 /**
  * ice_unmap_and_free_tx_buf - Release a Tx buffer
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 2209583c993e..7c4030caeea4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -380,6 +380,9 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring);
 void ice_free_tx_ring(struct ice_ring *tx_ring);
 void ice_free_rx_ring(struct ice_ring *rx_ring);
 int ice_napi_poll(struct napi_struct *napi, int budget);
+int
+ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
+		   u8 *raw_packet);
 int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget);
 void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring);
 #endif /* _ICE_TXRX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 0c14d89f7be9..fcf1f7853a41 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -628,6 +628,12 @@ struct ice_hw {
 	struct mutex fdir_fltr_lock;	/* protect Flow Director */
 	struct list_head fdir_list_head;
 
+	/* Book-keeping of side-band filter count per flow-type.
+	 * This is used to detect and handle input set changes for
+	 * respective flow-type.
+	 */
+	u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX];
+
 	struct ice_fd_hw_prof **fdir_prof;
 	DECLARE_BITMAP(fdir_perfect_fltr, ICE_FLTR_PTYPE_MAX);
 	struct mutex rss_locks;	/* protect RSS configuration */
-- 
cgit v1.2.3


From 165d80d6adab51b6a2f9c40ad0c8d3dec18d7bef Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:43 -0700
Subject: ice: Support IPv6 Flow Director filters

Extend supported filters to allow for IPv6 filters.

Supported fields are: src-ip, dst-ip, src-port, and dst-port
Supported flow-types are: tcp6, udp6, sctp6, ip6

Example usage:

ethtool -N eth0 flow-type tcp6 src-port 12 dst-port 13 \
src-ip fce0::1:34 dst-ip fce0::1:35 action 32

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 391 +++++++++++++++++++---
 drivers/net/ethernet/intel/ice/ice_fdir.c         | 303 +++++++++++++++--
 drivers/net/ethernet/intel/ice/ice_fdir.h         |  19 +-
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c    |   6 +
 drivers/net/ethernet/intel/ice/ice_type.h         |   4 +
 5 files changed, 642 insertions(+), 81 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 6badf2ef2255..aa85d5ad2477 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -7,6 +7,24 @@
 #include "ice_lib.h"
 #include "ice_flow.h"
 
+static struct in6_addr full_ipv6_addr_mask = {
+	.in6_u = {
+		.u6_addr8 = {
+			0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+			0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+		}
+	}
+};
+
+static struct in6_addr zero_ipv6_addr_mask = {
+	.in6_u = {
+		.u6_addr8 = {
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		}
+	}
+};
+
 /* calls to ice_flow_add_prof require the number of segments in the array
  * for segs_cnt. In this code that is one more than the index.
  */
@@ -30,6 +48,14 @@ static int ice_fltr_to_ethtool_flow(enum ice_fltr_ptype flow)
 		return SCTP_V4_FLOW;
 	case ICE_FLTR_PTYPE_NONF_IPV4_OTHER:
 		return IPV4_USER_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV6_TCP:
+		return TCP_V6_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV6_UDP:
+		return UDP_V6_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV6_SCTP:
+		return SCTP_V6_FLOW;
+	case ICE_FLTR_PTYPE_NONF_IPV6_OTHER:
+		return IPV6_USER_FLOW;
 	default:
 		/* 0 is undefined ethtool flow */
 		return 0;
@@ -53,6 +79,14 @@ static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth)
 		return ICE_FLTR_PTYPE_NONF_IPV4_SCTP;
 	case IPV4_USER_FLOW:
 		return ICE_FLTR_PTYPE_NONF_IPV4_OTHER;
+	case TCP_V6_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV6_TCP;
+	case UDP_V6_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV6_UDP;
+	case SCTP_V6_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV6_SCTP;
+	case IPV6_USER_FLOW:
+		return ICE_FLTR_PTYPE_NONF_IPV6_OTHER;
 	default:
 		return ICE_FLTR_PTYPE_NONF_NONE;
 	}
@@ -92,28 +126,64 @@ int ice_get_ethtool_fdir_entry(struct ice_hw *hw, struct ethtool_rxnfc *cmd)
 	case IPV4_USER_FLOW:
 		fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
 		fsp->h_u.usr_ip4_spec.proto = 0;
-		fsp->h_u.usr_ip4_spec.l4_4_bytes = rule->ip.l4_header;
-		fsp->h_u.usr_ip4_spec.tos = rule->ip.tos;
-		fsp->h_u.usr_ip4_spec.ip4src = rule->ip.src_ip;
-		fsp->h_u.usr_ip4_spec.ip4dst = rule->ip.dst_ip;
-		fsp->m_u.usr_ip4_spec.ip4src = rule->mask.src_ip;
-		fsp->m_u.usr_ip4_spec.ip4dst = rule->mask.dst_ip;
+		fsp->h_u.usr_ip4_spec.l4_4_bytes = rule->ip.v4.l4_header;
+		fsp->h_u.usr_ip4_spec.tos = rule->ip.v4.tos;
+		fsp->h_u.usr_ip4_spec.ip4src = rule->ip.v4.src_ip;
+		fsp->h_u.usr_ip4_spec.ip4dst = rule->ip.v4.dst_ip;
+		fsp->m_u.usr_ip4_spec.ip4src = rule->mask.v4.src_ip;
+		fsp->m_u.usr_ip4_spec.ip4dst = rule->mask.v4.dst_ip;
 		fsp->m_u.usr_ip4_spec.ip_ver = 0xFF;
 		fsp->m_u.usr_ip4_spec.proto = 0;
-		fsp->m_u.usr_ip4_spec.l4_4_bytes = rule->mask.l4_header;
-		fsp->m_u.usr_ip4_spec.tos = rule->mask.tos;
+		fsp->m_u.usr_ip4_spec.l4_4_bytes = rule->mask.v4.l4_header;
+		fsp->m_u.usr_ip4_spec.tos = rule->mask.v4.tos;
 		break;
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 	case SCTP_V4_FLOW:
-		fsp->h_u.tcp_ip4_spec.psrc = rule->ip.src_port;
-		fsp->h_u.tcp_ip4_spec.pdst = rule->ip.dst_port;
-		fsp->h_u.tcp_ip4_spec.ip4src = rule->ip.src_ip;
-		fsp->h_u.tcp_ip4_spec.ip4dst = rule->ip.dst_ip;
-		fsp->m_u.tcp_ip4_spec.psrc = rule->mask.src_port;
-		fsp->m_u.tcp_ip4_spec.pdst = rule->mask.dst_port;
-		fsp->m_u.tcp_ip4_spec.ip4src = rule->mask.src_ip;
-		fsp->m_u.tcp_ip4_spec.ip4dst = rule->mask.dst_ip;
+		fsp->h_u.tcp_ip4_spec.psrc = rule->ip.v4.src_port;
+		fsp->h_u.tcp_ip4_spec.pdst = rule->ip.v4.dst_port;
+		fsp->h_u.tcp_ip4_spec.ip4src = rule->ip.v4.src_ip;
+		fsp->h_u.tcp_ip4_spec.ip4dst = rule->ip.v4.dst_ip;
+		fsp->m_u.tcp_ip4_spec.psrc = rule->mask.v4.src_port;
+		fsp->m_u.tcp_ip4_spec.pdst = rule->mask.v4.dst_port;
+		fsp->m_u.tcp_ip4_spec.ip4src = rule->mask.v4.src_ip;
+		fsp->m_u.tcp_ip4_spec.ip4dst = rule->mask.v4.dst_ip;
+		break;
+	case IPV6_USER_FLOW:
+		fsp->h_u.usr_ip6_spec.l4_4_bytes = rule->ip.v6.l4_header;
+		fsp->h_u.usr_ip6_spec.tclass = rule->ip.v6.tc;
+		fsp->h_u.usr_ip6_spec.l4_proto = rule->ip.v6.proto;
+		memcpy(fsp->h_u.tcp_ip6_spec.ip6src, rule->ip.v6.src_ip,
+		       sizeof(struct in6_addr));
+		memcpy(fsp->h_u.tcp_ip6_spec.ip6dst, rule->ip.v6.dst_ip,
+		       sizeof(struct in6_addr));
+		memcpy(fsp->m_u.tcp_ip6_spec.ip6src, rule->mask.v6.src_ip,
+		       sizeof(struct in6_addr));
+		memcpy(fsp->m_u.tcp_ip6_spec.ip6dst, rule->mask.v6.dst_ip,
+		       sizeof(struct in6_addr));
+		fsp->m_u.usr_ip6_spec.l4_4_bytes = rule->mask.v6.l4_header;
+		fsp->m_u.usr_ip6_spec.tclass = rule->mask.v6.tc;
+		fsp->m_u.usr_ip6_spec.l4_proto = rule->mask.v6.proto;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		memcpy(fsp->h_u.tcp_ip6_spec.ip6src, rule->ip.v6.src_ip,
+		       sizeof(struct in6_addr));
+		memcpy(fsp->h_u.tcp_ip6_spec.ip6dst, rule->ip.v6.dst_ip,
+		       sizeof(struct in6_addr));
+		fsp->h_u.tcp_ip6_spec.psrc = rule->ip.v6.src_port;
+		fsp->h_u.tcp_ip6_spec.pdst = rule->ip.v6.dst_port;
+		memcpy(fsp->m_u.tcp_ip6_spec.ip6src,
+		       rule->mask.v6.src_ip,
+		       sizeof(struct in6_addr));
+		memcpy(fsp->m_u.tcp_ip6_spec.ip6dst,
+		       rule->mask.v6.dst_ip,
+		       sizeof(struct in6_addr));
+		fsp->m_u.tcp_ip6_spec.psrc = rule->mask.v6.src_port;
+		fsp->m_u.tcp_ip6_spec.pdst = rule->mask.v6.dst_port;
+		fsp->h_u.tcp_ip6_spec.tclass = rule->ip.v6.tc;
+		fsp->m_u.tcp_ip6_spec.tclass = rule->mask.v6.tc;
 		break;
 	default:
 		break;
@@ -441,6 +511,7 @@ err_prof:
 /**
  * ice_set_init_fdir_seg
  * @seg: flow segment for programming
+ * @l3_proto: ICE_FLOW_SEG_HDR_IPV4 or ICE_FLOW_SEG_HDR_IPV6
  * @l4_proto: ICE_FLOW_SEG_HDR_TCP or ICE_FLOW_SEG_HDR_UDP
  *
  * Set the configuration for perfect filters to the provided flow segment for
@@ -449,13 +520,24 @@ err_prof:
  */
 static int
 ice_set_init_fdir_seg(struct ice_flow_seg_info *seg,
+		      enum ice_flow_seg_hdr l3_proto,
 		      enum ice_flow_seg_hdr l4_proto)
 {
-	enum ice_flow_field src_port, dst_port;
+	enum ice_flow_field src_addr, dst_addr, src_port, dst_port;
 
 	if (!seg)
 		return -EINVAL;
 
+	if (l3_proto == ICE_FLOW_SEG_HDR_IPV4) {
+		src_addr = ICE_FLOW_FIELD_IDX_IPV4_SA;
+		dst_addr = ICE_FLOW_FIELD_IDX_IPV4_DA;
+	} else if (l3_proto == ICE_FLOW_SEG_HDR_IPV6) {
+		src_addr = ICE_FLOW_FIELD_IDX_IPV6_SA;
+		dst_addr = ICE_FLOW_FIELD_IDX_IPV6_DA;
+	} else {
+		return -EINVAL;
+	}
+
 	if (l4_proto == ICE_FLOW_SEG_HDR_TCP) {
 		src_port = ICE_FLOW_FIELD_IDX_TCP_SRC_PORT;
 		dst_port = ICE_FLOW_FIELD_IDX_TCP_DST_PORT;
@@ -466,17 +548,15 @@ ice_set_init_fdir_seg(struct ice_flow_seg_info *seg,
 		return -EINVAL;
 	}
 
-	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV4 | l4_proto);
+	ICE_FLOW_SET_HDRS(seg, l3_proto | l4_proto);
 
 	/* IP source address */
-	ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_SA,
-			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
-			 ICE_FLOW_FLD_OFF_INVAL, false);
+	ice_flow_set_fld(seg, src_addr, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, false);
 
 	/* IP destination address */
-	ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV4_DA,
-			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
-			 ICE_FLOW_FLD_OFF_INVAL, false);
+	ice_flow_set_fld(seg, dst_addr, ICE_FLOW_FLD_OFF_INVAL,
+			 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL, false);
 
 	/* Layer 4 source port */
 	ice_flow_set_fld(seg, src_port, ICE_FLOW_FLD_OFF_INVAL,
@@ -521,9 +601,17 @@ ice_create_init_fdir_rule(struct ice_pf *pf, enum ice_fltr_ptype flow)
 	}
 
 	if (flow == ICE_FLTR_PTYPE_NONF_IPV4_TCP)
-		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_TCP);
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_IPV4,
+					    ICE_FLOW_SEG_HDR_TCP);
 	else if (flow == ICE_FLTR_PTYPE_NONF_IPV4_UDP)
-		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_UDP);
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_IPV4,
+					    ICE_FLOW_SEG_HDR_UDP);
+	else if (flow == ICE_FLTR_PTYPE_NONF_IPV6_TCP)
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_IPV6,
+					    ICE_FLOW_SEG_HDR_TCP);
+	else if (flow == ICE_FLTR_PTYPE_NONF_IPV6_UDP)
+		ret = ice_set_init_fdir_seg(seg, ICE_FLOW_SEG_HDR_IPV6,
+					    ICE_FLOW_SEG_HDR_UDP);
 	else
 		ret = -EINVAL;
 	if (ret)
@@ -694,6 +782,156 @@ ice_set_fdir_ip4_usr_seg(struct ice_flow_seg_info *seg,
 	return 0;
 }
 
+/**
+ * ice_set_fdir_ip6_seg
+ * @seg: flow segment for programming
+ * @tcp_ip6_spec: mask data from ethtool
+ * @l4_proto: Layer 4 protocol to program
+ * @perfect_fltr: only valid on success; returns true if perfect filter,
+ *		  false if not
+ *
+ * Set the mask data into the flow segment to be used to program HW
+ * table based on provided L4 protocol for IPv6
+ */
+static int
+ice_set_fdir_ip6_seg(struct ice_flow_seg_info *seg,
+		     struct ethtool_tcpip6_spec *tcp_ip6_spec,
+		     enum ice_flow_seg_hdr l4_proto, bool *perfect_fltr)
+{
+	enum ice_flow_field src_port, dst_port;
+
+	/* make sure we don't have any empty rule */
+	if (!memcmp(tcp_ip6_spec->ip6src, &zero_ipv6_addr_mask,
+		    sizeof(struct in6_addr)) &&
+	    !memcmp(tcp_ip6_spec->ip6dst, &zero_ipv6_addr_mask,
+		    sizeof(struct in6_addr)) &&
+	    !tcp_ip6_spec->psrc && !tcp_ip6_spec->pdst)
+		return -EINVAL;
+
+	/* filtering on TC not supported */
+	if (tcp_ip6_spec->tclass)
+		return -EOPNOTSUPP;
+
+	if (l4_proto == ICE_FLOW_SEG_HDR_TCP) {
+		src_port = ICE_FLOW_FIELD_IDX_TCP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_TCP_DST_PORT;
+	} else if (l4_proto == ICE_FLOW_SEG_HDR_UDP) {
+		src_port = ICE_FLOW_FIELD_IDX_UDP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_UDP_DST_PORT;
+	} else if (l4_proto == ICE_FLOW_SEG_HDR_SCTP) {
+		src_port = ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT;
+		dst_port = ICE_FLOW_FIELD_IDX_SCTP_DST_PORT;
+	} else {
+		return -EINVAL;
+	}
+
+	*perfect_fltr = true;
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV6 | l4_proto);
+
+	if (!memcmp(tcp_ip6_spec->ip6src, &full_ipv6_addr_mask,
+		    sizeof(struct in6_addr)))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV6_SA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!memcmp(tcp_ip6_spec->ip6src, &zero_ipv6_addr_mask,
+			 sizeof(struct in6_addr)))
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	if (!memcmp(tcp_ip6_spec->ip6dst, &full_ipv6_addr_mask,
+		    sizeof(struct in6_addr)))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV6_DA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!memcmp(tcp_ip6_spec->ip6dst, &zero_ipv6_addr_mask,
+			 sizeof(struct in6_addr)))
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* Layer 4 source port */
+	if (tcp_ip6_spec->psrc == htons(0xFFFF))
+		ice_flow_set_fld(seg, src_port, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 false);
+	else if (!tcp_ip6_spec->psrc)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	/* Layer 4 destination port */
+	if (tcp_ip6_spec->pdst == htons(0xFFFF))
+		ice_flow_set_fld(seg, dst_port, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 false);
+	else if (!tcp_ip6_spec->pdst)
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/**
+ * ice_set_fdir_ip6_usr_seg
+ * @seg: flow segment for programming
+ * @usr_ip6_spec: ethtool userdef packet offset
+ * @perfect_fltr: only valid on success; returns true if perfect filter,
+ *		  false if not
+ *
+ * Set the offset data into the flow segment to be used to program HW
+ * table for IPv6
+ */
+static int
+ice_set_fdir_ip6_usr_seg(struct ice_flow_seg_info *seg,
+			 struct ethtool_usrip6_spec *usr_ip6_spec,
+			 bool *perfect_fltr)
+{
+	/* filtering on Layer 4 bytes not supported */
+	if (usr_ip6_spec->l4_4_bytes)
+		return -EOPNOTSUPP;
+	/* filtering on TC not supported */
+	if (usr_ip6_spec->tclass)
+		return -EOPNOTSUPP;
+	/* filtering on Layer 4 protocol not supported */
+	if (usr_ip6_spec->l4_proto)
+		return -EOPNOTSUPP;
+	/* empty rules are not valid */
+	if (!memcmp(usr_ip6_spec->ip6src, &zero_ipv6_addr_mask,
+		    sizeof(struct in6_addr)) &&
+	    !memcmp(usr_ip6_spec->ip6dst, &zero_ipv6_addr_mask,
+		    sizeof(struct in6_addr)))
+		return -EINVAL;
+
+	*perfect_fltr = true;
+	ICE_FLOW_SET_HDRS(seg, ICE_FLOW_SEG_HDR_IPV6);
+
+	if (!memcmp(usr_ip6_spec->ip6src, &full_ipv6_addr_mask,
+		    sizeof(struct in6_addr)))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV6_SA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!memcmp(usr_ip6_spec->ip6src, &zero_ipv6_addr_mask,
+			 sizeof(struct in6_addr)))
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	if (!memcmp(usr_ip6_spec->ip6dst, &full_ipv6_addr_mask,
+		    sizeof(struct in6_addr)))
+		ice_flow_set_fld(seg, ICE_FLOW_FIELD_IDX_IPV6_DA,
+				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
+				 ICE_FLOW_FLD_OFF_INVAL, false);
+	else if (!memcmp(usr_ip6_spec->ip6dst, &zero_ipv6_addr_mask,
+			 sizeof(struct in6_addr)))
+		*perfect_fltr = false;
+	else
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 /**
  * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter
  * @pf: PF structure
@@ -742,6 +980,25 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp)
 		ret = ice_set_fdir_ip4_usr_seg(seg, &fsp->m_u.usr_ip4_spec,
 					       &perfect_filter);
 		break;
+	case TCP_V6_FLOW:
+		ret = ice_set_fdir_ip6_seg(seg, &fsp->m_u.tcp_ip6_spec,
+					   ICE_FLOW_SEG_HDR_TCP,
+					   &perfect_filter);
+		break;
+	case UDP_V6_FLOW:
+		ret = ice_set_fdir_ip6_seg(seg, &fsp->m_u.tcp_ip6_spec,
+					   ICE_FLOW_SEG_HDR_UDP,
+					   &perfect_filter);
+		break;
+	case SCTP_V6_FLOW:
+		ret = ice_set_fdir_ip6_seg(seg, &fsp->m_u.tcp_ip6_spec,
+					   ICE_FLOW_SEG_HDR_SCTP,
+					   &perfect_filter);
+		break;
+	case IPV6_USER_FLOW:
+		ret = ice_set_fdir_ip6_usr_seg(seg, &fsp->m_u.usr_ip6_spec,
+					       &perfect_filter);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -910,6 +1167,14 @@ int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 		return err;
 
 	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP);
+	if (err)
+		return err;
+
+	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP);
+	if (err)
+		return err;
+
+	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP);
 
 	return err;
 }
@@ -1094,28 +1359,62 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp,
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 	case SCTP_V4_FLOW:
-		input->ip.dst_port = fsp->h_u.tcp_ip4_spec.pdst;
-		input->ip.src_port = fsp->h_u.tcp_ip4_spec.psrc;
-		input->ip.dst_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
-		input->ip.src_ip = fsp->h_u.tcp_ip4_spec.ip4src;
-		input->mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst;
-		input->mask.src_port = fsp->m_u.tcp_ip4_spec.psrc;
-		input->mask.dst_ip = fsp->m_u.tcp_ip4_spec.ip4dst;
-		input->mask.src_ip = fsp->m_u.tcp_ip4_spec.ip4src;
+		input->ip.v4.dst_port = fsp->h_u.tcp_ip4_spec.pdst;
+		input->ip.v4.src_port = fsp->h_u.tcp_ip4_spec.psrc;
+		input->ip.v4.dst_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+		input->ip.v4.src_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+		input->mask.v4.dst_port = fsp->m_u.tcp_ip4_spec.pdst;
+		input->mask.v4.src_port = fsp->m_u.tcp_ip4_spec.psrc;
+		input->mask.v4.dst_ip = fsp->m_u.tcp_ip4_spec.ip4dst;
+		input->mask.v4.src_ip = fsp->m_u.tcp_ip4_spec.ip4src;
 		break;
 	case IPV4_USER_FLOW:
-		input->ip.dst_ip = fsp->h_u.usr_ip4_spec.ip4dst;
-		input->ip.src_ip = fsp->h_u.usr_ip4_spec.ip4src;
-		input->ip.l4_header = fsp->h_u.usr_ip4_spec.l4_4_bytes;
-		input->ip.proto = fsp->h_u.usr_ip4_spec.proto;
-		input->ip.ip_ver = fsp->h_u.usr_ip4_spec.ip_ver;
-		input->ip.tos = fsp->h_u.usr_ip4_spec.tos;
-		input->mask.dst_ip = fsp->m_u.usr_ip4_spec.ip4dst;
-		input->mask.src_ip = fsp->m_u.usr_ip4_spec.ip4src;
-		input->mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes;
-		input->mask.proto = fsp->m_u.usr_ip4_spec.proto;
-		input->mask.ip_ver = fsp->m_u.usr_ip4_spec.ip_ver;
-		input->mask.tos = fsp->m_u.usr_ip4_spec.tos;
+		input->ip.v4.dst_ip = fsp->h_u.usr_ip4_spec.ip4dst;
+		input->ip.v4.src_ip = fsp->h_u.usr_ip4_spec.ip4src;
+		input->ip.v4.l4_header = fsp->h_u.usr_ip4_spec.l4_4_bytes;
+		input->ip.v4.proto = fsp->h_u.usr_ip4_spec.proto;
+		input->ip.v4.ip_ver = fsp->h_u.usr_ip4_spec.ip_ver;
+		input->ip.v4.tos = fsp->h_u.usr_ip4_spec.tos;
+		input->mask.v4.dst_ip = fsp->m_u.usr_ip4_spec.ip4dst;
+		input->mask.v4.src_ip = fsp->m_u.usr_ip4_spec.ip4src;
+		input->mask.v4.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes;
+		input->mask.v4.proto = fsp->m_u.usr_ip4_spec.proto;
+		input->mask.v4.ip_ver = fsp->m_u.usr_ip4_spec.ip_ver;
+		input->mask.v4.tos = fsp->m_u.usr_ip4_spec.tos;
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		memcpy(input->ip.v6.dst_ip, fsp->h_u.usr_ip6_spec.ip6dst,
+		       sizeof(struct in6_addr));
+		memcpy(input->ip.v6.src_ip, fsp->h_u.usr_ip6_spec.ip6src,
+		       sizeof(struct in6_addr));
+		input->ip.v6.dst_port = fsp->h_u.tcp_ip6_spec.pdst;
+		input->ip.v6.src_port = fsp->h_u.tcp_ip6_spec.psrc;
+		input->ip.v6.tc = fsp->h_u.tcp_ip6_spec.tclass;
+		memcpy(input->mask.v6.dst_ip, fsp->m_u.tcp_ip6_spec.ip6dst,
+		       sizeof(struct in6_addr));
+		memcpy(input->mask.v6.src_ip, fsp->m_u.tcp_ip6_spec.ip6src,
+		       sizeof(struct in6_addr));
+		input->mask.v6.dst_port = fsp->m_u.tcp_ip6_spec.pdst;
+		input->mask.v6.src_port = fsp->m_u.tcp_ip6_spec.psrc;
+		input->mask.v6.tc = fsp->m_u.tcp_ip6_spec.tclass;
+		break;
+	case IPV6_USER_FLOW:
+		memcpy(input->ip.v6.dst_ip, fsp->h_u.usr_ip6_spec.ip6dst,
+		       sizeof(struct in6_addr));
+		memcpy(input->ip.v6.src_ip, fsp->h_u.usr_ip6_spec.ip6src,
+		       sizeof(struct in6_addr));
+		input->ip.v6.l4_header = fsp->h_u.usr_ip6_spec.l4_4_bytes;
+		input->ip.v6.tc = fsp->h_u.usr_ip6_spec.tclass;
+		input->ip.v6.proto = fsp->h_u.usr_ip6_spec.l4_proto;
+		memcpy(input->mask.v6.dst_ip, fsp->m_u.usr_ip6_spec.ip6dst,
+		       sizeof(struct in6_addr));
+		memcpy(input->mask.v6.src_ip, fsp->m_u.usr_ip6_spec.ip6src,
+		       sizeof(struct in6_addr));
+		input->mask.v6.l4_header = fsp->m_u.usr_ip6_spec.l4_4_bytes;
+		input->mask.v6.tc = fsp->m_u.usr_ip6_spec.tclass;
+		input->mask.v6.proto = fsp->m_u.usr_ip6_spec.l4_proto;
 		break;
 	default:
 		/* not doing un-parsed flow types */
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 60a824363f06..d50cc6e9086e 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -40,6 +40,52 @@ static const u8 ice_fdir_ipv4_pkt[] = {
 	0x00, 0x00
 };
 
+static const u8 ice_fdir_tcpv6_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00,
+	0x00, 0x00, 0x00, 0x14, 0x06, 0x40, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x50, 0x00, 0x20, 0x00, 0x00, 0x00,
+	0x00, 0x00,
+};
+
+static const u8 ice_fdir_udpv6_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00,
+	0x00, 0x00, 0x00, 0x08, 0x11, 0x40, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x08, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_sctpv6_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00,
+	0x00, 0x00, 0x00, 0x0C, 0x84, 0x40, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00,
+};
+
+static const u8 ice_fdir_ipv6_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x86, 0xDD, 0x60, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x3B, 0x40, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
 static const u8 ice_fdir_tcp4_tun_pkt[] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
@@ -100,6 +146,76 @@ static const u8 ice_fdir_ip4_tun_pkt[] = {
 	0x00, 0x00, 0x00, 0x00,
 };
 
+static const u8 ice_fdir_tcp6_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x6e, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86, 0xdd,
+	0x60, 0x00, 0x00, 0x00, 0x00, 0x14, 0x06, 0x40,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x50, 0x00, 0x20, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_udp6_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x62, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86, 0xdd,
+	0x60, 0x00, 0x00, 0x00, 0x00, 0x08, 0x11, 0x40,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_sctp6_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x66, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86, 0xdd,
+	0x60, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x84, 0x40,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 ice_fdir_ip6_tun_pkt[] = {
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x45, 0x00,
+	0x00, 0x5a, 0x00, 0x00, 0x40, 0x00, 0x40, 0x11,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x04, 0x00, 0x00, 0x03, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x86, 0xdd,
+	0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3b, 0x40,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
 /* Flow Director no-op training packet table */
 static const struct ice_fdir_base_pkt ice_fdir_pkt[] = {
 	{
@@ -122,6 +238,26 @@ static const struct ice_fdir_base_pkt ice_fdir_pkt[] = {
 		sizeof(ice_fdir_ipv4_pkt), ice_fdir_ipv4_pkt,
 		sizeof(ice_fdir_ip4_tun_pkt), ice_fdir_ip4_tun_pkt,
 	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV6_TCP,
+		sizeof(ice_fdir_tcpv6_pkt), ice_fdir_tcpv6_pkt,
+		sizeof(ice_fdir_tcp6_tun_pkt), ice_fdir_tcp6_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV6_UDP,
+		sizeof(ice_fdir_udpv6_pkt), ice_fdir_udpv6_pkt,
+		sizeof(ice_fdir_udp6_tun_pkt), ice_fdir_udp6_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV6_SCTP,
+		sizeof(ice_fdir_sctpv6_pkt), ice_fdir_sctpv6_pkt,
+		sizeof(ice_fdir_sctp6_tun_pkt), ice_fdir_sctp6_tun_pkt,
+	},
+	{
+		ICE_FLTR_PTYPE_NONF_IPV6_OTHER,
+		sizeof(ice_fdir_ipv6_pkt), ice_fdir_ipv6_pkt,
+		sizeof(ice_fdir_ip6_tun_pkt), ice_fdir_ip6_tun_pkt,
+	},
 };
 
 #define ICE_FDIR_NUM_PKT ARRAY_SIZE(ice_fdir_pkt)
@@ -319,6 +455,21 @@ int ice_get_fdir_cnt_all(struct ice_hw *hw)
 	return hw->func_caps.fd_fltr_guar + hw->func_caps.fd_fltr_best_effort;
 }
 
+/**
+ * ice_pkt_insert_ipv6_addr - insert a be32 IPv6 address into a memory buffer
+ * @pkt: packet buffer
+ * @offset: offset into buffer
+ * @addr: IPv6 address to convert and insert into pkt at offset
+ */
+static void ice_pkt_insert_ipv6_addr(u8 *pkt, int offset, __be32 *addr)
+{
+	int idx;
+
+	for (idx = 0; idx < ICE_IPV6_ADDR_LEN_AS_U32; idx++)
+		memcpy(pkt + offset + idx * sizeof(*addr), &addr[idx],
+		       sizeof(*addr));
+}
+
 /**
  * ice_pkt_insert_u16 - insert a be16 value into a memory buffer
  * @pkt: packet buffer
@@ -359,7 +510,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 	u16 idx;
 
 	if (input->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
-		switch (input->ip.proto) {
+		switch (input->ip.v4.proto) {
 		case IPPROTO_TCP:
 			flow = ICE_FLTR_PTYPE_NONF_IPV4_TCP;
 			break;
@@ -375,6 +526,23 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 		default:
 			return ICE_ERR_PARAM;
 		}
+	} else if (input->flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) {
+		switch (input->ip.v6.proto) {
+		case IPPROTO_TCP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV6_TCP;
+			break;
+		case IPPROTO_UDP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV6_UDP;
+			break;
+		case IPPROTO_SCTP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV6_SCTP;
+			break;
+		case IPPROTO_IP:
+			flow = ICE_FLTR_PTYPE_NONF_IPV6_OTHER;
+			break;
+		default:
+			return ICE_ERR_PARAM;
+		}
 	} else {
 		flow = input->flow_type;
 	}
@@ -405,43 +573,79 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 	switch (flow) {
 	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
 		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
-				   input->ip.src_ip);
+				   input->ip.v4.src_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_TCP_DST_PORT_OFFSET,
-				   input->ip.src_port);
+				   input->ip.v4.src_port);
 		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
-				   input->ip.dst_ip);
+				   input->ip.v4.dst_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_TCP_SRC_PORT_OFFSET,
-				   input->ip.dst_port);
+				   input->ip.v4.dst_port);
 		if (frag)
 			loc[20] = ICE_FDIR_IPV4_PKT_FLAG_DF;
 		break;
 	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
 		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
-				   input->ip.src_ip);
+				   input->ip.v4.src_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_UDP_DST_PORT_OFFSET,
-				   input->ip.src_port);
+				   input->ip.v4.src_port);
 		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
-				   input->ip.dst_ip);
+				   input->ip.v4.dst_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_UDP_SRC_PORT_OFFSET,
-				   input->ip.dst_port);
+				   input->ip.v4.dst_port);
 		break;
 	case ICE_FLTR_PTYPE_NONF_IPV4_SCTP:
 		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
-				   input->ip.src_ip);
+				   input->ip.v4.src_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_SCTP_DST_PORT_OFFSET,
-				   input->ip.src_port);
+				   input->ip.v4.src_port);
 		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
-				   input->ip.dst_ip);
+				   input->ip.v4.dst_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_SCTP_SRC_PORT_OFFSET,
-				   input->ip.dst_port);
+				   input->ip.v4.dst_port);
 		break;
 	case ICE_FLTR_PTYPE_NONF_IPV4_OTHER:
 		ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET,
-				   input->ip.src_ip);
+				   input->ip.v4.src_ip);
 		ice_pkt_insert_u32(loc, ICE_IPV4_SRC_ADDR_OFFSET,
-				   input->ip.dst_ip);
+				   input->ip.v4.dst_ip);
 		ice_pkt_insert_u16(loc, ICE_IPV4_PROTO_OFFSET, 0);
 		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_TCP:
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET,
+					 input->ip.v6.src_ip);
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET,
+					 input->ip.v6.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV6_TCP_DST_PORT_OFFSET,
+				   input->ip.v6.src_port);
+		ice_pkt_insert_u16(loc, ICE_IPV6_TCP_SRC_PORT_OFFSET,
+				   input->ip.v6.dst_port);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_UDP:
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET,
+					 input->ip.v6.src_ip);
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET,
+					 input->ip.v6.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV6_UDP_DST_PORT_OFFSET,
+				   input->ip.v6.src_port);
+		ice_pkt_insert_u16(loc, ICE_IPV6_UDP_SRC_PORT_OFFSET,
+				   input->ip.v6.dst_port);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_SCTP:
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET,
+					 input->ip.v6.src_ip);
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET,
+					 input->ip.v6.dst_ip);
+		ice_pkt_insert_u16(loc, ICE_IPV6_SCTP_DST_PORT_OFFSET,
+				   input->ip.v6.src_port);
+		ice_pkt_insert_u16(loc, ICE_IPV6_SCTP_SRC_PORT_OFFSET,
+				   input->ip.v6.dst_port);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_OTHER:
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_DST_ADDR_OFFSET,
+					 input->ip.v6.src_ip);
+		ice_pkt_insert_ipv6_addr(loc, ICE_IPV6_SRC_ADDR_OFFSET,
+					 input->ip.v6.dst_ip);
+		break;
 	default:
 		return ICE_ERR_PARAM;
 	}
@@ -527,37 +731,68 @@ ice_fdir_update_cntrs(struct ice_hw *hw, enum ice_fltr_ptype flow, bool add)
 		hw->fdir_fltr_cnt[flow] += incr;
 }
 
+/**
+ * ice_cmp_ipv6_addr - compare 2 IP v6 addresses
+ * @a: IP v6 address
+ * @b: IP v6 address
+ *
+ * Returns 0 on equal, returns non-0 if different
+ */
+static int ice_cmp_ipv6_addr(__be32 *a, __be32 *b)
+{
+	return memcmp(a, b, 4 * sizeof(__be32));
+}
+
 /**
  * ice_fdir_comp_rules - compare 2 filters
  * @a: a Flow Director filter data structure
  * @b: a Flow Director filter data structure
+ * @v6: bool true if v6 filter
  *
  * Returns true if the filters match
  */
 static bool
-ice_fdir_comp_rules(struct ice_fdir_fltr *a,  struct ice_fdir_fltr *b)
+ice_fdir_comp_rules(struct ice_fdir_fltr *a,  struct ice_fdir_fltr *b, bool v6)
 {
 	enum ice_fltr_ptype flow_type = a->flow_type;
 
 	/* The calling function already checks that the two filters have the
 	 * same flow_type.
 	 */
-	if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
-	    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
-	    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) {
-		if (a->ip.dst_ip == b->ip.dst_ip &&
-		    a->ip.src_ip == b->ip.src_ip &&
-		    a->ip.dst_port == b->ip.dst_port &&
-		    a->ip.src_port == b->ip.src_port)
-			return true;
-	} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
-		if (a->ip.dst_ip == b->ip.dst_ip &&
-		    a->ip.src_ip == b->ip.src_ip &&
-		    a->ip.l4_header == b->ip.l4_header &&
-		    a->ip.proto == b->ip.proto &&
-		    a->ip.ip_ver == b->ip.ip_ver &&
-		    a->ip.tos == b->ip.tos)
-			return true;
+	if (!v6) {
+		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) {
+			if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
+			    a->ip.v4.src_ip == b->ip.v4.src_ip &&
+			    a->ip.v4.dst_port == b->ip.v4.dst_port &&
+			    a->ip.v4.src_port == b->ip.v4.src_port)
+				return true;
+		} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) {
+			if (a->ip.v4.dst_ip == b->ip.v4.dst_ip &&
+			    a->ip.v4.src_ip == b->ip.v4.src_ip &&
+			    a->ip.v4.l4_header == b->ip.v4.l4_header &&
+			    a->ip.v4.proto == b->ip.v4.proto &&
+			    a->ip.v4.ip_ver == b->ip.v4.ip_ver &&
+			    a->ip.v4.tos == b->ip.v4.tos)
+				return true;
+		}
+	} else {
+		if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_TCP ||
+		    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) {
+			if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
+			    a->ip.v6.src_port == b->ip.v6.src_port &&
+			    !ice_cmp_ipv6_addr(a->ip.v6.dst_ip,
+					       b->ip.v6.dst_ip) &&
+			    !ice_cmp_ipv6_addr(a->ip.v6.src_ip,
+					       b->ip.v6.src_ip))
+				return true;
+		} else if (flow_type == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) {
+			if (a->ip.v6.dst_port == b->ip.v6.dst_port &&
+			    a->ip.v6.src_port == b->ip.v6.src_port)
+				return true;
+		}
 	}
 
 	return false;
@@ -586,7 +821,9 @@ bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input)
 		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
 		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_SCTP ||
 		    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_OTHER)
-			ret = ice_fdir_comp_rules(rule, input);
+			ret = ice_fdir_comp_rules(rule, input, false);
+		else
+			ret = ice_fdir_comp_rules(rule, input, true);
 		if (ret) {
 			if (rule->fltr_id == input->fltr_id &&
 			    rule->q_index != input->q_index)
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 1a13c80e1eac..977dcbc1400d 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -80,6 +80,19 @@ struct ice_fdir_v4 {
 	u8 proto;
 };
 
+#define ICE_IPV6_ADDR_LEN_AS_U32		4
+
+struct ice_fdir_v6 {
+	__be32 dst_ip[ICE_IPV6_ADDR_LEN_AS_U32];
+	__be32 src_ip[ICE_IPV6_ADDR_LEN_AS_U32];
+	__be16 dst_port;
+	__be16 src_port;
+	__be32 l4_header; /* next header */
+	__be32 sec_parm_idx; /* security parameter index */
+	u8 tc;
+	u8 proto;
+};
+
 struct ice_fdir_extra {
 	u8 dst_mac[ETH_ALEN];	/* dest MAC address */
 	u32 usr_def[2];		/* user data */
@@ -91,8 +104,10 @@ struct ice_fdir_fltr {
 	struct list_head fltr_node;
 	enum ice_fltr_ptype flow_type;
 
-	struct ice_fdir_v4 ip;
-	struct ice_fdir_v4 mask;
+	union {
+		struct ice_fdir_v4 v4;
+		struct ice_fdir_v6 v6;
+	} ip, mask;
 
 	struct ice_fdir_extra ext_data;
 	struct ice_fdir_extra ext_mask;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 16d2f599bd70..da82783d1571 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -3518,6 +3518,12 @@ static const struct ice_fd_src_dst_pair ice_fd_pairs[] = {
 	{ ICE_PROT_IPV4_IL, 2, 12 },
 	{ ICE_PROT_IPV4_IL, 2, 16 },
 
+	{ ICE_PROT_IPV6_OF_OR_S, 8, 8 },
+	{ ICE_PROT_IPV6_OF_OR_S, 8, 24 },
+
+	{ ICE_PROT_IPV6_IL, 8, 8 },
+	{ ICE_PROT_IPV6_IL, 8, 24 },
+
 	{ ICE_PROT_TCP_IL, 1, 0 },
 	{ ICE_PROT_TCP_IL, 1, 2 },
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index fcf1f7853a41..f1bfe8c94f1f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -171,6 +171,10 @@ enum ice_fltr_ptype {
 	ICE_FLTR_PTYPE_NONF_IPV4_SCTP,
 	ICE_FLTR_PTYPE_NONF_IPV4_OTHER,
 	ICE_FLTR_PTYPE_FRAG_IPV4,
+	ICE_FLTR_PTYPE_NONF_IPV6_UDP,
+	ICE_FLTR_PTYPE_NONF_IPV6_TCP,
+	ICE_FLTR_PTYPE_NONF_IPV6_SCTP,
+	ICE_FLTR_PTYPE_NONF_IPV6_OTHER,
 	ICE_FLTR_PTYPE_MAX,
 };
 
-- 
cgit v1.2.3


From 2c57ffcb199004825184f96081fbf036d3b2426a Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:44 -0700
Subject: ice: Enable flex-bytes support

Flex-bytes allows for packet matching based on an offset and value. This
is supported via the ethtool user-def option.  It is specified by providing
an offset followed by a 2 byte match value. Offset is measured from the
start of the MAC address.

The following restrictions apply to flex-bytes. The specified offset must
be an even number and be smaller than 0x1fe.

Example usage:

ethtool -N eth0 flow-type tcp4 src-ip 192.168.0.55 dst-ip 172.16.0.55 \
src-port 12 dst-port 13 user-def 0x10ffff action 32

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c  |  88 +++++++++++-
 drivers/net/ethernet/intel/ice/ice_fdir.c          |   3 +
 drivers/net/ethernet/intel/ice/ice_fdir.h          |  13 ++
 drivers/net/ethernet/intel/ice/ice_flow.c          | 150 +++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_flow.h          |  12 ++
 drivers/net/ethernet/intel/ice/ice_protocol_type.h |   1 +
 6 files changed, 265 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index aa85d5ad2477..f240c062860b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -92,6 +92,19 @@ static enum ice_fltr_ptype ice_ethtool_flow_to_fltr(int eth)
 	}
 }
 
+/**
+ * ice_is_mask_valid - check mask field set
+ * @mask: full mask to check
+ * @field: field for which mask should be valid
+ *
+ * If the mask is fully set return true. If it is not valid for field return
+ * false.
+ */
+static bool ice_is_mask_valid(u64 mask, u64 field)
+{
+	return (mask & field) == field;
+}
+
 /**
  * ice_get_ethtool_fdir_entry - fill ethtool structure with fdir filter data
  * @hw: hardware structure that contains filter list
@@ -335,6 +348,53 @@ void ice_fdir_release_flows(struct ice_hw *hw)
 		ice_fdir_erase_flow_from_hw(hw, ICE_BLK_FD, flow);
 }
 
+/**
+ * ice_parse_rx_flow_user_data - deconstruct user-defined data
+ * @fsp: pointer to ethtool Rx flow specification
+ * @data: pointer to userdef data structure for storage
+ *
+ * Returns 0 on success, negative error value on failure
+ */
+static int
+ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+			    struct ice_rx_flow_userdef *data)
+{
+	u64 value, mask;
+
+	memset(data, 0, sizeof(*data));
+	if (!(fsp->flow_type & FLOW_EXT))
+		return 0;
+
+	value = be64_to_cpu(*((__force __be64 *)fsp->h_ext.data));
+	mask = be64_to_cpu(*((__force __be64 *)fsp->m_ext.data));
+	if (!mask)
+		return 0;
+
+#define ICE_USERDEF_FLEX_WORD_M	GENMASK_ULL(15, 0)
+#define ICE_USERDEF_FLEX_OFFS_S	16
+#define ICE_USERDEF_FLEX_OFFS_M	GENMASK_ULL(31, ICE_USERDEF_FLEX_OFFS_S)
+#define ICE_USERDEF_FLEX_FLTR_M	GENMASK_ULL(31, 0)
+
+	/* 0x1fe is the maximum value for offsets stored in the internal
+	 * filtering tables.
+	 */
+#define ICE_USERDEF_FLEX_MAX_OFFS_VAL 0x1fe
+
+	if (!ice_is_mask_valid(mask, ICE_USERDEF_FLEX_FLTR_M) ||
+	    value > ICE_USERDEF_FLEX_FLTR_M)
+		return -EINVAL;
+
+	data->flex_word = value & ICE_USERDEF_FLEX_WORD_M;
+	data->flex_offset = (value & ICE_USERDEF_FLEX_OFFS_M) >>
+			     ICE_USERDEF_FLEX_OFFS_S;
+	if (data->flex_offset > ICE_USERDEF_FLEX_MAX_OFFS_VAL)
+		return -EINVAL;
+
+	data->flex_fltr = true;
+
+	return 0;
+}
+
 /**
  * ice_fdir_num_avail_fltr - return the number of unused flow director filters
  * @hw: pointer to hardware structure
@@ -936,11 +996,13 @@ ice_set_fdir_ip6_usr_seg(struct ice_flow_seg_info *seg,
  * ice_cfg_fdir_xtrct_seq - Configure extraction sequence for the given filter
  * @pf: PF structure
  * @fsp: pointer to ethtool Rx flow specification
+ * @user: user defined data from flow specification
  *
  * Returns 0 on success.
  */
 static int
-ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp)
+ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp,
+		       struct ice_rx_flow_userdef *user)
 {
 	struct ice_flow_seg_info *seg, *tun_seg;
 	struct device *dev = ice_pf_to_dev(pf);
@@ -1008,6 +1070,18 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp)
 	/* tunnel segments are shifted up one. */
 	memcpy(&tun_seg[1], seg, sizeof(*seg));
 
+	if (user && user->flex_fltr) {
+		perfect_filter = false;
+		ice_flow_add_fld_raw(seg, user->flex_offset,
+				     ICE_FLTR_PRGM_FLEX_WORD_SIZE,
+				     ICE_FLOW_FLD_OFF_INVAL,
+				     ICE_FLOW_FLD_OFF_INVAL);
+		ice_flow_add_fld_raw(&tun_seg[1], user->flex_offset,
+				     ICE_FLTR_PRGM_FLEX_WORD_SIZE,
+				     ICE_FLOW_FLD_OFF_INVAL,
+				     ICE_FLOW_FLD_OFF_INVAL);
+	}
+
 	/* add filter for outer headers */
 	fltr_idx = ice_ethtool_flow_to_fltr(fsp->flow_type & ~FLOW_EXT);
 	ret = ice_fdir_set_hw_fltr_rule(pf, seg, fltr_idx,
@@ -1433,6 +1507,7 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp,
  */
 int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 {
+	struct ice_rx_flow_userdef userdata;
 	struct ethtool_rx_flow_spec *fsp;
 	struct ice_fdir_fltr *input;
 	struct device *dev;
@@ -1460,10 +1535,13 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 
 	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
 
+	if (ice_parse_rx_flow_user_data(fsp, &userdata))
+		return -EINVAL;
+
 	if (fsp->flow_type & FLOW_MAC_EXT)
 		return -EINVAL;
 
-	ret = ice_cfg_fdir_xtrct_seq(pf, fsp);
+	ret = ice_cfg_fdir_xtrct_seq(pf, fsp, &userdata);
 	if (ret)
 		return ret;
 
@@ -1495,6 +1573,12 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 		goto release_lock;
 	}
 
+	if (userdata.flex_fltr) {
+		input->flex_fltr = true;
+		input->flex_word = cpu_to_be16(userdata.flex_word);
+		input->flex_offset = userdata.flex_offset;
+	}
+
 	/* input struct is added to the HW filter list */
 	ice_fdir_update_list_entry(pf, input, fsp->location);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index d50cc6e9086e..6834df14332f 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -650,6 +650,9 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 		return ICE_ERR_PARAM;
 	}
 
+	if (input->flex_fltr)
+		ice_pkt_insert_u16(loc, input->flex_offset, input->flex_word);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
index 977dcbc1400d..1c587766daab 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
@@ -68,6 +68,14 @@ struct ice_fd_fltr_desc_ctx {
 	u8 fdid_mdid;
 };
 
+#define ICE_FLTR_PRGM_FLEX_WORD_SIZE	sizeof(__be16)
+
+struct ice_rx_flow_userdef {
+	u16 flex_word;
+	u16 flex_offset;
+	u16 flex_fltr;
+};
+
 struct ice_fdir_v4 {
 	__be32 dst_ip;
 	__be32 src_ip;
@@ -112,6 +120,11 @@ struct ice_fdir_fltr {
 	struct ice_fdir_extra ext_data;
 	struct ice_fdir_extra ext_mask;
 
+	/* flex byte filter data */
+	__be16 flex_word;
+	u16 flex_offset;
+	u16 flex_fltr;
+
 	/* filter control */
 	u16 q_index;
 	u16 dest_vsi;
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index f4b6c3933564..d74e5290677f 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -193,6 +193,40 @@ ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt)
 	return 0;
 }
 
+/* Sizes of fixed known protocol headers without header options */
+#define ICE_FLOW_PROT_HDR_SZ_MAC	14
+#define ICE_FLOW_PROT_HDR_SZ_IPV4	20
+#define ICE_FLOW_PROT_HDR_SZ_IPV6	40
+#define ICE_FLOW_PROT_HDR_SZ_TCP	20
+#define ICE_FLOW_PROT_HDR_SZ_UDP	8
+#define ICE_FLOW_PROT_HDR_SZ_SCTP	12
+
+/**
+ * ice_flow_calc_seg_sz - calculates size of a packet segment based on headers
+ * @params: information about the flow to be processed
+ * @seg: index of packet segment whose header size is to be determined
+ */
+static u16 ice_flow_calc_seg_sz(struct ice_flow_prof_params *params, u8 seg)
+{
+	u16 sz = ICE_FLOW_PROT_HDR_SZ_MAC;
+
+	/* L3 headers */
+	if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_IPV4)
+		sz += ICE_FLOW_PROT_HDR_SZ_IPV4;
+	else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_IPV6)
+		sz += ICE_FLOW_PROT_HDR_SZ_IPV6;
+
+	/* L4 headers */
+	if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_TCP)
+		sz += ICE_FLOW_PROT_HDR_SZ_TCP;
+	else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_UDP)
+		sz += ICE_FLOW_PROT_HDR_SZ_UDP;
+	else if (params->prof->segs[seg].hdrs & ICE_FLOW_SEG_HDR_SCTP)
+		sz += ICE_FLOW_PROT_HDR_SZ_SCTP;
+
+	return sz;
+}
+
 /**
  * ice_flow_proc_seg_hdrs - process protocol headers present in pkt segments
  * @params: information about the flow to be processed
@@ -347,6 +381,81 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params,
 	return 0;
 }
 
+/**
+ * ice_flow_xtract_raws - Create extract sequence entries for raw bytes
+ * @hw: pointer to the HW struct
+ * @params: information about the flow to be processed
+ * @seg: index of packet segment whose raw fields are to be be extracted
+ */
+static enum ice_status
+ice_flow_xtract_raws(struct ice_hw *hw, struct ice_flow_prof_params *params,
+		     u8 seg)
+{
+	u16 fv_words;
+	u16 hdrs_sz;
+	u8 i;
+
+	if (!params->prof->segs[seg].raws_cnt)
+		return 0;
+
+	if (params->prof->segs[seg].raws_cnt >
+	    ARRAY_SIZE(params->prof->segs[seg].raws))
+		return ICE_ERR_MAX_LIMIT;
+
+	/* Offsets within the segment headers are not supported */
+	hdrs_sz = ice_flow_calc_seg_sz(params, seg);
+	if (!hdrs_sz)
+		return ICE_ERR_PARAM;
+
+	fv_words = hw->blk[params->blk].es.fvw;
+
+	for (i = 0; i < params->prof->segs[seg].raws_cnt; i++) {
+		struct ice_flow_seg_fld_raw *raw;
+		u16 off, cnt, j;
+
+		raw = &params->prof->segs[seg].raws[i];
+
+		/* Storing extraction information */
+		raw->info.xtrct.prot_id = ICE_PROT_MAC_OF_OR_S;
+		raw->info.xtrct.off = (raw->off / ICE_FLOW_FV_EXTRACT_SZ) *
+			ICE_FLOW_FV_EXTRACT_SZ;
+		raw->info.xtrct.disp = (raw->off % ICE_FLOW_FV_EXTRACT_SZ) *
+			BITS_PER_BYTE;
+		raw->info.xtrct.idx = params->es_cnt;
+
+		/* Determine the number of field vector entries this raw field
+		 * consumes.
+		 */
+		cnt = DIV_ROUND_UP(raw->info.xtrct.disp +
+				   (raw->info.src.last * BITS_PER_BYTE),
+				   (ICE_FLOW_FV_EXTRACT_SZ * BITS_PER_BYTE));
+		off = raw->info.xtrct.off;
+		for (j = 0; j < cnt; j++) {
+			u16 idx;
+
+			/* Make sure the number of extraction sequence required
+			 * does not exceed the block's capability
+			 */
+			if (params->es_cnt >= hw->blk[params->blk].es.count ||
+			    params->es_cnt >= ICE_MAX_FV_WORDS)
+				return ICE_ERR_MAX_LIMIT;
+
+			/* some blocks require a reversed field vector layout */
+			if (hw->blk[params->blk].es.reverse)
+				idx = fv_words - params->es_cnt - 1;
+			else
+				idx = params->es_cnt;
+
+			params->es[idx].prot_id = raw->info.xtrct.prot_id;
+			params->es[idx].off = off;
+			params->es_cnt++;
+			off += ICE_FLOW_FV_EXTRACT_SZ;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * ice_flow_create_xtrct_seq - Create an extraction sequence for given segments
  * @hw: pointer to the HW struct
@@ -373,6 +482,11 @@ ice_flow_create_xtrct_seq(struct ice_hw *hw,
 			if (status)
 				return status;
 		}
+
+		/* Process raw matching bytes */
+		status = ice_flow_xtract_raws(hw, params, i);
+		if (status)
+			return status;
 	}
 
 	return status;
@@ -943,6 +1057,42 @@ ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
 	ice_flow_set_fld_ext(seg, fld, t, val_loc, mask_loc, last_loc);
 }
 
+/**
+ * ice_flow_add_fld_raw - sets locations of a raw field from entry's input buf
+ * @seg: packet segment the field being set belongs to
+ * @off: offset of the raw field from the beginning of the segment in bytes
+ * @len: length of the raw pattern to be matched
+ * @val_loc: location of the value to match from entry's input buffer
+ * @mask_loc: location of mask value from entry's input buffer
+ *
+ * This function specifies the offset of the raw field to be match from the
+ * beginning of the specified packet segment, and the locations, in the form of
+ * byte offsets from the start of the input buffer for a flow entry, from where
+ * the value to match and the mask value to be extracted. These locations are
+ * then stored in the flow profile. When adding flow entries to the associated
+ * flow profile, these locations can be used to quickly extract the values to
+ * create the content of a match entry. This function should only be used for
+ * fixed-size data structures.
+ */
+void
+ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len,
+		     u16 val_loc, u16 mask_loc)
+{
+	if (seg->raws_cnt < ICE_FLOW_SEG_RAW_FLD_MAX) {
+		seg->raws[seg->raws_cnt].off = off;
+		seg->raws[seg->raws_cnt].info.type = ICE_FLOW_FLD_TYPE_SIZE;
+		seg->raws[seg->raws_cnt].info.src.val = val_loc;
+		seg->raws[seg->raws_cnt].info.src.mask = mask_loc;
+		/* The "last" field is used to store the length of the field */
+		seg->raws[seg->raws_cnt].info.src.last = len;
+	}
+
+	/* Overflows of "raws" will be handled as an error condition later in
+	 * the flow when this information is processed.
+	 */
+	seg->raws_cnt++;
+}
+
 #define ICE_FLOW_RSS_SEG_HDR_L3_MASKS \
 	(ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6)
 
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 3c784c3b5db2..3913da2116d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -128,6 +128,7 @@ enum ice_flow_priority {
 };
 
 #define ICE_FLOW_SEG_MAX		2
+#define ICE_FLOW_SEG_RAW_FLD_MAX	2
 #define ICE_FLOW_FV_EXTRACT_SZ		2
 
 #define ICE_FLOW_SET_HDRS(seg, val)	((seg)->hdrs |= (u32)(val))
@@ -164,12 +165,20 @@ struct ice_flow_fld_info {
 	struct ice_flow_seg_xtrct xtrct;
 };
 
+struct ice_flow_seg_fld_raw {
+	struct ice_flow_fld_info info;
+	u16 off;	/* Offset from the start of the segment */
+};
+
 struct ice_flow_seg_info {
 	u32 hdrs;	/* Bitmask indicating protocol headers present */
 	u64 match;	/* Bitmask indicating header fields to be matched */
 	u64 range;	/* Bitmask indicating header fields matched as ranges */
 
 	struct ice_flow_fld_info fields[ICE_FLOW_FIELD_IDX_MAX];
+
+	u8 raws_cnt;	/* Number of raw fields to be matched */
+	struct ice_flow_seg_fld_raw raws[ICE_FLOW_SEG_RAW_FLD_MAX];
 };
 
 /* This structure describes a flow entry, and is tracked only in this file */
@@ -228,6 +237,9 @@ ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, u64 entry_h);
 void
 ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld,
 		 u16 val_loc, u16 mask_loc, u16 last_loc, bool range);
+void
+ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len,
+		     u16 val_loc, u16 mask_loc);
 void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle);
 enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
index babe4a485fd6..7f4c1ec1eff2 100644
--- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h
@@ -12,6 +12,7 @@
  */
 enum ice_prot_id {
 	ICE_PROT_ID_INVAL	= 0,
+	ICE_PROT_MAC_OF_OR_S	= 1,
 	ICE_PROT_IPV4_OF_OR_S	= 32,
 	ICE_PROT_IPV4_IL	= 33,
 	ICE_PROT_IPV6_OF_OR_S	= 40,
-- 
cgit v1.2.3


From 83af00395190bc2db05a67a417a2ea0d5967b74d Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Mon, 11 May 2020 18:01:45 -0700
Subject: ice: Restore filters following reset

Following a reset, Flow Director filters are cleared from the hardware.
Rebuild the filters using the software structures containing the filter
rules.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h              |  2 +
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 65 +++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.c          | 17 +++---
 drivers/net/ethernet/intel/ice/ice_main.c         | 31 +++++++++++
 4 files changed, 109 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 298a65a3799c..38739ee8cd94 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -566,6 +566,8 @@ int
 ice_get_fdir_fltr_ids(struct ice_hw *hw, struct ethtool_rxnfc *cmd,
 		      u32 *rule_locs);
 void ice_fdir_release_flows(struct ice_hw *hw);
+void ice_fdir_replay_flows(struct ice_hw *hw);
+void ice_fdir_replay_fltrs(struct ice_pf *pf);
 int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 int ice_open(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index f240c062860b..a0002032be61 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -348,6 +348,53 @@ void ice_fdir_release_flows(struct ice_hw *hw)
 		ice_fdir_erase_flow_from_hw(hw, ICE_BLK_FD, flow);
 }
 
+/**
+ * ice_fdir_replay_flows - replay HW Flow Director filter info
+ * @hw: pointer to HW instance
+ */
+void ice_fdir_replay_flows(struct ice_hw *hw)
+{
+	int flow;
+
+	for (flow = 0; flow < ICE_FLTR_PTYPE_MAX; flow++) {
+		int tun;
+
+		if (!hw->fdir_prof[flow] || !hw->fdir_prof[flow]->cnt)
+			continue;
+		for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
+			struct ice_flow_prof *hw_prof;
+			struct ice_fd_hw_prof *prof;
+			u64 prof_id;
+			int j;
+
+			prof = hw->fdir_prof[flow];
+			prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
+			ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id,
+					  prof->fdir_seg[tun], TNL_SEG_CNT(tun),
+					  &hw_prof);
+			for (j = 0; j < prof->cnt; j++) {
+				enum ice_flow_priority prio;
+				u64 entry_h = 0;
+				int err;
+
+				prio = ICE_FLOW_PRIO_NORMAL;
+				err = ice_flow_add_entry(hw, ICE_BLK_FD,
+							 prof_id,
+							 prof->vsi_h[0],
+							 prof->vsi_h[j],
+							 prio, prof->fdir_seg,
+							 &entry_h);
+				if (err) {
+					dev_err(ice_hw_to_dev(hw), "Could not replay Flow Director, flow type %d\n",
+						flow);
+					continue;
+				}
+				prof->entry_h[j][tun] = entry_h;
+			}
+		}
+	}
+}
+
 /**
  * ice_parse_rx_flow_user_data - deconstruct user-defined data
  * @fsp: pointer to ethtool Rx flow specification
@@ -1225,6 +1272,24 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input,
 	return 0;
 }
 
+/**
+ * ice_fdir_replay_fltrs - replay filters from the HW filter list
+ * @pf: board private structure
+ */
+void ice_fdir_replay_fltrs(struct ice_pf *pf)
+{
+	struct ice_fdir_fltr *f_rule;
+	struct ice_hw *hw = &pf->hw;
+
+	list_for_each_entry(f_rule, &hw->fdir_list_head, fltr_node) {
+		int err = ice_fdir_write_all_fltr(pf, f_rule, true);
+
+		if (err)
+			dev_dbg(ice_pf_to_dev(pf), "Flow Director error %d, could not reprogram filter %d\n",
+				err, f_rule->fltr_id);
+	}
+}
+
 /**
  * ice_fdir_create_dflt_rules - create default perfect filters
  * @pf: PF data structure
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 43c949e0a760..ff77fc3f633e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2748,6 +2748,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 		goto err_vsi;
 
 	ice_vsi_get_qs(vsi);
+
+	ice_alloc_fd_res(vsi);
 	ice_vsi_set_tc_cfg(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */
@@ -2756,6 +2758,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 		goto err_vsi;
 
 	switch (vsi->type) {
+	case ICE_VSI_CTRL:
 	case ICE_VSI_PF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
@@ -2780,12 +2783,14 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 			if (ret)
 				goto err_vectors;
 		}
-		/* Do not exit if configuring RSS had an issue, at least
-		 * receive traffic on first queue. Hence no need to capture
-		 * return value
-		 */
-		if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
-			ice_vsi_cfg_rss_lut_key(vsi);
+		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
+		if (vsi->type != ICE_VSI_CTRL)
+			/* Do not exit if configuring RSS had an issue, at
+			 * least receive traffic on first queue. Hence no
+			 * need to capture return value
+			 */
+			if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+				ice_vsi_cfg_rss_lut_key(vsi);
 		break;
 	case ICE_VSI_VF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index fecc3b29a4de..d06a3311a2dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4895,6 +4895,21 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_sched_init_port;
 	}
 
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) {
+		wr32(hw, PFQF_FD_ENA, PFQF_FD_ENA_FD_ENA_M);
+		if (!rd32(hw, PFQF_FD_SIZE)) {
+			u16 unused, guar, b_effort;
+
+			guar = hw->func_caps.fd_fltr_guar;
+			b_effort = hw->func_caps.fd_fltr_best_effort;
+
+			/* force guaranteed filter pool for PF */
+			ice_alloc_fd_guar_item(hw, &unused, guar);
+			/* force shared filter pool for PF */
+			ice_alloc_fd_shrd_item(hw, &unused, b_effort);
+		}
+	}
+
 	if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
 		ice_dcb_rebuild(pf);
 
@@ -4913,6 +4928,22 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		}
 	}
 
+	/* If Flow Director is active */
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) {
+		err = ice_vsi_rebuild_by_type(pf, ICE_VSI_CTRL);
+		if (err) {
+			dev_err(dev, "control VSI rebuild failed: %d\n", err);
+			goto err_vsi_rebuild;
+		}
+
+		/* replay HW Flow Director recipes */
+		if (hw->fdir_prof)
+			ice_fdir_replay_flows(hw);
+
+		/* replay Flow Director filters */
+		ice_fdir_replay_fltrs(pf);
+	}
+
 	ice_update_pf_netdev_link(pf);
 
 	/* tell the firmware we are up */
-- 
cgit v1.2.3


From 28bf26724fdb0e02267d19e280d6717ee810a10d Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Mon, 11 May 2020 18:01:46 -0700
Subject: ice: Implement aRFS

Enable accelerated Receive Flow Steering (aRFS). It is used to steer Rx
flows to a specific queue. This functionality is triggered by the network
stack through ndo_rx_flow_steer and requires Flow Director (ntuple on) to
function.

The fltr_info is used to add/remove/update flow rules in the HW, the
fltr_state is used to determine what to do with the filter with respect
to HW and/or SW, and the flow_id is used in co-ordination with the
network stack.

The work for aRFS is split into two paths: the ndo_rx_flow_steer
operation and the ice_service_task. The former is where the kernel hands
us an Rx SKB among other items to setup aRFS and the latter is where
the driver adds/updates/removes filter rules from HW and updates filter
state.

In the Rx path the following things can happen:
        1. New aRFS entries are added to the hash table and the state is
           set to ICE_ARFS_INACTIVE so the filter can be updated in HW
           by the ice_service_task path.
        2. aRFS entries have their Rx Queue updated if we receive a
           pre-existing flow_id and the filter state is ICE_ARFS_ACTIVE.
           The state is set to ICE_ARFS_INACTIVE so the filter can be
           updated in HW by the ice_service_task path.
        3. aRFS entries marked as ICE_ARFS_TODEL are deleted

In the ice_service_task path the following things can happen:
        1. New aRFS entries marked as ICE_ARFS_INACTIVE are added or
           updated in HW.
           and their state is updated to ICE_ARFS_ACTIVE.
        2. aRFS entries are deleted from HW and their state is updated
           to ICE_ARFS_TODEL.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile           |   1 +
 drivers/net/ethernet/intel/ice/ice.h              |  14 +
 drivers/net/ethernet/intel/ice/ice_arfs.c         | 663 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_arfs.h         |  82 +++
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c |   8 +-
 drivers/net/ethernet/intel/ice/ice_lib.c          |   1 +
 drivers/net/ethernet/intel/ice/ice_main.c         |  48 +-
 7 files changed, 805 insertions(+), 12 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_arfs.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_arfs.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 9ffa2e366766..980bbcc64b4b 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -26,4 +26,5 @@ ice-y := ice_main.o	\
 	 ice_ethtool.o
 ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
+ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o
 ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 38739ee8cd94..5792ee616b5c 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -34,6 +34,7 @@
 #include <linux/ctype.h>
 #include <linux/bpf.h>
 #include <linux/avf/virtchnl.h>
+#include <linux/cpu_rmap.h>
 #include <net/devlink.h>
 #include <net/ipv6.h>
 #include <net/xdp_sock.h>
@@ -52,6 +53,7 @@
 #include "ice_sriov.h"
 #include "ice_fdir.h"
 #include "ice_xsk.h"
+#include "ice_arfs.h"
 
 extern const char ice_drv_ver[];
 #define ICE_BAR0		0
@@ -271,6 +273,14 @@ struct ice_vsi {
 	u8 *rss_lut_user;	/* User configured lookup table entries */
 	u8 rss_lut_type;	/* used to configure Get/Set RSS LUT AQ call */
 
+	/* aRFS members only allocated for the PF VSI */
+#define ICE_MAX_ARFS_LIST	1024
+#define ICE_ARFS_LST_MASK	(ICE_MAX_ARFS_LIST - 1)
+	struct hlist_head *arfs_fltr_list;
+	struct ice_arfs_active_fltr_cntrs *arfs_fltr_cntrs;
+	spinlock_t arfs_lock;	/* protects aRFS hash table and filter state */
+	atomic_t *arfs_last_fltr_id;
+
 	u16 max_frame;
 	u16 rx_buf_len;
 
@@ -558,6 +568,9 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 const char *ice_stat_str(enum ice_status stat_err);
 const char *ice_aq_str(enum ice_aq_err aq_err);
+int
+ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add,
+		    bool is_tun);
 void ice_vsi_manage_fdir(struct ice_vsi *vsi, bool ena);
 int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd);
 int ice_del_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd);
@@ -571,5 +584,6 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf);
 int ice_fdir_create_dflt_rules(struct ice_pf *pf);
 int ice_open(struct net_device *netdev);
 int ice_stop(struct net_device *netdev);
+void ice_service_task_schedule(struct ice_pf *pf);
 
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
new file mode 100644
index 000000000000..6560acd76c94
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#include "ice.h"
+
+/**
+ * ice_is_arfs_active - helper to check is aRFS is active
+ * @vsi: VSI to check
+ */
+static bool ice_is_arfs_active(struct ice_vsi *vsi)
+{
+	return !!vsi->arfs_fltr_list;
+}
+
+/**
+ * ice_is_arfs_using_perfect_flow - check if aRFS has active perfect filters
+ * @hw: pointer to the HW structure
+ * @flow_type: flow type as Flow Director understands it
+ *
+ * Flow Director will query this function to see if aRFS is currently using
+ * the specified flow_type for perfect (4-tuple) filters.
+ */
+bool
+ice_is_arfs_using_perfect_flow(struct ice_hw *hw, enum ice_fltr_ptype flow_type)
+{
+	struct ice_arfs_active_fltr_cntrs *arfs_fltr_cntrs;
+	struct ice_pf *pf = hw->back;
+	struct ice_vsi *vsi;
+
+	vsi = ice_get_main_vsi(pf);
+	if (!vsi)
+		return false;
+
+	arfs_fltr_cntrs = vsi->arfs_fltr_cntrs;
+
+	/* active counters can be updated by multiple CPUs */
+	smp_mb__before_atomic();
+	switch (flow_type) {
+	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
+		return atomic_read(&arfs_fltr_cntrs->active_udpv4_cnt) > 0;
+	case ICE_FLTR_PTYPE_NONF_IPV6_UDP:
+		return atomic_read(&arfs_fltr_cntrs->active_udpv6_cnt) > 0;
+	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
+		return atomic_read(&arfs_fltr_cntrs->active_tcpv4_cnt) > 0;
+	case ICE_FLTR_PTYPE_NONF_IPV6_TCP:
+		return atomic_read(&arfs_fltr_cntrs->active_tcpv6_cnt) > 0;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ice_arfs_update_active_fltr_cntrs - update active filter counters for aRFS
+ * @vsi: VSI that aRFS is active on
+ * @entry: aRFS entry used to change counters
+ * @add: true to increment counter, false to decrement
+ */
+static void
+ice_arfs_update_active_fltr_cntrs(struct ice_vsi *vsi,
+				  struct ice_arfs_entry *entry, bool add)
+{
+	struct ice_arfs_active_fltr_cntrs *fltr_cntrs = vsi->arfs_fltr_cntrs;
+
+	switch (entry->fltr_info.flow_type) {
+	case ICE_FLTR_PTYPE_NONF_IPV4_TCP:
+		if (add)
+			atomic_inc(&fltr_cntrs->active_tcpv4_cnt);
+		else
+			atomic_dec(&fltr_cntrs->active_tcpv4_cnt);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_TCP:
+		if (add)
+			atomic_inc(&fltr_cntrs->active_tcpv6_cnt);
+		else
+			atomic_dec(&fltr_cntrs->active_tcpv6_cnt);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV4_UDP:
+		if (add)
+			atomic_inc(&fltr_cntrs->active_udpv4_cnt);
+		else
+			atomic_dec(&fltr_cntrs->active_udpv4_cnt);
+		break;
+	case ICE_FLTR_PTYPE_NONF_IPV6_UDP:
+		if (add)
+			atomic_inc(&fltr_cntrs->active_udpv6_cnt);
+		else
+			atomic_dec(&fltr_cntrs->active_udpv6_cnt);
+		break;
+	default:
+		dev_err(ice_pf_to_dev(vsi->back), "aRFS: Failed to update filter counters, invalid filter type %d\n",
+			entry->fltr_info.flow_type);
+	}
+}
+
+/**
+ * ice_arfs_del_flow_rules - delete the rules passed in from HW
+ * @vsi: VSI for the flow rules that need to be deleted
+ * @del_list_head: head of the list of ice_arfs_entry(s) for rule deletion
+ *
+ * Loop through the delete list passed in and remove the rules from HW. After
+ * each rule is deleted, disconnect and free the ice_arfs_entry because it is no
+ * longer being referenced by the aRFS hash table.
+ */
+static void
+ice_arfs_del_flow_rules(struct ice_vsi *vsi, struct hlist_head *del_list_head)
+{
+	struct ice_arfs_entry *e;
+	struct hlist_node *n;
+	struct device *dev;
+
+	dev = ice_pf_to_dev(vsi->back);
+
+	hlist_for_each_entry_safe(e, n, del_list_head, list_entry) {
+		int result;
+
+		result = ice_fdir_write_fltr(vsi->back, &e->fltr_info, false,
+					     false);
+		if (!result)
+			ice_arfs_update_active_fltr_cntrs(vsi, e, false);
+		else
+			dev_dbg(dev, "Unable to delete aRFS entry, err %d fltr_state %d fltr_id %d flow_id %d Q %d\n",
+				result, e->fltr_state, e->fltr_info.fltr_id,
+				e->flow_id, e->fltr_info.q_index);
+
+		/* The aRFS hash table is no longer referencing this entry */
+		hlist_del(&e->list_entry);
+		devm_kfree(dev, e);
+	}
+}
+
+/**
+ * ice_arfs_add_flow_rules - add the rules passed in from HW
+ * @vsi: VSI for the flow rules that need to be added
+ * @add_list_head: head of the list of ice_arfs_entry_ptr(s) for rule addition
+ *
+ * Loop through the add list passed in and remove the rules from HW. After each
+ * rule is added, disconnect and free the ice_arfs_entry_ptr node. Don't free
+ * the ice_arfs_entry(s) because they are still being referenced in the aRFS
+ * hash table.
+ */
+static void
+ice_arfs_add_flow_rules(struct ice_vsi *vsi, struct hlist_head *add_list_head)
+{
+	struct ice_arfs_entry_ptr *ep;
+	struct hlist_node *n;
+	struct device *dev;
+
+	dev = ice_pf_to_dev(vsi->back);
+
+	hlist_for_each_entry_safe(ep, n, add_list_head, list_entry) {
+		int result;
+
+		result = ice_fdir_write_fltr(vsi->back,
+					     &ep->arfs_entry->fltr_info, true,
+					     false);
+		if (!result)
+			ice_arfs_update_active_fltr_cntrs(vsi, ep->arfs_entry,
+							  true);
+		else
+			dev_dbg(dev, "Unable to add aRFS entry, err %d fltr_state %d fltr_id %d flow_id %d Q %d\n",
+				result, ep->arfs_entry->fltr_state,
+				ep->arfs_entry->fltr_info.fltr_id,
+				ep->arfs_entry->flow_id,
+				ep->arfs_entry->fltr_info.q_index);
+
+		hlist_del(&ep->list_entry);
+		devm_kfree(dev, ep);
+	}
+}
+
+/**
+ * ice_arfs_is_flow_expired - check if the aRFS entry has expired
+ * @vsi: VSI containing the aRFS entry
+ * @arfs_entry: aRFS entry that's being checked for expiration
+ *
+ * Return true if the flow has expired, else false. This function should be used
+ * to determine whether or not an aRFS entry should be removed from the hardware
+ * and software structures.
+ */
+static bool
+ice_arfs_is_flow_expired(struct ice_vsi *vsi, struct ice_arfs_entry *arfs_entry)
+{
+#define ICE_ARFS_TIME_DELTA_EXPIRATION	msecs_to_jiffies(5000)
+	if (rps_may_expire_flow(vsi->netdev, arfs_entry->fltr_info.q_index,
+				arfs_entry->flow_id,
+				arfs_entry->fltr_info.fltr_id))
+		return true;
+
+	/* expiration timer only used for UDP filters */
+	if (arfs_entry->fltr_info.flow_type != ICE_FLTR_PTYPE_NONF_IPV4_UDP &&
+	    arfs_entry->fltr_info.flow_type != ICE_FLTR_PTYPE_NONF_IPV6_UDP)
+		return false;
+
+	return time_in_range64(arfs_entry->time_activated +
+			       ICE_ARFS_TIME_DELTA_EXPIRATION,
+			       arfs_entry->time_activated, get_jiffies_64());
+}
+
+/**
+ * ice_arfs_update_flow_rules - add/delete aRFS rules in HW
+ * @vsi: the VSI to be forwarded to
+ * @idx: index into the table of aRFS filter lists. Obtained from skb->hash
+ * @add_list: list to populate with filters to be added to Flow Director
+ * @del_list: list to populate with filters to be deleted from Flow Director
+ *
+ * Iterate over the hlist at the index given in the aRFS hash table and
+ * determine if there are any aRFS entries that need to be either added or
+ * deleted in the HW. If the aRFS entry is marked as ICE_ARFS_INACTIVE the
+ * filter needs to be added to HW, else if it's marked as ICE_ARFS_ACTIVE and
+ * the flow has expired delete the filter from HW. The caller of this function
+ * is expected to add/delete rules on the add_list/del_list respectively.
+ */
+static void
+ice_arfs_update_flow_rules(struct ice_vsi *vsi, u16 idx,
+			   struct hlist_head *add_list,
+			   struct hlist_head *del_list)
+{
+	struct ice_arfs_entry *e;
+	struct hlist_node *n;
+	struct device *dev;
+
+	dev = ice_pf_to_dev(vsi->back);
+
+	/* go through the aRFS hlist at this idx and check for needed updates */
+	hlist_for_each_entry_safe(e, n, &vsi->arfs_fltr_list[idx], list_entry)
+		/* check if filter needs to be added to HW */
+		if (e->fltr_state == ICE_ARFS_INACTIVE) {
+			enum ice_fltr_ptype flow_type = e->fltr_info.flow_type;
+			struct ice_arfs_entry_ptr *ep =
+				devm_kzalloc(dev, sizeof(*ep), GFP_ATOMIC);
+
+			if (!ep)
+				continue;
+			INIT_HLIST_NODE(&ep->list_entry);
+			/* reference aRFS entry to add HW filter */
+			ep->arfs_entry = e;
+			hlist_add_head(&ep->list_entry, add_list);
+			e->fltr_state = ICE_ARFS_ACTIVE;
+			/* expiration timer only used for UDP flows */
+			if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
+			    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP)
+				e->time_activated = get_jiffies_64();
+		} else if (e->fltr_state == ICE_ARFS_ACTIVE) {
+			/* check if filter needs to be removed from HW */
+			if (ice_arfs_is_flow_expired(vsi, e)) {
+				/* remove aRFS entry from hash table for delete
+				 * and to prevent referencing it the next time
+				 * through this hlist index
+				 */
+				hlist_del(&e->list_entry);
+				e->fltr_state = ICE_ARFS_TODEL;
+				/* save reference to aRFS entry for delete */
+				hlist_add_head(&e->list_entry, del_list);
+			}
+		}
+}
+
+/**
+ * ice_sync_arfs_fltrs - update all aRFS filters
+ * @pf: board private structure
+ */
+void ice_sync_arfs_fltrs(struct ice_pf *pf)
+{
+	HLIST_HEAD(tmp_del_list);
+	HLIST_HEAD(tmp_add_list);
+	struct ice_vsi *pf_vsi;
+	unsigned int i;
+
+	pf_vsi = ice_get_main_vsi(pf);
+	if (!pf_vsi)
+		return;
+
+	if (!ice_is_arfs_active(pf_vsi))
+		return;
+
+	spin_lock_bh(&pf_vsi->arfs_lock);
+	/* Once we process aRFS for the PF VSI get out */
+	for (i = 0; i < ICE_MAX_ARFS_LIST; i++)
+		ice_arfs_update_flow_rules(pf_vsi, i, &tmp_add_list,
+					   &tmp_del_list);
+	spin_unlock_bh(&pf_vsi->arfs_lock);
+
+	/* use list of ice_arfs_entry(s) for delete */
+	ice_arfs_del_flow_rules(pf_vsi, &tmp_del_list);
+
+	/* use list of ice_arfs_entry_ptr(s) for add */
+	ice_arfs_add_flow_rules(pf_vsi, &tmp_add_list);
+}
+
+/**
+ * ice_arfs_build_entry - builds an aRFS entry based on input
+ * @vsi: destination VSI for this flow
+ * @fk: flow dissector keys for creating the tuple
+ * @rxq_idx: Rx queue to steer this flow to
+ * @flow_id: passed down from the stack and saved for flow expiration
+ *
+ * returns an aRFS entry on success and NULL on failure
+ */
+static struct ice_arfs_entry *
+ice_arfs_build_entry(struct ice_vsi *vsi, const struct flow_keys *fk,
+		     u16 rxq_idx, u32 flow_id)
+{
+	struct ice_arfs_entry *arfs_entry;
+	struct ice_fdir_fltr *fltr_info;
+	u8 ip_proto;
+
+	arfs_entry = devm_kzalloc(ice_pf_to_dev(vsi->back),
+				  sizeof(*arfs_entry),
+				  GFP_ATOMIC | __GFP_NOWARN);
+	if (!arfs_entry)
+		return NULL;
+
+	fltr_info = &arfs_entry->fltr_info;
+	fltr_info->q_index = rxq_idx;
+	fltr_info->dest_ctl = ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX;
+	fltr_info->dest_vsi = vsi->idx;
+	ip_proto = fk->basic.ip_proto;
+
+	if (fk->basic.n_proto == htons(ETH_P_IP)) {
+		fltr_info->ip.v4.proto = ip_proto;
+		fltr_info->flow_type = (ip_proto == IPPROTO_TCP) ?
+			ICE_FLTR_PTYPE_NONF_IPV4_TCP :
+			ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+		fltr_info->ip.v4.src_ip = fk->addrs.v4addrs.src;
+		fltr_info->ip.v4.dst_ip = fk->addrs.v4addrs.dst;
+		fltr_info->ip.v4.src_port = fk->ports.src;
+		fltr_info->ip.v4.dst_port = fk->ports.dst;
+	} else { /* ETH_P_IPV6 */
+		fltr_info->ip.v6.proto = ip_proto;
+		fltr_info->flow_type = (ip_proto == IPPROTO_TCP) ?
+			ICE_FLTR_PTYPE_NONF_IPV6_TCP :
+			ICE_FLTR_PTYPE_NONF_IPV6_UDP;
+		memcpy(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+		       sizeof(struct in6_addr));
+		memcpy(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+		       sizeof(struct in6_addr));
+		fltr_info->ip.v6.src_port = fk->ports.src;
+		fltr_info->ip.v6.dst_port = fk->ports.dst;
+	}
+
+	arfs_entry->flow_id = flow_id;
+	fltr_info->fltr_id =
+		atomic_inc_return(vsi->arfs_last_fltr_id) % RPS_NO_FILTER;
+
+	return arfs_entry;
+}
+
+/**
+ * ice_arfs_is_perfect_flow_set - Check to see if perfect flow is set
+ * @hw: pointer to HW structure
+ * @l3_proto: ETH_P_IP or ETH_P_IPV6 in network order
+ * @l4_proto: IPPROTO_UDP or IPPROTO_TCP
+ *
+ * We only support perfect (4-tuple) filters for aRFS. This function allows aRFS
+ * to check if perfect (4-tuple) flow rules are currently in place by Flow
+ * Director.
+ */
+static bool
+ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
+{
+	unsigned long *perfect_fltr = hw->fdir_perfect_fltr;
+
+	/* advanced Flow Director disabled, perfect filters always supported */
+	if (!perfect_fltr)
+		return true;
+
+	if (l3_proto == htons(ETH_P_IP) && l4_proto == IPPROTO_UDP)
+		return test_bit(ICE_FLTR_PTYPE_NONF_IPV4_UDP, perfect_fltr);
+	else if (l3_proto == htons(ETH_P_IP) && l4_proto == IPPROTO_TCP)
+		return test_bit(ICE_FLTR_PTYPE_NONF_IPV4_TCP, perfect_fltr);
+	else if (l3_proto == htons(ETH_P_IPV6) && l4_proto == IPPROTO_UDP)
+		return test_bit(ICE_FLTR_PTYPE_NONF_IPV6_UDP, perfect_fltr);
+	else if (l3_proto == htons(ETH_P_IPV6) && l4_proto == IPPROTO_TCP)
+		return test_bit(ICE_FLTR_PTYPE_NONF_IPV6_TCP, perfect_fltr);
+
+	return false;
+}
+
+/**
+ * ice_rx_flow_steer - steer the Rx flow to where application is being run
+ * @netdev: ptr to the netdev being adjusted
+ * @skb: buffer with required header information
+ * @rxq_idx: queue to which the flow needs to move
+ * @flow_id: flow identifier provided by the netdev
+ *
+ * Based on the skb, rxq_idx, and flow_id passed in add/update an entry in the
+ * aRFS hash table. Iterate over one of the hlists in the aRFS hash table and
+ * if the flow_id already exists in the hash table but the rxq_idx has changed
+ * mark the entry as ICE_ARFS_INACTIVE so it can get updated in HW, else
+ * if the entry is marked as ICE_ARFS_TODEL delete it from the aRFS hash table.
+ * If neither of the previous conditions are true then add a new entry in the
+ * aRFS hash table, which gets set to ICE_ARFS_INACTIVE by default so it can be
+ * added to HW.
+ */
+int
+ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
+		  u16 rxq_idx, u32 flow_id)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_arfs_entry *arfs_entry;
+	struct ice_vsi *vsi = np->vsi;
+	struct flow_keys fk;
+	struct ice_pf *pf;
+	__be16 n_proto;
+	u8 ip_proto;
+	u16 idx;
+	int ret;
+
+	/* failed to allocate memory for aRFS so don't crash */
+	if (unlikely(!vsi->arfs_fltr_list))
+		return -ENODEV;
+
+	pf = vsi->back;
+
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+		return -EPROTONOSUPPORT;
+
+	n_proto = fk.basic.n_proto;
+	/* Support only IPV4 and IPV6 */
+	if ((n_proto == htons(ETH_P_IP) && !ip_is_fragment(ip_hdr(skb))) ||
+	    n_proto == htons(ETH_P_IPV6))
+		ip_proto = fk.basic.ip_proto;
+	else
+		return -EPROTONOSUPPORT;
+
+	/* Support only TCP and UDP */
+	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP)
+		return -EPROTONOSUPPORT;
+
+	/* only support 4-tuple filters for aRFS */
+	if (!ice_arfs_is_perfect_flow_set(&pf->hw, n_proto, ip_proto))
+		return -EOPNOTSUPP;
+
+	/* choose the aRFS list bucket based on skb hash */
+	idx = skb_get_hash_raw(skb) & ICE_ARFS_LST_MASK;
+	/* search for entry in the bucket */
+	spin_lock_bh(&vsi->arfs_lock);
+	hlist_for_each_entry(arfs_entry, &vsi->arfs_fltr_list[idx],
+			     list_entry) {
+		struct ice_fdir_fltr *fltr_info;
+
+		/* keep searching for the already existing arfs_entry flow */
+		if (arfs_entry->flow_id != flow_id)
+			continue;
+
+		fltr_info = &arfs_entry->fltr_info;
+		ret = fltr_info->fltr_id;
+
+		if (fltr_info->q_index == rxq_idx ||
+		    arfs_entry->fltr_state != ICE_ARFS_ACTIVE)
+			goto out;
+
+		/* update the queue to forward to on an already existing flow */
+		fltr_info->q_index = rxq_idx;
+		arfs_entry->fltr_state = ICE_ARFS_INACTIVE;
+		ice_arfs_update_active_fltr_cntrs(vsi, arfs_entry, false);
+		goto out_schedule_service_task;
+	}
+
+	arfs_entry = ice_arfs_build_entry(vsi, &fk, rxq_idx, flow_id);
+	if (!arfs_entry) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = arfs_entry->fltr_info.fltr_id;
+	INIT_HLIST_NODE(&arfs_entry->list_entry);
+	hlist_add_head(&arfs_entry->list_entry, &vsi->arfs_fltr_list[idx]);
+out_schedule_service_task:
+	ice_service_task_schedule(pf);
+out:
+	spin_unlock_bh(&vsi->arfs_lock);
+	return ret;
+}
+
+/**
+ * ice_init_arfs_cntrs - initialize aRFS counter values
+ * @vsi: VSI that aRFS counters need to be initialized on
+ */
+static int ice_init_arfs_cntrs(struct ice_vsi *vsi)
+{
+	if (!vsi || vsi->type != ICE_VSI_PF)
+		return -EINVAL;
+
+	vsi->arfs_fltr_cntrs = kzalloc(sizeof(*vsi->arfs_fltr_cntrs),
+				       GFP_KERNEL);
+	if (!vsi->arfs_fltr_cntrs)
+		return -ENOMEM;
+
+	vsi->arfs_last_fltr_id = kzalloc(sizeof(*vsi->arfs_last_fltr_id),
+					 GFP_KERNEL);
+	if (!vsi->arfs_last_fltr_id) {
+		kfree(vsi->arfs_fltr_cntrs);
+		vsi->arfs_fltr_cntrs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_init_arfs - initialize aRFS resources
+ * @vsi: the VSI to be forwarded to
+ */
+void ice_init_arfs(struct ice_vsi *vsi)
+{
+	struct hlist_head *arfs_fltr_list;
+	unsigned int i;
+
+	if (!vsi || vsi->type != ICE_VSI_PF)
+		return;
+
+	arfs_fltr_list = kzalloc(sizeof(*arfs_fltr_list) * ICE_MAX_ARFS_LIST,
+				 GFP_KERNEL);
+	if (!arfs_fltr_list)
+		return;
+
+	if (ice_init_arfs_cntrs(vsi))
+		goto free_arfs_fltr_list;
+
+	for (i = 0; i < ICE_MAX_ARFS_LIST; i++)
+		INIT_HLIST_HEAD(&arfs_fltr_list[i]);
+
+	spin_lock_init(&vsi->arfs_lock);
+
+	vsi->arfs_fltr_list = arfs_fltr_list;
+
+	return;
+
+free_arfs_fltr_list:
+	kfree(arfs_fltr_list);
+}
+
+/**
+ * ice_clear_arfs - clear the aRFS hash table and any memory used for aRFS
+ * @vsi: the VSI to be forwarded to
+ */
+void ice_clear_arfs(struct ice_vsi *vsi)
+{
+	struct device *dev;
+	unsigned int i;
+
+	if (!vsi || vsi->type != ICE_VSI_PF || !vsi->back ||
+	    !vsi->arfs_fltr_list)
+		return;
+
+	dev = ice_pf_to_dev(vsi->back);
+	for (i = 0; i < ICE_MAX_ARFS_LIST; i++) {
+		struct ice_arfs_entry *r;
+		struct hlist_node *n;
+
+		spin_lock_bh(&vsi->arfs_lock);
+		hlist_for_each_entry_safe(r, n, &vsi->arfs_fltr_list[i],
+					  list_entry) {
+			hlist_del(&r->list_entry);
+			devm_kfree(dev, r);
+		}
+		spin_unlock_bh(&vsi->arfs_lock);
+	}
+
+	kfree(vsi->arfs_fltr_list);
+	vsi->arfs_fltr_list = NULL;
+	kfree(vsi->arfs_last_fltr_id);
+	vsi->arfs_last_fltr_id = NULL;
+	kfree(vsi->arfs_fltr_cntrs);
+	vsi->arfs_fltr_cntrs = NULL;
+}
+
+/**
+ * ice_free_cpu_rx_rmap - free setup CPU reverse map
+ * @vsi: the VSI to be forwarded to
+ */
+void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
+{
+	struct net_device *netdev;
+
+	if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list)
+		return;
+
+	netdev = vsi->netdev;
+	if (!netdev || !netdev->rx_cpu_rmap ||
+	    netdev->reg_state != NETREG_REGISTERED)
+		return;
+
+	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
+	netdev->rx_cpu_rmap = NULL;
+}
+
+/**
+ * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue
+ * @vsi: the VSI to be forwarded to
+ */
+int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
+{
+	struct net_device *netdev;
+	struct ice_pf *pf;
+	int base_idx, i;
+
+	if (!vsi || vsi->type != ICE_VSI_PF)
+		return -EINVAL;
+
+	pf = vsi->back;
+	netdev = vsi->netdev;
+	if (!pf || !netdev || !vsi->num_q_vectors ||
+	    vsi->netdev->reg_state != NETREG_REGISTERED)
+		return -EINVAL;
+
+	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
+		   vsi->type, netdev->name, vsi->num_q_vectors);
+
+	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
+	if (unlikely(!netdev->rx_cpu_rmap))
+		return -EINVAL;
+
+	base_idx = vsi->base_vector;
+	for (i = 0; i < vsi->num_q_vectors; i++)
+		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
+				     pf->msix_entries[base_idx + i].vector)) {
+			ice_free_cpu_rx_rmap(vsi);
+			return -EINVAL;
+		}
+
+	return 0;
+}
+
+/**
+ * ice_remove_arfs - remove/clear all aRFS resources
+ * @pf: device private structure
+ */
+void ice_remove_arfs(struct ice_pf *pf)
+{
+	struct ice_vsi *pf_vsi;
+
+	pf_vsi = ice_get_main_vsi(pf);
+	if (!pf_vsi)
+		return;
+
+	ice_free_cpu_rx_rmap(pf_vsi);
+	ice_clear_arfs(pf_vsi);
+}
+
+/**
+ * ice_rebuild_arfs - remove/clear all aRFS resources and rebuild after reset
+ * @pf: device private structure
+ */
+void ice_rebuild_arfs(struct ice_pf *pf)
+{
+	struct ice_vsi *pf_vsi;
+
+	pf_vsi = ice_get_main_vsi(pf);
+	if (!pf_vsi)
+		return;
+
+	ice_remove_arfs(pf);
+	if (ice_set_cpu_rx_rmap(pf_vsi)) {
+		dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n");
+		return;
+	}
+	ice_init_arfs(pf_vsi);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
new file mode 100644
index 000000000000..f39cd16403ed
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2020, Intel Corporation. */
+
+#ifndef _ICE_ARFS_H_
+#define _ICE_ARFS_H_
+enum ice_arfs_fltr_state {
+	ICE_ARFS_INACTIVE,
+	ICE_ARFS_ACTIVE,
+	ICE_ARFS_TODEL,
+};
+
+struct ice_arfs_entry {
+	struct ice_fdir_fltr fltr_info;
+	struct hlist_node list_entry;
+	u64 time_activated;	/* only valid for UDP flows */
+	u32 flow_id;
+	/* fltr_state = 0 - ICE_ARFS_INACTIVE:
+	 *	filter needs to be updated or programmed in HW.
+	 * fltr_state = 1 - ICE_ARFS_ACTIVE:
+	 *	filter is active and programmed in HW.
+	 * fltr_state = 2 - ICE_ARFS_TODEL:
+	 *	filter has been deleted from HW and needs to be removed from
+	 *	the aRFS hash table.
+	 */
+	u8 fltr_state;
+};
+
+struct ice_arfs_entry_ptr {
+	struct ice_arfs_entry *arfs_entry;
+	struct hlist_node list_entry;
+};
+
+struct ice_arfs_active_fltr_cntrs {
+	atomic_t active_tcpv4_cnt;
+	atomic_t active_tcpv6_cnt;
+	atomic_t active_udpv4_cnt;
+	atomic_t active_udpv6_cnt;
+};
+
+#ifdef CONFIG_RFS_ACCEL
+int
+ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
+		  u16 rxq_idx, u32 flow_id);
+void ice_clear_arfs(struct ice_vsi *vsi);
+void ice_free_cpu_rx_rmap(struct ice_vsi *vsi);
+void ice_init_arfs(struct ice_vsi *vsi);
+void ice_sync_arfs_fltrs(struct ice_pf *pf);
+int ice_set_cpu_rx_rmap(struct ice_vsi *vsi);
+void ice_remove_arfs(struct ice_pf *pf);
+void ice_rebuild_arfs(struct ice_pf *pf);
+bool
+ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
+			       enum ice_fltr_ptype flow_type);
+#else
+#define ice_sync_arfs_fltrs(pf) do {} while (0)
+#define ice_init_arfs(vsi) do {} while (0)
+#define ice_clear_arfs(vsi) do {} while (0)
+#define ice_remove_arfs(pf) do {} while (0)
+#define ice_free_cpu_rx_rmap(vsi) do {} while (0)
+#define ice_rebuild_arfs(pf) do {} while (0)
+
+static inline int ice_set_cpu_rx_rmap(struct ice_vsi __always_unused *vsi)
+{
+	return 0;
+}
+
+static inline int
+ice_rx_flow_steer(struct net_device __always_unused *netdev,
+		  const struct sk_buff __always_unused *skb,
+		  u16 __always_unused rxq_idx, u32 __always_unused flow_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool
+ice_is_arfs_using_perfect_flow(struct ice_hw __always_unused *hw,
+			       enum ice_fltr_ptype __always_unused flow_type)
+{
+	return false;
+}
+#endif /* CONFIG_RFS_ACCEL */
+#endif /* _ICE_ARFS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index a0002032be61..42803fc0ed18 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -566,6 +566,12 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg,
 			return -EINVAL;
 		}
 
+		if (ice_is_arfs_using_perfect_flow(hw, flow)) {
+			dev_err(dev, "aRFS using perfect flow type %d, cannot change input set\n",
+				flow);
+			return -EINVAL;
+		}
+
 		/* remove HW filter definition */
 		ice_fdir_rem_flow(hw, ICE_BLK_FD, flow);
 	}
@@ -1176,7 +1182,7 @@ err_exit:
  *
  * returns 0 on success and negative value on error
  */
-static int
+int
 ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add,
 		    bool is_tun)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index ff77fc3f633e..f81bd4c30bbc 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2175,6 +2175,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 				ice_vsi_cfg_rss_lut_key(vsi);
 				ice_vsi_set_rss_flow_fld(vsi);
 			}
+		ice_init_arfs(vsi);
 		break;
 	case ICE_VSI_VF:
 		/* VF driver will take care of creating netdev for this type and
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index d06a3311a2dc..c69567210584 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1113,7 +1113,7 @@ static void ice_clean_mailboxq_subtask(struct ice_pf *pf)
  *
  * If not already scheduled, this puts the task into the work queue.
  */
-static void ice_service_task_schedule(struct ice_pf *pf)
+void ice_service_task_schedule(struct ice_pf *pf)
 {
 	if (!test_bit(__ICE_SERVICE_DIS, pf->state) &&
 	    !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) &&
@@ -1483,7 +1483,7 @@ static void ice_service_task(struct work_struct *work)
 
 	ice_process_vflr_event(pf);
 	ice_clean_mailboxq_subtask(pf);
-
+	ice_sync_arfs_fltrs(pf);
 	/* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */
 	ice_service_task_complete(pf);
 
@@ -1642,9 +1642,14 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 		}
 
 		/* register for affinity change notifications */
-		q_vector->affinity_notify.notify = ice_irq_affinity_notify;
-		q_vector->affinity_notify.release = ice_irq_affinity_release;
-		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
+		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
+			struct irq_affinity_notify *affinity_notify;
+
+			affinity_notify = &q_vector->affinity_notify;
+			affinity_notify->notify = ice_irq_affinity_notify;
+			affinity_notify->release = ice_irq_affinity_release;
+			irq_set_affinity_notifier(irq_num, affinity_notify);
+		}
 
 		/* assign the mask for this irq */
 		irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
@@ -1656,8 +1661,9 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector) {
 		vector--;
-		irq_num = pf->msix_entries[base + vector].vector,
-		irq_set_affinity_notifier(irq_num, NULL);
+		irq_num = pf->msix_entries[base + vector].vector;
+		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
+			irq_set_affinity_notifier(irq_num, NULL);
 		irq_set_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
@@ -2611,12 +2617,22 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
 	 */
 	ice_napi_add(vsi);
 
+	status = ice_set_cpu_rx_rmap(vsi);
+	if (status) {
+		dev_err(ice_pf_to_dev(pf), "Failed to set CPU Rx map VSI %d error %d\n",
+			vsi->vsi_num, status);
+		status = -EINVAL;
+		goto unroll_napi_add;
+	}
 	status = ice_init_mac_fltr(pf);
 	if (status)
-		goto unroll_napi_add;
+		goto free_cpu_rx_map;
 
 	return status;
 
+free_cpu_rx_map:
+	ice_free_cpu_rx_rmap(vsi);
+
 unroll_napi_add:
 	if (vsi) {
 		ice_napi_del(vsi);
@@ -3519,6 +3535,8 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_service_task_stop(pf);
 
 	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
+	if (!ice_is_safe_mode(pf))
+		ice_remove_arfs(pf);
 	ice_devlink_destroy_port(pf);
 	ice_vsi_release_all(pf);
 	ice_free_irq_msix_misc(pf);
@@ -4036,11 +4054,14 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 		ret = ice_cfg_vlan_pruning(vsi, false, false);
 
 	if ((features & NETIF_F_NTUPLE) &&
-	    !(netdev->features & NETIF_F_NTUPLE))
+	    !(netdev->features & NETIF_F_NTUPLE)) {
 		ice_vsi_manage_fdir(vsi, true);
-	else if (!(features & NETIF_F_NTUPLE) &&
-		 (netdev->features & NETIF_F_NTUPLE))
+		ice_init_arfs(vsi);
+	} else if (!(features & NETIF_F_NTUPLE) &&
+		 (netdev->features & NETIF_F_NTUPLE)) {
 		ice_vsi_manage_fdir(vsi, false);
+		ice_clear_arfs(vsi);
+	}
 
 	return ret;
 }
@@ -4942,6 +4963,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 		/* replay Flow Director filters */
 		ice_fdir_replay_fltrs(pf);
+
+		ice_rebuild_arfs(pf);
 	}
 
 	ice_update_pf_netdev_link(pf);
@@ -5721,6 +5744,9 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_bridge_setlink = ice_bridge_setlink,
 	.ndo_fdb_add = ice_fdb_add,
 	.ndo_fdb_del = ice_fdb_del,
+#ifdef CONFIG_RFS_ACCEL
+	.ndo_rx_flow_steer = ice_rx_flow_steer,
+#endif
 	.ndo_tx_timeout = ice_tx_timeout,
 	.ndo_bpf = ice_xdp,
 	.ndo_xdp_xmit = ice_xdp_xmit,
-- 
cgit v1.2.3


From 4244910568ed2fed3532d86aa7fc910d2583fa41 Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 15 May 2020 17:36:30 -0700
Subject: ice: Call ice_aq_set_mac_cfg

As per the specification, the driver needs to call set_mac_cfg
(opcode 0x0603) to be able to exercise jumbo frames. Call the
function during initialization and the post reset rebuild flow.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 21 ++++++++
 drivers/net/ethernet/intel/ice/ice_common.c     | 69 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_common.h     |  2 +
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h |  5 ++
 drivers/net/ethernet/intel/ice/ice_main.c       |  6 +++
 5 files changed, 103 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index deada2e3d7c0..f80fb6570f8f 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1068,6 +1068,25 @@ struct ice_aqc_set_phy_cfg_data {
 	u8 rsvd1;
 };
 
+/* Set MAC Config command data structure (direct 0x0603) */
+struct ice_aqc_set_mac_cfg {
+	__le16 max_frame_size;
+	u8 params;
+#define ICE_AQ_SET_MAC_PACE_S		3
+#define ICE_AQ_SET_MAC_PACE_M		(0xF << ICE_AQ_SET_MAC_PACE_S)
+#define ICE_AQ_SET_MAC_PACE_TYPE_M	BIT(7)
+#define ICE_AQ_SET_MAC_PACE_TYPE_RATE	0
+#define ICE_AQ_SET_MAC_PACE_TYPE_FIXED	ICE_AQ_SET_MAC_PACE_TYPE_M
+	u8 tx_tmr_priority;
+	__le16 tx_tmr_value;
+	__le16 fc_refresh_threshold;
+	u8 drop_opts;
+#define ICE_AQ_SET_MAC_AUTO_DROP_MASK		BIT(0)
+#define ICE_AQ_SET_MAC_AUTO_DROP_NONE		0
+#define ICE_AQ_SET_MAC_AUTO_DROP_BLOCKING_PKTS	BIT(0)
+	u8 reserved[7];
+};
+
 /* Restart AN command data structure (direct 0x0605)
  * Also used for response, with only the lport_num field present.
  */
@@ -1774,6 +1793,7 @@ struct ice_aq_desc {
 		struct ice_aqc_download_pkg download_pkg;
 		struct ice_aqc_set_mac_lb set_mac_lb;
 		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
+		struct ice_aqc_set_mac_cfg set_mac_cfg;
 		struct ice_aqc_set_event_mask set_event_mask;
 		struct ice_aqc_get_link_status get_link_status;
 		struct ice_aqc_event_lan_overflow lan_overflow;
@@ -1870,6 +1890,7 @@ enum ice_adminq_opc {
 	/* PHY commands */
 	ice_aqc_opc_get_phy_caps			= 0x0600,
 	ice_aqc_opc_set_phy_cfg				= 0x0601,
+	ice_aqc_opc_set_mac_cfg				= 0x0603,
 	ice_aqc_opc_restart_an				= 0x0605,
 	ice_aqc_opc_get_link_status			= 0x0607,
 	ice_aqc_opc_set_event_mask			= 0x0613,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 3a4c14150107..0a0b00fffaf7 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -315,6 +315,71 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	return 0;
 }
 
+/**
+ * ice_fill_tx_timer_and_fc_thresh
+ * @hw: pointer to the HW struct
+ * @cmd: pointer to MAC cfg structure
+ *
+ * Add Tx timer and FC refresh threshold info to Set MAC Config AQ command
+ * descriptor
+ */
+static void
+ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw,
+				struct ice_aqc_set_mac_cfg *cmd)
+{
+	u16 fc_thres_val, tx_timer_val;
+	u32 val;
+
+	/* We read back the transmit timer and FC threshold value of
+	 * LFC. Thus, we will use index =
+	 * PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX.
+	 *
+	 * Also, because we are operating on transmit timer and FC
+	 * threshold of LFC, we don't turn on any bit in tx_tmr_priority
+	 */
+#define IDX_OF_LFC PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX
+
+	/* Retrieve the transmit timer */
+	val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(IDX_OF_LFC));
+	tx_timer_val = val &
+		PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M;
+	cmd->tx_tmr_value = cpu_to_le16(tx_timer_val);
+
+	/* Retrieve the FC threshold */
+	val = rd32(hw, PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(IDX_OF_LFC));
+	fc_thres_val = val & PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M;
+
+	cmd->fc_refresh_threshold = cpu_to_le16(fc_thres_val);
+}
+
+/**
+ * ice_aq_set_mac_cfg
+ * @hw: pointer to the HW struct
+ * @max_frame_size: Maximum Frame Size to be supported
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set MAC configuration (0x0603)
+ */
+enum ice_status
+ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_mac_cfg *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_mac_cfg;
+
+	if (max_frame_size == 0)
+		return ICE_ERR_PARAM;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_cfg);
+
+	cmd->max_frame_size = cpu_to_le16(max_frame_size);
+
+	ice_fill_tx_timer_and_fc_thresh(hw, cmd);
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
 /**
  * ice_init_fltr_mgmt_struct - initializes filter management list and locks
  * @hw: pointer to the HW struct
@@ -745,6 +810,10 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	status = ice_aq_manage_mac_read(hw, mac_buf, mac_buf_len, NULL);
 	devm_kfree(ice_hw_to_dev(hw), mac_buf);
 
+	if (status)
+		goto err_unroll_fltr_mgmt_struct;
+	/* enable jumbo frame support at MAC level */
+	status = ice_aq_set_mac_cfg(hw, ICE_AQ_SET_MAC_FRAME_SIZE_MAX, NULL);
 	if (status)
 		goto err_unroll_fltr_mgmt_struct;
 	/* Obtain counter base index which would be used by flow director */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 8104f3d64d96..bea755a658eb 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -108,6 +108,8 @@ enum ice_status
 ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd);
 enum ice_status
+ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd);
+enum ice_status
 ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		     struct ice_link_status *link, struct ice_sq_cd *cd);
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index c8b037d25053..1f9b427a35fa 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -219,6 +219,11 @@
 #define VPLAN_TX_QBASE_VFNUMQ_M			ICE_M(0xFF, 16)
 #define VPLAN_TXQ_MAPENA(_VF)			(0x00073800 + ((_VF) * 4))
 #define VPLAN_TXQ_MAPENA_TX_ENA_M		BIT(0)
+#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA(_i)	(0x001E36E0 + ((_i) * 32))
+#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_MAX_INDEX 8
+#define PRTMAC_HSEC_CTL_TX_PAUSE_QUANTA_HSEC_CTL_TX_PAUSE_QUANTA_M ICE_M(0xFFFF, 0)
+#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER(_i) (0x001E3800 + ((_i) * 32))
+#define PRTMAC_HSEC_CTL_TX_PAUSE_REFRESH_TIMER_M ICE_M(0xFFFF, 0)
 #define GL_MDCK_TX_TDPU				0x00049348
 #define GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M BIT(1)
 #define GL_MDET_RX				0x00294C00
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c69567210584..220f1bfc6376 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4901,6 +4901,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_init_ctrlq;
 	}
 
+	ret = ice_aq_set_mac_cfg(hw, ICE_AQ_SET_MAC_FRAME_SIZE_MAX, NULL);
+	if (ret) {
+		dev_err(dev, "set_mac_cfg failed %s\n", ice_stat_str(ret));
+		goto err_init_ctrlq;
+	}
+
 	err = ice_sched_init_port(hw->port_info);
 	if (err)
 		goto err_sched_init_port;
-- 
cgit v1.2.3


From 7438a3b0947a2ef43c16bfb7b5b19048d6d92b14 Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Fri, 15 May 2020 17:36:31 -0700
Subject: ice: print Rx MDD auto reset message before VF reset

Rx MDD auto reset message was not being logged because logging occurred
after the VF reset and the VF MDD data was reinitialized.

Log the Rx MDD auto reset message before triggering the VF reset.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c        |  7 ++++++-
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 25 ++++++++++++++++++------
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h |  2 ++
 3 files changed, 27 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 220f1bfc6376..bac5a0857c8c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1322,8 +1322,13 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 			 * PF can be configured to reset the VF through ethtool
 			 * private flag mdd-auto-reset-vf.
 			 */
-			if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+			if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
+				/* VF MDD event counters will be cleared by
+				 * reset, so print the event prior to reset.
+				 */
+				ice_print_vf_rx_mdd_event(vf);
 				ice_reset_vf(&pf->vf[i], false);
+			}
 		}
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 62c100d47592..e9c14d460731 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -3756,6 +3756,24 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id,
 	return 0;
 }
 
+/**
+ * ice_print_vf_rx_mdd_event - print VF Rx malicious driver detect event
+ * @vf: pointer to the VF structure
+ */
+void ice_print_vf_rx_mdd_event(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct device *dev;
+
+	dev = ice_pf_to_dev(pf);
+
+	dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
+		 vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id,
+		 vf->dflt_lan_addr.addr,
+		 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
+			  ? "on" : "off");
+}
+
 /**
  * ice_print_vfs_mdd_event - print VFs malicious driver detect event
  * @pf: pointer to the PF structure
@@ -3785,12 +3803,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf)
 		if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) {
 			vf->mdd_rx_events.last_printed =
 							vf->mdd_rx_events.count;
-
-			dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n",
-				 vf->mdd_rx_events.count, hw->pf_id, i,
-				 vf->dflt_lan_addr.addr,
-				 test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)
-					  ? "on" : "off");
+			ice_print_vf_rx_mdd_event(vf);
 		}
 
 		/* only print Tx MDD event message if there are new events */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 474293ff4fe5..0adff89a6749 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -132,6 +132,7 @@ bool ice_is_any_vf_in_promisc(struct ice_pf *pf);
 void
 ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event);
 void ice_print_vfs_mdd_events(struct ice_pf *pf);
+void ice_print_vf_rx_mdd_event(struct ice_vf *vf);
 #else /* CONFIG_PCI_IOV */
 #define ice_process_vflr_event(pf) do {} while (0)
 #define ice_free_vfs(pf) do {} while (0)
@@ -141,6 +142,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf);
 #define ice_set_vf_state_qs_dis(vf) do {} while (0)
 #define ice_vf_lan_overflow_event(pf, event) do {} while (0)
 #define ice_print_vfs_mdd_events(pf) do {} while (0)
+#define ice_print_vf_rx_mdd_event(vf) do {} while (0)
 
 static inline bool
 ice_reset_all_vfs(struct ice_pf __always_unused *pf,
-- 
cgit v1.2.3


From 4dc926d3a59e73b8c4adf51b261f1a1bbd48a989 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:36:32 -0700
Subject: ice: Fix Tx timeout when link is toggled on a VF's interface

Currently if the iavf is loaded and a VF link transitions from up to
down to up again a Tx timeout will be triggered. This happens because
Tx/Rx queue interrupts are only enabled when receiving the
VIRTCHNL_OP_CONFIG_MAP_IRQ message, which happens on reset or initial
iavf driver load, but not when bringing link up. This is problematic
because they are disabled on the VIRTCHNL_OP_DISABLE_QUEUES message,
which is part of bringing a VF's link down. However, they are not
enabled on the VIRTCHNL_OP_ENABLE_QUEUES message, which is part of
bringing a VF's link up.

Fix this by re-enabling the VF's Rx and Tx queue interrupts when they
were previously configured. This is done by first checking to make
sure the previous value in QINT_[R|T]QCTL.MSIX_INDX is not 0, which
is used to represent the OICR in the VF's interrupt space. If the
MSIX_INDX is non-zero then enable the interrupt by setting the
QINT_[R|T]CTL.CAUSE_ENA bit to 1.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 48 ++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index e9c14d460731..a12fce73efbc 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -2316,6 +2316,52 @@ static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs)
 	return true;
 }
 
+/**
+ * ice_vf_ena_txq_interrupt - enable Tx queue interrupt via QINT_TQCTL
+ * @vsi: VSI of the VF to configure
+ * @q_idx: VF queue index used to determine the queue in the PF's space
+ */
+static void ice_vf_ena_txq_interrupt(struct ice_vsi *vsi, u32 q_idx)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 pfq = vsi->txq_map[q_idx];
+	u32 reg;
+
+	reg = rd32(hw, QINT_TQCTL(pfq));
+
+	/* MSI-X index 0 in the VF's space is always for the OICR, which means
+	 * this is most likely a poll mode VF driver, so don't enable an
+	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
+	 */
+	if (!(reg & QINT_TQCTL_MSIX_INDX_M))
+		return;
+
+	wr32(hw, QINT_TQCTL(pfq), reg | QINT_TQCTL_CAUSE_ENA_M);
+}
+
+/**
+ * ice_vf_ena_rxq_interrupt - enable Tx queue interrupt via QINT_RQCTL
+ * @vsi: VSI of the VF to configure
+ * @q_idx: VF queue index used to determine the queue in the PF's space
+ */
+static void ice_vf_ena_rxq_interrupt(struct ice_vsi *vsi, u32 q_idx)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	u32 pfq = vsi->rxq_map[q_idx];
+	u32 reg;
+
+	reg = rd32(hw, QINT_RQCTL(pfq));
+
+	/* MSI-X index 0 in the VF's space is always for the OICR, which means
+	 * this is most likely a poll mode VF driver, so don't enable an
+	 * interrupt that was never configured via VIRTCHNL_OP_CONFIG_IRQ_MAP
+	 */
+	if (!(reg & QINT_RQCTL_MSIX_INDX_M))
+		return;
+
+	wr32(hw, QINT_RQCTL(pfq), reg | QINT_RQCTL_CAUSE_ENA_M);
+}
+
 /**
  * ice_vc_ena_qs_msg
  * @vf: pointer to the VF info
@@ -2376,6 +2422,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
 			goto error_param;
 		}
 
+		ice_vf_ena_rxq_interrupt(vsi, vf_q_id);
 		set_bit(vf_q_id, vf->rxq_ena);
 	}
 
@@ -2391,6 +2438,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
 		if (test_bit(vf_q_id, vf->txq_ena))
 			continue;
 
+		ice_vf_ena_txq_interrupt(vsi, vf_q_id);
 		set_bit(vf_q_id, vf->txq_ena);
 	}
 
-- 
cgit v1.2.3


From 47ebc7b02485aa0c0e18f96368e6f6958735fcea Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:36:33 -0700
Subject: ice: Check if unicast MAC exists before setting VF MAC

Currently if a unicast MAC is set via ndo_set_vf_mac, the PF driver will
set the VF's dflt_lan_addr.addr once some basic checks have passed. The
VF is then reset. During reset the PF driver will attempt to program the
VF's MAC from the dflt_lan_addr.addr field. This fails when the MAC
already exists on the PF's switch.

This is causing the VF to be completely disabled until removing/enabling
any VFs via sysfs.

Fix this by checking if the unicast MAC exists before triggering a VF
reset directly in ndo_set_vf_mac. Also, add a check if the unicast MAC
is set to the same value as before and return 0 if that is the case.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 43 ++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index a12fce73efbc..95e8bca562e5 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -3640,6 +3640,39 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
 	return 0;
 }
 
+/**
+ * ice_unicast_mac_exists - check if the unicast MAC exists on the PF's switch
+ * @pf: PF used to reference the switch's rules
+ * @umac: unicast MAC to compare against existing switch rules
+ *
+ * Return true on the first/any match, else return false
+ */
+static bool ice_unicast_mac_exists(struct ice_pf *pf, u8 *umac)
+{
+	struct ice_sw_recipe *mac_recipe_list =
+		&pf->hw.switch_info->recp_list[ICE_SW_LKUP_MAC];
+	struct ice_fltr_mgmt_list_entry *list_itr;
+	struct list_head *rule_head;
+	struct mutex *rule_lock; /* protect MAC filter list access */
+
+	rule_head = &mac_recipe_list->filt_rules;
+	rule_lock = &mac_recipe_list->filt_rule_lock;
+
+	mutex_lock(rule_lock);
+	list_for_each_entry(list_itr, rule_head, list_entry) {
+		u8 *existing_mac = &list_itr->fltr_info.l_data.mac.mac_addr[0];
+
+		if (ether_addr_equal(existing_mac, umac)) {
+			mutex_unlock(rule_lock);
+			return true;
+		}
+	}
+
+	mutex_unlock(rule_lock);
+
+	return false;
+}
+
 /**
  * ice_set_vf_mac
  * @netdev: network interface device structure
@@ -3663,10 +3696,20 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	}
 
 	vf = &pf->vf[vf_id];
+	/* nothing left to do, unicast MAC already set */
+	if (ether_addr_equal(vf->dflt_lan_addr.addr, mac))
+		return 0;
+
 	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		return ret;
 
+	if (ice_unicast_mac_exists(pf, mac)) {
+		netdev_err(netdev, "Unicast MAC %pM already exists on this PF. Preventing setting VF %u unicast MAC address to %pM\n",
+			   mac, vf_id, mac);
+		return -EINVAL;
+	}
+
 	/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
 	 * flow will use the updated dflt_lan_addr and add a MAC filter
 	 * using ice_add_mac. Also set pf_set_mac to indicate that the PF has
-- 
cgit v1.2.3


From b82729195892f5fc1dd69a8cfb23731d3ef55578 Mon Sep 17 00:00:00 2001
From: Victor Raj <victor.raj@intel.com>
Date: Fri, 15 May 2020 17:36:34 -0700
Subject: ice: check for compatibility between DDP package and firmware

Require the Dynamic Device Personalization (DDP) file to have the same
major version number and the same or older minor number than the firmware
version major and minor, respectively.

Check the OS and NVM package versions before downloading the package.
If the OS package version is not compatible with NVM then return an
appropriate error.

Split the 32-byte segment name into a 28-byte segment name and
a 4-byte Track-ID. Older packages will still work with this change
because no package has a name that will take up more than 28 bytes;
in this case the Track-ID will be 0.

Note that the driver will store the segment name as 32-bytes in the
ice_hw structure, in order to normalize the length of the various
package name strings that it uses.

Also add section ID and structure for the segment metadata section.

Signed-off-by: Victor Raj <victor.raj@intel.com>
Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h |   4 +-
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c  | 112 ++++++++++++++++++------
 drivers/net/ethernet/intel/ice/ice_flex_type.h  |   8 +-
 drivers/net/ethernet/intel/ice/ice_main.c       |   5 ++
 drivers/net/ethernet/intel/ice/ice_status.h     |   2 +
 drivers/net/ethernet/intel/ice/ice_type.h       |   1 +
 6 files changed, 102 insertions(+), 30 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index f80fb6570f8f..586d69491268 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1703,10 +1703,12 @@ struct ice_pkg_ver {
 };
 
 #define ICE_PKG_NAME_SIZE	32
+#define ICE_SEG_NAME_SIZE	28
 
 struct ice_aqc_get_pkg_info {
 	struct ice_pkg_ver ver;
-	char name[ICE_PKG_NAME_SIZE];
+	char name[ICE_SEG_NAME_SIZE];
+	__le32 track_id;
 	u8 is_in_nvm;
 	u8 is_active;
 	u8 is_active_at_boot;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index da82783d1571..4420fc02f7e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -864,8 +864,9 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type,
 	u32 i;
 
 	ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n",
-		  pkg_hdr->format_ver.major, pkg_hdr->format_ver.minor,
-		  pkg_hdr->format_ver.update, pkg_hdr->format_ver.draft);
+		  pkg_hdr->pkg_format_ver.major, pkg_hdr->pkg_format_ver.minor,
+		  pkg_hdr->pkg_format_ver.update,
+		  pkg_hdr->pkg_format_ver.draft);
 
 	/* Search all package segments for the requested segment type */
 	for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) {
@@ -1035,13 +1036,15 @@ ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg)
 {
 	struct ice_buf_table *ice_buf_tbl;
 
-	ice_debug(hw, ICE_DBG_PKG, "Segment version: %d.%d.%d.%d\n",
-		  ice_seg->hdr.seg_ver.major, ice_seg->hdr.seg_ver.minor,
-		  ice_seg->hdr.seg_ver.update, ice_seg->hdr.seg_ver.draft);
+	ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
+		  ice_seg->hdr.seg_format_ver.major,
+		  ice_seg->hdr.seg_format_ver.minor,
+		  ice_seg->hdr.seg_format_ver.update,
+		  ice_seg->hdr.seg_format_ver.draft);
 
 	ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
 		  le32_to_cpu(ice_seg->hdr.seg_type),
-		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_name);
+		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
 
 	ice_buf_tbl = ice_find_buf_table(ice_seg);
 
@@ -1086,14 +1089,16 @@ ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 
 	seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr);
 	if (seg_hdr) {
-		hw->ice_pkg_ver = seg_hdr->seg_ver;
-		memcpy(hw->ice_pkg_name, seg_hdr->seg_name,
+		hw->ice_pkg_ver = seg_hdr->seg_format_ver;
+		memcpy(hw->ice_pkg_name, seg_hdr->seg_id,
 		       sizeof(hw->ice_pkg_name));
 
-		ice_debug(hw, ICE_DBG_PKG, "Ice Pkg: %d.%d.%d.%d, %s\n",
-			  seg_hdr->seg_ver.major, seg_hdr->seg_ver.minor,
-			  seg_hdr->seg_ver.update, seg_hdr->seg_ver.draft,
-			  seg_hdr->seg_name);
+		ice_debug(hw, ICE_DBG_PKG, "Ice Seg: %d.%d.%d.%d, %s\n",
+			  seg_hdr->seg_format_ver.major,
+			  seg_hdr->seg_format_ver.minor,
+			  seg_hdr->seg_format_ver.update,
+			  seg_hdr->seg_format_ver.draft,
+			  seg_hdr->seg_id);
 	} else {
 		ice_debug(hw, ICE_DBG_INIT,
 			  "Did not find ice segment in driver package\n");
@@ -1134,9 +1139,11 @@ static enum ice_status ice_get_pkg_info(struct ice_hw *hw)
 		if (pkg_info->pkg_info[i].is_active) {
 			flags[place++] = 'A';
 			hw->active_pkg_ver = pkg_info->pkg_info[i].ver;
+			hw->active_track_id =
+				le32_to_cpu(pkg_info->pkg_info[i].track_id);
 			memcpy(hw->active_pkg_name,
 			       pkg_info->pkg_info[i].name,
-			       sizeof(hw->active_pkg_name));
+			       sizeof(pkg_info->pkg_info[i].name));
 			hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm;
 		}
 		if (pkg_info->pkg_info[i].is_active_at_boot)
@@ -1176,10 +1183,10 @@ static enum ice_status ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len)
 	if (len < sizeof(*pkg))
 		return ICE_ERR_BUF_TOO_SHORT;
 
-	if (pkg->format_ver.major != ICE_PKG_FMT_VER_MAJ ||
-	    pkg->format_ver.minor != ICE_PKG_FMT_VER_MNR ||
-	    pkg->format_ver.update != ICE_PKG_FMT_VER_UPD ||
-	    pkg->format_ver.draft != ICE_PKG_FMT_VER_DFT)
+	if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ ||
+	    pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR ||
+	    pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD ||
+	    pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT)
 		return ICE_ERR_CFG;
 
 	/* pkg must have at least one segment */
@@ -1260,6 +1267,68 @@ static enum ice_status ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver)
 	return 0;
 }
 
+/**
+ * ice_chk_pkg_compat
+ * @hw: pointer to the hardware structure
+ * @ospkg: pointer to the package hdr
+ * @seg: pointer to the package segment hdr
+ *
+ * This function checks the package version compatibility with driver and NVM
+ */
+static enum ice_status
+ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg,
+		   struct ice_seg **seg)
+{
+	struct ice_aqc_get_pkg_info_resp *pkg;
+	enum ice_status status;
+	u16 size;
+	u32 i;
+
+	/* Check package version compatibility */
+	status = ice_chk_pkg_version(&hw->pkg_ver);
+	if (status) {
+		ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n");
+		return status;
+	}
+
+	/* find ICE segment in given package */
+	*seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE,
+						     ospkg);
+	if (!*seg) {
+		ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n");
+		return ICE_ERR_CFG;
+	}
+
+	/* Check if FW is compatible with the OS package */
+	size = struct_size(pkg, pkg_info, ICE_PKG_CNT - 1);
+	pkg = kzalloc(size, GFP_KERNEL);
+	if (!pkg)
+		return ICE_ERR_NO_MEMORY;
+
+	status = ice_aq_get_pkg_info_list(hw, pkg, size, NULL);
+	if (status)
+		goto fw_ddp_compat_free_alloc;
+
+	for (i = 0; i < le32_to_cpu(pkg->count); i++) {
+		/* loop till we find the NVM package */
+		if (!pkg->pkg_info[i].is_in_nvm)
+			continue;
+		if ((*seg)->hdr.seg_format_ver.major !=
+			pkg->pkg_info[i].ver.major ||
+		    (*seg)->hdr.seg_format_ver.minor >
+			pkg->pkg_info[i].ver.minor) {
+			status = ICE_ERR_FW_DDP_MISMATCH;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "OS package is not compatible with NVM.\n");
+		}
+		/* done processing NVM package so break */
+		break;
+	}
+fw_ddp_compat_free_alloc:
+	kfree(pkg);
+	return status;
+}
+
 /**
  * ice_init_pkg - initialize/download package
  * @hw: pointer to the hardware structure
@@ -1310,17 +1379,10 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
 	/* before downloading the package, check package version for
 	 * compatibility with driver
 	 */
-	status = ice_chk_pkg_version(&hw->pkg_ver);
+	status = ice_chk_pkg_compat(hw, pkg, &seg);
 	if (status)
 		return status;
 
-	/* find segment in given package */
-	seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg);
-	if (!seg) {
-		ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n");
-		return ICE_ERR_CFG;
-	}
-
 	/* initialize package hints and then download package */
 	ice_init_pkg_hints(hw, seg);
 	status = ice_download_pkg(hw, seg);
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index 249fb66fc230..a6f391eac8ff 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -20,7 +20,7 @@ struct ice_fv {
 
 /* Package and segment headers and tables */
 struct ice_pkg_hdr {
-	struct ice_pkg_ver format_ver;
+	struct ice_pkg_ver pkg_format_ver;
 	__le32 seg_count;
 	__le32 seg_offset[1];
 };
@@ -30,9 +30,9 @@ struct ice_generic_seg_hdr {
 #define SEGMENT_TYPE_METADATA	0x00000001
 #define SEGMENT_TYPE_ICE	0x00000010
 	__le32 seg_type;
-	struct ice_pkg_ver seg_ver;
+	struct ice_pkg_ver seg_format_ver;
 	__le32 seg_size;
-	char seg_name[ICE_PKG_NAME_SIZE];
+	char seg_id[ICE_PKG_NAME_SIZE];
 };
 
 /* ice specific segment */
@@ -75,7 +75,7 @@ struct ice_buf_table {
 struct ice_global_metadata_seg {
 	struct ice_generic_seg_hdr hdr;
 	struct ice_pkg_ver pkg_ver;
-	__le32 track_id;
+	__le32 rsvd;
 	char pkg_name[ICE_PKG_NAME_SIZE];
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index bac5a0857c8c..5adf6c92872d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3052,6 +3052,9 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
 			*status = ICE_ERR_NOT_SUPPORTED;
 		}
 		break;
+	case ICE_ERR_FW_DDP_MISMATCH:
+		dev_err(dev, "The firmware loaded on the device is not compatible with the DDP package.  Please update the device's NVM.  Entering safe mode.\n");
+		break;
 	case ICE_ERR_BUF_TOO_SHORT:
 	case ICE_ERR_CFG:
 		dev_err(dev, "The DDP package file is invalid. Entering Safe Mode.\n");
@@ -5186,6 +5189,8 @@ const char *ice_stat_str(enum ice_status stat_err)
 		return "ICE_ERR_HW_TABLE";
 	case ICE_ERR_DOES_NOT_EXIST:
 		return "ICE_ERR_DOES_NOT_EXIST";
+	case ICE_ERR_FW_DDP_MISMATCH:
+		return "ICE_ERR_FW_DDP_MISMATCH";
 	case ICE_ERR_AQ_ERROR:
 		return "ICE_ERR_AQ_ERROR";
 	case ICE_ERR_AQ_TIMEOUT:
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index a9a8bc3aca42..546a02856d09 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -27,6 +27,8 @@ enum ice_status {
 	ICE_ERR_MAX_LIMIT			= -17,
 	ICE_ERR_RESET_ONGOING			= -18,
 	ICE_ERR_HW_TABLE			= -19,
+	ICE_ERR_FW_DDP_MISMATCH			= -20,
+
 	ICE_ERR_NVM_CHECKSUM			= -51,
 	ICE_ERR_BUF_TOO_SHORT			= -52,
 	ICE_ERR_NVM_BLANK_MODE			= -53,
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f1bfe8c94f1f..c1ad8622e65c 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -597,6 +597,7 @@ struct ice_hw {
 
 	/* Active package version (currently active) */
 	struct ice_pkg_ver active_pkg_ver;
+	u32 active_track_id;
 	u8 active_pkg_name[ICE_PKG_NAME_SIZE];
 	u8 active_pkg_in_nvm;
 
-- 
cgit v1.2.3


From 1fba4a8a92706c89716449b1aab1b6879f438d34 Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 15 May 2020 17:36:35 -0700
Subject: ice: Fix bad register reads

The "ethtool -d" handler reads registers in the ice_regs_dump_list array
and returns read values back to the userspace.

The register offsets PFINT0_ITR* are not valid as per the specification
and reading these causes a "unable to handle kernel paging request" bug
in the driver. Remove these registers from ice_regs_dump_list.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c    | 3 ---
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 3 ---
 2 files changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 72105d70cead..477ad33e0403 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -142,9 +142,6 @@ static const u32 ice_regs_dump_list[] = {
 	QINT_RQCTL(0),
 	PFINT_OICR_ENA,
 	QRX_ITR(0),
-	PF0INT_ITR_0(0),
-	PF0INT_ITR_1(0),
-	PF0INT_ITR_2(0),
 };
 
 struct ice_priv_flag {
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 1f9b427a35fa..2f1c776747a4 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -6,9 +6,6 @@
 #ifndef _ICE_HW_AUTOGEN_H_
 #define _ICE_HW_AUTOGEN_H_
 
-#define PF0INT_ITR_0(_i)			(0x03000004 + ((_i) * 4096))
-#define PF0INT_ITR_1(_i)			(0x03000008 + ((_i) * 4096))
-#define PF0INT_ITR_2(_i)			(0x0300000C + ((_i) * 4096))
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD_HEAD_S			0
-- 
cgit v1.2.3


From 9d68a79c3b8fe88c1444c401aaf3496f7ed2a05d Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:36:36 -0700
Subject: ice: fix usage of incorrect variable

The driver was using rq_last_status where it should have been
using sq_last_status. Fix the string to be using the correct
error reporting variable.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 2 +-
 drivers/net/ethernet/intel/ice/ice_main.c    | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 477ad33e0403..f39d4eb7fd8b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3251,7 +3251,7 @@ static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size)
 	if (status) {
 		dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n",
 			ice_stat_str(status),
-			ice_aq_str(hw->adminq.rq_last_status));
+			ice_aq_str(hw->adminq.sq_last_status));
 		err = -EIO;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 5adf6c92872d..6e6df4d690cc 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5232,7 +5232,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		if (status) {
 			dev_err(dev, "Cannot set RSS key, err %s aq_err %s\n",
 				ice_stat_str(status),
-				ice_aq_str(hw->adminq.rq_last_status));
+				ice_aq_str(hw->adminq.sq_last_status));
 			return -EIO;
 		}
 	}
@@ -5243,7 +5243,7 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		if (status) {
 			dev_err(dev, "Cannot set RSS lut, err %s aq_err %s\n",
 				ice_stat_str(status),
-				ice_aq_str(hw->adminq.rq_last_status));
+				ice_aq_str(hw->adminq.sq_last_status));
 			return -EIO;
 		}
 	}
@@ -5276,7 +5276,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		if (status) {
 			dev_err(dev, "Cannot get RSS key, err %s aq_err %s\n",
 				ice_stat_str(status),
-				ice_aq_str(hw->adminq.rq_last_status));
+				ice_aq_str(hw->adminq.sq_last_status));
 			return -EIO;
 		}
 	}
@@ -5287,7 +5287,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 		if (status) {
 			dev_err(dev, "Cannot get RSS lut, err %s aq_err %s\n",
 				ice_stat_str(status),
-				ice_aq_str(hw->adminq.rq_last_status));
+				ice_aq_str(hw->adminq.sq_last_status));
 			return -EIO;
 		}
 	}
-- 
cgit v1.2.3


From c1e0883012a75a04180a6ebf23a869172187c506 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:36:37 -0700
Subject: ice: cleanup unsigned loops

Fix loop variables that are comparing or assigning signed against
unsigned values, mostly by declaring loop counters as unsigned.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_nl.c      |  9 +++++----
 drivers/net/ethernet/intel/ice/ice_ethtool.c     | 10 +++++-----
 drivers/net/ethernet/intel/ice/ice_main.c        |  4 ++--
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c |  4 ++--
 4 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index c4c12414083a..93cf70d06fe5 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -671,7 +671,7 @@ static bool
 ice_dcbnl_find_app(struct ice_dcbx_cfg *cfg,
 		   struct ice_dcb_app_priority_table *app)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < cfg->numapps; i++) {
 		if (app->selector == cfg->app[i].selector &&
@@ -746,7 +746,8 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app)
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	struct ice_dcbx_cfg *old_cfg, *new_cfg;
-	int i, j, ret = 0;
+	unsigned int i, j;
+	int ret = 0;
 
 	if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED)
 		return -EINVAL;
@@ -869,7 +870,7 @@ void ice_dcbnl_set_all(struct ice_vsi *vsi)
 	struct ice_port_info *pi;
 	struct dcb_app sapp;
 	struct ice_pf *pf;
-	int i;
+	unsigned int i;
 
 	if (!netdev)
 		return;
@@ -941,7 +942,7 @@ ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
 		     struct ice_dcbx_cfg *new_cfg)
 {
 	struct ice_vsi *main_vsi = ice_get_main_vsi(pf);
-	int i;
+	unsigned int i;
 
 	if (!main_vsi)
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index f39d4eb7fd8b..fd1849155d85 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -205,7 +205,7 @@ ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 	struct ice_pf *pf = np->vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	u32 *regs_buf = (u32 *)p;
-	int i;
+	unsigned int i;
 
 	regs->version = 1;
 
@@ -308,7 +308,7 @@ out:
  */
 static bool ice_active_vfs(struct ice_pf *pf)
 {
-	int i;
+	unsigned int i;
 
 	ice_for_each_vf(pf, i) {
 		struct ice_vf *vf = &pf->vf[i];
@@ -378,7 +378,7 @@ static int ice_reg_pattern_test(struct ice_hw *hw, u32 reg, u32 mask)
 		0x00000000, 0xFFFFFFFF
 	};
 	u32 val, orig_val;
-	int i;
+	unsigned int i;
 
 	orig_val = rd32(hw, reg);
 	for (i = 0; i < ARRAY_SIZE(patterns); ++i) {
@@ -431,7 +431,7 @@ static u64 ice_reg_test(struct net_device *netdev)
 			GLINT_ITR(2, 1) - GLINT_ITR(2, 0)},
 		{GLINT_CTL, 0xffff0001, 1, 0}
 	};
-	int i;
+	unsigned int i;
 
 	netdev_dbg(netdev, "Register test\n");
 	for (i = 0; i < ARRAY_SIZE(ice_reg_list); ++i) {
@@ -3759,10 +3759,10 @@ ice_get_module_eeprom(struct net_device *netdev,
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status status;
 	bool is_sfp = false;
+	unsigned int i;
 	u16 offset = 0;
 	u8 value = 0;
 	u8 page = 0;
-	int i;
 
 	status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, 0,
 				   &value, 1, 0, NULL);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6e6df4d690cc..1c255b27244c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -452,7 +452,7 @@ static void
 ice_prepare_for_reset(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
-	int i;
+	unsigned int i;
 
 	/* already prepared for reset */
 	if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
@@ -1188,8 +1188,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
+	unsigned int i;
 	u32 reg;
-	int i;
 
 	if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state)) {
 		/* Since the VF MDD event logging is rate limited, check if
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 95e8bca562e5..9b09a111321c 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -80,7 +80,7 @@ ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode,
 		    enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
 {
 	struct ice_hw *hw = &pf->hw;
-	int i;
+	unsigned int i;
 
 	ice_for_each_vf(pf, i) {
 		struct ice_vf *vf = &pf->vf[i];
@@ -325,7 +325,7 @@ void ice_free_vfs(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
-	int tmp, i;
+	unsigned int tmp, i;
 
 	if (!pf->vf)
 		return;
-- 
cgit v1.2.3


From 54113ded67126a7f81245de7c9cd73f49c6b2d0c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 May 2020 13:21:36 +0200
Subject: r8169: remove mask argument from rtl_w0w1_eri

rtl_eri_read() returns the full 32bit value, therefore there's no
benefit in writing back parts of it only. handle it like the vendor
driver and write the full 32 bit always. Omitting the mask argument
avoids some overhead and makes the code better readable.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 66 ++++++++++++++-----------------
 1 file changed, 30 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 79817d4ffa47..42178a0bc23e 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1061,25 +1061,21 @@ static u32 rtl_eri_read(struct rtl8169_private *tp, int addr)
 	return _rtl_eri_read(tp, addr, ERIAR_EXGMAC);
 }
 
-static void rtl_w0w1_eri(struct rtl8169_private *tp, int addr, u32 mask, u32 p,
-			 u32 m)
+static void rtl_w0w1_eri(struct rtl8169_private *tp, int addr, u32 p, u32 m)
 {
-	u32 val;
+	u32 val = rtl_eri_read(tp, addr);
 
-	val = rtl_eri_read(tp, addr);
-	rtl_eri_write(tp, addr, mask, (val & ~m) | p);
+	rtl_eri_write(tp, addr, ERIAR_MASK_1111, (val & ~m) | p);
 }
 
-static void rtl_eri_set_bits(struct rtl8169_private *tp, int addr, u32 mask,
-			     u32 p)
+static void rtl_eri_set_bits(struct rtl8169_private *tp, int addr, u32 p)
 {
-	rtl_w0w1_eri(tp, addr, mask, p, 0);
+	rtl_w0w1_eri(tp, addr, p, 0);
 }
 
-static void rtl_eri_clear_bits(struct rtl8169_private *tp, int addr, u32 mask,
-			       u32 m)
+static void rtl_eri_clear_bits(struct rtl8169_private *tp, int addr, u32 m)
 {
-	rtl_w0w1_eri(tp, addr, mask, 0, m);
+	rtl_w0w1_eri(tp, addr, 0, m);
 }
 
 static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
@@ -1243,8 +1239,8 @@ static bool r8168_check_dash(struct rtl8169_private *tp)
 
 static void rtl_reset_packet_filter(struct rtl8169_private *tp)
 {
-	rtl_eri_clear_bits(tp, 0xdc, ERIAR_MASK_0001, BIT(0));
-	rtl_eri_set_bits(tp, 0xdc, ERIAR_MASK_0001, BIT(0));
+	rtl_eri_clear_bits(tp, 0xdc, BIT(0));
+	rtl_eri_set_bits(tp, 0xdc, BIT(0));
 }
 
 DECLARE_RTL_COND(rtl_efusear_cond)
@@ -1371,11 +1367,9 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	if (rtl_is_8168evl_up(tp)) {
 		tmp--;
 		if (wolopts & WAKE_MAGIC)
-			rtl_eri_set_bits(tp, 0x0dc, ERIAR_MASK_0100,
-					 MagicPacket_v2);
+			rtl_eri_set_bits(tp, 0x0dc, MagicPacket_v2);
 		else
-			rtl_eri_clear_bits(tp, 0x0dc, ERIAR_MASK_0100,
-					   MagicPacket_v2);
+			rtl_eri_clear_bits(tp, 0x0dc, MagicPacket_v2);
 	} else if (rtl_is_8125(tp)) {
 		tmp--;
 		if (wolopts & WAKE_MAGIC)
@@ -2119,7 +2113,7 @@ static void rtl8168_config_eee_mac(struct rtl8169_private *tp)
 	if (tp->mac_version != RTL_GIGA_MAC_VER_38)
 		RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
-	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_1111, 0x0003);
+	rtl_eri_set_bits(tp, 0x1b0, 0x0003);
 }
 
 static void rtl8125_config_eee_mac(struct rtl8169_private *tp)
@@ -2283,7 +2277,7 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40:
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_49:
-		rtl_eri_clear_bits(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000);
+		rtl_eri_clear_bits(tp, 0x1a8, 0xfc000000);
 		RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80);
 		break;
 	default:
@@ -2316,7 +2310,7 @@ static void rtl_pll_power_up(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_49:
 		RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0);
-		rtl_eri_set_bits(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000);
+		rtl_eri_set_bits(tp, 0x1a8, 0xfc000000);
 		break;
 	default:
 		break;
@@ -2925,8 +2919,8 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
 	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x07ff0060);
-	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_0001, BIT(4));
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00);
+	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
+	rtl_w0w1_eri(tp, 0x0d4, 0x0c00, 0xff00);
 
 	rtl_disable_clock_request(tp);
 
@@ -2949,8 +2943,8 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
 	rtl_reset_packet_filter(tp);
-	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_0001, BIT(4));
-	rtl_eri_set_bits(tp, 0x1d0, ERIAR_MASK_0001, BIT(4));
+	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
+	rtl_eri_set_bits(tp, 0x1d0, BIT(4));
 	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x00000060);
 
@@ -2979,7 +2973,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8168f_1);
 
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00);
+	rtl_w0w1_eri(tp, 0x0d4, 0x0c00, 0xff00);
 }
 
 static void rtl_hw_start_8411(struct rtl8169_private *tp)
@@ -2997,7 +2991,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8168f_1);
 
-	rtl_eri_set_bits(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00);
+	rtl_eri_set_bits(tp, 0x0d4, 0x0c00);
 }
 
 static void rtl_hw_start_8168g(struct rtl8169_private *tp)
@@ -3017,8 +3011,8 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 
 	rtl8168_config_eee_mac(tp);
 
-	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06);
-	rtl_eri_clear_bits(tp, 0x1b0, ERIAR_MASK_0011, BIT(12));
+	rtl_w0w1_eri(tp, 0x2fc, 0x01, 0x06);
+	rtl_eri_clear_bits(tp, 0x1b0, BIT(12));
 
 	rtl_pcie_state_l2l3_disable(tp);
 }
@@ -3244,9 +3238,9 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xdc, ERIAR_MASK_1111, BIT(4));
+	rtl_eri_set_bits(tp, 0xdc, BIT(4));
 
-	rtl_eri_set_bits(tp, 0xd4, ERIAR_MASK_1111, 0x1f00);
+	rtl_eri_set_bits(tp, 0xd4, 0x1f00);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
@@ -3262,7 +3256,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
-	rtl_eri_clear_bits(tp, 0x1b0, ERIAR_MASK_0011, BIT(12));
+	rtl_eri_clear_bits(tp, 0x1b0, BIT(12));
 
 	rtl_pcie_state_l2l3_disable(tp);
 
@@ -3299,7 +3293,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xd4, ERIAR_MASK_1111, 0x1f80);
+	rtl_eri_set_bits(tp, 0xd4, 0x1f80);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
@@ -3310,7 +3304,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 
 	rtl8168_config_eee_mac(tp);
 
-	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06);
+	rtl_w0w1_eri(tp, 0x2fc, 0x01, 0x06);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
@@ -3402,7 +3396,7 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xd4, ERIAR_MASK_1111, 0x1f90);
+	rtl_eri_set_bits(tp, 0xd4, 0x1f90);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
@@ -3418,7 +3412,7 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
-	rtl_eri_clear_bits(tp, 0x1b0, ERIAR_MASK_0011, BIT(12));
+	rtl_eri_clear_bits(tp, 0x1b0, BIT(12));
 
 	rtl_pcie_state_l2l3_disable(tp);
 
@@ -3543,7 +3537,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 	rtl_reset_packet_filter(tp);
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00);
+	rtl_w0w1_eri(tp, 0x0d4, 0x0e00, 0xff00);
 
 	/* disable EEE */
 	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
-- 
cgit v1.2.3


From a15aaa038b8ed213da7547f31c98345e2fe06d64 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 May 2020 13:22:22 +0200
Subject: r8169: remove mask argument from r8168dp_ocp_read

All callers read the full 32bit value, therefore the mask argument can
be removed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 42178a0bc23e..391b77710a7d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1078,9 +1078,9 @@ static void rtl_eri_clear_bits(struct rtl8169_private *tp, int addr, u32 m)
 	rtl_w0w1_eri(tp, addr, 0, m);
 }
 
-static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
+static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u16 reg)
 {
-	RTL_W32(tp, OCPAR, ((u32)mask & 0x0f) << 12 | (reg & 0x0fff));
+	RTL_W32(tp, OCPAR, 0x0fu << 12 | (reg & 0x0fff));
 	return rtl_loop_wait_high(tp, &rtl_ocpar_cond, 100, 20) ?
 		RTL_R32(tp, OCPDR) : ~0;
 }
@@ -1127,7 +1127,7 @@ DECLARE_RTL_COND(rtl_dp_ocp_read_cond)
 
 	reg = rtl8168_get_ocp_reg(tp);
 
-	return r8168dp_ocp_read(tp, 0x0f, reg) & 0x00000800;
+	return r8168dp_ocp_read(tp, reg) & 0x00000800;
 }
 
 DECLARE_RTL_COND(rtl_ep_ocp_read_cond)
@@ -1215,7 +1215,7 @@ static bool r8168dp_check_dash(struct rtl8169_private *tp)
 {
 	u16 reg = rtl8168_get_ocp_reg(tp);
 
-	return !!(r8168dp_ocp_read(tp, 0x0f, reg) & 0x00008000);
+	return !!(r8168dp_ocp_read(tp, reg) & 0x00008000);
 }
 
 static bool r8168ep_check_dash(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 787c0c04f4c28d10a1c49bcbd625c24a3e9155d1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 May 2020 13:23:21 +0200
Subject: r8169: remove mask argument from r8168ep_ocp_read

Remove the mask argument as it's not used by r8168ep_ocp_read().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 391b77710a7d..1a69ec92caa5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1085,7 +1085,7 @@ static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u16 reg)
 		RTL_R32(tp, OCPDR) : ~0;
 }
 
-static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
+static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u16 reg)
 {
 	return _rtl_eri_read(tp, reg, ERIAR_OOB);
 }
@@ -1132,7 +1132,7 @@ DECLARE_RTL_COND(rtl_dp_ocp_read_cond)
 
 DECLARE_RTL_COND(rtl_ep_ocp_read_cond)
 {
-	return r8168ep_ocp_read(tp, 0x0f, 0x124) & 0x00000001;
+	return r8168ep_ocp_read(tp, 0x124) & 0x00000001;
 }
 
 DECLARE_RTL_COND(rtl_ocp_tx_cond)
@@ -1157,8 +1157,7 @@ static void rtl8168dp_driver_start(struct rtl8169_private *tp)
 static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 {
 	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
-	r8168ep_ocp_write(tp, 0x01, 0x30,
-			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01);
 	rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10);
 }
 
@@ -1189,8 +1188,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
 {
 	rtl8168ep_stop_cmac(tp);
 	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
-	r8168ep_ocp_write(tp, 0x01, 0x30,
-			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01);
 	rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10);
 }
 
@@ -1220,7 +1218,7 @@ static bool r8168dp_check_dash(struct rtl8169_private *tp)
 
 static bool r8168ep_check_dash(struct rtl8169_private *tp)
 {
-	return !!(r8168ep_ocp_read(tp, 0x0f, 0x128) & 0x00000001);
+	return r8168ep_ocp_read(tp, 0x128) & 0x00000001;
 }
 
 static bool r8168_check_dash(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 9250dccc119e72aecb0dfa786c94b4d8eb67ea29 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Sat, 23 May 2020 15:27:11 +0200
Subject: net: ethernet: mtk_star_emac: use devm_register_netdev()

Use the new devres variant of register_netdev() in the mtk-star-emac
driver and shrink the code by a couple lines.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 789c77af501f..b74349cede28 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1519,13 +1519,6 @@ static void mtk_star_mdiobus_unregister(void *data)
 	mdiobus_unregister(priv->mii);
 }
 
-static void mtk_star_unregister_netdev(void *data)
-{
-	struct net_device *ndev = data;
-
-	unregister_netdev(ndev);
-}
-
 static int mtk_star_probe(struct platform_device *pdev)
 {
 	struct device_node *of_node;
@@ -1641,15 +1634,7 @@ static int mtk_star_probe(struct platform_device *pdev)
 
 	netif_napi_add(ndev, &priv->napi, mtk_star_poll, MTK_STAR_NAPI_WEIGHT);
 
-	ret = register_netdev(ndev);
-	if (ret)
-		return ret;
-
-	ret = devm_add_action_or_reset(dev, mtk_star_unregister_netdev, ndev);
-	if (ret)
-		return ret;
-
-	return 0;
+	return devm_register_netdev(dev, ndev);
 }
 
 static const struct of_device_id mtk_star_of_match[] = {
-- 
cgit v1.2.3


From debb7af6867f1331f72745732b4849c748e929a6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:50:57 +0300
Subject: mlxsw: spectrum: Rename IGMP trap group

The IGMP trap group will be used for MLD traps in the next patch, so
rename it to "MC_SNOOPING" which is more appropriate.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 14 +++++++-------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 3c3db1c874b6..602f9fdfd7ea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5531,7 +5531,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
-	MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index dfafd30c57b9..3457a3058eee 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4046,11 +4046,11 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, LLDP, TRAP_TO_CPU,
 		  false, SP_LLDP, DISCARD),
 	MLXSW_SP_RXL_MARK(DHCP, MIRROR_TO_CPU, DHCP, false),
-	MLXSW_SP_RXL_MARK(IGMP_QUERY, MIRROR_TO_CPU, IGMP, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, TRAP_TO_CPU, IGMP, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, TRAP_TO_CPU, IGMP, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V2_LEAVE, TRAP_TO_CPU, IGMP, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, IGMP, false),
+	MLXSW_SP_RXL_MARK(IGMP_QUERY, MIRROR_TO_CPU, MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IGMP_V2_LEAVE, TRAP_TO_CPU, MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false),
@@ -4155,7 +4155,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			rate = 128;
 			burst_size = 7;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD:
 			rate = 16 * 1024;
 			burst_size = 10;
@@ -4235,7 +4235,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			priority = 4;
 			tc = 4;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD:
 			priority = 3;
-- 
cgit v1.2.3


From 99129069b7123c22ca14529972946216757077ee Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:50:58 +0300
Subject: mlxsw: spectrum: Use same trap group for MLD and IGMP packets

Both packet types are needed for the same reason (multicast snooping),
so associate them with the same trap group.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      |  1 -
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 16 +++++++---------
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 602f9fdfd7ea..d51a4c4665d0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5542,7 +5542,6 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
-	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3457a3058eee..bab51dfb6e13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4054,14 +4054,14 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false),
-	MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU, IPV6_MLD,
-			  false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT, TRAP_TO_CPU, IPV6_MLD,
-			     false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_DONE, TRAP_TO_CPU, IPV6_MLD,
-			     false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT, TRAP_TO_CPU, IPV6_MLD,
+	MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU,
+			  MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT, TRAP_TO_CPU,
+			     MC_SNOOPING, false),
+	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_DONE, TRAP_TO_CPU, MC_SNOOPING,
 			     false),
+	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT, TRAP_TO_CPU,
+			     MC_SNOOPING, false),
 	/* L3 traps */
 	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),
 	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
@@ -4156,7 +4156,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD:
 			rate = 16 * 1024;
 			burst_size = 10;
 			break;
@@ -4237,7 +4236,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD:
 			priority = 3;
 			tc = 3;
 			break;
-- 
cgit v1.2.3


From 0ecb947412d7e95128a007f791b020a37ce5e9be Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:50:59 +0300
Subject: mlxsw: spectrum: Trap IPv4 DHCP packets in router

Currently, IPv4 DHCP packets are trapped during L2 forwarding, which
means that packets might be trapped unnecessarily. Instead, only trap
the DHCP packets that reach the router. Either because they were flooded
to the router port or forwarded to it by the FDB. This is consistent
with the corresponding IPv6 trap.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/trap.h     | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index bab51dfb6e13..fa6e630abb6e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4045,7 +4045,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_NO_MARK(LACP, TRAP_TO_CPU, LACP, true),
 	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, LLDP, TRAP_TO_CPU,
 		  false, SP_LLDP, DISCARD),
-	MLXSW_SP_RXL_MARK(DHCP, MIRROR_TO_CPU, DHCP, false),
 	MLXSW_SP_RXL_MARK(IGMP_QUERY, MIRROR_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
@@ -4074,6 +4073,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			  false),
 	MLXSW_SP_RXL_MARK(IPV4_OSPF, TRAP_TO_CPU, OSPF, false),
 	MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false),
+	MLXSW_SP_RXL_MARK(IPV4_DHCP, TRAP_TO_CPU, DHCP, false),
 	MLXSW_SP_RXL_MARK(IPV6_DHCP, TRAP_TO_CPU, DHCP, false),
 	MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false),
 	MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index eaa521b7561b..fac05433c488 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -59,6 +59,7 @@ enum {
 	MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_SOLICITATION = 0x8C,
 	MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_ADVERTISMENT = 0x8D,
 	MLXSW_TRAP_ID_L3_IPV6_REDIRECTION = 0x8E,
+	MLXSW_TRAP_ID_IPV4_DHCP = 0x8F,
 	MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90,
 	MLXSW_TRAP_ID_IPV6_MC_LINK_LOCAL_DEST = 0x91,
 	MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92,
-- 
cgit v1.2.3


From 938e6d0b7672317e54836610d9b9535dda19e90b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:00 +0300
Subject: mlxsw: spectrum: Change default rate and priority of DHCP packets

Reduce the default acceptable rate of DHCP packets to 128 packets per
second and reduce their priority. This is reasonable given the Spectrum
ASICs are limited to 128 ports at the moment.

These are only the default values. Users will be able to modify them via
devlink-trap.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index fa6e630abb6e..c2d6890803da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4152,6 +4152,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
 			rate = 128;
 			burst_size = 7;
 			break;
@@ -4161,7 +4162,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
@@ -4230,7 +4230,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			tc = 5;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
 			priority = 4;
 			tc = 4;
 			break;
@@ -4242,6 +4241,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
 			priority = 2;
 			tc = 2;
 			break;
-- 
cgit v1.2.3


From e0d848477a68ab940caf8a880d3181b5ef9e4e0e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:01 +0300
Subject: mlxsw: spectrum_buffers: Assign non-zero quotas to TC 0 of the CPU
 port

As explained in commit 9ffcc3725f09 ("mlxsw: spectrum: Allow packets to
be trapped from any PG"), incoming packets can be admitted to the shared
buffer and forwarded / trapped, if:

(Ingress{Port}.Usage < Thres && Ingress{Port,PG}.Usage < Thres &&
 Egress{Port}.Usage < Thres && Egress{Port,TC}.Usage < Thres)
||
(Ingress{Port}.Usage < Min || Ingress{Port,PG} < Min ||
 Egress{Port}.Usage < Min || Egress{Port,TC}.Usage < Min)

Trapped packets are scheduled to transmission through the CPU port.
Currently, the minimum and maximum quotas of traffic class (TC) 0 of the
CPU port are 0, which means it is not usable.

Assign non-zero quotas to TC 0 of the CPU port, so that it could be
utilized by subsequent patches.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 968f0902e4fe..21bfb2f6a6f0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -614,7 +614,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = {
 #define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, MLXSW_SP_SB_POOL_EGR_CPU)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
-	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
 	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
 	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
 	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
-- 
cgit v1.2.3


From 5047d819f5b1ad244675ba69b36af1ac44c76e34 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:02 +0300
Subject: mlxsw: spectrum: Align TC and trap priority

The traffic class (TC) attribute of packet traps determines through which
TC a packet trap will be scheduled through the CPU port.

The priority attribute determines which trap will be triggered in case
several packet traps match a packet.

We try to configure these attributes to the same value for all packet
traps as there is little reason not to.

Some packet traps did not use the same value, so rectify that now.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c      | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c2d6890803da..978f6d98e8c4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4253,7 +4253,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			priority = 0;
-			tc = 1;
+			tc = 0;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT:
 			priority = MLXSW_REG_HTGT_DEFAULT_PRIORITY;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 3a13b17cd1b8..1d414d0e5431 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -207,25 +207,25 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.group = DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
 		.priority = 0,
-		.tc = 1,
+		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
 		.priority = 0,
-		.tc = 1,
+		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(TUNNEL_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
 		.priority = 0,
-		.tc = 1,
+		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
 		.priority = 0,
-		.tc = 1,
+		.tc = 0,
 	},
 };
 
-- 
cgit v1.2.3


From d88f8cc158b9c3812172431a3761e86b92f2d53d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:03 +0300
Subject: mlxsw: spectrum_trap: Remove unnecessary field

Now that traffic class (TC) and priority are set to the same value,
there is no need to store both. Remove the first.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 1d414d0e5431..78f983c1a056 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -21,7 +21,6 @@ struct mlxsw_sp_trap_group_item {
 	struct devlink_trap_group group;
 	u16 hw_group_id;
 	u8 priority;
-	u8 tc;
 };
 
 #define MLXSW_SP_TRAP_LISTENERS_MAX 3
@@ -207,25 +206,21 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.group = DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
 		.priority = 0,
-		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
 		.priority = 0,
-		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(TUNNEL_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
 		.priority = 0,
-		.tc = 0,
 	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
 		.priority = 0,
-		.tc = 0,
 	},
 };
 
@@ -865,7 +860,7 @@ __mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core,
 	}
 
 	mlxsw_reg_htgt_pack(htgt_pl, group_item->hw_group_id, hw_policer_id,
-			    group_item->priority, group_item->tc);
+			    group_item->priority, group_item->priority);
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
-- 
cgit v1.2.3


From 32446438cc5bb09aa5ca43c18b0d13dc88569850 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:04 +0300
Subject: mlxsw: spectrum: Rename ARP trap group

The ARP trap group will be used for IPv6 ND traps in the next patch, so
rename it to "NEIGH_DISCOVERY" which is more appropriate.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 13 +++++++------
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index d51a4c4665d0..4d61c414348f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5536,7 +5536,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST,
-	MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 978f6d98e8c4..6ef8222cc0ae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4050,8 +4050,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_NO_MARK(IGMP_V2_LEAVE, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
-	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false),
-	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false),
+	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
+	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU,
 			  MC_SNOOPING, false),
@@ -4112,8 +4112,9 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
 	/* NVE traps */
-	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false),
-	MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, ARP, false),
+	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY, false),
+	MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY,
+			     false),
 	/* PTP traps */
 	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, PTP0, TRAP_TO_CPU,
 		  false, SP_PTP0, DISCARD),
@@ -4161,7 +4162,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 10;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
@@ -4238,7 +4239,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			priority = 3;
 			tc = 3;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
-- 
cgit v1.2.3


From b33f5d9fb71a65dde1477417b0e11205a2d21adc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:05 +0300
Subject: mlxsw: spectrum: Use same trap group for IPv6 ND and ARP packets

Both packet types are needed for the same reason (neighbour discovery),
so associate them with the same trap group.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6ef8222cc0ae..c4fdfe8fd5a3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4082,10 +4082,10 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			  false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISMENT, TRAP_TO_CPU, IPV6_ND,
 			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU, IPV6_ND,
-			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISMENT, TRAP_TO_CPU, IPV6_ND,
-			  false),
+	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU,
+			  NEIGH_DISCOVERY, false),
+	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISMENT, TRAP_TO_CPU,
+			  NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6_ND, false),
 	MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
-- 
cgit v1.2.3


From ce3c3bf0bfad4bb8652f3c3f5770d38a10ce2894 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:06 +0300
Subject: mlxsw: spectrum: Use dedicated trap group for sampled packets

The rate with which packets are sampled is determined by user space, so
there is no need to associate such packets with a policer.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 4d61c414348f..9b27a129b0a6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5547,6 +5547,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
 
 	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c4fdfe8fd5a3..d275887bba28 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4103,7 +4103,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			     ROUTER_EXP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
-		  false, SP_IP2ME, DISCARD),
+		  false, SP_PKT_SAMPLE, DISCARD),
 	/* ACL trap */
 	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, IP2ME, false),
 	/* Multicast Router Traps */
@@ -4252,6 +4252,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			priority = 1;
 			tc = 1;
 			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			priority = 0;
 			tc = 0;
-- 
cgit v1.2.3


From 154388e11255dbbcf68906fe8058fe72af346634 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 May 2020 00:51:07 +0300
Subject: mlxsw: spectrum: Fix spelling mistake in trap's name

Fix incorrect spelling of "advertisement".

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/trap.h     | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d275887bba28..943a24975799 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4080,11 +4080,11 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6_ND,
 			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISMENT, TRAP_TO_CPU, IPV6_ND,
+	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISEMENT, TRAP_TO_CPU, IPV6_ND,
 			  false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU,
 			  NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISMENT, TRAP_TO_CPU,
+	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISEMENT, TRAP_TO_CPU,
 			  NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6_ND, false),
 	MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index fac05433c488..1b89472a0908 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -55,9 +55,9 @@ enum {
 	MLXSW_TRAP_ID_IPV4_BGP = 0x88,
 	MLXSW_TRAP_ID_IPV6_BGP = 0x89,
 	MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,
-	MLXSW_TRAP_ID_L3_IPV6_ROUTER_ADVERTISMENT = 0x8B,
+	MLXSW_TRAP_ID_L3_IPV6_ROUTER_ADVERTISEMENT = 0x8B,
 	MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_SOLICITATION = 0x8C,
-	MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_ADVERTISMENT = 0x8D,
+	MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_ADVERTISEMENT = 0x8D,
 	MLXSW_TRAP_ID_L3_IPV6_REDIRECTION = 0x8E,
 	MLXSW_TRAP_ID_IPV4_DHCP = 0x8F,
 	MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90,
-- 
cgit v1.2.3


From ca23cb0bc50faae0d48786b2f9f702dbb528b925 Mon Sep 17 00:00:00 2001
From: Sven Auhagen <sven.auhagen@voleatech.de>
Date: Sat, 23 May 2020 12:14:08 +0200
Subject: mvneta: MVNETA_SKB_HEADROOM set last 3 bits to zero

For XDP the MVNETA_SKB_HEADROOM is used as an offset for
the received data.
The MVNETA manual states that the last 3 bits assumed to be 0.

This is currently the case but lets make it explicit in the definition
to prevent future problems.

Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 37947949345c..15e42a7f8a86 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -324,7 +324,8 @@
 	      ETH_HLEN + ETH_FCS_LEN,			     \
 	      cache_line_size())
 
-#define MVNETA_SKB_HEADROOM	max(XDP_PACKET_HEADROOM, NET_SKB_PAD)
+/* Driver assumes that the last 3 bits are 0 */
+#define MVNETA_SKB_HEADROOM	(max(XDP_PACKET_HEADROOM, NET_SKB_PAD) & ~0x7)
 #define MVNETA_SKB_PAD	(SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \
 			 MVNETA_SKB_HEADROOM))
 #define MVNETA_SKB_SIZE(len)	(SKB_DATA_ALIGN(len) + MVNETA_SKB_PAD)
-- 
cgit v1.2.3


From 880f8f99d12ca89d3ec76f688e0d92612054cbb1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 May 2020 12:46:49 -0700
Subject: bnx2x: allow bnx2x_bsc_read() to schedule

bnx2x_warpcore_read_sfp_module_eeprom() can call bnx2x_bsc_read()
three times before giving up.

This causes latency blips of at least 31 ms (58 ms being reported
by our teams)

Convert the long lasting loops of udelay() to usleep_range() ones,
and breaks the loops on precise time tracking.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ariel Elior <aelior@marvell.com>
Cc: Sudarsana Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 26 ++++++++++++++----------
 1 file changed, 15 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 517caedc0a87..1426c691c7c4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3085,6 +3085,7 @@ static int bnx2x_bsc_read(struct link_params *params,
 			  u8 xfer_cnt,
 			  u32 *data_array)
 {
+	u64 t0, delta;
 	u32 val, i;
 	int rc = 0;
 
@@ -3114,17 +3115,18 @@ static int bnx2x_bsc_read(struct link_params *params,
 	REG_WR(bp, MCP_REG_MCPR_IMC_COMMAND, val);
 
 	/* Poll for completion */
-	i = 0;
+	t0 = ktime_get_ns();
 	val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
 	while (((val >> MCPR_IMC_COMMAND_IMC_STATUS_BITSHIFT) & 0x3) != 1) {
-		udelay(10);
-		val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
-		if (i++ > 1000) {
-			DP(NETIF_MSG_LINK, "wr 0 byte timed out after %d try\n",
-								i);
+		delta = ktime_get_ns() - t0;
+		if (delta > 10 * NSEC_PER_MSEC) {
+			DP(NETIF_MSG_LINK, "wr 0 byte timed out after %Lu ns\n",
+					   delta);
 			rc = -EFAULT;
 			break;
 		}
+		usleep_range(10, 20);
+		val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
 	}
 	if (rc == -EFAULT)
 		return rc;
@@ -3138,16 +3140,18 @@ static int bnx2x_bsc_read(struct link_params *params,
 	REG_WR(bp, MCP_REG_MCPR_IMC_COMMAND, val);
 
 	/* Poll for completion */
-	i = 0;
+	t0 = ktime_get_ns();
 	val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
 	while (((val >> MCPR_IMC_COMMAND_IMC_STATUS_BITSHIFT) & 0x3) != 1) {
-		udelay(10);
-		val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
-		if (i++ > 1000) {
-			DP(NETIF_MSG_LINK, "rd op timed out after %d try\n", i);
+		delta = ktime_get_ns() - t0;
+		if (delta > 10 * NSEC_PER_MSEC) {
+			DP(NETIF_MSG_LINK, "rd op timed out after %Lu ns\n",
+					   delta);
 			rc = -EFAULT;
 			break;
 		}
+		usleep_range(10, 20);
+		val = REG_RD(bp, MCP_REG_MCPR_IMC_COMMAND);
 	}
 	if (rc == -EFAULT)
 		return rc;
-- 
cgit v1.2.3


From d29d5ff9daee41a2553843574257e5a6724d5453 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 May 2020 19:49:15 +0200
Subject: r8169: sync RTL8168g hw config with vendor driver

Sync hw config for RTL8168g with r8168 vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 79090aefac69..d034a57a0e1c 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3019,6 +3019,7 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_set_bits(tp, 0x0d4, 0x1f80);
 
 	rtl8168_config_eee_mac(tp);
 
-- 
cgit v1.2.3


From ee1350f94e5c7885142d736370e5fa7dc2c7747a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 May 2020 19:49:55 +0200
Subject: r8169: sync RTL8168h hw config with vendor driver

Sync hw config for RTL8168h with r8168 vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index d034a57a0e1c..173a4c41c4af 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3250,9 +3250,8 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	rtl_reset_packet_filter(tp);
 
-	rtl_eri_set_bits(tp, 0xdc, BIT(4));
-
 	rtl_eri_set_bits(tp, 0xd4, 0x1f00);
+	rtl_eri_set_bits(tp, 0xdc, 0x001c);
 
 	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
-- 
cgit v1.2.3


From 33b00ca1da49969da068f672e7c2430f16f1f85f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 May 2020 19:50:38 +0200
Subject: r8169: sync RTL8168evl hw config with vendor driver

Sync hw config for RTL8168evl with r8168 vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 173a4c41c4af..dfb07df47e0e 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2926,12 +2926,14 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	rtl_ephy_init(tp, e_info_8168e_2);
 
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_1111, 0x0000);
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
+	rtl_eri_set_bits(tp, 0x0d4, 0x1f00);
+	rtl_eri_set_bits(tp, 0x1d0, BIT(1));
+	rtl_reset_packet_filter(tp);
+	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
 	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x07ff0060);
-	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
-	rtl_w0w1_eri(tp, 0x0d4, 0x0c00, 0xff00);
 
 	rtl_disable_clock_request(tp);
 
-- 
cgit v1.2.3


From d05890c5aed0dd4709f27525862765f1c6ddec1a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 May 2020 19:52:27 +0200
Subject: r8169: sync RTL8168f/RTL8411 hw config with vendor driver

Sync hw config for RTL8168f/RTL8411 with r8168 vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index dfb07df47e0e..17c564457e52 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2953,11 +2953,11 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_1111, 0x0000);
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
 	rtl_reset_packet_filter(tp);
 	rtl_eri_set_bits(tp, 0x1b0, BIT(4));
-	rtl_eri_set_bits(tp, 0x1d0, BIT(4));
+	rtl_eri_set_bits(tp, 0x1d0, BIT(4) | BIT(1));
 	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x00000060);
 
@@ -2986,7 +2986,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8168f_1);
 
-	rtl_w0w1_eri(tp, 0x0d4, 0x0c00, 0xff00);
+	rtl_eri_set_bits(tp, 0x0d4, 0x1f00);
 }
 
 static void rtl_hw_start_8411(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From ff937b916eb6316fe4644564a572ed3b5867bc1f Mon Sep 17 00:00:00 2001
From: Yuval Basson <yuval.bason@marvell.com>
Date: Tue, 26 May 2020 09:41:20 +0300
Subject: qed: Add EDPM mode type for user-fw compatibility

In older FW versions the completion flag was treated as the ack flag in
edpm messages. Expose the FW option of setting which mode the QP is in
by adding a flag to the qedr <-> qed API.

Flag is added for backward compatibility with libqedr.
This flag will be set by qedr after determining whether the libqedr is
using the updated version.

Fixes: f10939403352 ("qed: Add support for QP verbs")
Signed-off-by: Yuval Basson <yuval.bason@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_rdma.c | 1 +
 drivers/net/ethernet/qlogic/qed/qed_rdma.h | 1 +
 drivers/net/ethernet/qlogic/qed/qed_roce.c | 3 +++
 include/linux/qed/qed_rdma_if.h            | 3 +++
 4 files changed, 8 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 50985871cd3d..98455f698f53 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1378,6 +1378,7 @@ qed_rdma_create_qp(void *rdma_cxt,
 		rc = qed_iwarp_create_qp(p_hwfn, qp, out_params);
 		qp->qpid = qp->icid;
 	} else {
+		qp->edpm_mode = GET_FIELD(in_params->flags, QED_ROCE_EDPM_MODE);
 		rc = qed_roce_alloc_cid(p_hwfn, &qp->icid);
 		qp->qpid = ((0xFF << 16) | qp->icid);
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.h b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
index 5a7ebc764bb6..3898cae61e7a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.h
@@ -183,6 +183,7 @@ struct qed_rdma_qp {
 	void *shared_queue;
 	dma_addr_t shared_queue_phys_addr;
 	struct qed_iwarp_ep *ep;
+	u8 edpm_mode;
 };
 
 static inline bool qed_rdma_is_xrc_qp(struct qed_rdma_qp *qp)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 46a4d09eacef..4566815f7b87 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -459,6 +459,9 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 		  ROCE_CREATE_QP_REQ_RAMROD_DATA_XRC_FLAG,
 		  qed_rdma_is_xrc_qp(qp));
 
+	SET_FIELD(p_ramrod->flags2,
+		  ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE, qp->edpm_mode);
+
 	p_ramrod->max_ord = qp->max_rd_atomic_req;
 	p_ramrod->traffic_class = qp->traffic_class_tos;
 	p_ramrod->hop_limit = qp->hop_limit_ttl;
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index f93edd5750a5..584077565f12 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -335,6 +335,9 @@ struct qed_rdma_create_qp_in_params {
 	u16 xrcd_id;
 	u8 stats_queue;
 	enum qed_rdma_qp_type qp_type;
+	u8 flags;
+#define QED_ROCE_EDPM_MODE_MASK      0x1
+#define QED_ROCE_EDPM_MODE_SHIFT     0
 };
 
 struct qed_rdma_create_qp_out_params {
-- 
cgit v1.2.3


From 58cff782cc55eb755826c649976aea9f5f8b3086 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 26 May 2020 14:29:00 +0200
Subject: flow_dissector: Parse multiple MPLS Label Stack Entries

The current MPLS dissector only parses the first MPLS Label Stack
Entry (second LSE can be parsed too, but only to set a key_id).

This patch adds the possibility to parse several LSEs by making
__skb_flow_dissect_mpls() return FLOW_DISSECT_RET_PROTO_AGAIN as long
as the Bottom Of Stack bit hasn't been seen, up to a maximum of
FLOW_DIS_MPLS_MAX entries.

FLOW_DIS_MPLS_MAX is arbitrarily set to 7. This should be enough for
many practical purposes, without wasting too much space.

To record the parsed values, flow_dissector_key_mpls is modified to
store an array of stack entries, instead of just the values of the
first one. A bit field, "used_lses", is also added to keep track of
the LSEs that have been set. The objective is to avoid defining a
new FLOW_DISSECTOR_KEY_MPLS_XX for each level of the MPLS stack.

TC flower is adapted for the new struct flow_dissector_key_mpls layout.
Matching on several MPLS Label Stack Entries will be added in the next
patch.

The NFP and MLX5 drivers are also adapted: nfp_flower_compile_mac() and
mlx5's parse_tunnel() now verify that the rule only uses the first LSE
and fail if it doesn't.

Finally, the behaviour of the FLOW_DISSECTOR_KEY_MPLS_ENTROPY key is
slightly modified. Instead of recording the first Entropy Label, it
now records the last one. This shouldn't have any consequences since
there doesn't seem to have any user of FLOW_DISSECTOR_KEY_MPLS_ENTROPY
in the tree. We'd probably better do a hash of all parsed MPLS labels
instead (excluding reserved labels) anyway. That'd give better entropy
and would probably also simplify the code. But that's not the purpose
of this patch, so I'm keeping that as a future possible improvement.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlx5/core/en/tc_tun_mplsoudp.c        | 27 +++++++----
 drivers/net/ethernet/netronome/nfp/flower/match.c  | 42 ++++++++++++-----
 include/net/flow_dissector.h                       | 14 +++++-
 net/core/flow_dissector.c                          | 49 +++++++++++++-------
 net/sched/cls_flower.c                             | 52 +++++++++++++++-------
 5 files changed, 132 insertions(+), 52 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
index 98ee62e427d2..b4a3c96d34fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
@@ -101,25 +101,36 @@ static int parse_tunnel(struct mlx5e_priv *priv,
 
 	flow_rule_match_mpls(rule, &match);
 
+	/* Only support matching the first LSE */
+	if (match.mask->used_lses != 1)
+		return -EOPNOTSUPP;
+
 	MLX5_SET(fte_match_set_misc2, misc2_c,
-		 outer_first_mpls_over_udp.mpls_label, match.mask->mpls_label);
+		 outer_first_mpls_over_udp.mpls_label,
+		 match.mask->ls[0].mpls_label);
 	MLX5_SET(fte_match_set_misc2, misc2_v,
-		 outer_first_mpls_over_udp.mpls_label, match.key->mpls_label);
+		 outer_first_mpls_over_udp.mpls_label,
+		 match.key->ls[0].mpls_label);
 
 	MLX5_SET(fte_match_set_misc2, misc2_c,
-		 outer_first_mpls_over_udp.mpls_exp, match.mask->mpls_tc);
+		 outer_first_mpls_over_udp.mpls_exp,
+		 match.mask->ls[0].mpls_tc);
 	MLX5_SET(fte_match_set_misc2, misc2_v,
-		 outer_first_mpls_over_udp.mpls_exp, match.key->mpls_tc);
+		 outer_first_mpls_over_udp.mpls_exp, match.key->ls[0].mpls_tc);
 
 	MLX5_SET(fte_match_set_misc2, misc2_c,
-		 outer_first_mpls_over_udp.mpls_s_bos, match.mask->mpls_bos);
+		 outer_first_mpls_over_udp.mpls_s_bos,
+		 match.mask->ls[0].mpls_bos);
 	MLX5_SET(fte_match_set_misc2, misc2_v,
-		 outer_first_mpls_over_udp.mpls_s_bos, match.key->mpls_bos);
+		 outer_first_mpls_over_udp.mpls_s_bos,
+		 match.key->ls[0].mpls_bos);
 
 	MLX5_SET(fte_match_set_misc2, misc2_c,
-		 outer_first_mpls_over_udp.mpls_ttl, match.mask->mpls_ttl);
+		 outer_first_mpls_over_udp.mpls_ttl,
+		 match.mask->ls[0].mpls_ttl);
 	MLX5_SET(fte_match_set_misc2, misc2_v,
-		 outer_first_mpls_over_udp.mpls_ttl, match.key->mpls_ttl);
+		 outer_first_mpls_over_udp.mpls_ttl,
+		 match.key->ls[0].mpls_ttl);
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 546bc01d507d..f7f01e2e3dce 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -74,9 +74,10 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 	return 0;
 }
 
-static void
+static int
 nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
-		       struct nfp_flower_mac_mpls *msk, struct flow_rule *rule)
+		       struct nfp_flower_mac_mpls *msk, struct flow_rule *rule,
+		       struct netlink_ext_ack *extack)
 {
 	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
 	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
@@ -97,14 +98,28 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 		u32 t_mpls;
 
 		flow_rule_match_mpls(rule, &match);
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.key->mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.key->mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.key->mpls_bos) |
+
+		/* Only support matching the first LSE */
+		if (match.mask->used_lses != 1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "unsupported offload: invalid LSE depth for MPLS match offload");
+			return -EOPNOTSUPP;
+		}
+
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
+				    match.key->ls[0].mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
+				    match.key->ls[0].mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
+				    match.key->ls[0].mpls_bos) |
 			 NFP_FLOWER_MASK_MPLS_Q;
 		ext->mpls_lse = cpu_to_be32(t_mpls);
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.mask->mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.mask->mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.mask->mpls_bos) |
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB,
+				    match.mask->ls[0].mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC,
+				    match.mask->ls[0].mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS,
+				    match.mask->ls[0].mpls_bos) |
 			 NFP_FLOWER_MASK_MPLS_Q;
 		msk->mpls_lse = cpu_to_be32(t_mpls);
 	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -121,6 +136,8 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 			msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
 		}
 	}
+
+	return 0;
 }
 
 static void
@@ -461,9 +478,12 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 	msk += sizeof(struct nfp_flower_in_port);
 
 	if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) {
-		nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext,
-				       (struct nfp_flower_mac_mpls *)msk,
-				       rule);
+		err = nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext,
+					     (struct nfp_flower_mac_mpls *)msk,
+					     rule, extack);
+		if (err)
+			return err;
+
 		ext += sizeof(struct nfp_flower_mac_mpls);
 		msk += sizeof(struct nfp_flower_mac_mpls);
 	}
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 628383915827..4fb1a69c6ecf 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -59,13 +59,25 @@ struct flow_dissector_key_vlan {
 	__be16	vlan_tpid;
 };
 
-struct flow_dissector_key_mpls {
+struct flow_dissector_mpls_lse {
 	u32	mpls_ttl:8,
 		mpls_bos:1,
 		mpls_tc:3,
 		mpls_label:20;
 };
 
+#define FLOW_DIS_MPLS_MAX 7
+struct flow_dissector_key_mpls {
+	struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */
+	u8 used_lses; /* One bit set for each Label Stack Entry in use */
+};
+
+static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls,
+					  int lse_index)
+{
+	mpls->used_lses |= 1 << lse_index;
+}
+
 #define FLOW_DIS_TUN_OPTS_MAX 255
 /**
  * struct flow_dissector_key_enc_opts:
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5dceed467f64..0aeb33572feb 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -480,47 +480,59 @@ EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 static enum flow_dissect_ret
 __skb_flow_dissect_mpls(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container, void *data, int nhoff, int hlen)
+			void *target_container, void *data, int nhoff, int hlen,
+			int lse_index, bool *entropy_label)
 {
-	struct flow_dissector_key_keyid *key_keyid;
-	struct mpls_label *hdr, _hdr[2];
-	u32 entry, label;
+	struct mpls_label *hdr, _hdr;
+	u32 entry, label, bos;
 
 	if (!dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
 	    !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
 		return FLOW_DISSECT_RET_OUT_GOOD;
 
+	if (lse_index >= FLOW_DIS_MPLS_MAX)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
 	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
 				   hlen, &_hdr);
 	if (!hdr)
 		return FLOW_DISSECT_RET_OUT_BAD;
 
-	entry = ntohl(hdr[0].entry);
+	entry = ntohl(hdr->entry);
 	label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+	bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
 
 	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
 		struct flow_dissector_key_mpls *key_mpls;
+		struct flow_dissector_mpls_lse *lse;
 
 		key_mpls = skb_flow_dissector_target(flow_dissector,
 						     FLOW_DISSECTOR_KEY_MPLS,
 						     target_container);
-		key_mpls->mpls_label = label;
-		key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
-					>> MPLS_LS_TTL_SHIFT;
-		key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
-					>> MPLS_LS_TC_SHIFT;
-		key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
-					>> MPLS_LS_S_SHIFT;
+		lse = &key_mpls->ls[lse_index];
+
+		lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+		lse->mpls_bos = bos;
+		lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
+		lse->mpls_label = label;
+		dissector_set_mpls_lse(key_mpls, lse_index);
 	}
 
-	if (label == MPLS_LABEL_ENTROPY) {
+	if (*entropy_label &&
+	    dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+		struct flow_dissector_key_keyid *key_keyid;
+
 		key_keyid = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
 						      target_container);
-		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+		key_keyid->keyid = cpu_to_be32(label);
 	}
-	return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*entropy_label = label == MPLS_LABEL_ENTROPY;
+
+	return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN;
 }
 
 static enum flow_dissect_ret
@@ -979,6 +991,8 @@ bool __skb_flow_dissect(const struct net *net,
 	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
+	bool mpls_el = false;
+	int mpls_lse = 0;
 	int num_hdrs = 0;
 	u8 ip_proto = 0;
 	bool ret;
@@ -1278,7 +1292,10 @@ proto_again:
 	case htons(ETH_P_MPLS_MC):
 		fdret = __skb_flow_dissect_mpls(skb, flow_dissector,
 						target_container, data,
-						nhoff, hlen);
+						nhoff, hlen, mpls_lse,
+						&mpls_el);
+		nhoff += sizeof(struct mpls_label);
+		mpls_lse++;
 		break;
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN) {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0c574700da75..f524afe0b7f5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -781,9 +781,17 @@ static int fl_set_key_mpls(struct nlattr **tb,
 			   struct flow_dissector_key_mpls *key_mask,
 			   struct netlink_ext_ack *extack)
 {
+	struct flow_dissector_mpls_lse *lse_mask;
+	struct flow_dissector_mpls_lse *lse_val;
+
+	lse_val = &key_val->ls[0];
+	lse_mask = &key_mask->ls[0];
+
 	if (tb[TCA_FLOWER_KEY_MPLS_TTL]) {
-		key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
-		key_mask->mpls_ttl = MPLS_TTL_MASK;
+		lse_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
+		lse_mask->mpls_ttl = MPLS_TTL_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_BOS]) {
 		u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]);
@@ -794,8 +802,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Bottom Of Stack (BOS) must be 0 or 1");
 			return -EINVAL;
 		}
-		key_val->mpls_bos = bos;
-		key_mask->mpls_bos = MPLS_BOS_MASK;
+		lse_val->mpls_bos = bos;
+		lse_mask->mpls_bos = MPLS_BOS_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_TC]) {
 		u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]);
@@ -806,8 +816,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Traffic Class (TC) must be between 0 and 7");
 			return -EINVAL;
 		}
-		key_val->mpls_tc = tc;
-		key_mask->mpls_tc = MPLS_TC_MASK;
+		lse_val->mpls_tc = tc;
+		lse_mask->mpls_tc = MPLS_TC_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
 		u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]);
@@ -818,8 +830,10 @@ static int fl_set_key_mpls(struct nlattr **tb,
 					    "Label must be between 0 and 1048575");
 			return -EINVAL;
 		}
-		key_val->mpls_label = label;
-		key_mask->mpls_label = MPLS_LABEL_MASK;
+		lse_val->mpls_label = label;
+		lse_mask->mpls_label = MPLS_LABEL_MASK;
+		dissector_set_mpls_lse(key_val, 0);
+		dissector_set_mpls_lse(key_mask, 0);
 	}
 	return 0;
 }
@@ -2222,31 +2236,37 @@ static int fl_dump_key_mpls(struct sk_buff *skb,
 			    struct flow_dissector_key_mpls *mpls_key,
 			    struct flow_dissector_key_mpls *mpls_mask)
 {
+	struct flow_dissector_mpls_lse *lse_mask;
+	struct flow_dissector_mpls_lse *lse_key;
 	int err;
 
 	if (!memchr_inv(mpls_mask, 0, sizeof(*mpls_mask)))
 		return 0;
-	if (mpls_mask->mpls_ttl) {
+
+	lse_mask = &mpls_mask->ls[0];
+	lse_key = &mpls_key->ls[0];
+
+	if (lse_mask->mpls_ttl) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TTL,
-				 mpls_key->mpls_ttl);
+				 lse_key->mpls_ttl);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_tc) {
+	if (lse_mask->mpls_tc) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_TC,
-				 mpls_key->mpls_tc);
+				 lse_key->mpls_tc);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_label) {
+	if (lse_mask->mpls_label) {
 		err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_LABEL,
-				  mpls_key->mpls_label);
+				  lse_key->mpls_label);
 		if (err)
 			return err;
 	}
-	if (mpls_mask->mpls_bos) {
+	if (lse_mask->mpls_bos) {
 		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_BOS,
-				 mpls_key->mpls_bos);
+				 lse_key->mpls_bos);
 		if (err)
 			return err;
 	}
-- 
cgit v1.2.3


From 8a448bf832af537d26aa557d183a16943dce4510 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Tue, 26 May 2020 00:27:10 +0800
Subject: net: ethernet: fec: move GPR register offset and bit into DT

The commit da722186f654 (net: fec: set GPR bit on suspend by DT
configuration) set the GPR reigster offset and bit in driver for
wake on lan feature.

But it introduces two issues here:
- one SOC has two instances, they have different bit
- different SOCs may have different offset and bit

So to support wake-on-lan feature on other i.MX platforms, it should
configure the GPR reigster offset and bit from DT.

So the patch is to improve the commit da722186f654 (net: fec: set GPR
bit on suspend by DT configuration) to support multiple ethernet
instances on i.MX series.

v2:
 * switch back to store the quirks bitmask in driver_data
v3:
 * suggested by Sascha Hauer, use a struct fec_devinfo for
   abstracting differences between different hardware variants,
   it can give more freedom to describe the differences.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2e209142f2d1..4acb91dce5fc 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -88,8 +88,6 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 
 struct fec_devinfo {
 	u32 quirks;
-	u8 stop_gpr_reg;
-	u8 stop_gpr_bit;
 };
 
 static const struct fec_devinfo fec_imx25_info = {
@@ -112,8 +110,6 @@ static const struct fec_devinfo fec_imx6q_info = {
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
 		  FEC_QUIRK_HAS_RACC,
-	.stop_gpr_reg = 0x34,
-	.stop_gpr_bit = 27,
 };
 
 static const struct fec_devinfo fec_mvf600_info = {
@@ -3476,19 +3472,23 @@ static int fec_enet_get_irq_cnt(struct platform_device *pdev)
 }
 
 static int fec_enet_init_stop_mode(struct fec_enet_private *fep,
-				   struct fec_devinfo *dev_info,
 				   struct device_node *np)
 {
 	struct device_node *gpr_np;
+	u32 out_val[3];
 	int ret = 0;
 
-	if (!dev_info)
-		return 0;
-
-	gpr_np = of_parse_phandle(np, "gpr", 0);
+	gpr_np = of_parse_phandle(np, "fsl,stop-mode", 0);
 	if (!gpr_np)
 		return 0;
 
+	ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val,
+					 ARRAY_SIZE(out_val));
+	if (ret) {
+		dev_dbg(&fep->pdev->dev, "no stop mode property\n");
+		return ret;
+	}
+
 	fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np);
 	if (IS_ERR(fep->stop_gpr.gpr)) {
 		dev_err(&fep->pdev->dev, "could not find gpr regmap\n");
@@ -3497,8 +3497,8 @@ static int fec_enet_init_stop_mode(struct fec_enet_private *fep,
 		goto out;
 	}
 
-	fep->stop_gpr.reg = dev_info->stop_gpr_reg;
-	fep->stop_gpr.bit = dev_info->stop_gpr_bit;
+	fep->stop_gpr.reg = out_val[1];
+	fep->stop_gpr.bit = out_val[2];
 
 out:
 	of_node_put(gpr_np);
@@ -3575,7 +3575,7 @@ fec_probe(struct platform_device *pdev)
 	if (of_get_property(np, "fsl,magic-packet", NULL))
 		fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
 
-	ret = fec_enet_init_stop_mode(fep, dev_info, np);
+	ret = fec_enet_init_stop_mode(fep, np);
 	if (ret)
 		goto failed_stop_mode;
 
-- 
cgit v1.2.3


From 12b1bc75cd460c30652db0d4a3bd3fc59c16742c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 May 2020 21:54:00 +0200
Subject: r8169: improve rtl_remove_one

Don't call netif_napi_del() manually, free_netdev() does this for us.
In addition reorder calls to match reverse order of calls in probe().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 17c564457e52..d672ae77c644 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4996,17 +4996,15 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	if (r8168_check_dash(tp))
-		rtl8168_driver_stop(tp);
-
-	netif_napi_del(&tp->napi);
+	if (pci_dev_run_wake(pdev))
+		pm_runtime_get_noresume(&pdev->dev);
 
 	unregister_netdev(dev);
 
-	rtl_release_firmware(tp);
+	if (r8168_check_dash(tp))
+		rtl8168_driver_stop(tp);
 
-	if (pci_dev_run_wake(pdev))
-		pm_runtime_get_noresume(&pdev->dev);
+	rtl_release_firmware(tp);
 
 	/* restore original MAC address */
 	rtl_rar_set(tp, dev->perm_addr);
-- 
cgit v1.2.3


From 3c2d8a046a4cd0bc835f2e6cfbc12f41d7f4323e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:43 +0300
Subject: mlxsw: spectrum: Use dedicated trap group for ACL trap

Packets that are trapped via tc's trap action are currently subject to
the same policer as packets hitting local routes. The latter are
critical to the correct functioning of the control plane, while the
former are mainly used for traffic inspection.

Split the ACL trap to a separate group with its own policer. Use a
higher priority for these traps than for traps using mirror action
(e.g., ARP, IGMP). Otherwise, packets matching both traps will not be
forwarded in hardware (because of trap action) and also not forwarded in
software because they will be marked with 'offload_fwd_mark'.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 9b27a129b0a6..5b5b96a82a34 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5548,6 +5548,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING,
 
 	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 943a24975799..e0811a7e13b9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4105,7 +4105,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_PKT_SAMPLE, DISCARD),
 	/* ACL trap */
-	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, IP2ME, false),
+	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, FLOW_LOGGING, false),
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false),
 	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),
@@ -4167,6 +4167,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
 			rate = 1024;
 			burst_size = 7;
 			break;
@@ -4230,6 +4231,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			priority = 5;
 			tc = 5;
 			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
 			priority = 4;
 			tc = 4;
-- 
cgit v1.2.3


From 761bc42fbecff8cfb8e529451fd0f13800d050c4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:44 +0300
Subject: mlxsw: spectrum: Use same switch case for identical groups

Trap groups that use the same policer settings can share the same switch
case.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index e0811a7e13b9..e8c9fc4cb6fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4168,9 +4168,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
-			rate = 1024;
-			burst_size = 7;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 			rate = 1024;
 			burst_size = 7;
-- 
cgit v1.2.3


From 412df3d1bb03e1fb97fee5ec9a9dc39e7ea459be Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:45 +0300
Subject: mlxsw: spectrum: Rename IPv6 ND trap group

The IPv6 Neighbour Discovery (ND) group will be used for various IPv6
packets, not all of which fall under the definition of ND, so rename it
to "IPV6" which is more appropriate.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5b5b96a82a34..6df7cc8a69f1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5542,7 +5542,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
-	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index e8c9fc4cb6fb..b420aa292d7c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4078,15 +4078,15 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false),
 	MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false),
 	MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6_ND,
+	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6,
 			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISEMENT, TRAP_TO_CPU, IPV6_ND,
+	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISEMENT, TRAP_TO_CPU, IPV6,
 			  false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU,
 			  NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISEMENT, TRAP_TO_CPU,
 			  NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6_ND, false),
+	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
@@ -4165,7 +4165,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
@@ -4239,7 +4239,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			tc = 3;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
 			priority = 2;
-- 
cgit v1.2.3


From 954eef26778cb878327bb38b937a0fcf51b8445b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:46 +0300
Subject: mlxsw: spectrum: Use same trap group for various IPv6 packets

Group these various IPv6 packets (e.g., router solicitations, router
advertisement) together and subject them to the same policer.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b420aa292d7c..141a605582c6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4067,9 +4067,9 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
 	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, ROUTER_EXP,
+	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, IPV6, false),
+	MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, IPV6, false),
+	MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, IPV6,
 			  false),
 	MLXSW_SP_RXL_MARK(IPV4_OSPF, TRAP_TO_CPU, OSPF, false),
 	MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false),
-- 
cgit v1.2.3


From d322309d726b77226cc4880ee6c38c26c1dac999 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:47 +0300
Subject: mlxsw: spectrum: Use separate trap group for FID miss

When a packet enters the device it is classified to a filtering
identifier (FID) based on the ingress port and VLAN. The FID miss trap
is used to trap packets for which a FID could not be found.

In mlxsw this trap should only be triggered when a port is enslaved to
an OVS bridge and a matching ACL rule could not be found, so as to
trigger learning.

These packets are therefore completely unrelated to packets hitting
local routes and should be in a different group. Move them.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6df7cc8a69f1..b55a833a5d17 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5549,6 +5549,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS,
 
 	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 141a605582c6..ac71d67457aa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4052,7 +4052,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false),
+	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, FID_MISS, false),
 	MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU,
 			  MC_SNOOPING, false),
 	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT, TRAP_TO_CPU,
@@ -4169,6 +4169,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			rate = 1024;
 			burst_size = 7;
 			break;
@@ -4248,6 +4249,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			priority = 1;
 			tc = 1;
 			break;
-- 
cgit v1.2.3


From 1e3cd589421af8fed677c017f12a5f78f59aa427 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:48 +0300
Subject: mlxsw: spectrum: Use same trap group for local routes and link-local
 destination

Packets with an IPv6 link-local destination (i.e., fe80::/10) should not
be forwarded and are therefore trapped to the CPU for local delivery.
Since these packets are trapped for the same logical reason as packets
hitting local routes, associate both traps with the same group.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ac71d67457aa..5fe51ee8a206 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4066,7 +4066,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
-	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, IPV6,
-- 
cgit v1.2.3


From 025b7de7f4e9b26c31c511e84a7cef14605e70ef Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:49 +0300
Subject: mlxsw: spectrum: Reduce priority of locally delivered packets

To align with recent recommended values. Will be configurable by future
patches.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c            | 2 +-
 tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5fe51ee8a206..b10e5aeaedef 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4235,11 +4235,11 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			tc = 4;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 			priority = 3;
 			tc = 3;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
index 58f3a05f08af..7d9e73a43a49 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
@@ -15,7 +15,7 @@ source mlxsw_lib.sh
 SB_POOL_ING=0
 SB_POOL_EGR_CPU=10
 
-SB_ITC_CPU_IP=3
+SB_ITC_CPU_IP=2
 SB_ITC_CPU_ARP=2
 SB_ITC=0
 
-- 
cgit v1.2.3


From 03cb0ce0ddc8c00b7c4c5becff7fb7cf44b00a91 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:50 +0300
Subject: mlxsw: switchx2: Move SwitchX-2 trap groups out of main enum

The number of Spectrum trap groups is not infinite, but two identifiers
are occupied by SwitchX-2 specific trap groups. Free these identifiers
by moving them out of the main enum.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 2 --
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 5 +++++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index b55a833a5d17..fd5e18b71114 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5526,8 +5526,6 @@ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4);
 
 enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
-	MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX,
-	MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 2503f61db5fb..b438f5576e18 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1404,6 +1404,11 @@ err_port_module_info_get:
 	return err;
 }
 
+enum {
+	MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX = 1,
+	MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL = 2,
+};
+
 #define MLXSW_SX_RXL(_trap_id) \
 	MLXSW_RXL(mlxsw_sx_rx_listener_func, _trap_id, TRAP_TO_CPU,	\
 		  false, SX2_RX, FORWARD)
-- 
cgit v1.2.3


From b87bde80daf77649efba90ef0b1079b84be92d39 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:51 +0300
Subject: mlxsw: spectrum_trap: Do not hard code "thin" policer identifier

As explained in commit e612523041ab ("mlxsw: spectrum_trap: Introduce
dummy group with thin policer"), the purpose of the "thin" policer is to
pass as less packets as possible to the CPU.

The identifier of this policer is currently set according to the maximum
number of used trap groups, but this is fragile: On Spectrum-1 the
maximum number of policers is less than the maximum number of trap
groups, which might result in an invalid policer identifier in case the
number of used trap groups grows beyond the policer limit.

Solve this by dynamically allocating the policer identifier.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 17 +++++++++++------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h |  2 ++
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 78f983c1a056..f4b812276a5a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -441,8 +441,6 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 	},
 };
 
-#define MLXSW_SP_THIN_POLICER_ID	(MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1)
-
 static struct mlxsw_sp_trap_policer_item *
 mlxsw_sp_trap_policer_item_lookup(struct mlxsw_sp *mlxsw_sp, u32 id)
 {
@@ -487,14 +485,21 @@ mlxsw_sp_trap_item_lookup(struct mlxsw_sp *mlxsw_sp, u16 id)
 
 static int mlxsw_sp_trap_cpu_policers_set(struct mlxsw_sp *mlxsw_sp)
 {
+	struct mlxsw_sp_trap *trap = mlxsw_sp->trap;
 	char qpcr_pl[MLXSW_REG_QPCR_LEN];
+	u16 hw_id;
 
 	/* The purpose of "thin" policer is to drop as many packets
 	 * as possible. The dummy group is using it.
 	 */
-	__set_bit(MLXSW_SP_THIN_POLICER_ID, mlxsw_sp->trap->policers_usage);
-	mlxsw_reg_qpcr_pack(qpcr_pl, MLXSW_SP_THIN_POLICER_ID,
-			    MLXSW_REG_QPCR_IR_UNITS_M, false, 1, 4);
+	hw_id = find_first_zero_bit(trap->policers_usage, trap->max_policers);
+	if (WARN_ON(hw_id == trap->max_policers))
+		return -ENOBUFS;
+
+	__set_bit(hw_id, trap->policers_usage);
+	trap->thin_policer_hw_id = hw_id;
+	mlxsw_reg_qpcr_pack(qpcr_pl, hw_id, MLXSW_REG_QPCR_IR_UNITS_M,
+			    false, 1, 4);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl);
 }
 
@@ -503,7 +508,7 @@ static int mlxsw_sp_trap_dummy_group_init(struct mlxsw_sp *mlxsw_sp)
 	char htgt_pl[MLXSW_REG_HTGT_LEN];
 
 	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY,
-			    MLXSW_SP_THIN_POLICER_ID, 0, 1);
+			    mlxsw_sp->trap->thin_policer_hw_id, 0, 1);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
index 759146897b3a..13ac412f4d53 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.h
@@ -17,6 +17,8 @@ struct mlxsw_sp_trap {
 	struct mlxsw_sp_trap_item *trap_items_arr;
 	u64 traps_count; /* Number of registered traps */
 
+	u16 thin_policer_hw_id;
+
 	u64 max_policers;
 	unsigned long policers_usage[]; /* Usage bitmap */
 };
-- 
cgit v1.2.3


From 500769bebef7a3b1a60c3f6028690677332446c6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:52 +0300
Subject: mlxsw: reg: Move all trap groups under the same enum

After the previous patch the split is no longer necessary and all the
trap groups can be moved under the same enum.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index fd5e18b71114..586a2f37fd12 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5548,18 +5548,14 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS,
-
-	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
-	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
-};
-
-enum mlxsw_reg_htgt_discard_trap_group {
-	MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
+
+	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
+	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
 };
 
 /* reg_htgt_trap_group
-- 
cgit v1.2.3


From 1260e083d4cff4dc223bb0913c35ba5e92d1b379 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:53 +0300
Subject: mlxsw: spectrum: Share one group for all locally delivered packets

Routed IP packets with the Router Alert option need to be trapped to
the CPU as they might need to be locally delivered to raw sockets with
the IP_ROUTER_ALERT / IPV6_ROUTER_ALERT socket option.

Move them to the same group with other packets that might need to be
trapped following route lookup.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b10e5aeaedef..016df2c14f0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4089,8 +4089,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
-	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, IP2ME, false),
+	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
 	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_CLASS_E, FORWARD,
-- 
cgit v1.2.3


From dacc4e3acf542ce4c8a6dcc1a350decb443cf7f3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:54 +0300
Subject: mlxsw: spectrum: Treat IPv6 link-local SIP as an exception

IPv6 packets that need to be forwarded and have a link-local source IP are
dropped by the kernel and an ICMPv6 "Destination unreachable" is sent to
the sending host.

As such, change the trap group of such packets so that they do not
interfere with IPv6 management packets. In the future this trap will be
exposed as an exception via devlink-trap.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 016df2c14f0e..5cb7fd650156 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4067,7 +4067,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
 	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, IP2ME, false),
-	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, IPV6, false),
+	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, IPV6,
 			  false),
-- 
cgit v1.2.3


From 9785b92b4443f2862495c9aa0ee8caed6f43523d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:55 +0300
Subject: mlxsw: spectrum: Add packet traps for BFD packets

Bidirectional Forwarding Detection (BFD) provides "low-overhead,
short-duration detection of failures in the path between adjacent
forwarding engines" (RFC 5880).

This is accomplished by exchanging BFD packets between the two
forwarding engines. Up until now these packets were trapped via the
general local delivery (i.e., IP2ME) trap which also traps a lot of
other packets that are not as time-sensitive as BFD packets.

Expose dedicated traps for BFD packets so that user space could
configure a dedicated policer for them.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 7 +++++++
 drivers/net/ethernet/mellanox/mlxsw/trap.h     | 2 ++
 3 files changed, 10 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 586a2f37fd12..38fa7304af0c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5548,6 +5548,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5cb7fd650156..c598ae9ed106 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4093,6 +4093,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
 	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
+	MLXSW_SP_RXL_MARK(IPV4_BFD, TRAP_TO_CPU, BFD, false),
+	MLXSW_SP_RXL_MARK(IPV6_BFD, TRAP_TO_CPU, BFD, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_CLASS_E, FORWARD,
 			     ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_MC_DMAC, FORWARD,
@@ -4185,6 +4187,10 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			rate = 360;
 			burst_size = 7;
 			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD:
+			rate = 20 * 1024;
+			burst_size = 10;
+			break;
 		default:
 			continue;
 		}
@@ -4226,6 +4232,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD:
 			priority = 5;
 			tc = 5;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 1b89472a0908..28e60697d14e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -66,6 +66,8 @@ enum {
 	MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1,
 	MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8,
 	MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
+	MLXSW_TRAP_ID_IPV4_BFD = 0xD0,
+	MLXSW_TRAP_ID_IPV6_BFD = 0xD1,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
 	MLXSW_TRAP_ID_DISCARD_NON_ROUTABLE = 0x11A,
-- 
cgit v1.2.3


From 10d3757fcb07a83101b6578a33bd800e81d27eea Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 26 May 2020 02:05:56 +0300
Subject: mlxsw: spectrum_router: Allow programming link-local prefix routes

The device has a trap for IPv6 packets that need be routed and have a
unicast link-local destination IP (i.e., fe80::/10). This allows mlxsw
to ignore link-local routes, as the packets will be trapped to the CPU
in any case.

However, since link-local routes are not programmed, it is possible for
routed packets to hit the default route which might also be programmed
to trap packets. This means that packets with a link-local destination
IP might be trapped for the wrong reason.

To overcome this, allow programming link-local prefix routes (usually
one fe80::/64 per-table), so that the packets will be forwarded until
reaching the link-local trap.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 71aee4914619..c939b3596566 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -5003,9 +5003,11 @@ static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt)
 {
 	/* Packets with link-local destination IP arriving to the router
 	 * are trapped to the CPU, so no need to program specific routes
-	 * for them.
+	 * for them. Only allow prefix routes (usually one fe80::/64) so
+	 * that packets are trapped for the right reason.
 	 */
-	if (ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL)
+	if ((ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) &&
+	    (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)))
 		return true;
 
 	/* Multicast routes aren't supported, so ignore them. Neighbour
-- 
cgit v1.2.3


From 53c0ec4f4db19d430570bbbfc80ce899419d29f4 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Tue, 26 May 2020 20:03:02 +0200
Subject: ne2k-pci: Fix various coding-style issues and improve printk() usage

Fixed a ton of minor checkpatch errors/warnings and remove version
printing at module init/when device is found and use MODULE_VERSION
instead. Also modifying the RTL8029 PCI string to include the compatible
RTL8029AS nic.
The only mayor issue remaining is the missing SPDX tag, but since the
exact version of the GPL is not stated anywhere inside the file, its
impossible to add such a tag at the moment.
But maybe it is possible, since 8390.h states Donald Becker's 8390
drivers are licensed under GPL 2.2 only (= GPL-2.0-only ?).
The kernel module containing this patch compiles and runs without
problems on a RTL8029AS-based NE2000 clone card with kernel 5.7.0-rc6.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/8390/ne2k-pci.c | 345 ++++++++++++++++++-----------------
 1 file changed, 182 insertions(+), 163 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 42985a82321a..77d78b4c59c4 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -1,39 +1,43 @@
-/* ne2k-pci.c: A NE2000 clone on PCI bus driver for Linux. */
-/*
-	A Linux device driver for PCI NE2000 clones.
-
-	Authors and other copyright holders:
-	1992-2000 by Donald Becker, NE2000 core and various modifications.
-	1995-1998 by Paul Gortmaker, core modifications and PCI support.
-	Copyright 1993 assigned to the United States Government as represented
-	by the Director, National Security Agency.
-
-	This software may be used and distributed according to the terms of
-	the GNU General Public License (GPL), incorporated herein by reference.
-	Drivers based on or derived from this code fall under the GPL and must
-	retain the authorship, copyright and license notice.  This file is not
-	a complete program and may only be used when the entire operating
-	system is licensed under the GPL.
-
-	The author may be reached as becker@scyld.com, or C/O
-	Scyld Computing Corporation
-	410 Severn Ave., Suite 210
-	Annapolis MD 21403
-
-	Issues remaining:
-	People are making PCI ne2000 clones! Oh the horror, the horror...
-	Limited full-duplex support.
-*/
+/* A Linux device driver for PCI NE2000 clones.
+ *
+ * Authors and other copyright holders:
+ * 1992-2000 by Donald Becker, NE2000 core and various modifications.
+ * 1995-1998 by Paul Gortmaker, core modifications and PCI support.
+ * Copyright 1993 assigned to the United States Government as represented
+ * by the Director, National Security Agency.
+ *
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ *
+ * The author may be reached as becker@scyld.com, or C/O
+ * Scyld Computing Corporation
+ * 410 Severn Ave., Suite 210
+ * Annapolis MD 21403
+ *
+ * Issues remaining:
+ * People are making PCI NE2000 clones! Oh the horror, the horror...
+ * Limited full-duplex support.
+ */
 
 #define DRV_NAME	"ne2k-pci"
+#define DRV_DESCRIPTION	"PCI NE2000 clone driver"
+#define DRV_AUTHOR	"Donald Becker / Paul Gortmaker"
 #define DRV_VERSION	"1.03"
 #define DRV_RELDATE	"9/22/2003"
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 /* The user-configurable values.
-   These may be modified when a driver module is loaded.*/
+ * These may be modified when a driver module is loaded.
+ */
+
+/* More are supported, limit only on options */
+#define MAX_UNITS 8
 
-#define MAX_UNITS 8				/* More are supported, limit only on options */
 /* Used to pass the full-duplex flag, etc. */
 static int full_duplex[MAX_UNITS];
 static int options[MAX_UNITS];
@@ -52,7 +56,7 @@ static int options[MAX_UNITS];
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/irq.h>
 #include <linux/uaccess.h>
 
@@ -60,20 +64,14 @@ static int options[MAX_UNITS];
 
 static u32 ne2k_msg_enable;
 
-/* These identify the driver base version and may not be removed. */
-static const char version[] =
-	KERN_INFO DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE
-	" D. Becker/P. Gortmaker\n";
-
 #if defined(__powerpc__)
 #define inl_le(addr)  le32_to_cpu(inl(addr))
 #define inw_le(addr)  le16_to_cpu(inw(addr))
 #endif
 
-#define PFX DRV_NAME ": "
-
-MODULE_AUTHOR("Donald Becker / Paul Gortmaker");
-MODULE_DESCRIPTION("PCI NE2000 clone driver");
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_VERSION(DRV_VERSION);
 MODULE_LICENSE("GPL");
 
 module_param_named(msg_enable, ne2k_msg_enable, uint, 0444);
@@ -83,7 +81,8 @@ MODULE_PARM_DESC(msg_enable, "Debug message level (see linux/netdevice.h for bit
 MODULE_PARM_DESC(options, "Bit 5: full duplex");
 MODULE_PARM_DESC(full_duplex, "full duplex setting(s) (1)");
 
-/* Some defines that people can play with if so inclined. */
+/* Some defines that people can play with if so inclined.
+ */
 
 /* Use 32 bit data-movement operations instead of 16 bit. */
 #define USE_LONGIO
@@ -91,14 +90,18 @@ MODULE_PARM_DESC(full_duplex, "full duplex setting(s) (1)");
 /* Do we implement the read before write bugfix ? */
 /* #define NE_RW_BUGFIX */
 
-/* Flags.  We rename an existing ei_status field to store flags! */
-/* Thus only the low 8 bits are usable for non-init-time flags. */
+/* Flags.  We rename an existing ei_status field to store flags!
+ * Thus only the low 8 bits are usable for non-init-time flags.
+ */
 #define ne2k_flags reg0
+
 enum {
-	ONLY_16BIT_IO=8, ONLY_32BIT_IO=4,	/* Chip can do only 16/32-bit xfers. */
-	FORCE_FDX=0x20,						/* User override. */
-	REALTEK_FDX=0x40, HOLTEK_FDX=0x80,
-	STOP_PG_0x60=0x100,
+	/* Chip can do only 16/32-bit xfers. */
+	ONLY_16BIT_IO = 8, ONLY_32BIT_IO = 4,
+	/* User override. */
+	FORCE_FDX = 0x20,
+	REALTEK_FDX = 0x40, HOLTEK_FDX = 0x80,
+	STOP_PG_0x60 = 0x100,
 };
 
 enum ne2k_pci_chipsets {
@@ -120,7 +123,7 @@ static struct {
 	char *name;
 	int flags;
 } pci_clone_list[] = {
-	{"RealTek RTL-8029", REALTEK_FDX},
+	{"RealTek RTL-8029(AS)", REALTEK_FDX},
 	{"Winbond 89C940", 0},
 	{"Compex RL2000", 0},
 	{"KTI ET32P2", 0},
@@ -149,13 +152,14 @@ static const struct pci_device_id ne2k_pci_tbl[] = {
 	{ 0x8c4a, 0x1980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CH_Winbond_89C940_8c4a },
 	{ 0, }
 };
+
 MODULE_DEVICE_TABLE(pci, ne2k_pci_tbl);
 
 
 /* ---- No user-serviceable parts below ---- */
 
 #define NE_BASE	 (dev->base_addr)
-#define NE_CMD	 	0x00
+#define NE_CMD		0x00
 #define NE_DATAPORT	0x10	/* NatSemi-defined port window offset. */
 #define NE_RESET	0x1f	/* Issue a read to reset, a write to clear. */
 #define NE_IO_EXTENT	0x20
@@ -168,18 +172,20 @@ static int ne2k_pci_open(struct net_device *dev);
 static int ne2k_pci_close(struct net_device *dev);
 
 static void ne2k_pci_reset_8390(struct net_device *dev);
-static void ne2k_pci_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr,
-			  int ring_page);
+static void ne2k_pci_get_8390_hdr(struct net_device *dev,
+				  struct e8390_pkt_hdr *hdr, int ring_page);
 static void ne2k_pci_block_input(struct net_device *dev, int count,
-			  struct sk_buff *skb, int ring_offset);
+				 struct sk_buff *skb, int ring_offset);
 static void ne2k_pci_block_output(struct net_device *dev, const int count,
-		const unsigned char *buf, const int start_page);
+				  const unsigned char *buf,
+				  const int start_page);
 static const struct ethtool_ops ne2k_pci_ethtool_ops;
 
 
 
 /* There is no room in the standard 8390 structure for extra info we need,
-   so we build a meta/outer-wrapper structure.. */
+ * so we build a meta/outer-wrapper structure..
+ */
 struct ne2k_pci_card {
 	struct net_device *dev;
 	struct pci_dev *pci_dev;
@@ -187,18 +193,17 @@ struct ne2k_pci_card {
 
 
 
-/*
-  NEx000-clone boards have a Station Address (SA) PROM (SAPROM) in the packet
-  buffer memory space.  By-the-spec NE2000 clones have 0x57,0x57 in bytes
-  0x0e,0x0f of the SAPROM, while other supposed NE2000 clones must be
-  detected by their SA prefix.
-
-  Reading the SAPROM from a word-wide card with the 8390 set in byte-wide
-  mode results in doubled values, which can be detected and compensated for.
-
-  The probe is also responsible for initializing the card and filling
-  in the 'dev' and 'ei_status' structures.
-*/
+/* NEx000-clone boards have a Station Address (SA) PROM (SAPROM) in the packet
+ * buffer memory space.  By-the-spec NE2000 clones have 0x57,0x57 in bytes
+ * 0x0e,0x0f of the SAPROM, while other supposed NE2000 clones must be
+ * detected by their SA prefix.
+ *
+ * Reading the SAPROM from a word-wide card with the 8390 set in byte-wide
+ * mode results in doubled values, which can be detected and compensated for.
+ *
+ * The probe is also responsible for initializing the card and filling
+ * in the 'dev' and 'ei_status' structures.
+ */
 
 static const struct net_device_ops ne2k_netdev_ops = {
 	.ndo_open		= ne2k_pci_open,
@@ -208,7 +213,7 @@ static const struct net_device_ops ne2k_netdev_ops = {
 	.ndo_get_stats		= ei_get_stats,
 	.ndo_set_rx_mode	= ei_set_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = ei_poll,
 #endif
@@ -227,28 +232,21 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 	int flags = pci_clone_list[chip_idx].flags;
 	struct ei_device *ei_local;
 
-/* when built into the kernel, we only print version if device is found */
-#ifndef MODULE
-	static int printed_version;
-	if (!printed_version++)
-		printk(version);
-#endif
-
 	fnd_cnt++;
 
-	i = pci_enable_device (pdev);
+	i = pci_enable_device(pdev);
 	if (i)
 		return i;
 
-	ioaddr = pci_resource_start (pdev, 0);
+	ioaddr = pci_resource_start(pdev, 0);
 	irq = pdev->irq;
 
-	if (!ioaddr || ((pci_resource_flags (pdev, 0) & IORESOURCE_IO) == 0)) {
+	if (!ioaddr || ((pci_resource_flags(pdev, 0) & IORESOURCE_IO) == 0)) {
 		dev_err(&pdev->dev, "no I/O resource at PCI BAR #0\n");
 		goto err_out;
 	}
 
-	if (request_region (ioaddr, NE_IO_EXTENT, DRV_NAME) == NULL) {
+	if (!request_region(ioaddr, NE_IO_EXTENT, DRV_NAME)) {
 		dev_err(&pdev->dev, "I/O resource 0x%x @ 0x%lx busy\n",
 			NE_IO_EXTENT, ioaddr);
 		goto err_out;
@@ -261,14 +259,17 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 	/* Do a preliminary verification that we have a 8390. */
 	{
 		int regd;
-		outb(E8390_NODMA+E8390_PAGE1+E8390_STOP, ioaddr + E8390_CMD);
+
+		outb(E8390_NODMA + E8390_PAGE1 + E8390_STOP, ioaddr + E8390_CMD);
 		regd = inb(ioaddr + 0x0d);
 		outb(0xff, ioaddr + 0x0d);
-		outb(E8390_NODMA+E8390_PAGE0, ioaddr + E8390_CMD);
-		inb(ioaddr + EN0_COUNTER0); /* Clear the counter by reading. */
+		outb(E8390_NODMA + E8390_PAGE0, ioaddr + E8390_CMD);
+		/* Clear the counter by reading. */
+		inb(ioaddr + EN0_COUNTER0);
 		if (inb(ioaddr + EN0_COUNTER0) != 0) {
 			outb(reg0, ioaddr);
-			outb(regd, ioaddr + 0x0d);	/* Restore the old values. */
+			/*  Restore the old values. */
+			outb(regd, ioaddr + 0x0d);
 			goto err_out_free_res;
 		}
 	}
@@ -291,9 +292,9 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 
 		outb(inb(ioaddr + NE_RESET), ioaddr + NE_RESET);
 
-		/* This looks like a horrible timing loop, but it should never take
-		   more than a few cycles.
-		*/
+		/* This looks like a horrible timing loop, but it should never
+		 * take more than a few cycles.
+		 */
 		while ((inb(ioaddr + EN0_ISR) & ENISR_RESET) == 0)
 			/* Limit wait: '2' avoids jiffy roll-over. */
 			if (jiffies - reset_start_time > 2) {
@@ -301,42 +302,53 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 					"Card failure (no reset ack).\n");
 				goto err_out_free_netdev;
 			}
-
-		outb(0xff, ioaddr + EN0_ISR);		/* Ack all intr. */
+		/* Ack all intr. */
+		outb(0xff, ioaddr + EN0_ISR);
 	}
 
 	/* Read the 16 bytes of station address PROM.
-	   We must first initialize registers, similar to NS8390_init(eifdev, 0).
-	   We can't reliably read the SAPROM address without this.
-	   (I learned the hard way!). */
+	 * We must first initialize registers, similar
+	 * to NS8390_init(eifdev, 0).
+	 * We can't reliably read the SAPROM address without this.
+	 * (I learned the hard way!).
+	 */
 	{
 		struct {unsigned char value, offset; } program_seq[] = {
-			{E8390_NODMA+E8390_PAGE0+E8390_STOP, E8390_CMD}, /* Select page 0*/
-			{0x49,	EN0_DCFG},	/* Set word-wide access. */
-			{0x00,	EN0_RCNTLO},	/* Clear the count regs. */
+			/* Select page 0 */
+			{E8390_NODMA + E8390_PAGE0 + E8390_STOP, E8390_CMD},
+			/* Set word-wide access */
+			{0x49,	EN0_DCFG},
+			/* Clear the count regs. */
+			{0x00,	EN0_RCNTLO},
+			/* Mask completion IRQ */
 			{0x00,	EN0_RCNTHI},
-			{0x00,	EN0_IMR},	/* Mask completion irq. */
+			{0x00,	EN0_IMR},
 			{0xFF,	EN0_ISR},
-			{E8390_RXOFF, EN0_RXCR},	/* 0x20  Set to monitor */
-			{E8390_TXOFF, EN0_TXCR},	/* 0x02  and loopback mode. */
+			/* 0x20 Set to monitor */
+			{E8390_RXOFF, EN0_RXCR},
+			/* 0x02 and loopback mode */
+			{E8390_TXOFF, EN0_TXCR},
 			{32,	EN0_RCNTLO},
 			{0x00,	EN0_RCNTHI},
-			{0x00,	EN0_RSARLO},	/* DMA starting at 0x0000. */
+			/* DMA starting at 0x0000 */
+			{0x00,	EN0_RSARLO},
 			{0x00,	EN0_RSARHI},
 			{E8390_RREAD+E8390_START, E8390_CMD},
 		};
 		for (i = 0; i < ARRAY_SIZE(program_seq); i++)
-			outb(program_seq[i].value, ioaddr + program_seq[i].offset);
+			outb(program_seq[i].value,
+			     ioaddr + program_seq[i].offset);
 
 	}
 
 	/* Note: all PCI cards have at least 16 bit access, so we don't have
-	   to check for 8 bit cards.  Most cards permit 32 bit access. */
+	 * to check for 8 bit cards.  Most cards permit 32 bit access.
+	 */
 	if (flags & ONLY_32BIT_IO) {
 		for (i = 0; i < 4 ; i++)
 			((u32 *)SA_prom)[i] = le32_to_cpu(inl(ioaddr + NE_DATAPORT));
 	} else
-		for(i = 0; i < 32 /*sizeof(SA_prom)*/; i++)
+		for (i = 0; i < 32 /* sizeof(SA_prom )*/; i++)
 			SA_prom[i] = inb(ioaddr + NE_DATAPORT);
 
 	/* We always set the 8390 registers for word mode. */
@@ -356,7 +368,7 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 	ei_status.word16 = 1;
 	ei_status.ne2k_flags = flags;
 	if (fnd_cnt < MAX_UNITS) {
-		if (full_duplex[fnd_cnt] > 0  ||  (options[fnd_cnt] & FORCE_FDX))
+		if (full_duplex[fnd_cnt] > 0 || (options[fnd_cnt] & FORCE_FDX))
 			ei_status.ne2k_flags |= FORCE_FDX;
 	}
 
@@ -388,16 +400,15 @@ static int ne2k_pci_init_one(struct pci_dev *pdev,
 	return 0;
 
 err_out_free_netdev:
-	free_netdev (dev);
+	free_netdev(dev);
 err_out_free_res:
-	release_region (ioaddr, NE_IO_EXTENT);
+	release_region(ioaddr, NE_IO_EXTENT);
 err_out:
 	pci_disable_device(pdev);
 	return -ENODEV;
 }
 
-/*
- * Magic incantation sequence for full duplex on the supported cards.
+/* Magic incantation sequence for full duplex on the supported cards.
  */
 static inline int set_realtek_fdx(struct net_device *dev)
 {
@@ -431,7 +442,9 @@ static int ne2k_pci_set_fdx(struct net_device *dev)
 
 static int ne2k_pci_open(struct net_device *dev)
 {
-	int ret = request_irq(dev->irq, ei_interrupt, IRQF_SHARED, dev->name, dev);
+	int ret = request_irq(dev->irq, ei_interrupt, IRQF_SHARED,
+			      dev->name, dev);
+
 	if (ret)
 		return ret;
 
@@ -450,7 +463,8 @@ static int ne2k_pci_close(struct net_device *dev)
 }
 
 /* Hard reset the card.  This used to pause for the same period that a
-   8390 reset command required, but that shouldn't be necessary. */
+ * 8390 reset command required, but that shouldn't be necessary.
+ */
 static void ne2k_pci_reset_8390(struct net_device *dev)
 {
 	unsigned long reset_start_time = jiffies;
@@ -467,31 +481,34 @@ static void ne2k_pci_reset_8390(struct net_device *dev)
 	/* This check _should_not_ be necessary, omit eventually. */
 	while ((inb(NE_BASE+EN0_ISR) & ENISR_RESET) == 0)
 		if (jiffies - reset_start_time > 2) {
-			netdev_err(dev, "ne2k_pci_reset_8390() did not complete.\n");
+			netdev_err(dev, "%s did not complete.\n", __func__);
 			break;
 		}
-	outb(ENISR_RESET, NE_BASE + EN0_ISR);	/* Ack intr. */
+	/* Ack intr. */
+	outb(ENISR_RESET, NE_BASE + EN0_ISR);
 }
 
 /* Grab the 8390 specific header. Similar to the block_input routine, but
-   we don't need to be concerned with ring wrap as the header will be at
-   the start of a page, so we optimize accordingly. */
+ * we don't need to be concerned with ring wrap as the header will be at
+ * the start of a page, so we optimize accordingly.
+ */
 
-static void ne2k_pci_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page)
+static void ne2k_pci_get_8390_hdr(struct net_device *dev,
+				  struct e8390_pkt_hdr *hdr, int ring_page)
 {
 
 	long nic_base = dev->base_addr;
 
-	/* This *shouldn't* happen. If it does, it's the last thing you'll see */
+	/* This *shouldn't* happen. If it does, it's the last thing you'll see
+	 */
 	if (ei_status.dmaing) {
-		netdev_err(dev, "DMAing conflict in ne2k_pci_get_8390_hdr "
-			   "[DMAstat:%d][irqlock:%d].\n",
-			   ei_status.dmaing, ei_status.irqlock);
+		netdev_err(dev, "DMAing conflict in %s [DMAstat:%d][irqlock:%d].\n",
+			   __func__, ei_status.dmaing, ei_status.irqlock);
 		return;
 	}
 
 	ei_status.dmaing |= 0x01;
-	outb(E8390_NODMA+E8390_PAGE0+E8390_START, nic_base+ NE_CMD);
+	outb(E8390_NODMA + E8390_PAGE0 + E8390_START, nic_base + NE_CMD);
 	outb(sizeof(struct e8390_pkt_hdr), nic_base + EN0_RCNTLO);
 	outb(0, nic_base + EN0_RCNTHI);
 	outb(0, nic_base + EN0_RSARLO);		/* On page boundary */
@@ -499,20 +516,22 @@ static void ne2k_pci_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *
 	outb(E8390_RREAD+E8390_START, nic_base + NE_CMD);
 
 	if (ei_status.ne2k_flags & ONLY_16BIT_IO) {
-		insw(NE_BASE + NE_DATAPORT, hdr, sizeof(struct e8390_pkt_hdr)>>1);
+		insw(NE_BASE + NE_DATAPORT, hdr,
+		     sizeof(struct e8390_pkt_hdr) >> 1);
 	} else {
-		*(u32*)hdr = le32_to_cpu(inl(NE_BASE + NE_DATAPORT));
+		*(u32 *)hdr = le32_to_cpu(inl(NE_BASE + NE_DATAPORT));
 		le16_to_cpus(&hdr->count);
 	}
-
-	outb(ENISR_RDC, nic_base + EN0_ISR);	/* Ack intr. */
+	/* Ack intr. */
+	outb(ENISR_RDC, nic_base + EN0_ISR);
 	ei_status.dmaing &= ~0x01;
 }
 
 /* Block input and output, similar to the Crynwr packet driver.  If you
-   are porting to a new ethercard, look at the packet driver source for hints.
-   The NEx000 doesn't share the on-board packet memory -- you have to put
-   the packet out through the "remote DMA" dataport using outb. */
+ *are porting to a new ethercard, look at the packet driver source for hints.
+ *The NEx000 doesn't share the on-board packet memory -- you have to put
+ *the packet out through the "remote DMA" dataport using outb.
+ */
 
 static void ne2k_pci_block_input(struct net_device *dev, int count,
 				 struct sk_buff *skb, int ring_offset)
@@ -520,30 +539,30 @@ static void ne2k_pci_block_input(struct net_device *dev, int count,
 	long nic_base = dev->base_addr;
 	char *buf = skb->data;
 
-	/* This *shouldn't* happen. If it does, it's the last thing you'll see */
+	/* This *shouldn't* happen.
+	 * If it does, it's the last thing you'll see.
+	 */
 	if (ei_status.dmaing) {
-		netdev_err(dev, "DMAing conflict in ne2k_pci_block_input "
-			   "[DMAstat:%d][irqlock:%d].\n",
-			   ei_status.dmaing, ei_status.irqlock);
+		netdev_err(dev, "DMAing conflict in %s [DMAstat:%d][irqlock:%d]\n",
+			   __func__, ei_status.dmaing, ei_status.irqlock);
 		return;
 	}
 	ei_status.dmaing |= 0x01;
 	if (ei_status.ne2k_flags & ONLY_32BIT_IO)
 		count = (count + 3) & 0xFFFC;
-	outb(E8390_NODMA+E8390_PAGE0+E8390_START, nic_base+ NE_CMD);
+	outb(E8390_NODMA + E8390_PAGE0 + E8390_START, nic_base + NE_CMD);
 	outb(count & 0xff, nic_base + EN0_RCNTLO);
 	outb(count >> 8, nic_base + EN0_RCNTHI);
 	outb(ring_offset & 0xff, nic_base + EN0_RSARLO);
 	outb(ring_offset >> 8, nic_base + EN0_RSARHI);
-	outb(E8390_RREAD+E8390_START, nic_base + NE_CMD);
+	outb(E8390_RREAD + E8390_START, nic_base + NE_CMD);
 
 	if (ei_status.ne2k_flags & ONLY_16BIT_IO) {
-		insw(NE_BASE + NE_DATAPORT,buf,count>>1);
-		if (count & 0x01) {
+		insw(NE_BASE + NE_DATAPORT, buf, count >> 1);
+		if (count & 0x01)
 			buf[count-1] = inb(NE_BASE + NE_DATAPORT);
-		}
 	} else {
-		insl(NE_BASE + NE_DATAPORT, buf, count>>2);
+		insl(NE_BASE + NE_DATAPORT, buf, count >> 2);
 		if (count & 3) {
 			buf += count & ~3;
 			if (count & 2) {
@@ -556,30 +575,32 @@ static void ne2k_pci_block_input(struct net_device *dev, int count,
 				*buf = inb(NE_BASE + NE_DATAPORT);
 		}
 	}
-
-	outb(ENISR_RDC, nic_base + EN0_ISR);	/* Ack intr. */
+	/* Ack intr. */
+	outb(ENISR_RDC, nic_base + EN0_ISR);
 	ei_status.dmaing &= ~0x01;
 }
 
 static void ne2k_pci_block_output(struct net_device *dev, int count,
-				  const unsigned char *buf, const int start_page)
+		const unsigned char *buf, const int start_page)
 {
 	long nic_base = NE_BASE;
 	unsigned long dma_start;
 
 	/* On little-endian it's always safe to round the count up for
-	   word writes. */
+	 * word writes.
+	 */
 	if (ei_status.ne2k_flags & ONLY_32BIT_IO)
 		count = (count + 3) & 0xFFFC;
 	else
 		if (count & 0x01)
 			count++;
 
-	/* This *shouldn't* happen. If it does, it's the last thing you'll see */
+	/* This *shouldn't* happen.
+	 * If it does, it's the last thing you'll see.
+	 */
 	if (ei_status.dmaing) {
-		netdev_err(dev, "DMAing conflict in ne2k_pci_block_output."
-			   "[DMAstat:%d][irqlock:%d]\n",
-			   ei_status.dmaing, ei_status.irqlock);
+		netdev_err(dev, "DMAing conflict in %s [DMAstat:%d][irqlock:%d]\n",
+			   __func__, ei_status.dmaing, ei_status.irqlock);
 		return;
 	}
 	ei_status.dmaing |= 0x01;
@@ -588,9 +609,10 @@ static void ne2k_pci_block_output(struct net_device *dev, int count,
 
 #ifdef NE8390_RW_BUGFIX
 	/* Handle the read-before-write bug the same way as the
-	   Crynwr packet driver -- the NatSemi method doesn't work.
-	   Actually this doesn't always work either, but if you have
-	   problems with your NEx000 this is better than nothing! */
+	 * Crynwr packet driver -- the NatSemi method doesn't work.
+	 * Actually this doesn't always work either, but if you have
+	 * problems with your NEx000 this is better than nothing!
+	 */
 	outb(0x42, nic_base + EN0_RCNTLO);
 	outb(0x00, nic_base + EN0_RCNTHI);
 	outb(0x42, nic_base + EN0_RSARLO);
@@ -599,16 +621,16 @@ static void ne2k_pci_block_output(struct net_device *dev, int count,
 #endif
 	outb(ENISR_RDC, nic_base + EN0_ISR);
 
-   /* Now the normal output. */
+	/* Now the normal output. */
 	outb(count & 0xff, nic_base + EN0_RCNTLO);
 	outb(count >> 8,   nic_base + EN0_RCNTHI);
 	outb(0x00, nic_base + EN0_RSARLO);
 	outb(start_page, nic_base + EN0_RSARHI);
 	outb(E8390_RWRITE+E8390_START, nic_base + NE_CMD);
 	if (ei_status.ne2k_flags & ONLY_16BIT_IO) {
-		outsw(NE_BASE + NE_DATAPORT, buf, count>>1);
+		outsw(NE_BASE + NE_DATAPORT, buf, count >> 1);
 	} else {
-		outsl(NE_BASE + NE_DATAPORT, buf, count>>2);
+		outsl(NE_BASE + NE_DATAPORT, buf, count >> 2);
 		if (count & 3) {
 			buf += count & ~3;
 			if (count & 2) {
@@ -623,14 +645,15 @@ static void ne2k_pci_block_output(struct net_device *dev, int count,
 	dma_start = jiffies;
 
 	while ((inb(nic_base + EN0_ISR) & ENISR_RDC) == 0)
-		if (jiffies - dma_start > 2) {			/* Avoid clock roll-over. */
+		/* Avoid clock roll-over. */
+		if (jiffies - dma_start > 2) {
 			netdev_warn(dev, "timeout waiting for Tx RDC.\n");
 			ne2k_pci_reset_8390(dev);
-			NS8390_init(dev,1);
+			NS8390_init(dev, 1);
 			break;
 		}
-
-	outb(ENISR_RDC, nic_base + EN0_ISR);	/* Ack intr. */
+	/* Ack intr. */
+	outb(ENISR_RDC, nic_base + EN0_ISR);
 	ei_status.dmaing &= ~0x01;
 }
 
@@ -640,9 +663,9 @@ static void ne2k_pci_get_drvinfo(struct net_device *dev,
 	struct ei_device *ei = netdev_priv(dev);
 	struct pci_dev *pci_dev = (struct pci_dev *) ei->priv;
 
-	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
-	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
-	strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->version, DRV_VERSION, sizeof(info->version));
+	strscpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
 }
 
 static u32 ne2k_pci_get_msglevel(struct net_device *dev)
@@ -677,9 +700,9 @@ static void ne2k_pci_remove_one(struct pci_dev *pdev)
 }
 
 #ifdef CONFIG_PM
-static int ne2k_pci_suspend (struct pci_dev *pdev, pm_message_t state)
+static int ne2k_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 {
-	struct net_device *dev = pci_get_drvdata (pdev);
+	struct net_device *dev = pci_get_drvdata(pdev);
 
 	netif_device_detach(dev);
 	pci_save_state(pdev);
@@ -689,9 +712,9 @@ static int ne2k_pci_suspend (struct pci_dev *pdev, pm_message_t state)
 	return 0;
 }
 
-static int ne2k_pci_resume (struct pci_dev *pdev)
+static int ne2k_pci_resume(struct pci_dev *pdev)
 {
-	struct net_device *dev = pci_get_drvdata (pdev);
+	struct net_device *dev = pci_get_drvdata(pdev);
 	int rc;
 
 	pci_set_power_state(pdev, PCI_D0);
@@ -718,24 +741,20 @@ static struct pci_driver ne2k_driver = {
 #ifdef CONFIG_PM
 	.suspend	= ne2k_pci_suspend,
 	.resume		= ne2k_pci_resume,
-#endif /* CONFIG_PM */
+#endif
 
 };
 
 
 static int __init ne2k_pci_init(void)
 {
-/* when a module, this is printed whether or not devices are found in probe */
-#ifdef MODULE
-	printk(version);
-#endif
 	return pci_register_driver(&ne2k_driver);
 }
 
 
 static void __exit ne2k_pci_cleanup(void)
 {
-	pci_unregister_driver (&ne2k_driver);
+	pci_unregister_driver(&ne2k_driver);
 }
 
 module_init(ne2k_pci_init);
-- 
cgit v1.2.3


From 7cf4eda481b235cbc7c210715cce19fde3d23d55 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 27 May 2020 09:15:55 +0100
Subject: mlxsw: spectrum_router: remove redundant initialization of pointer
 br_dev

The pointer br_dev is being initialized with a value that is never read
and is being updated with a new value later on. The initialization
is redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index c939b3596566..770de0222e7b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -7574,7 +7574,7 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 			  struct netlink_ext_ack *extack)
 {
-	struct net_device *br_dev = rif->dev;
+	struct net_device *br_dev;
 	u16 vid;
 	int err;
 
-- 
cgit v1.2.3


From f96e9641e92b54de27b93d1af03d74b8304ce00a Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 27 May 2020 11:24:04 +0200
Subject: net: ethernet: mtk-star-emac: fix error path in RX handling

The dma_addr field in desc_data must not be overwritten until after the
new skb is mapped. Currently we do replace it with uninitialized value
in error path. This change fixes it by moving the assignment before the
label to which we jump after mapping or allocation errors.

Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com> # build
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index b74349cede28..72bb624a6a68 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1308,6 +1308,8 @@ static int mtk_star_receive_packet(struct mtk_star_priv *priv)
 		goto push_new_skb;
 	}
 
+	desc_data.dma_addr = new_dma_addr;
+
 	/* We can't fail anymore at this point: it's safe to unmap the skb. */
 	mtk_star_dma_unmap_rx(priv, &desc_data);
 
@@ -1318,7 +1320,6 @@ static int mtk_star_receive_packet(struct mtk_star_priv *priv)
 	netif_receive_skb(desc_data.skb);
 
 push_new_skb:
-	desc_data.dma_addr = new_dma_addr;
 	desc_data.len = skb_tailroom(new_skb);
 	desc_data.skb = new_skb;
 
-- 
cgit v1.2.3


From f99c0646ef83076dba88255c42482d1b4325f890 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 27 May 2020 15:34:45 +0200
Subject: mtk-star-emac: mark PM functions as __maybe_unused

Without CONFIG_PM, the compiler warns about two unused functions:

drivers/net/ethernet/mediatek/mtk_star_emac.c:1472:12: error: unused function 'mtk_star_suspend' [-Werror,-Wunused-function]
drivers/net/ethernet/mediatek/mtk_star_emac.c:1488:12: error: unused function 'mtk_star_resume' [-Werror,-Wunused-function]

Mark these as __maybe_unused.

Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 72bb624a6a68..8596ca0e60eb 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1468,7 +1468,7 @@ out_put_node:
 	return ret;
 }
 
-static int mtk_star_suspend(struct device *dev)
+static __maybe_unused int mtk_star_suspend(struct device *dev)
 {
 	struct mtk_star_priv *priv;
 	struct net_device *ndev;
@@ -1484,7 +1484,7 @@ static int mtk_star_suspend(struct device *dev)
 	return 0;
 }
 
-static int mtk_star_resume(struct device *dev)
+static __maybe_unused int mtk_star_resume(struct device *dev)
 {
 	struct mtk_star_priv *priv;
 	struct net_device *ndev;
-- 
cgit v1.2.3


From 7ff4f3f315db361e35c1d61a6fdbfddbe345b633 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 26 May 2020 17:01:48 +0200
Subject: net: mscc: use the PHY MII ioctl interface when possible

Allow ioctl to be implemented by the PHY, when a PHY is attached to the
Ocelot switch. In case the ioctl is a request to set or get the hardware
timestamp, use the Ocelot switch implementation for now.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index e621c4c3ee86..2151c08a57c7 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1204,18 +1204,16 @@ static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->chip_port;
 
-	/* The function is only used for PTP operations for now */
-	if (!ocelot->ptp)
-		return -EOPNOTSUPP;
-
-	switch (cmd) {
-	case SIOCSHWTSTAMP:
-		return ocelot_hwstamp_set(ocelot, port, ifr);
-	case SIOCGHWTSTAMP:
-		return ocelot_hwstamp_get(ocelot, port, ifr);
-	default:
-		return -EOPNOTSUPP;
+	if (ocelot->ptp) {
+		switch (cmd) {
+		case SIOCSHWTSTAMP:
+			return ocelot_hwstamp_set(ocelot, port, ifr);
+		case SIOCGHWTSTAMP:
+			return ocelot_hwstamp_get(ocelot, port, ifr);
+		}
 	}
+
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
 }
 
 static const struct net_device_ops ocelot_port_netdev_ops = {
-- 
cgit v1.2.3


From b2e118f638fb8984e430624a8cf27483cc23cf8d Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 26 May 2020 17:01:49 +0200
Subject: net: mscc: allow offloading timestamping operations to the PHY

This patch adds support for offloading timestamping operations not only
to the Ocelot switch (as already supported) but to compatible PHYs.
When both the PHY and the Ocelot switch support timestamping operations,
the PHY implementation is chosen as the timestamp will happen closer to
the medium.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c       | 5 ++++-
 drivers/net/ethernet/mscc/ocelot_board.c | 3 ++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 2151c08a57c7..9cfe1fd98c30 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1204,7 +1204,10 @@ static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->chip_port;
 
-	if (ocelot->ptp) {
+	/* If the attached PHY device isn't capable of timestamping operations,
+	 * use our own (when possible).
+	 */
+	if (!phy_has_hwtstamp(dev->phydev) && ocelot->ptp) {
 		switch (cmd) {
 		case SIOCSHWTSTAMP:
 			return ocelot_hwstamp_set(ocelot, port, ifr);
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 67a8d61c926a..4a15d2ff8b70 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -189,7 +189,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 			skb->offload_fwd_mark = 1;
 
 		skb->protocol = eth_type_trans(skb, dev);
-		netif_rx(skb);
+		if (!skb_defer_rx_timestamp(skb))
+			netif_rx(skb);
 		dev->stats.rx_bytes += len;
 		dev->stats.rx_packets++;
 	} while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp));
-- 
cgit v1.2.3


From 4cd5beaa89a95b331e5586d55469f5569faa18f6 Mon Sep 17 00:00:00 2001
From: Guangbin Huang <huangguangbin2@huawei.com>
Date: Wed, 27 May 2020 08:59:14 +0800
Subject: net: hns3: add a resetting check in
 hclgevf_init_nic_client_instance()

To prevent from initializing VF NIC client in reset handling state,
this patch adds resetting check in hclgevf_init_nic_client_instance().

Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 32341dcaa6c1..59fcb80671c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2713,6 +2713,7 @@ static int hclgevf_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
 					    struct hnae3_client *client)
 {
 	struct hclgevf_dev *hdev = ae_dev->priv;
+	int rst_cnt = hdev->rst_stats.rst_cnt;
 	int ret;
 
 	ret = client->ops->init_instance(&hdev->nic);
@@ -2720,6 +2721,14 @@ static int hclgevf_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
 		return ret;
 
 	set_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state);
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) ||
+	    rst_cnt != hdev->rst_stats.rst_cnt) {
+		clear_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state);
+
+		client->ops->uninit_instance(&hdev->nic, 0);
+		return -EBUSY;
+	}
+
 	hnae3_set_client_init_flag(client, ae_dev, 1);
 
 	if (netif_msg_drv(&hdev->nic))
-- 
cgit v1.2.3


From 60c800c64d8fdd2fc5b8c62686fb08c6a6fb1045 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Wed, 27 May 2020 08:59:15 +0800
Subject: net: hns3: change the order of reinitializing RoCE and NIC client
 during reset

The HNS RDMA driver will support VF device later, whose
re-initialization should be done after PF's. This patch
changes the order of hclge_reset_prepare_up() and
hclge_notify_roce_client(), so that PF's RoCE client
will be reinitialized before VF's.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b796d3fb5b0b..6e1e2cf385c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3770,11 +3770,6 @@ static int hclge_reset_rebuild(struct hclge_dev *hdev)
 
 	hclge_clear_reset_cause(hdev);
 
-	ret = hclge_reset_prepare_up(hdev);
-	if (ret)
-		return ret;
-
-
 	ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
 	/* ignore RoCE notify error if it fails HCLGE_RESET_MAX_FAIL_CNT - 1
 	 * times
@@ -3783,6 +3778,10 @@ static int hclge_reset_rebuild(struct hclge_dev *hdev)
 	    hdev->rst_stats.reset_fail_cnt < HCLGE_RESET_MAX_FAIL_CNT - 1)
 		return ret;
 
+	ret = hclge_reset_prepare_up(hdev);
+	if (ret)
+		return ret;
+
 	rtnl_lock();
 	ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 	rtnl_unlock();
-- 
cgit v1.2.3


From 01952206e17ee34b5fe32f211619ac59ec043990 Mon Sep 17 00:00:00 2001
From: Yufeng Mo <moyufeng@huawei.com>
Date: Wed, 27 May 2020 08:59:16 +0800
Subject: net: hns3: remove unnecessary MAC enable in app loopback

Packets will not pass through MAC during app loopback.
Therefore, it is meaningless to enable MAC while doing
app loopback. This patch removes this unnecessary action.

Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 6e1e2cf385c8..7c9f2ba1f272 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6583,8 +6583,6 @@ static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en)
 	/* 2 Then setup the loopback flag */
 	loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
 	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, en ? 1 : 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, en ? 1 : 0);
 
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
-- 
cgit v1.2.3


From 6f45a9bdd2aee6cc1e4223fdc9e4f548a3f54595 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 27 May 2020 08:59:17 +0800
Subject: net: hns3: add a print for initializing CMDQ when reset pending

When initializing CMDQ fails because of reset pending,
there is no hint for debugging, so adds a log for it.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 7f509eff562e..64a1d0bdd7d1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -426,6 +426,9 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	 * reset may happen when lower level reset is being processed.
 	 */
 	if ((hclge_is_reset_pending(hdev))) {
+		dev_err(&hdev->pdev->dev,
+			"failed to init cmd since reset %#lx pending\n",
+			hdev->reset_pending);
 		ret = -EBUSY;
 		goto err_cmd_init;
 	}
-- 
cgit v1.2.3


From 22bef5e78f1193b664f59834361704cb22f9d5d7 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:36:38 -0700
Subject: ice: fix signed vs unsigned comparisons

Fix the remaining signed vs unsigned issues, which appear
when compiling with -Werror=sign-compare.

Many of these are because there is an external interface that is passing
an int to us (which we can't change) but that we (rightfully) store
and compare against as an unsigned in our data structures.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 4 ++--
 drivers/net/ethernet/intel/ice/ice_main.c | 8 ++++----
 drivers/net/ethernet/intel/ice/ice_txrx.h | 7 ++++---
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 94d833b4e745..9452c0eb70b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -13,7 +13,7 @@
  */
 static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
 {
-	int offset, i;
+	unsigned int offset, i;
 
 	mutex_lock(qs_cfg->qs_mutex);
 	offset = bitmap_find_next_zero_area(qs_cfg->pf_map, qs_cfg->pf_map_size,
@@ -39,7 +39,7 @@ static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
  */
 static int __ice_vsi_get_qs_sc(struct ice_qs_cfg *qs_cfg)
 {
-	int i, index = 0;
+	unsigned int i, index = 0;
 
 	mutex_lock(qs_cfg->qs_mutex);
 	for (i = 0; i < qs_cfg->q_count; i++) {
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1c255b27244c..c2da3e1a2e17 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5035,7 +5035,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	struct ice_pf *pf = vsi->back;
 	u8 count = 0;
 
-	if (new_mtu == netdev->mtu) {
+	if (new_mtu == (int)netdev->mtu) {
 		netdev_warn(netdev, "MTU is already %u\n", netdev->mtu);
 		return 0;
 	}
@@ -5050,11 +5050,11 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		}
 	}
 
-	if (new_mtu < netdev->min_mtu) {
+	if (new_mtu < (int)netdev->min_mtu) {
 		netdev_err(netdev, "new MTU invalid. min_mtu is %d\n",
 			   netdev->min_mtu);
 		return -EINVAL;
-	} else if (new_mtu > netdev->max_mtu) {
+	} else if (new_mtu > (int)netdev->max_mtu) {
 		netdev_err(netdev, "new MTU invalid. max_mtu is %d\n",
 			   netdev->min_mtu);
 		return -EINVAL;
@@ -5075,7 +5075,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EBUSY;
 	}
 
-	netdev->mtu = new_mtu;
+	netdev->mtu = (unsigned int)new_mtu;
 
 	/* if VSI is up, bring it down and then back up */
 	if (!test_and_set_bit(__ICE_DOWN, vsi->state)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index cf21b4fe928a..e70c4619edc3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -38,7 +38,8 @@
  */
 #if (PAGE_SIZE < 8192)
 #define ICE_2K_TOO_SMALL_WITH_PADDING \
-((NET_SKB_PAD + ICE_RXBUF_1536) > SKB_WITH_OVERHEAD(ICE_RXBUF_2048))
+	((unsigned int)(NET_SKB_PAD + ICE_RXBUF_1536) > \
+			SKB_WITH_OVERHEAD(ICE_RXBUF_2048))
 
 /**
  * ice_compute_pad - compute the padding
@@ -107,8 +108,8 @@ static inline int ice_skb_pad(void)
 #define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \
 		     ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR)
 #define ICE_DESC_UNUSED(R)	\
-	((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
-	(R)->next_to_clean - (R)->next_to_use - 1)
+	(u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+	      (R)->next_to_clean - (R)->next_to_use - 1)
 
 #define ICE_TX_FLAGS_TSO	BIT(0)
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
-- 
cgit v1.2.3


From f0cbbb9c6e06532fc839770de20e1e94e0d999dd Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:36:39 -0700
Subject: ice: remove unused macro

The driver had an unused define that can be removed.  Found by
compiler -Werror=unused-macros check.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_nl.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 93cf70d06fe5..87f91b750d59 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -7,8 +7,6 @@
 #include "ice_dcb_nl.h"
 #include <net/dcbnl.h>
 
-#define ICE_APP_PROT_ID_ROCE	0x8915
-
 /**
  * ice_dcbnl_devreset - perform enough of a ifdown/ifup to sync DCBNL info
  * @netdev: device associated with interface that needs reset
-- 
cgit v1.2.3


From bf8987df8aa57da884276b07a64307eac577eaaf Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Fri, 15 May 2020 17:36:40 -0700
Subject: ice: set VF default LAN address

Remove is_zero_ether_add() check when setting the VF default LAN address.
This check assumed that the address had been delete and zeroed before
calling ice_vc_add_mac_addr(). Now the default LAN address will be set
to the last unicast MAC address added by the VF.

The default LAN address is reported by the PF via ndo_get_vf_config.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 9b09a111321c..efd54299a220 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -2862,9 +2862,11 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr)
 		return -EIO;
 	}
 
-	/* only set dflt_lan_addr once */
-	if (is_zero_ether_addr(vf->dflt_lan_addr.addr) &&
-	    is_unicast_ether_addr(mac_addr))
+	/* Set the default LAN address to the latest unicast MAC address added
+	 * by the VF. The default LAN address is reported by the PF via
+	 * ndo_get_vf_config.
+	 */
+	if (is_unicast_ether_addr(mac_addr))
 		ether_addr_copy(vf->dflt_lan_addr.addr, mac_addr);
 
 	vf->num_mac++;
-- 
cgit v1.2.3


From 5df42c8267418bfb8da54cc4772b397ea4c88aea Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:36:41 -0700
Subject: ice: fix MAC write command

The manage MAC write command was implemented in an overly complex way
that actually didn't work, as it wasn't symmetric to the manage MAC
read command, and was feeding bytes out of order to the firmware. Fix
the implementation by just using a simple array to represent the MAC
address when it is being written via firmware command.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 10 ++++------
 drivers/net/ethernet/intel/ice/ice_common.c     |  5 +----
 2 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 586d69491268..f04c338fb6e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -156,13 +156,11 @@ struct ice_aqc_manage_mac_write {
 #define ICE_AQC_MAN_MAC_WR_MC_MAG_EN		BIT(0)
 #define ICE_AQC_MAN_MAC_WR_WOL_LAA_PFR_KEEP	BIT(1)
 #define ICE_AQC_MAN_MAC_WR_S		6
-#define ICE_AQC_MAN_MAC_WR_M		(3 << ICE_AQC_MAN_MAC_WR_S)
+#define ICE_AQC_MAN_MAC_WR_M		ICE_M(3, ICE_AQC_MAN_MAC_WR_S)
 #define ICE_AQC_MAN_MAC_UPDATE_LAA	0
-#define ICE_AQC_MAN_MAC_UPDATE_LAA_WOL	(BIT(0) << ICE_AQC_MAN_MAC_WR_S)
-	/* High 16 bits of MAC address in big endian order */
-	__be16 sah;
-	/* Low 32 bits of MAC address in big endian order */
-	__be32 sal;
+#define ICE_AQC_MAN_MAC_UPDATE_LAA_WOL	BIT(ICE_AQC_MAN_MAC_WR_S)
+	/* byte stream in network order */
+	u8 mac_addr[ETH_ALEN];
 	__le32 addr_high;
 	__le32 addr_low;
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 0a0b00fffaf7..5da369ae33e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1994,10 +1994,7 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_manage_mac_write);
 
 	cmd->flags = flags;
-
-	/* Prep values for flags, sah, sal */
-	cmd->sah = htons(*((const u16 *)mac_addr));
-	cmd->sal = htonl(*((const u32 *)(mac_addr + 2)));
+	ether_addr_copy(cmd->mac_addr, mac_addr);
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
 }
-- 
cgit v1.2.3


From 1aaef2bc4e0a5ce9e4dd86359e6a0bf52c6aa64f Mon Sep 17 00:00:00 2001
From: Surabhi Boob <surabhi.boob@intel.com>
Date: Fri, 15 May 2020 17:36:42 -0700
Subject: ice: Fix memory leak

Handle memory leak on filter management initialization failure.

Signed-off-by: Surabhi Boob <surabhi.boob@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 5da369ae33e0..ee62cfa3a69e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -387,6 +387,7 @@ ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd)
 static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 {
 	struct ice_switch_info *sw;
+	enum ice_status status;
 
 	hw->switch_info = devm_kzalloc(ice_hw_to_dev(hw),
 				       sizeof(*hw->switch_info), GFP_KERNEL);
@@ -397,7 +398,12 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 
 	INIT_LIST_HEAD(&sw->vsi_list_map_head);
 
-	return ice_init_def_sw_recp(hw);
+	status = ice_init_def_sw_recp(hw);
+	if (status) {
+		devm_kfree(ice_hw_to_dev(hw), hw->switch_info);
+		return status;
+	}
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 68d270783742783f96e89ef92ac24ab3c7fb1d31 Mon Sep 17 00:00:00 2001
From: Surabhi Boob <surabhi.boob@intel.com>
Date: Fri, 15 May 2020 17:36:43 -0700
Subject: ice: Fix for memory leaks and modify ICE_FREE_CQ_BUFS

Handle memory leaks during control queue initialization and
buffer allocation failures. The macro ICE_FREE_CQ_BUFS is modified to
re-use for this fix.

Signed-off-by: Surabhi Boob <surabhi.boob@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 49 +++++++++++++++------------
 1 file changed, 28 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 9a865962296d..62c2c1e621d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -199,7 +199,9 @@ unwind_alloc_rq_bufs:
 		cq->rq.r.rq_bi[i].pa = 0;
 		cq->rq.r.rq_bi[i].size = 0;
 	}
+	cq->rq.r.rq_bi = NULL;
 	devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head);
+	cq->rq.dma_head = NULL;
 
 	return ICE_ERR_NO_MEMORY;
 }
@@ -245,7 +247,9 @@ unwind_alloc_sq_bufs:
 		cq->sq.r.sq_bi[i].pa = 0;
 		cq->sq.r.sq_bi[i].size = 0;
 	}
+	cq->sq.r.sq_bi = NULL;
 	devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head);
+	cq->sq.dma_head = NULL;
 
 	return ICE_ERR_NO_MEMORY;
 }
@@ -304,6 +308,28 @@ ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	return 0;
 }
 
+#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
+do {									\
+	int i;								\
+	/* free descriptors */						\
+	if ((qi)->ring.r.ring##_bi)					\
+		for (i = 0; i < (qi)->num_##ring##_entries; i++)	\
+			if ((qi)->ring.r.ring##_bi[i].pa) {		\
+				dmam_free_coherent(ice_hw_to_dev(hw),	\
+					(qi)->ring.r.ring##_bi[i].size,	\
+					(qi)->ring.r.ring##_bi[i].va,	\
+					(qi)->ring.r.ring##_bi[i].pa);	\
+					(qi)->ring.r.ring##_bi[i].va = NULL;\
+					(qi)->ring.r.ring##_bi[i].pa = 0;\
+					(qi)->ring.r.ring##_bi[i].size = 0;\
+		}							\
+	/* free the buffer info list */					\
+	if ((qi)->ring.cmd_buf)						\
+		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
+	/* free DMA head */						\
+	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
+} while (0)
+
 /**
  * ice_init_sq - main initialization routine for Control ATQ
  * @hw: pointer to the hardware structure
@@ -357,6 +383,7 @@ static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
+	ICE_FREE_CQ_BUFS(hw, cq, sq);
 	ice_free_cq_ring(hw, &cq->sq);
 
 init_ctrlq_exit:
@@ -416,33 +443,13 @@ static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
+	ICE_FREE_CQ_BUFS(hw, cq, rq);
 	ice_free_cq_ring(hw, &cq->rq);
 
 init_ctrlq_exit:
 	return ret_code;
 }
 
-#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
-do {									\
-	int i;								\
-	/* free descriptors */						\
-	for (i = 0; i < (qi)->num_##ring##_entries; i++)		\
-		if ((qi)->ring.r.ring##_bi[i].pa) {			\
-			dmam_free_coherent(ice_hw_to_dev(hw),		\
-					   (qi)->ring.r.ring##_bi[i].size,\
-					   (qi)->ring.r.ring##_bi[i].va,\
-					   (qi)->ring.r.ring##_bi[i].pa);\
-			(qi)->ring.r.ring##_bi[i].va = NULL;		\
-			(qi)->ring.r.ring##_bi[i].pa = 0;		\
-			(qi)->ring.r.ring##_bi[i].size = 0;		\
-		}							\
-	/* free the buffer info list */					\
-	if ((qi)->ring.cmd_buf)						\
-		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
-	/* free DMA head */						\
-	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
-} while (0)
-
 /**
  * ice_shutdown_sq - shutdown the Control ATQ
  * @hw: pointer to the hardware structure
-- 
cgit v1.2.3


From 4f1fe43c920b92ac41c34f151fe452d46936b79d Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:36:44 -0700
Subject: ice: Add more Rx errors to netdev's rx_error counter

Currently we are only including illegal_bytes and rx_crc_errors in the
PF netdev's rx_error counter. There are many more causes of Rx errors
that the device supports and reports via Ethtool. Accumulate all Rx
errors in the PF netdev's rx_error counter.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c2da3e1a2e17..93a42ff7496b 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4295,7 +4295,13 @@ void ice_update_vsi_stats(struct ice_vsi *vsi)
 	if (vsi->type == ICE_VSI_PF) {
 		cur_ns->rx_crc_errors = pf->stats.crc_errors;
 		cur_ns->rx_errors = pf->stats.crc_errors +
-				    pf->stats.illegal_bytes;
+				    pf->stats.illegal_bytes +
+				    pf->stats.rx_len_errors +
+				    pf->stats.rx_undersize +
+				    pf->hw_csum_rx_error +
+				    pf->stats.rx_jabber +
+				    pf->stats.rx_fragments +
+				    pf->stats.rx_oversize;
 		cur_ns->rx_length_errors = pf->stats.rx_len_errors;
 		/* record drops from the port level */
 		cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
-- 
cgit v1.2.3


From 1960827570c7ed83fb0725debf856b06f46e1a77 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:42:13 -0700
Subject: ice: Don't allow VLAN stripping change when pvid set

Currently, if the PVID is set in the VLAN handling section of the VSI
context the driver still allows VLAN stripping to be enabled/disabled.
VLAN stripping should only be modifiable when the PVID is not set. Fix
this by preventing VLAN stripping modification when PVID is set.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index f81bd4c30bbc..89962c14e31f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1812,6 +1812,12 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 	enum ice_status status;
 	int ret = 0;
 
+	/* do not allow modifying VLAN stripping when a port VLAN is configured
+	 * on this VSI
+	 */
+	if (vsi->info.pvid)
+		return 0;
+
 	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
 	if (!ctxt)
 		return -ENOMEM;
-- 
cgit v1.2.3


From b5c7f857e5c98c21271678992fb2634df38292f5 Mon Sep 17 00:00:00 2001
From: Evan Swanson <evan.swanson@intel.com>
Date: Fri, 15 May 2020 17:42:14 -0700
Subject: ice: Handle critical FW error during admin queue initialization

A race condition between FW and SW can occur between admin queue setup and
the first command sent. A link event may occur and FW attempts to notify a
non-existent queue. FW will set the critical error bit and disable the
queue. When this happens retry queue setup.

Signed-off-by: Evan Swanson <evan.swanson@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c   | 126 ++++++++++++++----------
 drivers/net/ethernet/intel/ice/ice_controlq.h   |   3 +
 drivers/net/ethernet/intel/ice/ice_hw_autogen.h |   2 +
 drivers/net/ethernet/intel/ice/ice_main.c       |   2 +
 drivers/net/ethernet/intel/ice/ice_status.h     |   1 +
 5 files changed, 80 insertions(+), 54 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 62c2c1e621d2..479a74efc536 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -12,6 +12,7 @@ do {								\
 	(qinfo)->sq.bal = prefix##_ATQBAL;			\
 	(qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M;	\
 	(qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M;	\
+	(qinfo)->sq.len_crit_mask = prefix##_ATQLEN_ATQCRIT_M;	\
 	(qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M;		\
 	(qinfo)->rq.head = prefix##_ARQH;			\
 	(qinfo)->rq.tail = prefix##_ARQT;			\
@@ -20,6 +21,7 @@ do {								\
 	(qinfo)->rq.bal = prefix##_ARQBAL;			\
 	(qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M;	\
 	(qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M;	\
+	(qinfo)->rq.len_crit_mask = prefix##_ARQLEN_ARQCRIT_M;	\
 	(qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M;		\
 } while (0)
 
@@ -641,6 +643,50 @@ init_ctrlq_free_sq:
 	return ret_code;
 }
 
+/**
+ * ice_shutdown_ctrlq - shutdown routine for any control queue
+ * @hw: pointer to the hardware structure
+ * @q_type: specific Control queue type
+ *
+ * NOTE: this function does not destroy the control queue locks.
+ */
+static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
+{
+	struct ice_ctl_q_info *cq;
+
+	switch (q_type) {
+	case ICE_CTL_Q_ADMIN:
+		cq = &hw->adminq;
+		if (ice_check_sq_alive(hw, cq))
+			ice_aq_q_shutdown(hw, true);
+		break;
+	case ICE_CTL_Q_MAILBOX:
+		cq = &hw->mailboxq;
+		break;
+	default:
+		return;
+	}
+
+	ice_shutdown_sq(hw, cq);
+	ice_shutdown_rq(hw, cq);
+}
+
+/**
+ * ice_shutdown_all_ctrlq - shutdown routine for all control queues
+ * @hw: pointer to the hardware structure
+ *
+ * NOTE: this function does not destroy the control queue locks. The driver
+ * may call this at runtime to shutdown and later restart control queues, such
+ * as in response to a reset event.
+ */
+void ice_shutdown_all_ctrlq(struct ice_hw *hw)
+{
+	/* Shutdown FW admin queue */
+	ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+	/* Shutdown PF-VF Mailbox */
+	ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
+}
+
 /**
  * ice_init_all_ctrlq - main initialization routine for all control queues
  * @hw: pointer to the hardware structure
@@ -656,17 +702,27 @@ init_ctrlq_free_sq:
  */
 enum ice_status ice_init_all_ctrlq(struct ice_hw *hw)
 {
-	enum ice_status ret_code;
+	enum ice_status status;
+	u32 retry = 0;
 
 	/* Init FW admin queue */
-	ret_code = ice_init_ctrlq(hw, ICE_CTL_Q_ADMIN);
-	if (ret_code)
-		return ret_code;
+	do {
+		status = ice_init_ctrlq(hw, ICE_CTL_Q_ADMIN);
+		if (status)
+			return status;
 
-	ret_code = ice_init_check_adminq(hw);
-	if (ret_code)
-		return ret_code;
+		status = ice_init_check_adminq(hw);
+		if (status != ICE_ERR_AQ_FW_CRITICAL)
+			break;
 
+		ice_debug(hw, ICE_DBG_AQ_MSG,
+			  "Retry Admin Queue init due to FW critical error\n");
+		ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
+		msleep(ICE_CTL_Q_ADMIN_INIT_MSEC);
+	} while (retry++ < ICE_CTL_Q_ADMIN_INIT_TIMEOUT);
+
+	if (status)
+		return status;
 	/* Init Mailbox queue */
 	return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX);
 }
@@ -707,50 +763,6 @@ enum ice_status ice_create_all_ctrlq(struct ice_hw *hw)
 	return ice_init_all_ctrlq(hw);
 }
 
-/**
- * ice_shutdown_ctrlq - shutdown routine for any control queue
- * @hw: pointer to the hardware structure
- * @q_type: specific Control queue type
- *
- * NOTE: this function does not destroy the control queue locks.
- */
-static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
-{
-	struct ice_ctl_q_info *cq;
-
-	switch (q_type) {
-	case ICE_CTL_Q_ADMIN:
-		cq = &hw->adminq;
-		if (ice_check_sq_alive(hw, cq))
-			ice_aq_q_shutdown(hw, true);
-		break;
-	case ICE_CTL_Q_MAILBOX:
-		cq = &hw->mailboxq;
-		break;
-	default:
-		return;
-	}
-
-	ice_shutdown_sq(hw, cq);
-	ice_shutdown_rq(hw, cq);
-}
-
-/**
- * ice_shutdown_all_ctrlq - shutdown routine for all control queues
- * @hw: pointer to the hardware structure
- *
- * NOTE: this function does not destroy the control queue locks. The driver
- * may call this at runtime to shutdown and later restart control queues, such
- * as in response to a reset event.
- */
-void ice_shutdown_all_ctrlq(struct ice_hw *hw)
-{
-	/* Shutdown FW admin queue */
-	ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN);
-	/* Shutdown PF-VF Mailbox */
-	ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX);
-}
-
 /**
  * ice_destroy_ctrlq_locks - Destroy locks for a control queue
  * @cq: pointer to the control queue
@@ -1049,9 +1061,15 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 
 	/* update the error if time out occurred */
 	if (!cmd_completed) {
-		ice_debug(hw, ICE_DBG_AQ_MSG,
-			  "Control Send Queue Writeback timeout.\n");
-		status = ICE_ERR_AQ_TIMEOUT;
+		if (rd32(hw, cq->rq.len) & cq->rq.len_crit_mask ||
+		    rd32(hw, cq->sq.len) & cq->sq.len_crit_mask) {
+			ice_debug(hw, ICE_DBG_AQ_MSG, "Critical FW error.\n");
+			status = ICE_ERR_AQ_FW_CRITICAL;
+		} else {
+			ice_debug(hw, ICE_DBG_AQ_MSG,
+				  "Control Send Queue Writeback timeout.\n");
+			status = ICE_ERR_AQ_TIMEOUT;
+		}
 	}
 
 sq_send_command_error:
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index bf0ebe6149e8..faaa08e8171b 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -34,6 +34,8 @@ enum ice_ctl_q {
 /* Control Queue timeout settings - max delay 250ms */
 #define ICE_CTL_Q_SQ_CMD_TIMEOUT	2500  /* Count 2500 times */
 #define ICE_CTL_Q_SQ_CMD_USEC		100   /* Check every 100usec */
+#define ICE_CTL_Q_ADMIN_INIT_TIMEOUT	10    /* Count 10 times */
+#define ICE_CTL_Q_ADMIN_INIT_MSEC	100   /* Check every 100msec */
 
 struct ice_ctl_q_ring {
 	void *dma_head;			/* Virtual address to DMA head */
@@ -59,6 +61,7 @@ struct ice_ctl_q_ring {
 	u32 bal;
 	u32 len_mask;
 	u32 len_ena_mask;
+	u32 len_crit_mask;
 	u32 head_mask;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 2f1c776747a4..1086c9f778b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -39,6 +39,7 @@
 #define PF_MBX_ARQH_ARQH_M			ICE_M(0x3FF, 0)
 #define PF_MBX_ARQLEN				0x0022E480
 #define PF_MBX_ARQLEN_ARQLEN_M			ICE_M(0x3FF, 0)
+#define PF_MBX_ARQLEN_ARQCRIT_M			BIT(30)
 #define PF_MBX_ARQLEN_ARQENABLE_M		BIT(31)
 #define PF_MBX_ARQT				0x0022E580
 #define PF_MBX_ATQBAH				0x0022E180
@@ -47,6 +48,7 @@
 #define PF_MBX_ATQH_ATQH_M			ICE_M(0x3FF, 0)
 #define PF_MBX_ATQLEN				0x0022E200
 #define PF_MBX_ATQLEN_ATQLEN_M			ICE_M(0x3FF, 0)
+#define PF_MBX_ATQLEN_ATQCRIT_M			BIT(30)
 #define PF_MBX_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_MBX_ATQT				0x0022E300
 #define PRTDCB_GENC				0x00083000
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 93a42ff7496b..247e7b186b3c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5207,6 +5207,8 @@ const char *ice_stat_str(enum ice_status stat_err)
 		return "ICE_ERR_AQ_NO_WORK";
 	case ICE_ERR_AQ_EMPTY:
 		return "ICE_ERR_AQ_EMPTY";
+	case ICE_ERR_AQ_FW_CRITICAL:
+		return "ICE_ERR_AQ_FW_CRITICAL";
 	}
 
 	return "ICE_ERR_UNKNOWN";
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index 546a02856d09..4028c6365172 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -37,6 +37,7 @@ enum ice_status {
 	ICE_ERR_AQ_FULL				= -102,
 	ICE_ERR_AQ_NO_WORK			= -103,
 	ICE_ERR_AQ_EMPTY			= -104,
+	ICE_ERR_AQ_FW_CRITICAL			= -105,
 };
 
 #endif /* _ICE_STATUS_H_ */
-- 
cgit v1.2.3


From c8f135c6ee7851ad72bd4d877216950fcbd45fb6 Mon Sep 17 00:00:00 2001
From: Marta Plantykow <marta.a.plantykow@intel.com>
Date: Fri, 15 May 2020 17:42:15 -0700
Subject: ice: Change number of XDP TxQ to 0 when destroying rings

When XDP Tx rings are destroyed the number of XDP Tx queues
is not changing. This patch is changing this number to 0.

Signed-off-by: Marta Plantykow <marta.a.plantykow@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 247e7b186b3c..081fec3131cd 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1899,6 +1899,9 @@ free_qmap:
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
 		max_txqs[i] = vsi->num_txq;
 
+	/* change number of XDP Tx queues to 0 */
+	vsi->num_xdp_txq = 0;
+
 	return ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			       max_txqs);
 }
-- 
cgit v1.2.3


From 49d358e0e746dc24bfb1b1cf98c17064e5177424 Mon Sep 17 00:00:00 2001
From: Marta Plantykow <marta.a.plantykow@intel.com>
Date: Fri, 15 May 2020 17:42:16 -0700
Subject: ice: Add XDP Tx to VSI ring stats

When XDP Tx program is loaded and packets are sent from
interface, VSI statistics are not updated. This patch adds
packets sent on Tx XDP ring to VSI ring stats.

Signed-off-by: Marta Plantykow <marta.a.plantykow@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 42 ++++++++++++++++++++++++-------
 1 file changed, 33 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 081fec3131cd..81c5f0ce5b8f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4219,6 +4219,33 @@ ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes)
 	} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 }
 
+/**
+ * ice_update_vsi_tx_ring_stats - Update VSI Tx ring stats counters
+ * @vsi: the VSI to be updated
+ * @rings: rings to work on
+ * @count: number of rings
+ */
+static void
+ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_ring **rings,
+			     u16 count)
+{
+	struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
+	u16 i;
+
+	for (i = 0; i < count; i++) {
+		struct ice_ring *ring;
+		u64 pkts, bytes;
+
+		ring = READ_ONCE(rings[i]);
+		ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
+		vsi_stats->tx_packets += pkts;
+		vsi_stats->tx_bytes += bytes;
+		vsi->tx_restart += ring->tx_stats.restart_q;
+		vsi->tx_busy += ring->tx_stats.tx_busy;
+		vsi->tx_linearize += ring->tx_stats.tx_linearize;
+	}
+}
+
 /**
  * ice_update_vsi_ring_stats - Update VSI stats counters
  * @vsi: the VSI to be updated
@@ -4246,15 +4273,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 	rcu_read_lock();
 
 	/* update Tx rings counters */
-	ice_for_each_txq(vsi, i) {
-		ring = READ_ONCE(vsi->tx_rings[i]);
-		ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes);
-		vsi_stats->tx_packets += pkts;
-		vsi_stats->tx_bytes += bytes;
-		vsi->tx_restart += ring->tx_stats.restart_q;
-		vsi->tx_busy += ring->tx_stats.tx_busy;
-		vsi->tx_linearize += ring->tx_stats.tx_linearize;
-	}
+	ice_update_vsi_tx_ring_stats(vsi, vsi->tx_rings, vsi->num_txq);
 
 	/* update Rx rings counters */
 	ice_for_each_rxq(vsi, i) {
@@ -4266,6 +4285,11 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 		vsi->rx_page_failed += ring->rx_stats.alloc_page_failed;
 	}
 
+	/* update XDP Tx rings counters */
+	if (ice_is_xdp_ena_vsi(vsi))
+		ice_update_vsi_tx_ring_stats(vsi, vsi->xdp_rings,
+					     vsi->num_xdp_txq);
+
 	rcu_read_unlock();
 }
 
-- 
cgit v1.2.3


From ae15e0ba1b333f391ab0d678abb752cb6a7f2782 Mon Sep 17 00:00:00 2001
From: Marta Plantykow <marta.a.plantykow@intel.com>
Date: Fri, 15 May 2020 17:42:17 -0700
Subject: ice: Change number of XDP Tx queues to match number of Rx queues

In current implementation number of XDP Tx queues is the same as
the number of transmit queues, which is not always true. This
patch changes this number to match the number of receive queues.
XDP programs are running on Rx rings, so what we actually need to
provide is the XDP Tx ring per each Rx ring so that the whole XDP
ecosystem is functional, e.g. if the result of XDP prog is XDP_TX
then you have the need to access the XDP Tx ring.

Signed-off-by: Marta Plantykow <marta.a.plantykow@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c  | 2 +-
 drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 89962c14e31f..6f3ee8ac11ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2785,7 +2785,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 
 		ice_vsi_map_rings_to_vectors(vsi);
 		if (ice_is_xdp_ena_vsi(vsi)) {
-			vsi->num_xdp_txq = vsi->alloc_txq;
+			vsi->num_xdp_txq = vsi->alloc_rxq;
 			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog);
 			if (ret)
 				goto err_vectors;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 81c5f0ce5b8f..b64c4e796636 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1935,7 +1935,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 	}
 
 	if (!ice_is_xdp_ena_vsi(vsi) && prog) {
-		vsi->num_xdp_txq = vsi->alloc_txq;
+		vsi->num_xdp_txq = vsi->alloc_rxq;
 		xdp_ring_err = ice_prepare_xdp_rings(vsi, prog);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
-- 
cgit v1.2.3


From 7e34786a74e14038faadabb24b0d7f4436961c6b Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 15 May 2020 17:42:18 -0700
Subject: ice: avoid undefined behavior

When writing the driver's struct ice_tlan_ctx structure, do not write the
8-bit element int_q_state with the associated internal-to-hardware field
which is 122-bits, otherwise the helper function ice_write_byte() will use
undefined behavior when setting the mask used for that write.  This should
not cause any functional change and will avoid use of undefined behavior.
Also, update a comment to highlight this structure element is not written.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c      |  5 +++--
 drivers/net/ethernet/intel/ice/ice_common.c    | 12 ++++++++++--
 drivers/net/ethernet/intel/ice/ice_common.h    |  3 ++-
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h |  2 +-
 4 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 9452c0eb70b0..18076e0d12d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -638,6 +638,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring,
 	struct ice_aqc_add_txqs_perq *txq;
 	struct ice_pf *pf = vsi->back;
 	u8 buf_len = sizeof(*qg_buf);
+	struct ice_hw *hw = &pf->hw;
 	enum ice_status status;
 	u16 pf_q;
 	u8 tc;
@@ -646,13 +647,13 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring,
 	ice_setup_tx_ctx(ring, &tlan_ctx, pf_q);
 	/* copy context contents into the qg_buf */
 	qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
-	ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+	ice_set_ctx(hw, (u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
 		    ice_tlan_ctx_info);
 
 	/* init queue specific tail reg. It is referred as
 	 * transmit comm scheduler queue doorbell.
 	 */
-	ring->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+	ring->tail = hw->hw_addr + QTX_COMM_DBELL(pf_q);
 
 	if (IS_ENABLED(CONFIG_DCB))
 		tc = ring->dcb_tc;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index ee62cfa3a69e..8c73e161829d 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1098,7 +1098,7 @@ ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 
 	rlan_ctx->prefena = 1;
 
-	ice_set_ctx((u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info);
+	ice_set_ctx(hw, (u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info);
 	return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index);
 }
 
@@ -3199,12 +3199,14 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 
 /**
  * ice_set_ctx - set context bits in packed structure
+ * @hw: pointer to the hardware structure
  * @src_ctx:  pointer to a generic non-packed context structure
  * @dest_ctx: pointer to memory for the packed structure
  * @ce_info:  a description of the structure to be transformed
  */
 enum ice_status
-ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
+ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx,
+	    const struct ice_ctx_ele *ce_info)
 {
 	int f;
 
@@ -3213,6 +3215,12 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 		 * using the correct size so that we are correct regardless
 		 * of the endianness of the machine.
 		 */
+		if (ce_info[f].width > (ce_info[f].size_of * BITS_PER_BYTE)) {
+			ice_debug(hw, ICE_DBG_QCTX,
+				  "Field %d width of %d bits larger than size of %d byte(s) ... skipping write\n",
+				  f, ce_info[f].width, ce_info[f].size_of);
+			continue;
+		}
 		switch (ce_info[f].size_of) {
 		case sizeof(u8):
 			ice_write_byte(src_ctx, dest_ctx, &ce_info[f]);
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index bea755a658eb..9b9e50d2398b 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -70,7 +70,8 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
 void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
 extern const struct ice_ctx_ele ice_tlan_ctx_info[];
 enum ice_status
-ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info);
+ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx,
+	    const struct ice_ctx_ele *ce_info);
 
 extern struct mutex ice_global_cfg_lock_sw;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index bd2cd3435768..14dfbbc1b2cf 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -581,7 +581,7 @@ struct ice_tlan_ctx {
 	u8 drop_ena;
 	u8 cache_prof_idx;
 	u8 pkt_shaper_prof_idx;
-	u8 int_q_state;	/* width not needed - internal do not write */
+	u8 int_q_state;	/* width not needed - internal - DO NOT WRITE!!! */
 };
 
 /* macro to make the table lines short */
-- 
cgit v1.2.3


From 13f90b393f7338e6a2b2646fa1b677cc8b50cd23 Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 15 May 2020 17:42:19 -0700
Subject: ice: Refactor Rx checksum checks

We don't need both rx_status and rx_error parameters, as the latter is
a subset of the former. Remove rx_error completely and check the right bit
in rx_status.

Rename rx_status to rx_status0, and rx_status_err1 to
rx_status1. This naming more closely reflects the specification.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1ba97172d8d0..ab2031b1c635 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -84,17 +84,12 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
-	u16 rx_error, rx_status;
-	u16 rx_stat_err1;
+	u16 rx_status0, rx_status1;
 	bool ipv4, ipv6;
 
-	rx_status = le16_to_cpu(rx_desc->wb.status_error0);
-	rx_error = rx_status & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
-				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S) |
-				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S) |
-				BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S));
+	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
+	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
 
-	rx_stat_err1 = le16_to_cpu(rx_desc->wb.status_error1);
 	decoded = ice_decode_rx_desc_ptype(ptype);
 
 	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
@@ -106,7 +101,7 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 		return;
 
 	/* check if HW has decoded the packet and checksum */
-	if (!(rx_status & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
+	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
 		return;
 
 	if (!(decoded.known && decoded.outer_ip))
@@ -117,22 +112,22 @@ ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
 	       (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6);
 
-	if (ipv4 && (rx_error & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
-				 BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S))))
+	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
+				   BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S))))
 		goto checksum_fail;
-	else if (ipv6 && (rx_status &
-		 (BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S))))
+
+	if (ipv6 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S))))
 		goto checksum_fail;
 
 	/* check for L4 errors and handle packets that were not able to be
 	 * checksummed due to arrival speed
 	 */
-	if (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S))
+	if (rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S))
 		goto checksum_fail;
 
 	/* check for outer UDP checksum error in tunneled packets */
-	if ((rx_stat_err1 & BIT(ICE_RX_FLEX_DESC_STATUS1_NAT_S)) &&
-	    (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S)))
+	if ((rx_status1 & BIT(ICE_RX_FLEX_DESC_STATUS1_NAT_S)) &&
+	    (rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S)))
 		goto checksum_fail;
 
 	/* If there is an outer header present that might contain a checksum
-- 
cgit v1.2.3


From ea651a86d46895a8b342664db66c3dee3412ad34 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Wed, 6 Nov 2019 09:57:12 -0800
Subject: net/mlx5: E-Switch, Refactor eswitch egress acl codes

Refactor the egress acl codes so that offloads and legacy modes
can configure specifically their own needs of egress acl table,
groups and rules. While at it, restructure the eswitch egress
acl codes into eswitch directory and different files:
. Acl egress helper functions to acl_helper.c/h
. Acl egress functions used in offloads mode to acl_egress_ofld.c
. Acl egress functions used in legacy mode to acl_egress_lgy.c

This patch does not change any functionality.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   3 +
 .../mellanox/mlx5/core/esw/acl/egress_lgcy.c       | 170 +++++++++++++++
 .../mellanox/mlx5/core/esw/acl/egress_ofld.c       |  88 ++++++++
 .../ethernet/mellanox/mlx5/core/esw/acl/helper.c   | 142 +++++++++++++
 .../ethernet/mellanox/mlx5/core/esw/acl/helper.h   |  22 ++
 .../net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h |  13 ++
 .../net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h |  13 ++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  | 235 +--------------------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  15 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |  36 +---
 10 files changed, 462 insertions(+), 275 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index e5ee9103fefb..ad046b2ea4f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -46,6 +46,9 @@ mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
 #
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
 				      ecpf.o rdma.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
+				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o
+
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
new file mode 100644
index 000000000000..d46f8b225ebe
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "helper.h"
+#include "lgcy.h"
+
+static void esw_acl_egress_lgcy_rules_destroy(struct mlx5_vport *vport)
+{
+	esw_acl_egress_vlan_destroy(vport);
+	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_rule)) {
+		mlx5_del_flow_rules(vport->egress.legacy.drop_rule);
+		vport->egress.legacy.drop_rule = NULL;
+	}
+}
+
+static int esw_acl_egress_lgcy_groups_create(struct mlx5_eswitch *esw,
+					     struct mlx5_vport *vport)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_group *drop_grp;
+	u32 *flow_group_in;
+	int err = 0;
+
+	err = esw_acl_egress_vlan_grp_create(esw, vport);
+	if (err)
+		return err;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
+	drop_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in);
+	if (IS_ERR(drop_grp)) {
+		err = PTR_ERR(drop_grp);
+		esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
+			 vport->vport, err);
+		goto drop_grp_err;
+	}
+
+	vport->egress.legacy.drop_grp = drop_grp;
+	kvfree(flow_group_in);
+	return 0;
+
+drop_grp_err:
+	kvfree(flow_group_in);
+alloc_err:
+	esw_acl_egress_vlan_grp_destroy(vport);
+	return err;
+}
+
+static void esw_acl_egress_lgcy_groups_destroy(struct mlx5_vport *vport)
+{
+	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_grp)) {
+		mlx5_destroy_flow_group(vport->egress.legacy.drop_grp);
+		vport->egress.legacy.drop_grp = NULL;
+	}
+	esw_acl_egress_vlan_grp_destroy(vport);
+}
+
+int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
+			      struct mlx5_vport *vport)
+{
+	struct mlx5_flow_destination drop_ctr_dst = {};
+	struct mlx5_flow_destination *dst = NULL;
+	struct mlx5_fc *drop_counter = NULL;
+	struct mlx5_flow_act flow_act = {};
+	/* The egress acl table contains 2 rules:
+	 * 1)Allow traffic with vlan_tag=vst_vlan_id
+	 * 2)Drop all other traffic.
+	 */
+	int table_size = 2;
+	int dest_num = 0;
+	int err = 0;
+
+	if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) {
+		drop_counter = mlx5_fc_create(esw->dev, false);
+		if (IS_ERR(drop_counter))
+			esw_warn(esw->dev,
+				 "vport[%d] configure egress drop rule counter err(%ld)\n",
+				 vport->vport, PTR_ERR(drop_counter));
+		vport->egress.legacy.drop_counter = drop_counter;
+	}
+
+	esw_acl_egress_lgcy_rules_destroy(vport);
+
+	if (!vport->info.vlan && !vport->info.qos) {
+		esw_acl_egress_lgcy_cleanup(esw, vport);
+		return 0;
+	}
+
+	if (!IS_ERR_OR_NULL(vport->egress.acl))
+		return 0;
+
+	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+						 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						 table_size);
+	if (IS_ERR_OR_NULL(vport->egress.acl)) {
+		err = PTR_ERR(vport->egress.acl);
+		vport->egress.acl = NULL;
+		goto out;
+	}
+
+	err = esw_acl_egress_lgcy_groups_create(esw, vport);
+	if (err)
+		goto out;
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
+		  vport->vport, vport->info.vlan, vport->info.qos);
+
+	/* Allowed vlan rule */
+	err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
+					 MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+	if (err)
+		goto out;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	/* Attach egress drop flow counter */
+	if (!IS_ERR_OR_NULL(drop_counter)) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter);
+		dst = &drop_ctr_dst;
+		dest_num++;
+	}
+	vport->egress.legacy.drop_rule =
+		mlx5_add_flow_rules(vport->egress.acl, NULL,
+				    &flow_act, dst, dest_num);
+	if (IS_ERR(vport->egress.legacy.drop_rule)) {
+		err = PTR_ERR(vport->egress.legacy.drop_rule);
+		esw_warn(esw->dev,
+			 "vport[%d] configure egress drop rule failed, err(%d)\n",
+			 vport->vport, err);
+		vport->egress.legacy.drop_rule = NULL;
+		goto out;
+	}
+
+	return err;
+
+out:
+	esw_acl_egress_lgcy_cleanup(esw, vport);
+	return err;
+}
+
+void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw,
+				 struct mlx5_vport *vport)
+{
+	if (IS_ERR_OR_NULL(vport->egress.acl))
+		goto clean_drop_counter;
+
+	esw_debug(esw->dev, "Destroy vport[%d] E-Switch egress ACL\n", vport->vport);
+
+	esw_acl_egress_lgcy_rules_destroy(vport);
+	esw_acl_egress_lgcy_groups_destroy(vport);
+	esw_acl_egress_table_destroy(vport);
+
+clean_drop_counter:
+	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter)) {
+		mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
+		vport->egress.legacy.drop_counter = NULL;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
new file mode 100644
index 000000000000..49a53ebf56dd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "helper.h"
+#include "ofld.h"
+
+static int esw_acl_egress_ofld_rules_create(struct mlx5_eswitch *esw,
+					    struct mlx5_vport *vport)
+{
+	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	/* For prio tag mode, there is only 1 FTEs:
+	 * 1) prio tag packets - pop the prio tag VLAN, allow
+	 * Unmatched traffic is allowed by default
+	 */
+	esw_debug(esw->dev,
+		  "vport[%d] configure prio tag egress rules\n", vport->vport);
+
+	/* prio tag vlan rule - pop it so vport receives untagged packets */
+	return esw_egress_acl_vlan_create(esw, vport, NULL, 0,
+					  MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
+					  MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+}
+
+static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport)
+{
+	esw_acl_egress_vlan_destroy(vport);
+}
+
+static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw,
+					     struct mlx5_vport *vport)
+{
+	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	return esw_acl_egress_vlan_grp_create(esw, vport);
+}
+
+static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
+{
+	esw_acl_egress_vlan_grp_destroy(vport);
+}
+
+int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	int err;
+
+	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	esw_acl_egress_ofld_rules_destroy(vport);
+
+	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+						 MLX5_FLOW_NAMESPACE_ESW_EGRESS, 0);
+	if (IS_ERR_OR_NULL(vport->egress.acl)) {
+		err = PTR_ERR(vport->egress.acl);
+		vport->egress.acl = NULL;
+		return err;
+	}
+
+	err = esw_acl_egress_ofld_groups_create(esw, vport);
+	if (err)
+		goto group_err;
+
+	esw_debug(esw->dev, "vport[%d] configure egress rules\n", vport->vport);
+
+	err = esw_acl_egress_ofld_rules_create(esw, vport);
+	if (err)
+		goto rules_err;
+
+	return 0;
+
+rules_err:
+	esw_acl_egress_ofld_groups_destroy(vport);
+group_err:
+	esw_acl_egress_table_destroy(vport);
+	return err;
+}
+
+void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport)
+{
+	esw_acl_egress_ofld_rules_destroy(vport);
+	esw_acl_egress_ofld_groups_destroy(vport);
+	esw_acl_egress_table_destroy(vport);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
new file mode 100644
index 000000000000..8b7996721a7c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "helper.h"
+
+struct mlx5_flow_table *
+esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *acl;
+	int acl_supported;
+	int vport_index;
+	int err;
+
+	acl_supported = (ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS) ?
+			MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support) :
+			MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support);
+
+	if (!acl_supported)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,
+		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");
+
+	vport_index = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport_index);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",
+			 vport_num);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	acl = mlx5_create_vport_flow_table(root_ns, 0, size, 0, vport_num);
+	if (IS_ERR(acl)) {
+		err = PTR_ERR(acl);
+		esw_warn(dev, "vport[%d] create %s ACL table, err(%d)\n", vport_num,
+			 ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress", err);
+	}
+	return acl;
+}
+
+int esw_egress_acl_vlan_create(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport,
+			       struct mlx5_flow_destination *fwd_dest,
+			       u16 vlan_id, u32 flow_action)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	if (vport->egress.allowed_vlan)
+		return -EEXIST;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vlan_id);
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = flow_action;
+	vport->egress.allowed_vlan =
+		mlx5_add_flow_rules(vport->egress.acl, spec,
+				    &flow_act, fwd_dest, 0);
+	if (IS_ERR(vport->egress.allowed_vlan)) {
+		err = PTR_ERR(vport->egress.allowed_vlan);
+		esw_warn(esw->dev,
+			 "vport[%d] configure egress vlan rule failed, err(%d)\n",
+			 vport->vport, err);
+		vport->egress.allowed_vlan = NULL;
+	}
+
+	kvfree(spec);
+	return err;
+}
+
+void esw_acl_egress_vlan_destroy(struct mlx5_vport *vport)
+{
+	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
+		mlx5_del_flow_rules(vport->egress.allowed_vlan);
+		vport->egress.allowed_vlan = NULL;
+	}
+}
+
+int esw_acl_egress_vlan_grp_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *vlan_grp;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int ret = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+				      flow_group_in, match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.first_vid);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
+
+	vlan_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in);
+	if (IS_ERR(vlan_grp)) {
+		ret = PTR_ERR(vlan_grp);
+		esw_warn(esw->dev,
+			 "Failed to create E-Switch vport[%d] egress pop vlans flow group, err(%d)\n",
+			 vport->vport, ret);
+		goto out;
+	}
+	vport->egress.vlan_grp = vlan_grp;
+
+out:
+	kvfree(flow_group_in);
+	return ret;
+}
+
+void esw_acl_egress_vlan_grp_destroy(struct mlx5_vport *vport)
+{
+	if (!IS_ERR_OR_NULL(vport->egress.vlan_grp)) {
+		mlx5_destroy_flow_group(vport->egress.vlan_grp);
+		vport->egress.vlan_grp = NULL;
+	}
+}
+
+void esw_acl_egress_table_destroy(struct mlx5_vport *vport)
+{
+	if (IS_ERR_OR_NULL(vport->egress.acl))
+		return;
+
+	mlx5_destroy_flow_table(vport->egress.acl);
+	vport->egress.acl = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
new file mode 100644
index 000000000000..543372df6196
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#ifndef __MLX5_ESWITCH_ACL_HELPER_H__
+#define __MLX5_ESWITCH_ACL_HELPER_H__
+
+#include "eswitch.h"
+
+/* General acl helper functions */
+struct mlx5_flow_table *
+esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size);
+
+/* Egress acl helper functions */
+void esw_acl_egress_table_destroy(struct mlx5_vport *vport);
+int esw_egress_acl_vlan_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			       struct mlx5_flow_destination *fwd_dest,
+			       u16 vlan_id, u32 flow_action);
+void esw_acl_egress_vlan_destroy(struct mlx5_vport *vport);
+int esw_acl_egress_vlan_grp_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void esw_acl_egress_vlan_grp_destroy(struct mlx5_vport *vport);
+
+#endif /* __MLX5_ESWITCH_ACL_HELPER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
new file mode 100644
index 000000000000..6b05a3af4462
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#ifndef __MLX5_ESWITCH_ACL_LGCY_H__
+#define __MLX5_ESWITCH_ACL_LGCY_H__
+
+#include "eswitch.h"
+
+/* Eswitch acl egress external APIs */
+int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
+#endif /* __MLX5_ESWITCH_ACL_LGCY_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
new file mode 100644
index 000000000000..fc912b254226
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#ifndef __MLX5_ESWITCH_ACL_OFLD_H__
+#define __MLX5_ESWITCH_ACL_OFLD_H__
+
+#include "eswitch.h"
+
+/* Eswitch acl egress external APIs */
+int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport);
+
+#endif /* __MLX5_ESWITCH_ACL_OFLD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ac79b7c9aeb3..ae74486b9c9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/mlx5_ifc.h>
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
+#include "esw/acl/lgcy.h"
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "eswitch.h"
@@ -936,121 +937,6 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_group *vlan_grp = NULL;
-	struct mlx5_flow_group *drop_grp = NULL;
-	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_flow_namespace *root_ns;
-	struct mlx5_flow_table *acl;
-	void *match_criteria;
-	u32 *flow_group_in;
-	/* The egress acl table contains 2 rules:
-	 * 1)Allow traffic with vlan_tag=vst_vlan_id
-	 * 2)Drop all other traffic.
-	 */
-	int table_size = 2;
-	int err = 0;
-
-	if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
-		return -EOPNOTSUPP;
-
-	if (!IS_ERR_OR_NULL(vport->egress.acl))
-		return 0;
-
-	esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n",
-		  vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
-
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-			mlx5_eswitch_vport_num_to_index(esw, vport->vport));
-	if (!root_ns) {
-		esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
-		return -EOPNOTSUPP;
-	}
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!flow_group_in)
-		return -ENOMEM;
-
-	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR(acl)) {
-		err = PTR_ERR(acl);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
-			 vport->vport, err);
-		goto out;
-	}
-
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.first_vid);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
-
-	vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR(vlan_grp)) {
-		err = PTR_ERR(vlan_grp);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
-			 vport->vport, err);
-		goto out;
-	}
-
-	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
-	drop_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR(drop_grp)) {
-		err = PTR_ERR(drop_grp);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
-			 vport->vport, err);
-		goto out;
-	}
-
-	vport->egress.acl = acl;
-	vport->egress.drop_grp = drop_grp;
-	vport->egress.allowed_vlans_grp = vlan_grp;
-out:
-	kvfree(flow_group_in);
-	if (err && !IS_ERR_OR_NULL(vlan_grp))
-		mlx5_destroy_flow_group(vlan_grp);
-	if (err && !IS_ERR_OR_NULL(acl))
-		mlx5_destroy_flow_table(acl);
-	return err;
-}
-
-void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport)
-{
-	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
-		mlx5_del_flow_rules(vport->egress.allowed_vlan);
-		vport->egress.allowed_vlan = NULL;
-	}
-
-	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_rule)) {
-		mlx5_del_flow_rules(vport->egress.legacy.drop_rule);
-		vport->egress.legacy.drop_rule = NULL;
-	}
-}
-
-void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport)
-{
-	if (IS_ERR_OR_NULL(vport->egress.acl))
-		return;
-
-	esw_debug(esw->dev, "Destroy vport[%d] E-Switch egress ACL\n", vport->vport);
-
-	esw_vport_cleanup_egress_rules(esw, vport);
-	mlx5_destroy_flow_group(vport->egress.allowed_vlans_grp);
-	mlx5_destroy_flow_group(vport->egress.drop_grp);
-	mlx5_destroy_flow_table(vport->egress.acl);
-	vport->egress.allowed_vlans_grp = NULL;
-	vport->egress.drop_grp = NULL;
-	vport->egress.acl = NULL;
-}
-
 static int
 esw_vport_create_legacy_ingress_acl_groups(struct mlx5_eswitch *esw,
 					   struct mlx5_vport *vport)
@@ -1346,102 +1232,6 @@ out:
 	return err;
 }
 
-int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw,
-					  struct mlx5_vport *vport,
-					  u16 vlan_id, u32 flow_action)
-{
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_spec *spec;
-	int err = 0;
-
-	if (vport->egress.allowed_vlan)
-		return -EEXIST;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
-
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
-	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vlan_id);
-
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = flow_action;
-	vport->egress.allowed_vlan =
-		mlx5_add_flow_rules(vport->egress.acl, spec,
-				    &flow_act, NULL, 0);
-	if (IS_ERR(vport->egress.allowed_vlan)) {
-		err = PTR_ERR(vport->egress.allowed_vlan);
-		esw_warn(esw->dev,
-			 "vport[%d] configure egress vlan rule failed, err(%d)\n",
-			 vport->vport, err);
-		vport->egress.allowed_vlan = NULL;
-	}
-
-	kvfree(spec);
-	return err;
-}
-
-static int esw_vport_egress_config(struct mlx5_eswitch *esw,
-				   struct mlx5_vport *vport)
-{
-	struct mlx5_fc *counter = vport->egress.legacy.drop_counter;
-	struct mlx5_flow_destination drop_ctr_dst = {0};
-	struct mlx5_flow_destination *dst = NULL;
-	struct mlx5_flow_act flow_act = {0};
-	int dest_num = 0;
-	int err = 0;
-
-	esw_vport_cleanup_egress_rules(esw, vport);
-
-	if (!vport->info.vlan && !vport->info.qos) {
-		esw_vport_disable_egress_acl(esw, vport);
-		return 0;
-	}
-
-	err = esw_vport_enable_egress_acl(esw, vport);
-	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "failed to enable egress acl (%d) on vport[%d]\n",
-			       err, vport->vport);
-		return err;
-	}
-
-	esw_debug(esw->dev,
-		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
-		  vport->vport, vport->info.vlan, vport->info.qos);
-
-	/* Allowed vlan rule */
-	err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, vport->info.vlan,
-						    MLX5_FLOW_CONTEXT_ACTION_ALLOW);
-	if (err)
-		return err;
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
-
-	/* Attach egress drop flow counter */
-	if (counter) {
-		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
-		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		drop_ctr_dst.counter_id = mlx5_fc_id(counter);
-		dst = &drop_ctr_dst;
-		dest_num++;
-	}
-	vport->egress.legacy.drop_rule =
-		mlx5_add_flow_rules(vport->egress.acl, NULL,
-				    &flow_act, dst, dest_num);
-	if (IS_ERR(vport->egress.legacy.drop_rule)) {
-		err = PTR_ERR(vport->egress.legacy.drop_rule);
-		esw_warn(esw->dev,
-			 "vport[%d] configure egress drop rule failed, err(%d)\n",
-			 vport->vport, err);
-		vport->egress.legacy.drop_rule = NULL;
-	}
-
-	return err;
-}
-
 static bool element_type_supported(struct mlx5_eswitch *esw, int type)
 {
 	const struct mlx5_core_dev *dev = esw->dev;
@@ -1667,17 +1457,7 @@ static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
 	if (ret)
 		goto ingress_err;
 
-	if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) {
-		vport->egress.legacy.drop_counter = mlx5_fc_create(esw->dev, false);
-		if (IS_ERR(vport->egress.legacy.drop_counter)) {
-			esw_warn(esw->dev,
-				 "vport[%d] configure egress drop rule counter failed\n",
-				 vport->vport);
-			vport->egress.legacy.drop_counter = NULL;
-		}
-	}
-
-	ret = esw_vport_egress_config(esw, vport);
+	ret = esw_acl_egress_lgcy_setup(esw, vport);
 	if (ret)
 		goto egress_err;
 
@@ -1685,9 +1465,6 @@ static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
 
 egress_err:
 	esw_vport_disable_legacy_ingress_acl(esw, vport);
-	mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
-	vport->egress.legacy.drop_counter = NULL;
-
 ingress_err:
 	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
 	vport->ingress.legacy.drop_counter = NULL;
@@ -1710,9 +1487,7 @@ static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw,
 	if (mlx5_esw_is_manager_vport(esw, vport->vport))
 		return;
 
-	esw_vport_disable_egress_acl(esw, vport);
-	mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
-	vport->egress.legacy.drop_counter = NULL;
+	esw_acl_egress_lgcy_cleanup(esw, vport);
 
 	esw_vport_disable_legacy_ingress_acl(esw, vport);
 	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
@@ -2433,7 +2208,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 		err = esw_vport_ingress_config(esw, evport);
 		if (err)
 			return err;
-		err = esw_vport_egress_config(esw, evport);
+		err = esw_acl_egress_lgcy_setup(esw, evport);
 	}
 
 	return err;
@@ -2734,7 +2509,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	if (!vport->enabled)
 		goto unlock;
 
-	if (vport->egress.legacy.drop_counter)
+	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter))
 		mlx5_fc_query(dev, vport->egress.legacy.drop_counter,
 			      &stats->rx_dropped, &bytes);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ccbbea3e0505..490410401631 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -99,10 +99,10 @@ struct vport_ingress {
 
 struct vport_egress {
 	struct mlx5_flow_table *acl;
-	struct mlx5_flow_group *allowed_vlans_grp;
-	struct mlx5_flow_group *drop_grp;
 	struct mlx5_flow_handle  *allowed_vlan;
+	struct mlx5_flow_group *vlan_grp;
 	struct {
+		struct mlx5_flow_group *drop_grp;
 		struct mlx5_flow_handle *drop_rule;
 		struct mlx5_fc *drop_counter;
 	} legacy;
@@ -291,12 +291,7 @@ int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw,
 				       struct mlx5_vport *vport,
 				       int table_size);
 void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport);
-void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport);
-int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport);
-void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport);
+
 int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 			       u32 rate_mbps);
 
@@ -458,10 +453,6 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
-int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw,
-					  struct mlx5_vport *vport,
-					  u16 vlan_id, u32 flow_action);
-
 static inline bool mlx5_esw_qos_enabled(struct mlx5_eswitch *esw)
 {
 	return esw->qos.enabled;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 554fc64d8ef6..0b00b30187ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "esw/acl/ofld.h"
 #include "esw/chains.h"
 #include "rdma.h"
 #include "en.h"
@@ -2093,37 +2094,6 @@ group_err:
 	return err;
 }
 
-static int esw_vport_egress_config(struct mlx5_eswitch *esw,
-				   struct mlx5_vport *vport)
-{
-	int err;
-
-	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
-		return 0;
-
-	esw_vport_cleanup_egress_rules(esw, vport);
-
-	err = esw_vport_enable_egress_acl(esw, vport);
-	if (err)
-		return err;
-
-	/* For prio tag mode, there is only 1 FTEs:
-	 * 1) prio tag packets - pop the prio tag VLAN, allow
-	 * Unmatched traffic is allowed by default
-	 */
-	esw_debug(esw->dev,
-		  "vport[%d] configure prio tag egress rules\n", vport->vport);
-
-	/* prio tag vlan rule - pop it so VF receives untagged packets */
-	err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, 0,
-						    MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
-						    MLX5_FLOW_CONTEXT_ACTION_ALLOW);
-	if (err)
-		esw_vport_disable_egress_acl(esw, vport);
-
-	return err;
-}
-
 static bool
 esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 {
@@ -2167,7 +2137,7 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 		return err;
 
 	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
-		err = esw_vport_egress_config(esw, vport);
+		err = esw_acl_egress_ofld_setup(esw, vport);
 		if (err) {
 			esw_vport_cleanup_ingress_rules(esw, vport);
 			esw_vport_del_ingress_acl_modify_metadata(esw, vport);
@@ -2182,7 +2152,7 @@ void
 esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
 				      struct mlx5_vport *vport)
 {
-	esw_vport_disable_egress_acl(esw, vport);
+	esw_acl_egress_ofld_cleanup(vport);
 	esw_vport_cleanup_ingress_rules(esw, vport);
 	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
 	esw_vport_destroy_ingress_acl_group(vport);
-- 
cgit v1.2.3


From 07bab9502641dff9c3c864162270d12c6dd0e834 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Fri, 27 Mar 2020 23:12:22 -0700
Subject: net/mlx5: E-Switch, Refactor eswitch ingress acl codes

Restructure the eswitch ingress acl codes into eswitch directory
and different files:
. Acl ingress helper functions to acl_helper.c/h
. Acl ingress functions used in offloads mode to acl_ingress_ofld.c
. Acl ingress functions used in legacy mode to acl_ingress_lgy.c

This patch does not change any functionality.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   3 +-
 .../ethernet/mellanox/mlx5/core/esw/acl/helper.c   |  18 ++
 .../ethernet/mellanox/mlx5/core/esw/acl/helper.h   |   4 +
 .../mellanox/mlx5/core/esw/acl/ingress_lgcy.c      | 279 ++++++++++++++++++
 .../mellanox/mlx5/core/esw/acl/ingress_ofld.c      | 293 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h |   4 +
 .../net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  | 322 +--------------------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |   6 -
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 269 +----------------
 10 files changed, 619 insertions(+), 583 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ad046b2ea4f9..3934dc258041 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -47,7 +47,8 @@ mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
 				      ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
-				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o
+				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
+				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index 8b7996721a7c..22f4c1c28006 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -140,3 +140,21 @@ void esw_acl_egress_table_destroy(struct mlx5_vport *vport)
 	mlx5_destroy_flow_table(vport->egress.acl);
 	vport->egress.acl = NULL;
 }
+
+void esw_acl_ingress_table_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->ingress.acl)
+		return;
+
+	mlx5_destroy_flow_table(vport->ingress.acl);
+	vport->ingress.acl = NULL;
+}
+
+void esw_acl_ingress_allow_rule_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->ingress.allow_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->ingress.allow_rule);
+	vport->ingress.allow_rule = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
index 543372df6196..8dc4cab66a71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
@@ -19,4 +19,8 @@ void esw_acl_egress_vlan_destroy(struct mlx5_vport *vport);
 int esw_acl_egress_vlan_grp_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 void esw_acl_egress_vlan_grp_destroy(struct mlx5_vport *vport);
 
+/* Ingress acl helper functions */
+void esw_acl_ingress_table_destroy(struct mlx5_vport *vport);
+void esw_acl_ingress_allow_rule_destroy(struct mlx5_vport *vport);
+
 #endif /* __MLX5_ESWITCH_ACL_HELPER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
new file mode 100644
index 000000000000..9bda4fe2eafa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "helper.h"
+#include "lgcy.h"
+
+static void esw_acl_ingress_lgcy_rules_destroy(struct mlx5_vport *vport)
+{
+	if (vport->ingress.legacy.drop_rule) {
+		mlx5_del_flow_rules(vport->ingress.legacy.drop_rule);
+		vport->ingress.legacy.drop_rule = NULL;
+	}
+	esw_acl_ingress_allow_rule_destroy(vport);
+}
+
+static int esw_acl_ingress_lgcy_groups_create(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_group *g;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
+
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "vport[%d] ingress create untagged spoofchk flow group, err(%d)\n",
+			 vport->vport, err);
+		goto spoof_err;
+	}
+	vport->ingress.legacy.allow_untagged_spoofchk_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
+
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
+			 vport->vport, err);
+		goto untagged_err;
+	}
+	vport->ingress.legacy.allow_untagged_only_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_OUTER_HEADERS);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
+
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "vport[%d] ingress create spoofchk flow group, err(%d)\n",
+			 vport->vport, err);
+		goto allow_spoof_err;
+	}
+	vport->ingress.legacy.allow_spoofchk_only_grp = g;
+
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
+
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "vport[%d] ingress create drop flow group, err(%d)\n",
+			 vport->vport, err);
+		goto drop_err;
+	}
+	vport->ingress.legacy.drop_grp = g;
+	kvfree(flow_group_in);
+	return 0;
+
+drop_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_spoofchk_only_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
+		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
+	}
+allow_spoof_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_only_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
+		vport->ingress.legacy.allow_untagged_only_grp = NULL;
+	}
+untagged_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_spoofchk_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
+		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
+	}
+spoof_err:
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void esw_acl_ingress_lgcy_groups_destroy(struct mlx5_vport *vport)
+{
+	if (vport->ingress.legacy.allow_spoofchk_only_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
+		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
+	}
+	if (vport->ingress.legacy.allow_untagged_only_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
+		vport->ingress.legacy.allow_untagged_only_grp = NULL;
+	}
+	if (vport->ingress.legacy.allow_untagged_spoofchk_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
+		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
+	}
+	if (vport->ingress.legacy.drop_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.drop_grp);
+		vport->ingress.legacy.drop_grp = NULL;
+	}
+}
+
+int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport)
+{
+	struct mlx5_flow_destination drop_ctr_dst = {};
+	struct mlx5_flow_destination *dst = NULL;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec = NULL;
+	struct mlx5_fc *counter = NULL;
+	/* The ingress acl table contains 4 groups
+	 * (2 active rules at the same time -
+	 *      1 allow rule from one of the first 3 groups.
+	 *      1 drop rule from the last group):
+	 * 1)Allow untagged traffic with smac=original mac.
+	 * 2)Allow untagged traffic.
+	 * 3)Allow traffic with smac=original mac.
+	 * 4)Drop all other traffic.
+	 */
+	int table_size = 4;
+	int dest_num = 0;
+	int err = 0;
+	u8 *smac_v;
+
+	esw_acl_ingress_lgcy_rules_destroy(vport);
+
+	if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) {
+		counter = mlx5_fc_create(esw->dev, false);
+		if (IS_ERR(counter))
+			esw_warn(esw->dev,
+				 "vport[%d] configure ingress drop rule counter failed\n",
+				 vport->vport);
+		vport->ingress.legacy.drop_counter = counter;
+	}
+
+	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
+		esw_acl_ingress_lgcy_cleanup(esw, vport);
+		return 0;
+	}
+
+	if (!vport->ingress.acl) {
+		vport->ingress.acl = esw_acl_table_create(esw, vport->vport,
+							  MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+							  table_size);
+		if (IS_ERR_OR_NULL(vport->ingress.acl)) {
+			err = PTR_ERR(vport->ingress.acl);
+			vport->ingress.acl = NULL;
+			return err;
+		}
+
+		err = esw_acl_ingress_lgcy_groups_create(esw, vport);
+		if (err)
+			goto out;
+	}
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
+		  vport->vport, vport->info.vlan, vport->info.qos);
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	if (vport->info.vlan || vport->info.qos)
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.cvlan_tag);
+
+	if (vport->info.spoofchk) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.smac_47_16);
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 outer_headers.smac_15_0);
+		smac_v = MLX5_ADDR_OF(fte_match_param,
+				      spec->match_value,
+				      outer_headers.smac_47_16);
+		ether_addr_copy(smac_v, vport->info.mac);
+	}
+
+	/* Create ingress allow rule */
+	memset(spec, 0, sizeof(*spec));
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
+							&flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.allow_rule)) {
+		err = PTR_ERR(vport->ingress.allow_rule);
+		esw_warn(esw->dev,
+			 "vport[%d] configure ingress allow rule, err(%d)\n",
+			 vport->vport, err);
+		vport->ingress.allow_rule = NULL;
+		goto out;
+	}
+
+	memset(&flow_act, 0, sizeof(flow_act));
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+	/* Attach drop flow counter */
+	if (counter) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		drop_ctr_dst.counter_id = mlx5_fc_id(counter);
+		dst = &drop_ctr_dst;
+		dest_num++;
+	}
+	vport->ingress.legacy.drop_rule =
+		mlx5_add_flow_rules(vport->ingress.acl, NULL,
+				    &flow_act, dst, dest_num);
+	if (IS_ERR(vport->ingress.legacy.drop_rule)) {
+		err = PTR_ERR(vport->ingress.legacy.drop_rule);
+		esw_warn(esw->dev,
+			 "vport[%d] configure ingress drop rule, err(%d)\n",
+			 vport->vport, err);
+		vport->ingress.legacy.drop_rule = NULL;
+		goto out;
+	}
+	kvfree(spec);
+	return 0;
+
+out:
+	esw_acl_ingress_lgcy_cleanup(esw, vport);
+	kvfree(spec);
+	return err;
+}
+
+void esw_acl_ingress_lgcy_cleanup(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
+{
+	if (IS_ERR_OR_NULL(vport->ingress.acl))
+		goto clean_drop_counter;
+
+	esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport);
+
+	esw_acl_ingress_lgcy_rules_destroy(vport);
+	esw_acl_ingress_lgcy_groups_destroy(vport);
+	esw_acl_ingress_table_destroy(vport);
+
+clean_drop_counter:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.drop_counter)) {
+		mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
+		vport->ingress.legacy.drop_counter = NULL;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
new file mode 100644
index 000000000000..1bae549f3fa7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "helper.h"
+#include "ofld.h"
+
+static bool
+esw_acl_ingress_prio_tag_enabled(const struct mlx5_eswitch *esw,
+				 const struct mlx5_vport *vport)
+{
+	return (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
+		mlx5_eswitch_is_vf_vport(esw, vport->vport));
+}
+
+static int esw_acl_ingress_prio_tag_create(struct mlx5_eswitch *esw,
+					   struct mlx5_vport *vport)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	/* For prio tag mode, there is only 1 FTEs:
+	 * 1) Untagged packets - push prio tag VLAN and modify metadata if
+	 * required, allow
+	 * Unmatched traffic is allowed by default
+	 */
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	/* Untagged packets - push prio tag VLAN, allow */
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.cvlan_tag, 0);
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
+			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_act.vlan[0].ethtype = ETH_P_8021Q;
+	flow_act.vlan[0].vid = 0;
+	flow_act.vlan[0].prio = 0;
+
+	if (vport->ingress.offloads.modify_metadata_rule) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+		flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
+	}
+
+	vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
+							&flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.allow_rule)) {
+		err = PTR_ERR(vport->ingress.allow_rule);
+		esw_warn(esw->dev,
+			 "vport[%d] configure ingress untagged allow rule, err(%d)\n",
+			 vport->vport, err);
+		vport->ingress.allow_rule = NULL;
+	}
+
+	kvfree(spec);
+	return err;
+}
+
+static int esw_acl_ingress_mod_metadata_create(struct mlx5_eswitch *esw,
+					       struct mlx5_vport *vport)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_flow_act flow_act = {};
+	int err = 0;
+	u32 key;
+
+	key = mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport);
+	key >>= ESW_SOURCE_PORT_METADATA_OFFSET;
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field,
+		 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+	MLX5_SET(set_action_in, action, data, key);
+	MLX5_SET(set_action_in, action, offset,
+		 ESW_SOURCE_PORT_METADATA_OFFSET);
+	MLX5_SET(set_action_in, action, length,
+		 ESW_SOURCE_PORT_METADATA_BITS);
+
+	vport->ingress.offloads.modify_metadata =
+		mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+					 1, action);
+	if (IS_ERR(vport->ingress.offloads.modify_metadata)) {
+		err = PTR_ERR(vport->ingress.offloads.modify_metadata);
+		esw_warn(esw->dev,
+			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
+	vport->ingress.offloads.modify_metadata_rule =
+				mlx5_add_flow_rules(vport->ingress.acl,
+						    NULL, &flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) {
+		err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule);
+		esw_warn(esw->dev,
+			 "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
+			 vport->vport, err);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
+		vport->ingress.offloads.modify_metadata_rule = NULL;
+	}
+	return err;
+}
+
+static void esw_acl_ingress_mod_metadata_destroy(struct mlx5_eswitch *esw,
+						 struct mlx5_vport *vport)
+{
+	if (!vport->ingress.offloads.modify_metadata_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule);
+	mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
+	vport->ingress.offloads.modify_metadata_rule = NULL;
+}
+
+static int esw_acl_ingress_ofld_rules_create(struct mlx5_eswitch *esw,
+					     struct mlx5_vport *vport)
+{
+	int err;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		err = esw_acl_ingress_mod_metadata_create(esw, vport);
+		if (err) {
+			esw_warn(esw->dev,
+				 "vport(%d) create ingress modify metadata, err(%d)\n",
+				 vport->vport, err);
+			return err;
+		}
+	}
+
+	if (esw_acl_ingress_prio_tag_enabled(esw, vport)) {
+		err = esw_acl_ingress_prio_tag_create(esw, vport);
+		if (err) {
+			esw_warn(esw->dev,
+				 "vport(%d) create ingress prio tag rule, err(%d)\n",
+				 vport->vport, err);
+			goto prio_tag_err;
+		}
+	}
+
+	return 0;
+
+prio_tag_err:
+	esw_acl_ingress_mod_metadata_destroy(esw, vport);
+	return err;
+}
+
+static void esw_acl_ingress_ofld_rules_destroy(struct mlx5_eswitch *esw,
+					       struct mlx5_vport *vport)
+{
+	esw_acl_ingress_allow_rule_destroy(vport);
+	esw_acl_ingress_mod_metadata_destroy(esw, vport);
+}
+
+static int esw_acl_ingress_ofld_groups_create(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *g;
+	void *match_criteria;
+	u32 *flow_group_in;
+	u32 flow_index = 0;
+	int ret = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	if (esw_acl_ingress_prio_tag_enabled(esw, vport)) {
+		/* This group is to hold FTE to match untagged packets when prio_tag
+		 * is enabled.
+		 */
+		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+					      flow_group_in, match_criteria);
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);
+
+		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+		if (IS_ERR(g)) {
+			ret = PTR_ERR(g);
+			esw_warn(esw->dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
+				 vport->vport, ret);
+			goto prio_tag_err;
+		}
+		vport->ingress.offloads.metadata_prio_tag_grp = g;
+		flow_index++;
+	}
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		/* This group holds an FTE with no match to add metadata for
+		 * tagged packets if prio-tag is enabled, or for all untagged
+		 * traffic in case prio-tag is disabled.
+		 */
+		memset(flow_group_in, 0, inlen);
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);
+
+		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+		if (IS_ERR(g)) {
+			ret = PTR_ERR(g);
+			esw_warn(esw->dev, "vport[%d] ingress create drop flow group, err(%d)\n",
+				 vport->vport, ret);
+			goto metadata_err;
+		}
+		vport->ingress.offloads.metadata_allmatch_grp = g;
+	}
+
+	kvfree(flow_group_in);
+	return 0;
+
+metadata_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.offloads.metadata_prio_tag_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
+		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
+	}
+prio_tag_err:
+	kvfree(flow_group_in);
+	return ret;
+}
+
+static void esw_acl_ingress_ofld_groups_destroy(struct mlx5_vport *vport)
+{
+	if (vport->ingress.offloads.metadata_allmatch_grp) {
+		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_allmatch_grp);
+		vport->ingress.offloads.metadata_allmatch_grp = NULL;
+	}
+
+	if (vport->ingress.offloads.metadata_prio_tag_grp) {
+		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
+		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
+	}
+}
+
+int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport)
+{
+	int num_ftes = 0;
+	int err;
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+	    !esw_acl_ingress_prio_tag_enabled(esw, vport))
+		return 0;
+
+	esw_acl_ingress_allow_rule_destroy(vport);
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		num_ftes++;
+	if (esw_acl_ingress_prio_tag_enabled(esw, vport))
+		num_ftes++;
+
+	vport->ingress.acl = esw_acl_table_create(esw, vport->vport,
+						  MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						  num_ftes);
+	if (IS_ERR_OR_NULL(vport->ingress.acl)) {
+		err = PTR_ERR(vport->ingress.acl);
+		vport->ingress.acl = NULL;
+		return err;
+	}
+
+	err = esw_acl_ingress_ofld_groups_create(esw, vport);
+	if (err)
+		goto group_err;
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure ingress rules\n", vport->vport);
+
+	err = esw_acl_ingress_ofld_rules_create(esw, vport);
+	if (err)
+		goto rules_err;
+
+	return 0;
+
+rules_err:
+	esw_acl_ingress_ofld_groups_destroy(vport);
+group_err:
+	esw_acl_ingress_table_destroy(vport);
+	return err;
+}
+
+void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
+{
+	esw_acl_ingress_ofld_rules_destroy(esw, vport);
+	esw_acl_ingress_ofld_groups_destroy(vport);
+	esw_acl_ingress_table_destroy(vport);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
index 6b05a3af4462..44c152da3d83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/lgcy.h
@@ -10,4 +10,8 @@
 int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 
+/* Eswitch acl ingress external APIs */
+int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void esw_acl_ingress_lgcy_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
 #endif /* __MLX5_ESWITCH_ACL_LGCY_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
index fc912b254226..9e5e0fac29ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
@@ -10,4 +10,8 @@
 int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport);
 
+/* Eswitch acl ingress external APIs */
+int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
 #endif /* __MLX5_ESWITCH_ACL_OFLD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ae74486b9c9e..20ab13ff2303 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -937,301 +937,6 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-static int
-esw_vport_create_legacy_ingress_acl_groups(struct mlx5_eswitch *esw,
-					   struct mlx5_vport *vport)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_flow_group *g;
-	void *match_criteria;
-	u32 *flow_group_in;
-	int err;
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!flow_group_in)
-		return -ENOMEM;
-
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
-
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
-
-	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "vport[%d] ingress create untagged spoofchk flow group, err(%d)\n",
-			 vport->vport, err);
-		goto spoof_err;
-	}
-	vport->ingress.legacy.allow_untagged_spoofchk_grp = g;
-
-	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
-
-	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
-			 vport->vport, err);
-		goto untagged_err;
-	}
-	vport->ingress.legacy.allow_untagged_only_grp = g;
-
-	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
-
-	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "vport[%d] ingress create spoofchk flow group, err(%d)\n",
-			 vport->vport, err);
-		goto allow_spoof_err;
-	}
-	vport->ingress.legacy.allow_spoofchk_only_grp = g;
-
-	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
-
-	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "vport[%d] ingress create drop flow group, err(%d)\n",
-			 vport->vport, err);
-		goto drop_err;
-	}
-	vport->ingress.legacy.drop_grp = g;
-	kvfree(flow_group_in);
-	return 0;
-
-drop_err:
-	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_spoofchk_only_grp)) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
-		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
-	}
-allow_spoof_err:
-	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_only_grp)) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
-		vport->ingress.legacy.allow_untagged_only_grp = NULL;
-	}
-untagged_err:
-	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_spoofchk_grp)) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
-		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
-	}
-spoof_err:
-	kvfree(flow_group_in);
-	return err;
-}
-
-int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport, int table_size)
-{
-	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_flow_namespace *root_ns;
-	struct mlx5_flow_table *acl;
-	int vport_index;
-	int err;
-
-	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
-		return -EOPNOTSUPP;
-
-	esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
-		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
-
-	vport_index = mlx5_eswitch_vport_num_to_index(esw, vport->vport);
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-						    vport_index);
-	if (!root_ns) {
-		esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n",
-			 vport->vport);
-		return -EOPNOTSUPP;
-	}
-
-	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR(acl)) {
-		err = PTR_ERR(acl);
-		esw_warn(dev, "vport[%d] ingress create flow Table, err(%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-	vport->ingress.acl = acl;
-	return 0;
-}
-
-void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport)
-{
-	if (!vport->ingress.acl)
-		return;
-
-	mlx5_destroy_flow_table(vport->ingress.acl);
-	vport->ingress.acl = NULL;
-}
-
-void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
-				     struct mlx5_vport *vport)
-{
-	if (vport->ingress.legacy.drop_rule) {
-		mlx5_del_flow_rules(vport->ingress.legacy.drop_rule);
-		vport->ingress.legacy.drop_rule = NULL;
-	}
-
-	if (vport->ingress.allow_rule) {
-		mlx5_del_flow_rules(vport->ingress.allow_rule);
-		vport->ingress.allow_rule = NULL;
-	}
-}
-
-static void esw_vport_disable_legacy_ingress_acl(struct mlx5_eswitch *esw,
-						 struct mlx5_vport *vport)
-{
-	if (!vport->ingress.acl)
-		return;
-
-	esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport);
-
-	esw_vport_cleanup_ingress_rules(esw, vport);
-	if (vport->ingress.legacy.allow_spoofchk_only_grp) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
-		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
-	}
-	if (vport->ingress.legacy.allow_untagged_only_grp) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
-		vport->ingress.legacy.allow_untagged_only_grp = NULL;
-	}
-	if (vport->ingress.legacy.allow_untagged_spoofchk_grp) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
-		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
-	}
-	if (vport->ingress.legacy.drop_grp) {
-		mlx5_destroy_flow_group(vport->ingress.legacy.drop_grp);
-		vport->ingress.legacy.drop_grp = NULL;
-	}
-	esw_vport_destroy_ingress_acl_table(vport);
-}
-
-static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport)
-{
-	struct mlx5_fc *counter = vport->ingress.legacy.drop_counter;
-	struct mlx5_flow_destination drop_ctr_dst = {0};
-	struct mlx5_flow_destination *dst = NULL;
-	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec = NULL;
-	int dest_num = 0;
-	int err = 0;
-	u8 *smac_v;
-
-	/* The ingress acl table contains 4 groups
-	 * (2 active rules at the same time -
-	 *      1 allow rule from one of the first 3 groups.
-	 *      1 drop rule from the last group):
-	 * 1)Allow untagged traffic with smac=original mac.
-	 * 2)Allow untagged traffic.
-	 * 3)Allow traffic with smac=original mac.
-	 * 4)Drop all other traffic.
-	 */
-	int table_size = 4;
-
-	esw_vport_cleanup_ingress_rules(esw, vport);
-
-	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
-		esw_vport_disable_legacy_ingress_acl(esw, vport);
-		return 0;
-	}
-
-	if (!vport->ingress.acl) {
-		err = esw_vport_create_ingress_acl_table(esw, vport, table_size);
-		if (err) {
-			esw_warn(esw->dev,
-				 "vport[%d] enable ingress acl err (%d)\n",
-				 err, vport->vport);
-			return err;
-		}
-
-		err = esw_vport_create_legacy_ingress_acl_groups(esw, vport);
-		if (err)
-			goto out;
-	}
-
-	esw_debug(esw->dev,
-		  "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
-		  vport->vport, vport->info.vlan, vport->info.qos);
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	if (vport->info.vlan || vport->info.qos)
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-
-	if (vport->info.spoofchk) {
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_47_16);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_15_0);
-		smac_v = MLX5_ADDR_OF(fte_match_param,
-				      spec->match_value,
-				      outer_headers.smac_47_16);
-		ether_addr_copy(smac_v, vport->info.mac);
-	}
-
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	vport->ingress.allow_rule =
-		mlx5_add_flow_rules(vport->ingress.acl, spec,
-				    &flow_act, NULL, 0);
-	if (IS_ERR(vport->ingress.allow_rule)) {
-		err = PTR_ERR(vport->ingress.allow_rule);
-		esw_warn(esw->dev,
-			 "vport[%d] configure ingress allow rule, err(%d)\n",
-			 vport->vport, err);
-		vport->ingress.allow_rule = NULL;
-		goto out;
-	}
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
-
-	/* Attach drop flow counter */
-	if (counter) {
-		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
-		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		drop_ctr_dst.counter_id = mlx5_fc_id(counter);
-		dst = &drop_ctr_dst;
-		dest_num++;
-	}
-	vport->ingress.legacy.drop_rule =
-		mlx5_add_flow_rules(vport->ingress.acl, NULL,
-				    &flow_act, dst, dest_num);
-	if (IS_ERR(vport->ingress.legacy.drop_rule)) {
-		err = PTR_ERR(vport->ingress.legacy.drop_rule);
-		esw_warn(esw->dev,
-			 "vport[%d] configure ingress drop rule, err(%d)\n",
-			 vport->vport, err);
-		vport->ingress.legacy.drop_rule = NULL;
-		goto out;
-	}
-	kvfree(spec);
-	return 0;
-
-out:
-	esw_vport_disable_legacy_ingress_acl(esw, vport);
-	kvfree(spec);
-	return err;
-}
-
 static bool element_type_supported(struct mlx5_eswitch *esw, int type)
 {
 	const struct mlx5_core_dev *dev = esw->dev;
@@ -1443,17 +1148,7 @@ static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
 	if (mlx5_esw_is_manager_vport(esw, vport->vport))
 		return 0;
 
-	if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) {
-		vport->ingress.legacy.drop_counter = mlx5_fc_create(esw->dev, false);
-		if (IS_ERR(vport->ingress.legacy.drop_counter)) {
-			esw_warn(esw->dev,
-				 "vport[%d] configure ingress drop rule counter failed\n",
-				 vport->vport);
-			vport->ingress.legacy.drop_counter = NULL;
-		}
-	}
-
-	ret = esw_vport_ingress_config(esw, vport);
+	ret = esw_acl_ingress_lgcy_setup(esw, vport);
 	if (ret)
 		goto ingress_err;
 
@@ -1464,10 +1159,8 @@ static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
 	return 0;
 
 egress_err:
-	esw_vport_disable_legacy_ingress_acl(esw, vport);
+	esw_acl_ingress_lgcy_cleanup(esw, vport);
 ingress_err:
-	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
-	vport->ingress.legacy.drop_counter = NULL;
 	return ret;
 }
 
@@ -1488,10 +1181,7 @@ static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw,
 		return;
 
 	esw_acl_egress_lgcy_cleanup(esw, vport);
-
-	esw_vport_disable_legacy_ingress_acl(esw, vport);
-	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
-	vport->ingress.legacy.drop_counter = NULL;
+	esw_acl_ingress_lgcy_cleanup(esw, vport);
 }
 
 static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw,
@@ -2123,7 +1813,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	ether_addr_copy(evport->info.mac, mac);
 	evport->info.node_guid = node_guid;
 	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
-		err = esw_vport_ingress_config(esw, evport);
+		err = esw_acl_ingress_lgcy_setup(esw, evport);
 
 unlock:
 	mutex_unlock(&esw->state_lock);
@@ -2205,7 +1895,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 	evport->info.vlan = vlan;
 	evport->info.qos = qos;
 	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) {
-		err = esw_vport_ingress_config(esw, evport);
+		err = esw_acl_ingress_lgcy_setup(esw, evport);
 		if (err)
 			return err;
 		err = esw_acl_egress_lgcy_setup(esw, evport);
@@ -2250,7 +1940,7 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
 			       evport->vport);
 	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
-		err = esw_vport_ingress_config(esw, evport);
+		err = esw_acl_ingress_lgcy_setup(esw, evport);
 	if (err)
 		evport->info.spoofchk = pschk;
 	mutex_unlock(&esw->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 490410401631..ca7b7961c295 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -285,12 +285,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw);
 int esw_offloads_enable(struct mlx5_eswitch *esw);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
-void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
-				     struct mlx5_vport *vport);
-int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport,
-				       int table_size);
-void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport);
 
 int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 			       u32 rate_mbps);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 0b00b30187ce..11bc9cc1d5f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -235,13 +235,6 @@ static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
 	return &esw->offloads.vport_reps[idx];
 }
 
-static bool
-esw_check_ingress_prio_tag_enabled(const struct mlx5_eswitch *esw,
-				   const struct mlx5_vport *vport)
-{
-	return (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
-		mlx5_eswitch_is_vf_vport(esw, vport->vport));
-}
 
 static void
 mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
@@ -1852,248 +1845,6 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 }
 
-static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
-					     struct mlx5_vport *vport)
-{
-	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec;
-	int err = 0;
-
-	/* For prio tag mode, there is only 1 FTEs:
-	 * 1) Untagged packets - push prio tag VLAN and modify metadata if
-	 * required, allow
-	 * Unmatched traffic is allowed by default
-	 */
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
-
-	/* Untagged packets - push prio tag VLAN, allow */
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET(fte_match_param, spec->match_value, outer_headers.cvlan_tag, 0);
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
-			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	flow_act.vlan[0].ethtype = ETH_P_8021Q;
-	flow_act.vlan[0].vid = 0;
-	flow_act.vlan[0].prio = 0;
-
-	if (vport->ingress.offloads.modify_metadata_rule) {
-		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-		flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
-	}
-
-	vport->ingress.allow_rule =
-		mlx5_add_flow_rules(vport->ingress.acl, spec,
-				    &flow_act, NULL, 0);
-	if (IS_ERR(vport->ingress.allow_rule)) {
-		err = PTR_ERR(vport->ingress.allow_rule);
-		esw_warn(esw->dev,
-			 "vport[%d] configure ingress untagged allow rule, err(%d)\n",
-			 vport->vport, err);
-		vport->ingress.allow_rule = NULL;
-	}
-
-	kvfree(spec);
-	return err;
-}
-
-static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
-						     struct mlx5_vport *vport)
-{
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
-	struct mlx5_flow_act flow_act = {};
-	int err = 0;
-	u32 key;
-
-	key = mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport);
-	key >>= ESW_SOURCE_PORT_METADATA_OFFSET;
-
-	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
-	MLX5_SET(set_action_in, action, field,
-		 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
-	MLX5_SET(set_action_in, action, data, key);
-	MLX5_SET(set_action_in, action, offset,
-		 ESW_SOURCE_PORT_METADATA_OFFSET);
-	MLX5_SET(set_action_in, action, length,
-		 ESW_SOURCE_PORT_METADATA_BITS);
-
-	vport->ingress.offloads.modify_metadata =
-		mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-					 1, action);
-	if (IS_ERR(vport->ingress.offloads.modify_metadata)) {
-		err = PTR_ERR(vport->ingress.offloads.modify_metadata);
-		esw_warn(esw->dev,
-			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
-			 vport->vport, err);
-		return err;
-	}
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
-	vport->ingress.offloads.modify_metadata_rule =
-				mlx5_add_flow_rules(vport->ingress.acl,
-						    NULL, &flow_act, NULL, 0);
-	if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) {
-		err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule);
-		esw_warn(esw->dev,
-			 "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
-			 vport->vport, err);
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
-		vport->ingress.offloads.modify_metadata_rule = NULL;
-	}
-	return err;
-}
-
-static void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
-						      struct mlx5_vport *vport)
-{
-	if (vport->ingress.offloads.modify_metadata_rule) {
-		mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule);
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
-
-		vport->ingress.offloads.modify_metadata_rule = NULL;
-	}
-}
-
-static int esw_vport_create_ingress_acl_group(struct mlx5_eswitch *esw,
-					      struct mlx5_vport *vport)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_group *g;
-	void *match_criteria;
-	u32 *flow_group_in;
-	u32 flow_index = 0;
-	int ret = 0;
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!flow_group_in)
-		return -ENOMEM;
-
-	if (esw_check_ingress_prio_tag_enabled(esw, vport)) {
-		/* This group is to hold FTE to match untagged packets when prio_tag
-		 * is enabled.
-		 */
-		memset(flow_group_in, 0, inlen);
-
-		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					      flow_group_in, match_criteria);
-		MLX5_SET(create_flow_group_in, flow_group_in,
-			 match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
-		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
-		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);
-
-		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-		if (IS_ERR(g)) {
-			ret = PTR_ERR(g);
-			esw_warn(esw->dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
-				 vport->vport, ret);
-			goto prio_tag_err;
-		}
-		vport->ingress.offloads.metadata_prio_tag_grp = g;
-		flow_index++;
-	}
-
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		/* This group holds an FTE with no matches for add metadata for
-		 * tagged packets, if prio-tag is enabled (as a fallthrough),
-		 * or all traffic in case prio-tag is disabled.
-		 */
-		memset(flow_group_in, 0, inlen);
-		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
-		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);
-
-		g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
-		if (IS_ERR(g)) {
-			ret = PTR_ERR(g);
-			esw_warn(esw->dev, "vport[%d] ingress create drop flow group, err(%d)\n",
-				 vport->vport, ret);
-			goto metadata_err;
-		}
-		vport->ingress.offloads.metadata_allmatch_grp = g;
-	}
-
-	kvfree(flow_group_in);
-	return 0;
-
-metadata_err:
-	if (!IS_ERR_OR_NULL(vport->ingress.offloads.metadata_prio_tag_grp)) {
-		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
-		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
-	}
-prio_tag_err:
-	kvfree(flow_group_in);
-	return ret;
-}
-
-static void esw_vport_destroy_ingress_acl_group(struct mlx5_vport *vport)
-{
-	if (vport->ingress.offloads.metadata_allmatch_grp) {
-		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_allmatch_grp);
-		vport->ingress.offloads.metadata_allmatch_grp = NULL;
-	}
-
-	if (vport->ingress.offloads.metadata_prio_tag_grp) {
-		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_prio_tag_grp);
-		vport->ingress.offloads.metadata_prio_tag_grp = NULL;
-	}
-}
-
-static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport)
-{
-	int num_ftes = 0;
-	int err;
-
-	if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
-	    !esw_check_ingress_prio_tag_enabled(esw, vport))
-		return 0;
-
-	esw_vport_cleanup_ingress_rules(esw, vport);
-
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
-		num_ftes++;
-	if (esw_check_ingress_prio_tag_enabled(esw, vport))
-		num_ftes++;
-
-	err = esw_vport_create_ingress_acl_table(esw, vport, num_ftes);
-	if (err) {
-		esw_warn(esw->dev,
-			 "failed to enable ingress acl (%d) on vport[%d]\n",
-			 err, vport->vport);
-		return err;
-	}
-
-	err = esw_vport_create_ingress_acl_group(esw, vport);
-	if (err)
-		goto group_err;
-
-	esw_debug(esw->dev,
-		  "vport[%d] configure ingress rules\n", vport->vport);
-
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
-		if (err)
-			goto metadata_err;
-	}
-
-	if (esw_check_ingress_prio_tag_enabled(esw, vport)) {
-		err = esw_vport_ingress_prio_tag_config(esw, vport);
-		if (err)
-			goto prio_tag_err;
-	}
-	return 0;
-
-prio_tag_err:
-	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
-metadata_err:
-	esw_vport_destroy_ingress_acl_group(vport);
-group_err:
-	esw_vport_destroy_ingress_acl_table(vport);
-	return err;
-}
-
 static bool
 esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 {
@@ -2132,19 +1883,20 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 {
 	int err;
 
-	err = esw_vport_ingress_config(esw, vport);
+	err = esw_acl_ingress_ofld_setup(esw, vport);
 	if (err)
 		return err;
 
 	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
 		err = esw_acl_egress_ofld_setup(esw, vport);
-		if (err) {
-			esw_vport_cleanup_ingress_rules(esw, vport);
-			esw_vport_del_ingress_acl_modify_metadata(esw, vport);
-			esw_vport_destroy_ingress_acl_group(vport);
-			esw_vport_destroy_ingress_acl_table(vport);
-		}
+		if (err)
+			goto egress_err;
 	}
+
+	return 0;
+
+egress_err:
+	esw_acl_ingress_ofld_cleanup(esw, vport);
 	return err;
 }
 
@@ -2153,10 +1905,7 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
 				      struct mlx5_vport *vport)
 {
 	esw_acl_egress_ofld_cleanup(vport);
-	esw_vport_cleanup_ingress_rules(esw, vport);
-	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
-	esw_vport_destroy_ingress_acl_group(vport);
-	esw_vport_destroy_ingress_acl_table(vport);
+	esw_acl_ingress_ofld_cleanup(esw, vport);
 }
 
 static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
-- 
cgit v1.2.3


From bf773dc0e6d55a828a9111124b1d7836f2d4492c Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Mon, 16 Mar 2020 17:32:50 -0700
Subject: net/mlx5: E-Switch, Introduce APIs to enable egress acl
 forward-to-vport rule

By default, e-switch vport's egress acl just forward packets to its
counterpart NIC vport using existing egress acl table.

During port failover in bonding scenario where two VFs representors
are bonded, the egress acl forward-to-vport rule will be added to
the existing egress acl table of e-switch vport of passive/inactive
slave representor to forward packets to other NIC vport ie. the active
slave representor's NIC vport to handle egress "failover" traffic.

Enable egress acl and have APIs to create and destroy egress acl
forward-to-vport rule and group.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/esw/acl/egress_ofld.c       | 185 ++++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h |  10 ++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  16 +-
 3 files changed, 187 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
index 49a53ebf56dd..07b2acd7e6b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -6,55 +6,165 @@
 #include "helper.h"
 #include "ofld.h"
 
+static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->egress.offloads.fwd_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->egress.offloads.fwd_rule);
+	vport->egress.offloads.fwd_rule = NULL;
+}
+
+static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw,
+						struct mlx5_vport *vport,
+						struct mlx5_flow_destination *fwd_dest)
+{
+	struct mlx5_flow_act flow_act = {};
+	int err = 0;
+
+	esw_debug(esw->dev, "vport(%d) configure egress acl rule fwd2vport(%d)\n",
+		  vport->vport, fwd_dest->vport.num);
+
+	/* Delete the old egress forward-to-vport rule if any */
+	esw_acl_egress_ofld_fwd2vport_destroy(vport);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+
+	vport->egress.offloads.fwd_rule =
+		mlx5_add_flow_rules(vport->egress.acl, NULL,
+				    &flow_act, fwd_dest, 1);
+	if (IS_ERR(vport->egress.offloads.fwd_rule)) {
+		err = PTR_ERR(vport->egress.offloads.fwd_rule);
+		esw_warn(esw->dev,
+			 "vport(%d) failed to add fwd2vport acl rule err(%d)\n",
+			 vport->vport, err);
+		vport->egress.offloads.fwd_rule = NULL;
+	}
+
+	return err;
+}
+
 static int esw_acl_egress_ofld_rules_create(struct mlx5_eswitch *esw,
-					    struct mlx5_vport *vport)
+					    struct mlx5_vport *vport,
+					    struct mlx5_flow_destination *fwd_dest)
 {
-	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
-		return 0;
+	int err = 0;
+	int action;
+
+	if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) {
+		/* For prio tag mode, there is only 1 FTEs:
+		 * 1) prio tag packets - pop the prio tag VLAN, allow
+		 * Unmatched traffic is allowed by default
+		 */
+		esw_debug(esw->dev,
+			  "vport[%d] configure prio tag egress rules\n", vport->vport);
+
+		action = MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		action |= fwd_dest ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
+			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+
+		/* prio tag vlan rule - pop it so vport receives untagged packets */
+		err = esw_egress_acl_vlan_create(esw, vport, fwd_dest, 0, action);
+		if (err)
+			goto prio_err;
+	}
 
-	/* For prio tag mode, there is only 1 FTEs:
-	 * 1) prio tag packets - pop the prio tag VLAN, allow
-	 * Unmatched traffic is allowed by default
-	 */
-	esw_debug(esw->dev,
-		  "vport[%d] configure prio tag egress rules\n", vport->vport);
+	if (fwd_dest) {
+		err = esw_acl_egress_ofld_fwd2vport_create(esw, vport, fwd_dest);
+		if (err)
+			goto fwd_err;
+	}
 
-	/* prio tag vlan rule - pop it so vport receives untagged packets */
-	return esw_egress_acl_vlan_create(esw, vport, NULL, 0,
-					  MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
-					  MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+	return 0;
+
+fwd_err:
+	esw_acl_egress_vlan_destroy(vport);
+prio_err:
+	return err;
 }
 
 static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport)
 {
 	esw_acl_egress_vlan_destroy(vport);
+	esw_acl_egress_ofld_fwd2vport_destroy(vport);
 }
 
 static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw,
 					     struct mlx5_vport *vport)
 {
-	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
-		return 0;
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *fwd_grp;
+	u32 *flow_group_in;
+	u32 flow_index = 0;
+	int ret = 0;
+
+	if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) {
+		ret = esw_acl_egress_vlan_grp_create(esw, vport);
+		if (ret)
+			return ret;
+
+		flow_index++;
+	}
+
+	if (!mlx5_esw_acl_egress_fwd2vport_supported(esw))
+		goto out;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in) {
+		ret = -ENOMEM;
+		goto fwd_grp_err;
+	}
+
+	/* This group holds 1 FTE to forward all packets to other vport
+	 * when bond vports is supported.
+	 */
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, flow_index);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, flow_index);
+	fwd_grp = mlx5_create_flow_group(vport->egress.acl, flow_group_in);
+	if (IS_ERR(fwd_grp)) {
+		ret = PTR_ERR(fwd_grp);
+		esw_warn(esw->dev,
+			 "Failed to create vport[%d] egress fwd2vport flow group, err(%d)\n",
+			 vport->vport, ret);
+		kvfree(flow_group_in);
+		goto fwd_grp_err;
+	}
+	vport->egress.offloads.fwd_grp = fwd_grp;
+	kvfree(flow_group_in);
+	return 0;
 
-	return esw_acl_egress_vlan_grp_create(esw, vport);
+fwd_grp_err:
+	esw_acl_egress_vlan_grp_destroy(vport);
+out:
+	return ret;
 }
 
 static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 {
+	if (!IS_ERR_OR_NULL(vport->egress.offloads.fwd_grp)) {
+		mlx5_destroy_flow_group(vport->egress.offloads.fwd_grp);
+		vport->egress.offloads.fwd_grp = NULL;
+	}
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 
 int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
+	int table_size = 0;
 	int err;
 
-	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+	if (!mlx5_esw_acl_egress_fwd2vport_supported(esw) &&
+	    !MLX5_CAP_GEN(esw->dev, prio_tag_required))
 		return 0;
 
 	esw_acl_egress_ofld_rules_destroy(vport);
 
+	if (mlx5_esw_acl_egress_fwd2vport_supported(esw))
+		table_size++;
+	if (MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		table_size++;
 	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
-						 MLX5_FLOW_NAMESPACE_ESW_EGRESS, 0);
+						 MLX5_FLOW_NAMESPACE_ESW_EGRESS, table_size);
 	if (IS_ERR_OR_NULL(vport->egress.acl)) {
 		err = PTR_ERR(vport->egress.acl);
 		vport->egress.acl = NULL;
@@ -67,7 +177,7 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 
 	esw_debug(esw->dev, "vport[%d] configure egress rules\n", vport->vport);
 
-	err = esw_acl_egress_ofld_rules_create(esw, vport);
+	err = esw_acl_egress_ofld_rules_create(esw, vport, NULL);
 	if (err)
 		goto rules_err;
 
@@ -86,3 +196,40 @@ void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport)
 	esw_acl_egress_ofld_groups_destroy(vport);
 	esw_acl_egress_table_destroy(vport);
 }
+
+int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num,
+				   u16 passive_vport_num)
+{
+	struct mlx5_vport *passive_vport = mlx5_eswitch_get_vport(esw, passive_vport_num);
+	struct mlx5_vport *active_vport = mlx5_eswitch_get_vport(esw, active_vport_num);
+	struct mlx5_flow_destination fwd_dest = {};
+
+	if (IS_ERR(active_vport))
+		return PTR_ERR(active_vport);
+	if (IS_ERR(passive_vport))
+		return PTR_ERR(passive_vport);
+
+	/* Cleanup and recreate rules WITHOUT fwd2vport of active vport */
+	esw_acl_egress_ofld_rules_destroy(active_vport);
+	esw_acl_egress_ofld_rules_create(esw, active_vport, NULL);
+
+	/* Cleanup and recreate all rules + fwd2vport rule of passive vport to forward */
+	esw_acl_egress_ofld_rules_destroy(passive_vport);
+	fwd_dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	fwd_dest.vport.num = active_vport_num;
+	fwd_dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
+	fwd_dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
+
+	return esw_acl_egress_ofld_rules_create(esw, passive_vport, &fwd_dest);
+}
+
+int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	esw_acl_egress_ofld_rules_destroy(vport);
+	return esw_acl_egress_ofld_rules_create(esw, vport, NULL);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
index 9e5e0fac29ef..90ddc5d7da46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
@@ -9,6 +9,16 @@
 /* Eswitch acl egress external APIs */
 int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport);
+int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num,
+				   u16 passive_vport_num);
+int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num);
+
+static inline bool mlx5_esw_acl_egress_fwd2vport_supported(struct mlx5_eswitch *esw)
+{
+	return esw && esw->mode == MLX5_ESWITCH_OFFLOADS &&
+		mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+		MLX5_CAP_ESW_FLOWTABLE(esw->dev, egress_acl_forward_to_vport);
+}
 
 /* Eswitch acl ingress external APIs */
 int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ca7b7961c295..7b6b3686b666 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -101,11 +101,17 @@ struct vport_egress {
 	struct mlx5_flow_table *acl;
 	struct mlx5_flow_handle  *allowed_vlan;
 	struct mlx5_flow_group *vlan_grp;
-	struct {
-		struct mlx5_flow_group *drop_grp;
-		struct mlx5_flow_handle *drop_rule;
-		struct mlx5_fc *drop_counter;
-	} legacy;
+	union {
+		struct {
+			struct mlx5_flow_group *drop_grp;
+			struct mlx5_flow_handle *drop_rule;
+			struct mlx5_fc *drop_counter;
+		} legacy;
+		struct {
+			struct mlx5_flow_group *fwd_grp;
+			struct mlx5_flow_handle *fwd_rule;
+		} offloads;
+	};
 };
 
 struct mlx5_vport_drop_stats {
-- 
cgit v1.2.3


From 7e51891a237f9ea319f53f9beb83afb0077d88e6 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Fri, 21 Jun 2019 13:23:44 -0700
Subject: net/mlx5e: Use netdev events to set/del egress acl forward-to-vport
 rule

Register a notifier block to handle netdev events for bond device
of non-uplink representors to support eswitch vports bonding.

When a non-uplink representor is a lower dev (slave) of bond and
becomes active, adding egress acl forward-to-vport rule of all slave
netdevs (active + standby) to forward to this representor's vport. Use
change lower netdev event to do this.

Use change upper event to detect slave representor unslaved from lag
device to delete its vport egress acl forward rule if any.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   3 +-
 .../net/ethernet/mellanox/mlx5/core/en/rep/bond.c  | 161 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |   8 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |   7 +
 4 files changed, 175 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 3934dc258041..b61e47bc16e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -34,7 +34,8 @@ mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o lib/geneve.o lib/port_tun.o lag_mp.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag_mp.o lib/geneve.o lib/port_tun.o \
+					en_rep.o en/rep/bond.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					en/mapping.o esw/chains.o en/tc_tun.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
new file mode 100644
index 000000000000..d0aab36f1947
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
+
+#include <net/lag.h>
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "esw/acl/ofld.h"
+#include "en_rep.h"
+
+struct mlx5e_rep_bond {
+	struct notifier_block nb;
+	struct netdev_net_notifier nn;
+};
+
+static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	/* A given netdev is not a representor or not a slave of LAG configuration */
+	if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev))
+		return false;
+
+	/* Egress acl forward to vport is supported only non-uplink representor */
+	return rpriv->rep->vport != MLX5_VPORT_UPLINK;
+}
+
+static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr)
+{
+	struct netdev_notifier_changelowerstate_info *info;
+	struct netdev_lag_lower_state_info *lag_info;
+	struct mlx5e_rep_priv *rpriv;
+	struct net_device *lag_dev;
+	struct mlx5e_priv *priv;
+	struct list_head *iter;
+	struct net_device *dev;
+	u16 acl_vport_num;
+	u16 fwd_vport_num;
+
+	if (!mlx5e_rep_is_lag_netdev(netdev))
+		return;
+
+	info = ptr;
+	lag_info = info->lower_state_info;
+	/* This is not an event of a representor becoming active slave */
+	if (!lag_info->tx_enabled)
+		return;
+
+	priv = netdev_priv(netdev);
+	rpriv = priv->ppriv;
+	fwd_vport_num = rpriv->rep->vport;
+	lag_dev = netdev_master_upper_dev_get(netdev);
+
+	netdev_dbg(netdev, "lag_dev(%s)'s slave vport(%d) is txable(%d)\n",
+		   lag_dev->name, fwd_vport_num, net_lag_port_dev_txable(netdev));
+
+	/* Point everyone's egress acl to the vport of the active representor */
+	netdev_for_each_lower_dev(lag_dev, dev, iter) {
+		priv = netdev_priv(dev);
+		rpriv = priv->ppriv;
+		acl_vport_num = rpriv->rep->vport;
+		if (acl_vport_num != fwd_vport_num) {
+			mlx5_esw_acl_egress_vport_bond(priv->mdev->priv.eswitch,
+						       fwd_vport_num,
+						       acl_vport_num);
+		}
+	}
+}
+
+static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr)
+{
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *priv;
+
+	if (!mlx5e_rep_is_lag_netdev(netdev))
+		return;
+
+	/* Nothing to setup for new enslaved representor */
+	if (info->linking)
+		return;
+
+	priv = netdev_priv(netdev);
+	rpriv = priv->ppriv;
+	netdev_dbg(netdev, "Unslave, reset vport(%d) egress acl\n", rpriv->rep->vport);
+
+	/* Reset all egress acl rules of unslave representor's vport */
+	mlx5_esw_acl_egress_vport_unbond(priv->mdev->priv.eswitch,
+					 rpriv->rep->vport);
+}
+
+/* Bond device of representors and netdev events are used here in specific way
+ * to support eswitch vports bonding and to perform failover of eswitch vport
+ * by modifying the vport's egress acl of lower dev representors. Thus this
+ * also change the traditional behavior of lower dev under bond device.
+ * All non-representor netdevs or representors of other vendors as lower dev
+ * of bond device are not supported.
+ */
+static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb,
+				       unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_CHANGELOWERSTATE:
+		mlx5e_rep_changelowerstate_event(netdev, ptr);
+		break;
+	case NETDEV_CHANGEUPPER:
+		mlx5e_rep_changeupper_event(netdev, ptr);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+/* If HW support eswitch vports bonding, register a specific notifier to
+ * handle it when two or more representors are bonded
+ */
+int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct net_device *netdev = rpriv->netdev;
+	struct mlx5e_priv *priv;
+	int ret = 0;
+
+	priv = netdev_priv(netdev);
+	if (!mlx5_esw_acl_egress_fwd2vport_supported(priv->mdev->priv.eswitch))
+		goto out;
+
+	uplink_priv->bond = kvzalloc(sizeof(*uplink_priv->bond), GFP_KERNEL);
+	if (!uplink_priv->bond) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	uplink_priv->bond->nb.notifier_call = mlx5e_rep_esw_bond_netevent;
+	ret = register_netdevice_notifier_dev_net(netdev,
+						  &uplink_priv->bond->nb,
+						  &uplink_priv->bond->nn);
+	if (ret) {
+		netdev_err(netdev, "register bonding netevent notifier, err(%d)\n", ret);
+		kvfree(uplink_priv->bond);
+		uplink_priv->bond = NULL;
+	}
+out:
+	return ret;
+}
+
+void mlx5e_rep_bond_cleanup(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+	if (!mlx5_esw_acl_egress_fwd2vport_supported(priv->mdev->priv.eswitch) ||
+	    !rpriv->uplink_priv.bond)
+		return;
+
+	unregister_netdevice_notifier_dev_net(rpriv->netdev,
+					      &rpriv->uplink_priv.bond->nb,
+					      &rpriv->uplink_priv.bond->nn);
+	kvfree(rpriv->uplink_priv.bond);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 4e13e37a9ecd..12593d75e885 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -959,16 +959,18 @@ static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
 
 	mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
 
+	mlx5e_rep_bond_init(rpriv);
 	err = mlx5e_rep_tc_netdevice_event_register(rpriv);
 	if (err) {
 		mlx5_core_err(priv->mdev, "Failed to register netdev notifier, err: %d\n",
 			      err);
-		goto tc_rep_cleanup;
+		goto err_event_reg;
 	}
 
 	return 0;
 
-tc_rep_cleanup:
+err_event_reg:
+	mlx5e_rep_bond_cleanup(rpriv);
 	mlx5e_rep_tc_cleanup(rpriv);
 	return err;
 }
@@ -1001,7 +1003,7 @@ static void mlx5e_cleanup_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
 {
 	mlx5e_rep_tc_netdevice_event_unregister(rpriv);
 	mlx5e_rep_indr_clean_block_privs(rpriv);
-
+	mlx5e_rep_bond_cleanup(rpriv);
 	mlx5e_rep_tc_cleanup(rpriv);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 1c4af8522467..7e56787aa224 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -56,6 +56,7 @@ struct mlx5e_neigh_update_table {
 };
 
 struct mlx5_tc_ct_priv;
+struct mlx5e_rep_bond;
 struct mlx5_rep_uplink_priv {
 	/* Filters DB - instantiated by the uplink representor and shared by
 	 * the uplink's VFs
@@ -89,6 +90,9 @@ struct mlx5_rep_uplink_priv {
 	struct mapping_ctx *tunnel_enc_opts_mapping;
 
 	struct mlx5_tc_ct_priv *ct_priv;
+
+	/* support eswitch vports bonding */
+	struct mlx5e_rep_bond *bond;
 };
 
 struct mlx5e_rep_priv {
@@ -211,6 +215,9 @@ struct mlx5e_rep_sq {
 
 void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev);
 void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev);
+int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv);
+void mlx5e_rep_bond_cleanup(struct mlx5e_rep_priv *rpriv);
+
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
-- 
cgit v1.2.3


From 553f9328385d954644d74dedb655f85b687a9470 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Fri, 2 Aug 2019 16:13:10 -0700
Subject: net/mlx5e: Support tc block sharing for representors

Currently offloading a rule over a tc block shared by multiple
representors fails because an e-switch global hashtable to keep
the mapping from tc cookies to mlx5e flow instances is used, and
tc block sharing offloads the same rule/cookie multiple times,
each time for different representor sharing the tc block.

Changing the implementation and behavior by acknowledging and returning
success if the same rule/cookie is offloaded again to other slave
representor sharing the tc block by setting, checking and comparing
the netdev that added the rule first.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 571da14809fe..f3e65a15c950 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -145,6 +145,7 @@ struct mlx5e_tc_flow {
 	struct list_head	hairpin; /* flows sharing the same hairpin */
 	struct list_head	peer;    /* flows with peer flow */
 	struct list_head	unready; /* flows not ready to be offloaded (e.g due to missing route) */
+	struct net_device	*orig_dev; /* netdev adding flow first */
 	int			tmp_efi_index;
 	struct list_head	tmp_list; /* temporary flow list used by neigh update */
 	refcount_t		refcnt;
@@ -4624,11 +4625,21 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 	return err;
 }
 
+static bool is_flow_rule_duplicate_allowed(struct net_device *dev,
+					   struct mlx5e_rep_priv *rpriv)
+{
+	/* Offloaded flow rule is allowed to duplicate on non-uplink representor
+	 * sharing tc block with other slaves of a lag device.
+	 */
+	return netif_is_lag_port(dev) && rpriv->rep->vport != MLX5_VPORT_UPLINK;
+}
+
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct flow_cls_offload *f, unsigned long flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5e_tc_flow *flow;
 	int err = 0;
 
@@ -4636,6 +4647,12 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params);
 	rcu_read_unlock();
 	if (flow) {
+		/* Same flow rule offloaded to non-uplink representor sharing tc block,
+		 * just return 0.
+		 */
+		if (is_flow_rule_duplicate_allowed(dev, rpriv) && flow->orig_dev != dev)
+			goto out;
+
 		NL_SET_ERR_MSG_MOD(extack,
 				   "flow cookie already exists, ignoring");
 		netdev_warn_once(priv->netdev,
@@ -4650,6 +4667,12 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
+	/* Flow rule offloaded to non-uplink representor sharing tc block,
+	 * set the flow's owner dev.
+	 */
+	if (is_flow_rule_duplicate_allowed(dev, rpriv))
+		flow->orig_dev = dev;
+
 	err = rhashtable_lookup_insert_fast(tc_ht, &flow->node, tc_ht_params);
 	if (err)
 		goto err_free;
-- 
cgit v1.2.3


From d34eb2fcd00472323d9e26ee0aec498c2c6f5b6f Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 5 Mar 2019 21:11:14 +0200
Subject: net/mlx5e: Offload flow rules to active lower representor

When a bond device is created over one or more non uplink representors,
and when a flow rule is offloaded to such bond device, offload a rule
to the active lower device.

Assuming that this is active-backup lag, the rules should be offloaded
to the active lower device which is the representor of the direct
path (not the failover).

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 35 ++++++++++++++++++-------
 1 file changed, 26 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f3e65a15c950..58f797da4d8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -50,6 +50,7 @@
 #include <net/arp.h>
 #include <net/ipv6_stubs.h>
 #include <net/bareudp.h>
+#include <net/bonding.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en/rep/tc.h"
@@ -3759,6 +3760,28 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev,
+					  struct net_device *out_dev)
+{
+	struct net_device *fdb_out_dev = out_dev;
+	struct net_device *uplink_upper;
+
+	rcu_read_lock();
+	uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev);
+	if (uplink_upper && netif_is_lag_master(uplink_upper) &&
+	    uplink_upper == out_dev) {
+		fdb_out_dev = uplink_dev;
+	} else if (netif_is_lag_master(out_dev)) {
+		fdb_out_dev = bond_option_active_slave_get_rcu(netdev_priv(out_dev));
+		if (fdb_out_dev &&
+		    (!mlx5e_eswitch_rep(fdb_out_dev) ||
+		     !netdev_port_same_parent_id(fdb_out_dev, uplink_dev)))
+			fdb_out_dev = NULL;
+	}
+	rcu_read_unlock();
+	return fdb_out_dev;
+}
+
 static int add_vlan_push_action(struct mlx5e_priv *priv,
 				struct mlx5_esw_flow_attr *attr,
 				struct net_device **out_dev,
@@ -4074,7 +4097,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			} else if (netdev_port_same_parent_id(priv->netdev, out_dev)) {
 				struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 				struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
-				struct net_device *uplink_upper;
 
 				if (is_duplicated_output_device(priv->netdev,
 								out_dev,
@@ -4086,14 +4108,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				ifindexes[if_count] = out_dev->ifindex;
 				if_count++;
 
-				rcu_read_lock();
-				uplink_upper =
-					netdev_master_upper_dev_get_rcu(uplink_dev);
-				if (uplink_upper &&
-				    netif_is_lag_master(uplink_upper) &&
-				    uplink_upper == out_dev)
-					out_dev = uplink_dev;
-				rcu_read_unlock();
+				out_dev = get_fdb_out_dev(uplink_dev, out_dev);
+				if (!out_dev)
+					return -ENODEV;
 
 				if (is_vlan_dev(out_dev)) {
 					err = add_vlan_push_action(priv, attr,
-- 
cgit v1.2.3


From d97555e1452943264295cd3c1f066474bc3660dd Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Fri, 28 Feb 2020 14:28:27 -0800
Subject: net/mlx5e: Add bond_metadata and its slave entries

Adding bond_metadata and its slave entries to represent a lag device
and its slaves VF representors. Bond_metadata structure includes a
unique metadata shared by slaves VF respresentors, and a list of slaves
representors slave entries.

On enslaving event, create a bond_metadata structure representing
the upper lag device of this slave representor if it has not been
created yet. Create and add entry for the slave representor to the
slaves list.

On unslaving event, free the slave entry of the slave representor.
On the last unslave event, free the bond_metadata structure and its
resources.

Introduce APIs to create and remove bond_metadata and its resources,
enslave and unslave VF representor slave entries.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/bond.c  | 128 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |   5 +
 2 files changed, 133 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
index d0aab36f1947..932e94362ceb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2020 Mellanox Technologies Inc. All rights reserved. */
 
+#include <linux/netdevice.h>
+#include <linux/list.h>
 #include <net/lag.h>
 
 #include "mlx5_core.h"
@@ -11,8 +13,132 @@
 struct mlx5e_rep_bond {
 	struct notifier_block nb;
 	struct netdev_net_notifier nn;
+	struct list_head metadata_list;
 };
 
+struct mlx5e_rep_bond_slave_entry {
+	struct list_head list;
+	struct net_device *netdev;
+};
+
+struct mlx5e_rep_bond_metadata {
+	struct list_head list; /* link to global list of rep_bond_metadata */
+	struct mlx5_eswitch *esw;
+	 /* private of uplink holding rep bond metadata list */
+	struct net_device *lag_dev;
+	u32 metadata_reg_c_0;
+
+	struct list_head slaves_list; /* slaves list */
+	int slaves;
+};
+
+static struct mlx5e_rep_bond_metadata *
+mlx5e_lookup_rep_bond_metadata(struct mlx5_rep_uplink_priv *uplink_priv,
+			       const struct net_device *lag_dev)
+{
+	struct mlx5e_rep_bond_metadata *found = NULL;
+	struct mlx5e_rep_bond_metadata *cur;
+
+	list_for_each_entry(cur, &uplink_priv->bond->metadata_list, list) {
+		if (cur->lag_dev == lag_dev) {
+			found = cur;
+			break;
+		}
+	}
+
+	return found;
+}
+
+static struct mlx5e_rep_bond_slave_entry *
+mlx5e_lookup_rep_bond_slave_entry(struct mlx5e_rep_bond_metadata *mdata,
+				  const struct net_device *netdev)
+{
+	struct mlx5e_rep_bond_slave_entry *found = NULL;
+	struct mlx5e_rep_bond_slave_entry *cur;
+
+	list_for_each_entry(cur, &mdata->slaves_list, list) {
+		if (cur->netdev == netdev) {
+			found = cur;
+			break;
+		}
+	}
+
+	return found;
+}
+
+static void mlx5e_rep_bond_metadata_release(struct mlx5e_rep_bond_metadata *mdata)
+{
+	netdev_dbg(mdata->lag_dev, "destroy rep_bond_metadata(%d)\n",
+		   mdata->metadata_reg_c_0);
+	list_del(&mdata->list);
+	WARN_ON(!list_empty(&mdata->slaves_list));
+	kfree(mdata);
+}
+
+/* This must be called under rtnl_lock */
+int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
+			   struct net_device *lag_dev)
+{
+	struct mlx5e_rep_bond_slave_entry *s_entry;
+	struct mlx5e_rep_bond_metadata *mdata;
+	struct mlx5e_rep_priv *rpriv;
+
+	ASSERT_RTNL();
+
+	rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	mdata = mlx5e_lookup_rep_bond_metadata(&rpriv->uplink_priv, lag_dev);
+	if (!mdata) {
+		/* First netdev becomes slave, no metadata presents the lag_dev. Create one */
+		mdata = kzalloc(sizeof(*mdata), GFP_KERNEL);
+		if (!mdata)
+			return -ENOMEM;
+
+		mdata->lag_dev = lag_dev;
+		mdata->esw = esw;
+		INIT_LIST_HEAD(&mdata->slaves_list);
+		list_add(&mdata->list, &rpriv->uplink_priv.bond->metadata_list);
+
+		netdev_dbg(lag_dev, "create rep_bond_metadata(%d)\n",
+			   mdata->metadata_reg_c_0);
+	}
+
+	s_entry = kzalloc(sizeof(*s_entry), GFP_KERNEL);
+	if (!s_entry)
+		return -ENOMEM;
+
+	s_entry->netdev = netdev;
+	mdata->slaves++;
+	list_add_tail(&s_entry->list, &mdata->slaves_list);
+
+	return 0;
+}
+
+/* This must be called under rtnl_lock */
+void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
+			    const struct net_device *netdev,
+			    const struct net_device *lag_dev)
+{
+	struct mlx5e_rep_bond_slave_entry *s_entry;
+	struct mlx5e_rep_bond_metadata *mdata;
+	struct mlx5e_rep_priv *rpriv;
+
+	ASSERT_RTNL();
+
+	rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	mdata = mlx5e_lookup_rep_bond_metadata(&rpriv->uplink_priv, lag_dev);
+	if (!mdata)
+		return;
+
+	s_entry = mlx5e_lookup_rep_bond_slave_entry(mdata, netdev);
+	if (!s_entry)
+		return;
+
+	list_del(&s_entry->list);
+	if (--mdata->slaves == 0)
+		mlx5e_rep_bond_metadata_release(mdata);
+	kfree(s_entry);
+}
+
 static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -133,6 +259,7 @@ int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv)
 		goto out;
 	}
 
+	INIT_LIST_HEAD(&uplink_priv->bond->metadata_list);
 	uplink_priv->bond->nb.notifier_call = mlx5e_rep_esw_bond_netevent;
 	ret = register_netdevice_notifier_dev_net(netdev,
 						  &uplink_priv->bond->nb,
@@ -142,6 +269,7 @@ int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv)
 		kvfree(uplink_priv->bond);
 		uplink_priv->bond = NULL;
 	}
+
 out:
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 7e56787aa224..ed741b6e6af2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -217,6 +217,11 @@ void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev);
 void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev);
 int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv);
 void mlx5e_rep_bond_cleanup(struct mlx5e_rep_priv *rpriv);
+int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
+			   struct net_device *lag_dev);
+void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
+			    const struct net_device *netdev,
+			    const struct net_device *lag_dev);
 
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
-- 
cgit v1.2.3


From 133dcfc577eaec6538db4ebd8b9205b361f59018 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Fri, 28 Feb 2020 16:10:34 -0800
Subject: net/mlx5: E-Switch, Alloc and free unique metadata for match

Introduce infrastructure to create unique metadata for match
for vport without depending on vport_num. Vport uses its
default metadata for match in standalone configuration but
will share a different unique "bond_metadata" for match with
other vports in bond configuration.

Using ida to generate unique metadata for match for vports
in default and bond configurations.

Introduce APIs to generate, free metadata for match.
Introduce APIs to set vport's bond_metadata and replace its
ingress acl rules with bond_metatada.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/esw/acl/ingress_ofld.c      | 29 +++++++
 .../net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h |  2 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |  2 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  6 ++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 96 ++++++++++++++--------
 5 files changed, 103 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
index 1bae549f3fa7..4e55d7225a26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
@@ -291,3 +291,32 @@ void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw,
 	esw_acl_ingress_ofld_groups_destroy(vport);
 	esw_acl_ingress_table_destroy(vport);
 }
+
+/* Caller must hold rtnl_lock */
+int mlx5_esw_acl_ingress_vport_bond_update(struct mlx5_eswitch *esw, u16 vport_num,
+					   u32 metadata)
+{
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
+	int err;
+
+	if (WARN_ON_ONCE(IS_ERR(vport))) {
+		esw_warn(esw->dev, "vport(%d) invalid!\n", vport_num);
+		err = PTR_ERR(vport);
+		goto out;
+	}
+
+	esw_acl_ingress_ofld_rules_destroy(esw, vport);
+
+	vport->metadata = metadata ? metadata : vport->default_metadata;
+
+	/* Recreate ingress acl rules with vport->metadata */
+	err = esw_acl_ingress_ofld_rules_create(esw, vport);
+	if (err)
+		goto out;
+
+	return 0;
+
+out:
+	vport->metadata = vport->default_metadata;
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
index 90ddc5d7da46..c57869b93d60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h
@@ -23,5 +23,7 @@ static inline bool mlx5_esw_acl_egress_fwd2vport_supported(struct mlx5_eswitch *
 /* Eswitch acl ingress external APIs */
 int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
 void esw_acl_ingress_ofld_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+int mlx5_esw_acl_ingress_vport_bond_update(struct mlx5_eswitch *esw, u16 vport_num,
+					   u32 metadata);
 
 #endif /* __MLX5_ESWITCH_ACL_OFLD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 20ab13ff2303..1116ab9bea6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1730,6 +1730,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	mutex_init(&esw->offloads.decap_tbl_lock);
 	hash_init(esw->offloads.decap_tbl);
 	atomic64_set(&esw->offloads.num_flows, 0);
+	ida_init(&esw->offloads.vport_metadata_ida);
 	mutex_init(&esw->state_lock);
 	mutex_init(&esw->mode_lock);
 
@@ -1768,6 +1769,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	esw_offloads_cleanup_reps(esw);
 	mutex_destroy(&esw->mode_lock);
 	mutex_destroy(&esw->state_lock);
+	ida_destroy(&esw->offloads.vport_metadata_ida);
 	mutex_destroy(&esw->offloads.mod_hdr.lock);
 	mutex_destroy(&esw->offloads.encap_tbl_lock);
 	mutex_destroy(&esw->offloads.decap_tbl_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 7b6b3686b666..a5175e98c0b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -149,6 +149,8 @@ struct mlx5_vport {
 
 	struct vport_ingress    ingress;
 	struct vport_egress     egress;
+	u32                     default_metadata;
+	u32                     metadata;
 
 	struct mlx5_vport_info  info;
 
@@ -224,6 +226,7 @@ struct mlx5_esw_offload {
 	u8 inline_mode;
 	atomic64_t num_flows;
 	enum devlink_eswitch_encap_mode encap;
+	struct ida vport_metadata_ida;
 };
 
 /* E-Switch MC FDB table hash node */
@@ -292,6 +295,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 
+u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw);
+void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata);
+
 int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 			       u32 rate_mbps);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 11bc9cc1d5f0..060354bb211a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/etherdevice.h>
+#include <linux/idr.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
 #include <linux/mlx5/vport.h>
@@ -1877,15 +1878,69 @@ static bool esw_use_vport_metadata(const struct mlx5_eswitch *esw)
 	       esw_check_vport_match_metadata_supported(esw);
 }
 
+u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
+{
+	u32 num_vports = GENMASK(ESW_VPORT_BITS - 1, 0) - 1;
+	u32 vhca_id_mask = GENMASK(ESW_VHCA_ID_BITS - 1, 0);
+	u32 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
+	u32 start;
+	u32 end;
+	int id;
+
+	/* Make sure the vhca_id fits the ESW_VHCA_ID_BITS */
+	WARN_ON_ONCE(vhca_id >= BIT(ESW_VHCA_ID_BITS));
+
+	/* Trim vhca_id to ESW_VHCA_ID_BITS */
+	vhca_id &= vhca_id_mask;
+
+	start = (vhca_id << ESW_VPORT_BITS);
+	end = start + num_vports;
+	if (!vhca_id)
+		start += 1; /* zero is reserved/invalid metadata */
+	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, start, end, GFP_KERNEL);
+
+	return (id < 0) ? 0 : id;
+}
+
+void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata)
+{
+	ida_free(&esw->offloads.vport_metadata_ida, metadata);
+}
+
+static int esw_offloads_vport_metadata_setup(struct mlx5_eswitch *esw,
+					     struct mlx5_vport *vport)
+{
+	if (vport->vport == MLX5_VPORT_UPLINK)
+		return 0;
+
+	vport->default_metadata = mlx5_esw_match_metadata_alloc(esw);
+	vport->metadata = vport->default_metadata;
+	return vport->metadata ? 0 : -ENOSPC;
+}
+
+static void esw_offloads_vport_metadata_cleanup(struct mlx5_eswitch *esw,
+						struct mlx5_vport *vport)
+{
+	if (vport->vport == MLX5_VPORT_UPLINK || !vport->default_metadata)
+		return;
+
+	WARN_ON(vport->metadata != vport->default_metadata);
+	mlx5_esw_match_metadata_free(esw, vport->default_metadata);
+}
+
 int
 esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 				     struct mlx5_vport *vport)
 {
 	int err;
 
+	err = esw_offloads_vport_metadata_setup(esw, vport);
+	if (err)
+		goto metadata_err;
+
 	err = esw_acl_ingress_ofld_setup(esw, vport);
 	if (err)
-		return err;
+		goto ingress_err;
 
 	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
 		err = esw_acl_egress_ofld_setup(esw, vport);
@@ -1897,6 +1952,9 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 
 egress_err:
 	esw_acl_ingress_ofld_cleanup(esw, vport);
+ingress_err:
+	esw_offloads_vport_metadata_cleanup(esw, vport);
+metadata_err:
 	return err;
 }
 
@@ -1906,6 +1964,7 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
 {
 	esw_acl_egress_ofld_cleanup(vport);
 	esw_acl_ingress_ofld_cleanup(esw, vport);
+	esw_offloads_vport_metadata_cleanup(esw, vport);
 }
 
 static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
@@ -2571,38 +2630,11 @@ EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);
 u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 					      u16 vport_num)
 {
-	u32 vport_num_mask = GENMASK(ESW_VPORT_BITS - 1, 0);
-	u32 vhca_id_mask = GENMASK(ESW_VHCA_ID_BITS - 1, 0);
-	u32 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
-	u32 val;
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 
-	/* Make sure the vhca_id fits the ESW_VHCA_ID_BITS */
-	WARN_ON_ONCE(vhca_id >= BIT(ESW_VHCA_ID_BITS));
-
-	/* Trim vhca_id to ESW_VHCA_ID_BITS */
-	vhca_id &= vhca_id_mask;
-
-	/* Make sure pf and ecpf map to end of ESW_VPORT_BITS range so they
-	 * don't overlap with VF numbers, and themselves, after trimming.
-	 */
-	WARN_ON_ONCE((MLX5_VPORT_UPLINK & vport_num_mask) <
-		     vport_num_mask - 1);
-	WARN_ON_ONCE((MLX5_VPORT_ECPF & vport_num_mask) <
-		     vport_num_mask - 1);
-	WARN_ON_ONCE((MLX5_VPORT_UPLINK & vport_num_mask) ==
-		     (MLX5_VPORT_ECPF & vport_num_mask));
-
-	/* Make sure that the VF vport_num fits ESW_VPORT_BITS and don't
-	 * overlap with pf and ecpf.
-	 */
-	if (vport_num != MLX5_VPORT_UPLINK &&
-	    vport_num != MLX5_VPORT_ECPF)
-		WARN_ON_ONCE(vport_num >= vport_num_mask - 1);
-
-	/* We can now trim vport_num to ESW_VPORT_BITS */
-	vport_num &= vport_num_mask;
+	if (WARN_ON_ONCE(IS_ERR(vport)))
+		return 0;
 
-	val = (vhca_id << ESW_VPORT_BITS) | vport_num;
-	return val << (32 - ESW_SOURCE_PORT_METADATA_BITS);
+	return vport->metadata << (32 - ESW_SOURCE_PORT_METADATA_BITS);
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
-- 
cgit v1.2.3


From 88e96e533cfa11e996c59a44bbb6b0e0b9891970 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Mon, 2 Mar 2020 10:33:49 -0800
Subject: net/mlx5e: Slave representors sharing unique metadata for match

Bonded slave representors' vports must share a unique metadata
for match.

On enslaving event of slave representor to lag device, allocate
new unique "bond_metadata" for match if this is the first slave.
The subsequent enslaved representors will share the same unique
"bond_metadata".

On unslaving event of slave representor, reset the slave
representor's vport to use its own default metadata.

Replace ingress acl and rx rules of the slave representors' vports
using new vport->bond_metadata.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/bond.c  | 65 ++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   | 22 +++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |  1 +
 3 files changed, 80 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
index 932e94362ceb..13500f60bef6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -71,6 +71,7 @@ static void mlx5e_rep_bond_metadata_release(struct mlx5e_rep_bond_metadata *mdat
 	netdev_dbg(mdata->lag_dev, "destroy rep_bond_metadata(%d)\n",
 		   mdata->metadata_reg_c_0);
 	list_del(&mdata->list);
+	mlx5_esw_match_metadata_free(mdata->esw, mdata->metadata_reg_c_0);
 	WARN_ON(!list_empty(&mdata->slaves_list));
 	kfree(mdata);
 }
@@ -82,6 +83,8 @@ int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
 	struct mlx5e_rep_bond_slave_entry *s_entry;
 	struct mlx5e_rep_bond_metadata *mdata;
 	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *priv;
+	int err;
 
 	ASSERT_RTNL();
 
@@ -96,6 +99,11 @@ int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
 		mdata->lag_dev = lag_dev;
 		mdata->esw = esw;
 		INIT_LIST_HEAD(&mdata->slaves_list);
+		mdata->metadata_reg_c_0 = mlx5_esw_match_metadata_alloc(esw);
+		if (!mdata->metadata_reg_c_0) {
+			kfree(mdata);
+			return -ENOSPC;
+		}
 		list_add(&mdata->list, &rpriv->uplink_priv.bond->metadata_list);
 
 		netdev_dbg(lag_dev, "create rep_bond_metadata(%d)\n",
@@ -103,14 +111,33 @@ int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
 	}
 
 	s_entry = kzalloc(sizeof(*s_entry), GFP_KERNEL);
-	if (!s_entry)
-		return -ENOMEM;
+	if (!s_entry) {
+		err = -ENOMEM;
+		goto entry_alloc_err;
+	}
 
 	s_entry->netdev = netdev;
+	priv = netdev_priv(netdev);
+	rpriv = priv->ppriv;
+
+	err = mlx5_esw_acl_ingress_vport_bond_update(esw, rpriv->rep->vport,
+						     mdata->metadata_reg_c_0);
+	if (err)
+		goto ingress_err;
+
 	mdata->slaves++;
 	list_add_tail(&s_entry->list, &mdata->slaves_list);
+	netdev_dbg(netdev, "enslave rep vport(%d) lag_dev(%s) metadata(0x%x)\n",
+		   rpriv->rep->vport, lag_dev->name, mdata->metadata_reg_c_0);
 
 	return 0;
+
+ingress_err:
+	kfree(s_entry);
+entry_alloc_err:
+	if (!mdata->slaves)
+		mlx5e_rep_bond_metadata_release(mdata);
+	return err;
 }
 
 /* This must be called under rtnl_lock */
@@ -121,6 +148,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
 	struct mlx5e_rep_bond_slave_entry *s_entry;
 	struct mlx5e_rep_bond_metadata *mdata;
 	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *priv;
 
 	ASSERT_RTNL();
 
@@ -133,7 +161,16 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
 	if (!s_entry)
 		return;
 
+	priv = netdev_priv(netdev);
+	rpriv = priv->ppriv;
+
+	mlx5_esw_acl_ingress_vport_bond_update(esw, rpriv->rep->vport, 0);
+	mlx5e_rep_bond_update(priv, false);
 	list_del(&s_entry->list);
+
+	netdev_dbg(netdev, "unslave rep vport(%d) lag_dev(%s) metadata(0x%x)\n",
+		   rpriv->rep->vport, lag_dev->name, mdata->metadata_reg_c_0);
+
 	if (--mdata->slaves == 0)
 		mlx5e_rep_bond_metadata_release(mdata);
 	kfree(s_entry);
@@ -163,6 +200,7 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt
 	struct net_device *dev;
 	u16 acl_vport_num;
 	u16 fwd_vport_num;
+	int err;
 
 	if (!mlx5e_rep_is_lag_netdev(netdev))
 		return;
@@ -187,11 +225,28 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt
 		rpriv = priv->ppriv;
 		acl_vport_num = rpriv->rep->vport;
 		if (acl_vport_num != fwd_vport_num) {
-			mlx5_esw_acl_egress_vport_bond(priv->mdev->priv.eswitch,
-						       fwd_vport_num,
-						       acl_vport_num);
+			/* Only single rx_rule for unique bond_metadata should be
+			 * present, delete it if it's saved as passive vport's
+			 * rx_rule with destination as passive vport's root_ft
+			 */
+			mlx5e_rep_bond_update(priv, true);
+			err = mlx5_esw_acl_egress_vport_bond(priv->mdev->priv.eswitch,
+							     fwd_vport_num,
+							     acl_vport_num);
+			if (err)
+				netdev_warn(dev,
+					    "configure slave vport(%d) egress fwd, err(%d)",
+					    acl_vport_num, err);
 		}
 	}
+
+	/* Insert new rx_rule for unique bond_metadata, save it as active vport's
+	 * rx_rule with new destination as active vport's root_ft
+	 */
+	err = mlx5e_rep_bond_update(netdev_priv(netdev), false);
+	if (err)
+		netdev_warn(netdev, "configure active slave vport(%d) rx_rule, err(%d)",
+			    fwd_vport_num, err);
 }
 
 static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 12593d75e885..af89a4803c7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -854,6 +854,24 @@ static int mlx5e_create_rep_vport_rx_rule(struct mlx5e_priv *priv)
 	return 0;
 }
 
+static void rep_vport_rx_rule_destroy(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	if (!rpriv->vport_rx_rule)
+		return;
+
+	mlx5_del_flow_rules(rpriv->vport_rx_rule);
+	rpriv->vport_rx_rule = NULL;
+}
+
+int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup)
+{
+	rep_vport_rx_rule_destroy(priv);
+
+	return cleanup ? 0 : mlx5e_create_rep_vport_rx_rule(priv);
+}
+
 static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -918,9 +936,7 @@ err_close_drop_rq:
 
 static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-
-	mlx5_del_flow_rules(rpriv->vport_rx_rule);
+	rep_vport_rx_rule_destroy(priv);
 	mlx5e_destroy_rep_root_ft(priv);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index ed741b6e6af2..da9f1686d525 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -222,6 +222,7 @@ int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev,
 void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
 			    const struct net_device *netdev,
 			    const struct net_device *lag_dev);
+int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup);
 
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
-- 
cgit v1.2.3


From 9728366f53d283be943ee99d5989f155e55fc077 Mon Sep 17 00:00:00 2001
From: Vu Pham <vuhuong@mellanox.com>
Date: Thu, 12 Mar 2020 10:26:25 -0700
Subject: net/mlx5e: Use change upper event to setup representors'
 bond_metadata

Use change upper event to detect slave representor from
enslaving/unslaving to/from lag device.

On enslaving event, call mlx5_enslave_rep() API to create, add
this slave representor shadow entry to the slaves list of
bond_metadata structure representing master lag device and use
its metadata to setup ingress acl metadata header.

On unslaving event, resetting the vport of unslaved representor
to use its default ingress/egress acls and rx rules with its
default_metadata.

The last slave will free the shared bond_metadata and its
unique metadata.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/bond.c  | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
index 13500f60bef6..bdb71332cbf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -164,8 +164,13 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
 	priv = netdev_priv(netdev);
 	rpriv = priv->ppriv;
 
+	/* Reset bond_metadata to zero first then reset all ingress/egress
+	 * acls and rx rules of unslave representor's vport
+	 */
 	mlx5_esw_acl_ingress_vport_bond_update(esw, rpriv->rep->vport, 0);
+	mlx5_esw_acl_egress_vport_unbond(esw, rpriv->rep->vport);
 	mlx5e_rep_bond_update(priv, false);
+
 	list_del(&s_entry->list);
 
 	netdev_dbg(netdev, "unslave rep vport(%d) lag_dev(%s) metadata(0x%x)\n",
@@ -253,22 +258,23 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct mlx5e_rep_priv *rpriv;
+	struct net_device *lag_dev;
 	struct mlx5e_priv *priv;
 
 	if (!mlx5e_rep_is_lag_netdev(netdev))
 		return;
 
-	/* Nothing to setup for new enslaved representor */
-	if (info->linking)
-		return;
-
 	priv = netdev_priv(netdev);
 	rpriv = priv->ppriv;
-	netdev_dbg(netdev, "Unslave, reset vport(%d) egress acl\n", rpriv->rep->vport);
+	lag_dev = info->upper_dev;
 
-	/* Reset all egress acl rules of unslave representor's vport */
-	mlx5_esw_acl_egress_vport_unbond(priv->mdev->priv.eswitch,
-					 rpriv->rep->vport);
+	netdev_dbg(netdev, "%sslave vport(%d) lag(%s)\n",
+		   info->linking ? "en" : "un", rpriv->rep->vport, lag_dev->name);
+
+	if (info->linking)
+		mlx5e_rep_bond_enslave(priv->mdev->priv.eswitch, netdev, lag_dev);
+	else
+		mlx5e_rep_bond_unslave(priv->mdev->priv.eswitch, netdev, lag_dev);
 }
 
 /* Bond device of representors and netdev events are used here in specific way
-- 
cgit v1.2.3


From 810cbb25549b81f0c0848320f8a1614106d3a0e1 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 14 May 2020 23:42:45 -0500
Subject: net/mlx5: Add missing mutex destroy

Add mutex destroy calls to balance with mutex_init() done in the init
path.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 92f2395dd31a..30de3bf35c6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1272,7 +1272,7 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 					    mlx5_debugfs_root);
 	if (!priv->dbg_root) {
 		dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n");
-		return -ENOMEM;
+		goto err_dbg_root;
 	}
 
 	err = mlx5_health_init(dev);
@@ -1289,15 +1289,27 @@ err_pagealloc_init:
 	mlx5_health_cleanup(dev);
 err_health_init:
 	debugfs_remove(dev->priv.dbg_root);
-
+err_dbg_root:
+	mutex_destroy(&priv->pgdir_mutex);
+	mutex_destroy(&priv->alloc_mutex);
+	mutex_destroy(&priv->bfregs.wc_head.lock);
+	mutex_destroy(&priv->bfregs.reg_head.lock);
+	mutex_destroy(&dev->intf_state_mutex);
 	return err;
 }
 
 static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
+	struct mlx5_priv *priv = &dev->priv;
+
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg_root);
+	mutex_destroy(&priv->pgdir_mutex);
+	mutex_destroy(&priv->alloc_mutex);
+	mutex_destroy(&priv->bfregs.wc_head.lock);
+	mutex_destroy(&priv->bfregs.reg_head.lock);
+	mutex_destroy(&dev->intf_state_mutex);
 }
 
 #define MLX5_IB_MOD "mlx5_ib"
-- 
cgit v1.2.3


From 4a5d5d7392106a48c7db345a3843e854b66ea0ff Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 11 May 2020 19:20:29 +0000
Subject: net/mlx5e: Helper function to set ethertype

Set ethertype match in a helper function as a pre-step towards
optimizing it.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c  |  5 +----
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 21 +++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c     | 14 ++++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h     |  3 +++
 4 files changed, 27 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 995b2ef1fb3b..ba72410c55fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -134,10 +134,7 @@ mlx5_tc_ct_set_tuple_match(struct mlx5_flow_spec *spec,
 
 		flow_rule_match_basic(rule, &match);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(match.mask->n_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(match.key->n_proto));
+		mlx5e_tc_set_ethertype(headers_c, headers_v, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 match.mask->ip_proto);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index e99382f58807..6d7fded75264 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -512,6 +512,13 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_dissector_key_basic key_basic = {};
+		struct flow_dissector_key_basic mask_basic = {
+			.n_proto = htons(0xFFFF),
+		};
+		struct flow_match_basic match_basic = {
+			.key = &key_basic, .mask = &mask_basic,
+		};
 		struct flow_match_control match;
 		u16 addr_type;
 
@@ -537,10 +544,9 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 				 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
 				 ntohl(match.key->dst));
 
-			MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c,
-					 ethertype);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-				 ETH_P_IP);
+			key_basic.n_proto = htons(ETH_P_IP);
+			mlx5e_tc_set_ethertype(headers_c, headers_v,
+					       &match_basic);
 		} else if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
 			struct flow_match_ipv6_addrs match;
 
@@ -563,10 +569,9 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 			       &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout,
 								  ipv6));
 
-			MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c,
-					 ethertype);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-				 ETH_P_IPV6);
+			key_basic.n_proto = htons(ETH_P_IPV6);
+			mlx5e_tc_set_ethertype(headers_c, headers_v,
+					       &match_basic);
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 58f797da4d8d..680b9e090057 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2020,6 +2020,15 @@ u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow)
 	return flow->tunnel_id;
 }
 
+void mlx5e_tc_set_ethertype(void *headers_c, void *headers_v,
+			    struct flow_match_basic *match)
+{
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+		 ntohs(match->mask->n_proto));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+		 ntohs(match->key->n_proto));
+}
+
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5e_tc_flow *flow,
 			     struct mlx5_flow_spec *spec,
@@ -2241,10 +2250,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(match.mask->n_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(match.key->n_proto));
+		mlx5e_tc_set_ethertype(headers_c, headers_v, &match);
 
 		if (match.mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 037aa73bf9ab..144b71f571ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -170,6 +170,9 @@ void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 struct mlx5e_tc_flow;
 u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
 
+void mlx5e_tc_set_ethertype(void *headers_c, void *headers_v,
+			    struct flow_match_basic *match);
+
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
-- 
cgit v1.2.3


From fca533041aac0426f5b5618a564aeb588fc125e9 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Tue, 19 May 2020 05:55:59 +0000
Subject: net/mlx5e: Optimize performance for IPv4/IPv6 ethertype

The HW is optimized for IPv4/IPv6. For such cases, pending capability,
avoid matching on ethertype, and use ip_version field instead.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/diag/fs_tracepoint.c        | 85 +++++++++++-----------
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c |  7 +-
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |  8 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 40 +++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |  5 +-
 5 files changed, 85 insertions(+), 60 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 8ecac81a385d..a700f3c86899 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -76,58 +76,59 @@ static void print_lyr_2_4_hdrs(struct trace_seq *p,
 		.v = MLX5_GET(fte_match_set_lyr_2_4, value, dmac_47_16) << 16 |
 		     MLX5_GET(fte_match_set_lyr_2_4, value, dmac_15_0)};
 	MASK_VAL_L2(u16, ethertype, ethertype);
+	MASK_VAL_L2(u8, ip_version, ip_version);
 
 	PRINT_MASKED_VALP(smac, u8 *, p, "%pM");
 	PRINT_MASKED_VALP(dmac, u8 *, p, "%pM");
 	PRINT_MASKED_VAL(ethertype, p, "%04x");
 
-	if (ethertype.m == 0xffff) {
-		if (ethertype.v == ETH_P_IP) {
+	if ((ethertype.m == 0xffff && ethertype.v == ETH_P_IP) ||
+	    (ip_version.m == 0xf && ip_version.v == 4)) {
 #define MASK_VAL_L2_BE(type, name, fld) \
 	MASK_VAL_BE(type, fte_match_set_lyr_2_4, name, mask, value, fld)
-			MASK_VAL_L2_BE(u32, src_ipv4,
-				       src_ipv4_src_ipv6.ipv4_layout.ipv4);
-			MASK_VAL_L2_BE(u32, dst_ipv4,
-				       dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+		MASK_VAL_L2_BE(u32, src_ipv4,
+			       src_ipv4_src_ipv6.ipv4_layout.ipv4);
+		MASK_VAL_L2_BE(u32, dst_ipv4,
+			       dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
 
-			PRINT_MASKED_VALP(src_ipv4, typeof(&src_ipv4.v), p,
-					  "%pI4");
-			PRINT_MASKED_VALP(dst_ipv4, typeof(&dst_ipv4.v), p,
-					  "%pI4");
-		} else if (ethertype.v == ETH_P_IPV6) {
-			static const struct in6_addr full_ones = {
-				.in6_u.u6_addr32 = {__constant_htonl(0xffffffff),
-						    __constant_htonl(0xffffffff),
-						    __constant_htonl(0xffffffff),
-						    __constant_htonl(0xffffffff)},
-			};
-			DECLARE_MASK_VAL(struct in6_addr, src_ipv6);
-			DECLARE_MASK_VAL(struct in6_addr, dst_ipv6);
+		PRINT_MASKED_VALP(src_ipv4, typeof(&src_ipv4.v), p,
+				  "%pI4");
+		PRINT_MASKED_VALP(dst_ipv4, typeof(&dst_ipv4.v), p,
+				  "%pI4");
+	} else if ((ethertype.m == 0xffff && ethertype.v == ETH_P_IPV6) ||
+		   (ip_version.m == 0xf && ip_version.v == 6)) {
+		static const struct in6_addr full_ones = {
+			.in6_u.u6_addr32 = {__constant_htonl(0xffffffff),
+					    __constant_htonl(0xffffffff),
+					    __constant_htonl(0xffffffff),
+					    __constant_htonl(0xffffffff)},
+		};
+		DECLARE_MASK_VAL(struct in6_addr, src_ipv6);
+		DECLARE_MASK_VAL(struct in6_addr, dst_ipv6);
 
-			memcpy(src_ipv6.m.in6_u.u6_addr8,
-			       MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
-					    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-			       sizeof(src_ipv6.m));
-			memcpy(dst_ipv6.m.in6_u.u6_addr8,
-			       MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
-					    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-			       sizeof(dst_ipv6.m));
-			memcpy(src_ipv6.v.in6_u.u6_addr8,
-			       MLX5_ADDR_OF(fte_match_set_lyr_2_4, value,
-					    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-			       sizeof(src_ipv6.v));
-			memcpy(dst_ipv6.v.in6_u.u6_addr8,
-			       MLX5_ADDR_OF(fte_match_set_lyr_2_4, value,
-					    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-			       sizeof(dst_ipv6.v));
+		memcpy(src_ipv6.m.in6_u.u6_addr8,
+		       MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       sizeof(src_ipv6.m));
+		memcpy(dst_ipv6.m.in6_u.u6_addr8,
+		       MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       sizeof(dst_ipv6.m));
+		memcpy(src_ipv6.v.in6_u.u6_addr8,
+		       MLX5_ADDR_OF(fte_match_set_lyr_2_4, value,
+				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       sizeof(src_ipv6.v));
+		memcpy(dst_ipv6.v.in6_u.u6_addr8,
+		       MLX5_ADDR_OF(fte_match_set_lyr_2_4, value,
+				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       sizeof(dst_ipv6.v));
 
-			if (!memcmp(&src_ipv6.m, &full_ones, sizeof(full_ones)))
-				trace_seq_printf(p, "src_ipv6=%pI6 ",
-						 &src_ipv6.v);
-			if (!memcmp(&dst_ipv6.m, &full_ones, sizeof(full_ones)))
-				trace_seq_printf(p, "dst_ipv6=%pI6 ",
-						 &dst_ipv6.v);
-		}
+		if (!memcmp(&src_ipv6.m, &full_ones, sizeof(full_ones)))
+			trace_seq_printf(p, "src_ipv6=%pI6 ",
+					 &src_ipv6.v);
+		if (!memcmp(&dst_ipv6.m, &full_ones, sizeof(full_ones)))
+			trace_seq_printf(p, "dst_ipv6=%pI6 ",
+					 &dst_ipv6.v);
 	}
 
 #define PRINT_MASKED_VAL_L2(type, name, fld, p, format) {\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index ba72410c55fa..afc19dca1f5f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -119,7 +119,7 @@ mlx5_tc_ct_get_ct_priv(struct mlx5e_priv *priv)
 }
 
 static int
-mlx5_tc_ct_set_tuple_match(struct mlx5_flow_spec *spec,
+mlx5_tc_ct_set_tuple_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
 			   struct flow_rule *rule)
 {
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
@@ -134,7 +134,8 @@ mlx5_tc_ct_set_tuple_match(struct mlx5_flow_spec *spec,
 
 		flow_rule_match_basic(rule, &match);
 
-		mlx5e_tc_set_ethertype(headers_c, headers_v, &match);
+		mlx5e_tc_set_ethertype(priv->mdev, &match, true, headers_c,
+				       headers_v);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
 			 match.mask->ip_proto);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
@@ -530,7 +531,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	attr->counter = entry->counter;
 	attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
 
-	mlx5_tc_ct_set_tuple_match(spec, flow_rule);
+	mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
 	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG,
 				    entry->zone & MLX5_CT_ZONE_MASK,
 				    MLX5_CT_ZONE_MASK);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 6d7fded75264..7cce85faa16f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -545,8 +545,8 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 				 ntohl(match.key->dst));
 
 			key_basic.n_proto = htons(ETH_P_IP);
-			mlx5e_tc_set_ethertype(headers_c, headers_v,
-					       &match_basic);
+			mlx5e_tc_set_ethertype(priv->mdev, &match_basic, true,
+					       headers_c, headers_v);
 		} else if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
 			struct flow_match_ipv6_addrs match;
 
@@ -570,8 +570,8 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 								  ipv6));
 
 			key_basic.n_proto = htons(ETH_P_IPV6);
-			mlx5e_tc_set_ethertype(headers_c, headers_v,
-					       &match_basic);
+			mlx5e_tc_set_ethertype(priv->mdev, &match_basic, true,
+					       headers_c, headers_v);
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 680b9e090057..0f119c08b835 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2020,13 +2020,30 @@ u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow)
 	return flow->tunnel_id;
 }
 
-void mlx5e_tc_set_ethertype(void *headers_c, void *headers_v,
-			    struct flow_match_basic *match)
-{
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-		 ntohs(match->mask->n_proto));
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-		 ntohs(match->key->n_proto));
+void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev,
+			    struct flow_match_basic *match, bool outer,
+			    void *headers_c, void *headers_v)
+{
+	bool ip_version_cap;
+
+	ip_version_cap = outer ?
+		MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
+					  ft_field_support.outer_ip_version) :
+		MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
+					  ft_field_support.inner_ip_version);
+
+	if (ip_version_cap && match->mask->n_proto == htons(0xFFFF) &&
+	    (match->key->n_proto == htons(ETH_P_IP) ||
+	     match->key->n_proto == htons(ETH_P_IPV6))) {
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_version);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_version,
+			 match->key->n_proto == htons(ETH_P_IP) ? 4 : 6);
+	} else {
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+			 ntohs(match->mask->n_proto));
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+			 ntohs(match->key->n_proto));
+	}
 }
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
@@ -2250,7 +2267,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
-		mlx5e_tc_set_ethertype(headers_c, headers_v, &match);
+		mlx5e_tc_set_ethertype(priv->mdev, &match,
+				       match_level == outer_match_level,
+				       headers_c, headers_v);
 
 		if (match.mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
@@ -3126,16 +3145,19 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 {
 	const struct flow_action_entry *act;
 	bool modify_ip_header;
+	void *headers_c;
 	void *headers_v;
 	u16 ethertype;
 	u8 ip_proto;
 	int i, err;
 
+	headers_c = get_match_headers_criteria(actions, spec);
 	headers_v = get_match_headers_value(actions, spec);
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
-	if (ethertype != ETH_P_IP && ethertype != ETH_P_IPV6)
+	if (MLX5_GET(fte_match_set_lyr_2_4, headers_c, ip_version) == 0 &&
+	    ethertype != ETH_P_IP && ethertype != ETH_P_IPV6)
 		goto out_ok;
 
 	modify_ip_header = false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 144b71f571ea..5c330b0cae21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -170,8 +170,9 @@ void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 struct mlx5e_tc_flow;
 u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
 
-void mlx5e_tc_set_ethertype(void *headers_c, void *headers_v,
-			    struct flow_match_basic *match);
+void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev,
+			    struct flow_match_basic *match, bool outer,
+			    void *headers_c, void *headers_v);
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 
-- 
cgit v1.2.3


From cedb28191fdfb4fc1da0a7612465624998de7da2 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Wed, 20 May 2020 18:09:14 +0300
Subject: net/mlx5: DR, Add a spinlock to protect the send ring

Adding this lock will allow writing steering entries without
locking the dr_domain and allow parallel insertion.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c  | 13 +++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h |  1 +
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index b8d97d44be7b..f421013b0b54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -357,9 +357,11 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
 	u32 buff_offset;
 	int ret;
 
+	spin_lock(&send_ring->lock);
+
 	ret = dr_handle_pending_wc(dmn, send_ring);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	if (send_info->write.length > dmn->info.max_inline_size) {
 		buff_offset = (send_ring->tx_head &
@@ -377,7 +379,9 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
 	dr_fill_data_segs(send_ring, send_info);
 	dr_post_send(send_ring->qp, send_info);
 
-	return 0;
+out_unlock:
+	spin_unlock(&send_ring->lock);
+	return ret;
 }
 
 static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn,
@@ -563,9 +567,7 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
 	send_info.remote_addr = action->rewrite.chunk->mr_addr;
 	send_info.rkey = action->rewrite.chunk->rkey;
 
-	mutex_lock(&dmn->mutex);
 	ret = dr_postsend_icm_data(dmn, &send_info);
-	mutex_unlock(&dmn->mutex);
 
 	return ret;
 }
@@ -886,6 +888,7 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
 	init_attr.pdn = dmn->pdn;
 	init_attr.uar = dmn->uar;
 	init_attr.max_send_wr = QUEUE_SIZE;
+	spin_lock_init(&dmn->send_ring->lock);
 
 	dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr);
 	if (!dmn->send_ring->qp)  {
@@ -990,7 +993,9 @@ int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
 			return ret;
 	}
 
+	spin_lock(&send_ring->lock);
 	ret = dr_handle_pending_wc(dmn, send_ring);
+	spin_unlock(&send_ring->lock);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 984783238baa..b6061c639cb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -1043,6 +1043,7 @@ struct mlx5dr_send_ring {
 	struct ib_wc wc[MAX_SEND_CQE];
 	u8 sync_buff[MIN_READ_SYNC];
 	struct mlx5dr_mr *sync_mr;
+	spinlock_t lock; /* Protect the data path of the send ring */
 };
 
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
-- 
cgit v1.2.3


From ed03a418abe8e5a3ba541a805314bbf8a9eadda3 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Wed, 20 May 2020 18:09:35 +0300
Subject: net/mlx5: DR, Split RX and TX lock for parallel insertion

Change the locking flow to support RX and TX locks, splitting
the single lock to two will allow inserting rules in parallel
for RX and TX parts of the FDB.

Locking the dr_domain will be done by locking the RX domain
and the TX domain locks, this is mostly used for control operations
on the dr_domain. When inserting rules for RX or TX the single
nic_doamin RX or TX lock will be used. Splitting the lock is safe since
RX and TX domains are logically separated from each other, shared
objects such the send-ring and memory pool are protected by locks.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/steering/dr_domain.c        | 14 +++++-----
 .../mellanox/mlx5/core/steering/dr_matcher.c       | 10 +++----
 .../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 31 ++++++++++------------
 .../mellanox/mlx5/core/steering/dr_table.c         | 12 ++++-----
 .../mellanox/mlx5/core/steering/dr_types.h         | 24 ++++++++++++++++-
 5 files changed, 56 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 48b6358b6845..890767a2a7cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -297,7 +297,8 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
 	dmn->mdev = mdev;
 	dmn->type = type;
 	refcount_set(&dmn->refcount, 1);
-	mutex_init(&dmn->mutex);
+	mutex_init(&dmn->info.rx.mutex);
+	mutex_init(&dmn->info.tx.mutex);
 
 	if (dr_domain_caps_init(mdev, dmn)) {
 		mlx5dr_err(dmn, "Failed init domain, no caps\n");
@@ -345,9 +346,9 @@ int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
 	int ret = 0;
 
 	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
-		mutex_lock(&dmn->mutex);
+		mlx5dr_domain_lock(dmn);
 		ret = mlx5dr_send_ring_force_drain(dmn);
-		mutex_unlock(&dmn->mutex);
+		mlx5dr_domain_unlock(dmn);
 		if (ret) {
 			mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n",
 				   flags, ret);
@@ -371,7 +372,8 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 	dr_domain_uninit_cache(dmn);
 	dr_domain_uninit_resources(dmn);
 	dr_domain_caps_uninit(dmn);
-	mutex_destroy(&dmn->mutex);
+	mutex_destroy(&dmn->info.tx.mutex);
+	mutex_destroy(&dmn->info.rx.mutex);
 	kfree(dmn);
 	return 0;
 }
@@ -379,7 +381,7 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn)
 {
-	mutex_lock(&dmn->mutex);
+	mlx5dr_domain_lock(dmn);
 
 	if (dmn->peer_dmn)
 		refcount_dec(&dmn->peer_dmn->refcount);
@@ -389,5 +391,5 @@ void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 	if (dmn->peer_dmn)
 		refcount_inc(&dmn->peer_dmn->refcount);
 
-	mutex_unlock(&dmn->mutex);
+	mlx5dr_domain_unlock(dmn);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index a95938874798..31abcbb95ca2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -690,7 +690,7 @@ mlx5dr_matcher_create(struct mlx5dr_table *tbl,
 	refcount_set(&matcher->refcount, 1);
 	INIT_LIST_HEAD(&matcher->matcher_list);
 
-	mutex_lock(&tbl->dmn->mutex);
+	mlx5dr_domain_lock(tbl->dmn);
 
 	ret = dr_matcher_init(matcher, mask);
 	if (ret)
@@ -700,14 +700,14 @@ mlx5dr_matcher_create(struct mlx5dr_table *tbl,
 	if (ret)
 		goto matcher_uninit;
 
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 
 	return matcher;
 
 matcher_uninit:
 	dr_matcher_uninit(matcher);
 free_matcher:
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 	kfree(matcher);
 dec_ref:
 	refcount_dec(&tbl->refcount);
@@ -791,13 +791,13 @@ int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher)
 	if (refcount_read(&matcher->refcount) > 1)
 		return -EBUSY;
 
-	mutex_lock(&tbl->dmn->mutex);
+	mlx5dr_domain_lock(tbl->dmn);
 
 	dr_matcher_remove_from_tbl(matcher);
 	dr_matcher_uninit(matcher);
 	refcount_dec(&matcher->tbl->refcount);
 
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 	kfree(matcher);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index cce3ee7a6614..cd708dcc2e3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -938,7 +938,10 @@ static bool dr_rule_verify(struct mlx5dr_matcher *matcher,
 static int dr_rule_destroy_rule_nic(struct mlx5dr_rule *rule,
 				    struct mlx5dr_rule_rx_tx *nic_rule)
 {
+	mlx5dr_domain_nic_lock(nic_rule->nic_matcher->nic_tbl->nic_dmn);
 	dr_rule_clean_rule_members(rule, nic_rule);
+	mlx5dr_domain_nic_unlock(nic_rule->nic_matcher->nic_tbl->nic_dmn);
+
 	return 0;
 }
 
@@ -1039,18 +1042,18 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 	if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param))
 		return 0;
 
+	hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL);
+	if (!hw_ste_arr)
+		return -ENOMEM;
+
+	mlx5dr_domain_nic_lock(nic_dmn);
+
 	ret = mlx5dr_matcher_select_builders(matcher,
 					     nic_matcher,
 					     dr_rule_get_ipv(&param->outer),
 					     dr_rule_get_ipv(&param->inner));
 	if (ret)
-		goto out_err;
-
-	hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL);
-	if (!hw_ste_arr) {
-		ret = -ENOMEM;
-		goto out_err;
-	}
+		goto free_hw_ste;
 
 	/* Set the tag values inside the ste array */
 	ret = mlx5dr_ste_build_ste_arr(matcher, nic_matcher, param, hw_ste_arr);
@@ -1115,6 +1118,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 	if (htbl)
 		mlx5dr_htbl_put(htbl);
 
+	mlx5dr_domain_nic_unlock(nic_dmn);
+
 	kfree(hw_ste_arr);
 
 	return 0;
@@ -1129,8 +1134,8 @@ free_rule:
 		kfree(ste_info);
 	}
 free_hw_ste:
+	mlx5dr_domain_nic_unlock(nic_dmn);
 	kfree(hw_ste_arr);
-out_err:
 	return ret;
 }
 
@@ -1232,31 +1237,23 @@ struct mlx5dr_rule *mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
 {
 	struct mlx5dr_rule *rule;
 
-	mutex_lock(&matcher->tbl->dmn->mutex);
 	refcount_inc(&matcher->refcount);
 
 	rule = dr_rule_create_rule(matcher, value, num_actions, actions);
 	if (!rule)
 		refcount_dec(&matcher->refcount);
 
-	mutex_unlock(&matcher->tbl->dmn->mutex);
-
 	return rule;
 }
 
 int mlx5dr_rule_destroy(struct mlx5dr_rule *rule)
 {
 	struct mlx5dr_matcher *matcher = rule->matcher;
-	struct mlx5dr_table *tbl = rule->matcher->tbl;
 	int ret;
 
-	mutex_lock(&tbl->dmn->mutex);
-
 	ret = dr_rule_destroy_rule(rule);
-
-	mutex_unlock(&tbl->dmn->mutex);
-
 	if (!ret)
 		refcount_dec(&matcher->refcount);
+
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
index c2fe48d7b75a..b599b6beb5b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
@@ -14,7 +14,7 @@ int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
 	if (action && action->action_type != DR_ACTION_TYP_FT)
 		return -EOPNOTSUPP;
 
-	mutex_lock(&tbl->dmn->mutex);
+	mlx5dr_domain_lock(tbl->dmn);
 
 	if (!list_empty(&tbl->matcher_list))
 		last_matcher = list_last_entry(&tbl->matcher_list,
@@ -78,7 +78,7 @@ int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
 		refcount_inc(&action->refcount);
 
 out:
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 	return ret;
 }
 
@@ -95,7 +95,7 @@ static void dr_table_uninit_fdb(struct mlx5dr_table *tbl)
 
 static void dr_table_uninit(struct mlx5dr_table *tbl)
 {
-	mutex_lock(&tbl->dmn->mutex);
+	mlx5dr_domain_lock(tbl->dmn);
 
 	switch (tbl->dmn->type) {
 	case MLX5DR_DOMAIN_TYPE_NIC_RX:
@@ -112,7 +112,7 @@ static void dr_table_uninit(struct mlx5dr_table *tbl)
 		break;
 	}
 
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 }
 
 static int dr_table_init_nic(struct mlx5dr_domain *dmn,
@@ -177,7 +177,7 @@ static int dr_table_init(struct mlx5dr_table *tbl)
 
 	INIT_LIST_HEAD(&tbl->matcher_list);
 
-	mutex_lock(&tbl->dmn->mutex);
+	mlx5dr_domain_lock(tbl->dmn);
 
 	switch (tbl->dmn->type) {
 	case MLX5DR_DOMAIN_TYPE_NIC_RX:
@@ -201,7 +201,7 @@ static int dr_table_init(struct mlx5dr_table *tbl)
 		break;
 	}
 
-	mutex_unlock(&tbl->dmn->mutex);
+	mlx5dr_domain_unlock(tbl->dmn);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index b6061c639cb1..c6d5a81d138b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -636,6 +636,7 @@ struct mlx5dr_domain_rx_tx {
 	u64 drop_icm_addr;
 	u64 default_icm_addr;
 	enum mlx5dr_ste_entry_type ste_type;
+	struct mutex mutex; /* protect rx/tx domain */
 };
 
 struct mlx5dr_domain_info {
@@ -660,7 +661,6 @@ struct mlx5dr_domain {
 	struct mlx5_uars_page *uar;
 	enum mlx5dr_domain_type type;
 	refcount_t refcount;
-	struct mutex mutex; /* protect domain */
 	struct mlx5dr_icm_pool *ste_icm_pool;
 	struct mlx5dr_icm_pool *action_icm_pool;
 	struct mlx5dr_send_ring *send_ring;
@@ -814,6 +814,28 @@ struct mlx5dr_icm_chunk {
 	struct list_head *miss_list;
 };
 
+static inline void mlx5dr_domain_nic_lock(struct mlx5dr_domain_rx_tx *nic_dmn)
+{
+	mutex_lock(&nic_dmn->mutex);
+}
+
+static inline void mlx5dr_domain_nic_unlock(struct mlx5dr_domain_rx_tx *nic_dmn)
+{
+	mutex_unlock(&nic_dmn->mutex);
+}
+
+static inline void mlx5dr_domain_lock(struct mlx5dr_domain *dmn)
+{
+	mlx5dr_domain_nic_lock(&dmn->info.rx);
+	mlx5dr_domain_nic_lock(&dmn->info.tx);
+}
+
+static inline void mlx5dr_domain_unlock(struct mlx5dr_domain *dmn)
+{
+	mlx5dr_domain_nic_unlock(&dmn->info.tx);
+	mlx5dr_domain_nic_unlock(&dmn->info.rx);
+}
+
 static inline int
 mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps)
 {
-- 
cgit v1.2.3


From 3f0d97cdfe6e900a5c71817b0dfb77247afee36d Mon Sep 17 00:00:00 2001
From: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>
Date: Fri, 15 May 2020 17:42:20 -0700
Subject: ice: Check UMEM FQ size when allocating bufs

If a UMEM is present on a queue when an interface/queue pair is being
enabled, the driver will try to prepare the Rx buffers in advance to
improve performance. However, if fill queue is shorter than HW Rx ring,
the driver will report failure after getting the last address from the
fill queue.

This still lets the driver process the packets correctly during the NAPI
poll, but leads to a constant NAPI rescheduling. Not allocating the
buffers in advance would result in a potential performance decrease.

Commit d57d76428ae9 ("xsk: Add API to check for available entries in FQ")
provides an API that lets drivers check the number of addresses that the
fill queue holds.

Notify the user if fill queue is not long enough to prepare all buffers
before packet processing starts, and allocate the buffers during the
NAPI poll. If the fill queue size is sufficient, prepare Rx buffers in
advance.

Signed-off-by: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 18076e0d12d0..a174911d8994 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -281,7 +281,9 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
  */
 int ice_setup_rx_ctx(struct ice_ring *ring)
 {
+	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	int chain_len = ICE_MAX_CHAINED_RX_BUFS;
+	u16 num_bufs = ICE_DESC_UNUSED(ring);
 	struct ice_vsi *vsi = ring->vsi;
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
@@ -324,7 +326,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 				return err;
 			xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
 
-			dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
+			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
@@ -408,7 +410,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
 	if (err) {
-		dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+		dev_err(dev, "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
 			pf_q, err);
 		return -EIO;
 	}
@@ -426,13 +428,23 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
-	err = ring->xsk_umem ?
-	      ice_alloc_rx_bufs_zc(ring, ICE_DESC_UNUSED(ring)) :
-	      ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring));
-	if (err)
-		dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
-			 ring->xsk_umem ? "UMEM enabled " : "",
-			 ring->q_index, pf_q);
+	if (ring->xsk_umem) {
+		if (!xsk_buff_can_alloc(ring->xsk_umem, num_bufs)) {
+			dev_warn(dev, "UMEM does not provide enough addresses to fill %d buffers on Rx ring %d\n",
+				 num_bufs, ring->q_index);
+			dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n");
+
+			return 0;
+		}
+
+		err = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		if (err)
+			dev_info(dev, "Failed to allocate some buffers on UMEM enabled Rx ring %d (pf_q %d)\n",
+				 ring->q_index, pf_q);
+		return 0;
+	}
+
+	ice_alloc_rx_bufs(ring, num_bufs);
 
 	return 0;
 }
-- 
cgit v1.2.3


From b113cabd4378ddd98dccdd7748a16f9f1f094ef0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 27 May 2020 15:41:06 +0200
Subject: sfc: avoid an unused-variable warning

'nic_data' is no longer used outside of the #ifdef block
in efx_ef10_set_mac_address:

drivers/net/ethernet/sfc/ef10.c:3231:28: error: unused variable 'nic_data' [-Werror,-Wunused-variable]
        struct efx_ef10_nic_data *nic_data = efx->nic_data;

Move the variable into a local scope.

Fixes: dfcabb078847 ("sfc: move vport_id to struct efx_nic")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index e634e8110585..964c5e842cec 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3228,7 +3228,6 @@ reset_nic:
 static int efx_ef10_set_mac_address(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_SET_MAC_IN_LEN);
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	bool was_enabled = efx->port_enabled;
 	int rc;
 
@@ -3256,6 +3255,7 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx)
 
 #ifdef CONFIG_SFC_SRIOV
 	if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) {
+		struct efx_ef10_nic_data *nic_data = efx->nic_data;
 		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
 
 		if (rc == -EPERM) {
-- 
cgit v1.2.3


From 9918f2d22fd3ff1e76693512d29e743eba3dc8cb Mon Sep 17 00:00:00 2001
From: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Date: Fri, 15 May 2020 17:42:22 -0700
Subject: ice: Poll for reset completion when DDP load fails

There are certain cases where the DDP load fails and the FW issues a
core reset. For these cases, wait for reset to complete before
proceeding with reset of the driver init.

Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b64c4e796636..6583acf32575 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3086,6 +3086,9 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status)
 		case ICE_AQ_RC_EBADMAN:
 		case ICE_AQ_RC_EBADBUF:
 			dev_err(dev, "An error occurred on the device while loading the DDP package.  The device will be reset.\n");
+			/* poll for reset to complete */
+			if (ice_check_reset(hw))
+				dev_err(dev, "Error resetting device. Please reload the driver\n");
 			return;
 		default:
 			break;
-- 
cgit v1.2.3


From 072064a43ef38fab8559edfbf12f918f8acdd85b Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 15 May 2020 17:42:23 -0700
Subject: ice: cleanup VSI context initialization

Remove an unnecessary copy of vsi->info into ctxt->info in ice_vsi_init.
This line is essentially a no-op because ice_set_dflt_vsi_ctx performs
a memset to clear the info from the context structure.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 6f3ee8ac11ce..89e8e4f7f56f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -938,7 +938,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi)
 	if (!ctxt)
 		return -ENOMEM;
 
-	ctxt->info = vsi->info;
 	switch (vsi->type) {
 	case ICE_VSI_CTRL:
 	case ICE_VSI_LB:
-- 
cgit v1.2.3


From bc3a024101ca497bea4c69be4054c32a5c349f1d Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 15 May 2020 17:42:24 -0700
Subject: ice: fix potential double free in probe unrolling

If ice_init_interrupt_scheme fails, ice_probe will jump to clearing up
the interrupts. This can lead to some static analysis tools such as the
compiler sanitizers complaining about double free problems.

Since ice_init_interrupt_scheme already unrolls internally on failure,
there is no need to call ice_clear_interrupt_scheme when it fails. Add
a new unroll label and use that instead.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6583acf32575..5cffaf360cb0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3418,7 +3418,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_interrupt_unroll;
+		goto err_init_vsi_unroll;
 	}
 
 	/* In case of MSIX we are going to setup the misc vector right here
@@ -3511,6 +3511,7 @@ err_msix_misc_unroll:
 	ice_free_irq_msix_misc(pf);
 err_init_interrupt_unroll:
 	ice_clear_interrupt_scheme(pf);
+err_init_vsi_unroll:
 	devm_kfree(dev, pf->vsi);
 err_init_pf_unroll:
 	ice_deinit_pf(pf);
-- 
cgit v1.2.3


From c2b313b783e0441dab2441cc1ee216eb4b9447a6 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 15 May 2020 17:42:25 -0700
Subject: ice: fix kernel BUG if register_netdev fails

If register_netdev() fails, the driver will attempt to cleanup the
q_vectors and inadvertently trigger a kernel BUG due to a NULL pointer
dereference.

This occurs because cleaning up q_vectors attempts to call
netif_napi_del on napi_structs which were never initialized.

Resolve this by releasing the netdev in ice_cfg_netdev and setting
vsi->netdev to NULL. This ensures that after ice_cfg_netdev fails the
state is rewound to match as if ice_cfg_netdev was never called.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 5cffaf360cb0..69854b8644a6 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2428,7 +2428,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	err = register_netdev(vsi->netdev);
 	if (err)
-		goto err_destroy_devlink_port;
+		goto err_free_netdev;
 
 	devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev);
 
@@ -2439,9 +2439,11 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	return 0;
 
+err_free_netdev:
+	free_netdev(vsi->netdev);
+	vsi->netdev = NULL;
 err_destroy_devlink_port:
 	ice_devlink_destroy_port(pf);
-
 	return err;
 }
 
-- 
cgit v1.2.3


From d3112cd1abec7a28bbe885c2151875bcff4e9092 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Fri, 15 May 2020 17:42:26 -0700
Subject: ice: Declare functions static

ice_get_pfa_module_tlv() and ice_read_sr_word() are not being called
outside of their file. Declare them as static.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_nvm.c | 5 +++--
 drivers/net/ethernet/intel/ice/ice_nvm.h | 4 ----
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 7c2a06892bbb..b049c1c30c88 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -172,7 +172,8 @@ void ice_release_nvm(struct ice_hw *hw)
  *
  * Reads one 16 bit word from the Shadow RAM using the ice_read_sr_word_aq.
  */
-enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
+static enum ice_status
+ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
 {
 	enum ice_status status;
 
@@ -196,7 +197,7 @@ enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
  * Area (PFA) and returns the TLV pointer and length. The caller can
  * use these to read the variable length TLV value.
  */
-enum ice_status
+static enum ice_status
 ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		       u16 module_type)
 {
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h
index 999f273ba6ad..165eda07b93d 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.h
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.h
@@ -11,10 +11,6 @@ enum ice_status
 ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
 		  bool read_shadow_ram);
 enum ice_status
-ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
-		       u16 module_type);
-enum ice_status
 ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size);
 enum ice_status ice_init_nvm(struct ice_hw *hw);
-enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data);
 #endif /* _ICE_NVM_H_ */
-- 
cgit v1.2.3


From ac3716134a40b04e18a2dda78800797129138005 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:07 -0700
Subject: ice: Refactor ice_ena_vf_mappings to split MSIX and queue mappings

Currently ice_ena_vf_mappings() does all of the VF's MSIX and queue
mapping in one function. This makes it hard to digest. Fix this by
creating a new function for enabling MSIX mappings and one for enabling
queue mappings.

Also, rename some variables in the functions for clarity.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 91 +++++++++++++++---------
 1 file changed, 59 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index efd54299a220..621ec0cc6fff 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -651,55 +651,70 @@ ice_alloc_vf_res_exit:
 }
 
 /**
- * ice_ena_vf_mappings
- * @vf: pointer to the VF structure
+ * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware
+ * @vf: VF to enable MSIX mappings for
  *
- * Enable VF vectors and queues allocation by writing the details into
- * respective registers.
+ * Some of the registers need to be indexed/configured using hardware global
+ * device values and other registers need 0-based values, which represent PF
+ * based values.
  */
-static void ice_ena_vf_mappings(struct ice_vf *vf)
+static void ice_ena_vf_msix_mappings(struct ice_vf *vf)
 {
-	int abs_vf_id, abs_first, abs_last;
+	int device_based_first_msix, device_based_last_msix;
+	int pf_based_first_msix, pf_based_last_msix, v;
 	struct ice_pf *pf = vf->pf;
-	struct ice_vsi *vsi;
-	struct device *dev;
-	int first, last, v;
+	int device_based_vf_id;
 	struct ice_hw *hw;
 	u32 reg;
 
-	dev = ice_pf_to_dev(pf);
 	hw = &pf->hw;
-	vsi = pf->vsi[vf->lan_vsi_idx];
-	first = vf->first_vector_idx;
-	last = (first + pf->num_msix_per_vf) - 1;
-	abs_first = first + pf->hw.func_caps.common_cap.msix_vector_first_id;
-	abs_last = (abs_first + pf->num_msix_per_vf) - 1;
-	abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
-
-	/* VF Vector allocation */
-	reg = (((abs_first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) |
-	       ((abs_last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) |
-	       VPINT_ALLOC_VALID_M);
+	pf_based_first_msix = vf->first_vector_idx;
+	pf_based_last_msix = (pf_based_first_msix + pf->num_msix_per_vf) - 1;
+
+	device_based_first_msix = pf_based_first_msix +
+		pf->hw.func_caps.common_cap.msix_vector_first_id;
+	device_based_last_msix =
+		(device_based_first_msix + pf->num_msix_per_vf) - 1;
+	device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
+
+	reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) &
+		VPINT_ALLOC_FIRST_M) |
+	       ((device_based_last_msix << VPINT_ALLOC_LAST_S) &
+		VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M);
 	wr32(hw, VPINT_ALLOC(vf->vf_id), reg);
 
-	reg = (((abs_first << VPINT_ALLOC_PCI_FIRST_S)
+	reg = (((device_based_first_msix << VPINT_ALLOC_PCI_FIRST_S)
 		 & VPINT_ALLOC_PCI_FIRST_M) |
-	       ((abs_last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) |
-	       VPINT_ALLOC_PCI_VALID_M);
+	       ((device_based_last_msix << VPINT_ALLOC_PCI_LAST_S) &
+		VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M);
 	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);
+
 	/* map the interrupts to its functions */
-	for (v = first; v <= last; v++) {
-		reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
+	for (v = pf_based_first_msix; v <= pf_based_last_msix; v++) {
+		reg = (((device_based_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
 			GLINT_VECT2FUNC_VF_NUM_M) |
 		       ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) &
 			GLINT_VECT2FUNC_PF_NUM_M));
 		wr32(hw, GLINT_VECT2FUNC(v), reg);
 	}
 
-	/* Map mailbox interrupt. We put an explicit 0 here to remind us that
-	 * VF admin queue interrupts will go to VF MSI-X vector 0.
-	 */
-	wr32(hw, VPINT_MBX_CTL(abs_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M | 0);
+	/* Map mailbox interrupt to VF MSI-X vector 0 */
+	wr32(hw, VPINT_MBX_CTL(device_based_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M);
+}
+
+/**
+ * ice_ena_vf_q_mappings - enable Rx/Tx queue mappings for a VF
+ * @vf: VF to enable the mappings for
+ * @max_txq: max Tx queues allowed on the VF's VSI
+ * @max_rxq: max Rx queues allowed on the VF's VSI
+ */
+static void ice_ena_vf_q_mappings(struct ice_vf *vf, u16 max_txq, u16 max_rxq)
+{
+	struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	struct ice_hw *hw = &vf->pf->hw;
+	u32 reg;
+
 	/* set regardless of mapping mode */
 	wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M);
 
@@ -711,7 +726,7 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 		 */
 		reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) &
 			VPLAN_TX_QBASE_VFFIRSTQ_M) |
-		       (((vsi->alloc_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) &
+		       (((max_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) &
 			VPLAN_TX_QBASE_VFNUMQ_M));
 		wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg);
 	} else {
@@ -729,7 +744,7 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 		 */
 		reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) &
 			VPLAN_RX_QBASE_VFFIRSTQ_M) |
-		       (((vsi->alloc_txq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) &
+		       (((max_rxq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) &
 			VPLAN_RX_QBASE_VFNUMQ_M));
 		wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg);
 	} else {
@@ -737,6 +752,18 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 	}
 }
 
+/**
+ * ice_ena_vf_mappings - enable VF MSIX and queue mapping
+ * @vf: pointer to the VF structure
+ */
+static void ice_ena_vf_mappings(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
+
+	ice_ena_vf_msix_mappings(vf);
+	ice_ena_vf_q_mappings(vf, vsi->alloc_txq, vsi->alloc_rxq);
+}
+
 /**
  * ice_determine_res
  * @pf: pointer to the PF structure
-- 
cgit v1.2.3


From 02337f1f59148ad2d361feae0a11f6596b04632b Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:08 -0700
Subject: ice: Simplify ice_sriov_configure

Add a new function for checking if SR-IOV can be configured based on
the PF and/or device's state/capabilities. Also, simplify the flow in
ice_sriov_configure().

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 72 ++++++++++++++++--------
 1 file changed, 48 insertions(+), 24 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 621ec0cc6fff..b699ca81d8c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1460,6 +1460,8 @@ static bool ice_pf_state_is_nominal(struct ice_pf *pf)
  * ice_pci_sriov_ena - Enable or change number of VFs
  * @pf: pointer to the PF structure
  * @num_vfs: number of VFs to allocate
+ *
+ * Returns 0 on success and negative on failure
  */
 static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
 {
@@ -1467,20 +1469,10 @@ static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
 	struct device *dev = ice_pf_to_dev(pf);
 	int err;
 
-	if (!ice_pf_state_is_nominal(pf)) {
-		dev_err(dev, "Cannot enable SR-IOV, device not ready\n");
-		return -EBUSY;
-	}
-
-	if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) {
-		dev_err(dev, "This device is not capable of SR-IOV\n");
-		return -EOPNOTSUPP;
-	}
-
 	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
 		ice_free_vfs(pf);
 	else if (pre_existing_vfs && pre_existing_vfs == num_vfs)
-		return num_vfs;
+		return 0;
 
 	if (num_vfs > pf->num_vfs_supported) {
 		dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n",
@@ -1496,37 +1488,69 @@ static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
 	}
 
 	set_bit(ICE_FLAG_SRIOV_ENA, pf->flags);
-	return num_vfs;
+	return 0;
+}
+
+/**
+ * ice_check_sriov_allowed - check if SR-IOV is allowed based on various checks
+ * @pf: PF to enabled SR-IOV on
+ */
+static int ice_check_sriov_allowed(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+
+	if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) {
+		dev_err(dev, "This device is not capable of SR-IOV\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (ice_is_safe_mode(pf)) {
+		dev_err(dev, "SR-IOV cannot be configured - Device is in Safe Mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!ice_pf_state_is_nominal(pf)) {
+		dev_err(dev, "Cannot enable SR-IOV, device not ready\n");
+		return -EBUSY;
+	}
+
+	return 0;
 }
 
 /**
  * ice_sriov_configure - Enable or change number of VFs via sysfs
  * @pdev: pointer to a pci_dev structure
- * @num_vfs: number of VFs to allocate
+ * @num_vfs: number of VFs to allocate or 0 to free VFs
  *
- * This function is called when the user updates the number of VFs in sysfs.
+ * This function is called when the user updates the number of VFs in sysfs. On
+ * success return whatever num_vfs was set to by the caller. Return negative on
+ * failure.
  */
 int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 	struct device *dev = ice_pf_to_dev(pf);
+	int err;
 
-	if (ice_is_safe_mode(pf)) {
-		dev_err(dev, "SR-IOV cannot be configured - Device is in Safe Mode\n");
-		return -EOPNOTSUPP;
-	}
+	err = ice_check_sriov_allowed(pf);
+	if (err)
+		return err;
 
-	if (num_vfs)
-		return ice_pci_sriov_ena(pf, num_vfs);
+	if (!num_vfs) {
+		if (!pci_vfs_assigned(pdev)) {
+			ice_free_vfs(pf);
+			return 0;
+		}
 
-	if (!pci_vfs_assigned(pdev)) {
-		ice_free_vfs(pf);
-	} else {
 		dev_err(dev, "can't free VFs because some are assigned to VMs.\n");
 		return -EBUSY;
 	}
 
-	return 0;
+	err = ice_pci_sriov_ena(pf, num_vfs);
+	if (err)
+		return err;
+
+	return num_vfs;
 }
 
 /**
-- 
cgit v1.2.3


From cfcee02b6c15e8866d03cae3b80edc4e9ad8cc7d Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:09 -0700
Subject: ice: Add helper function for clearing VPGEN_VFRTRIG

Create a helper function for clearing VPGEN_VFRTRIG as this needs to be
done on reset to notify the VF that we are done resetting it. Also, it
needs to be done on SR-IOV initialization/creation in case it was left
in a bad state after SR-IOV tear down.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 31 +++++++++++++++---------
 1 file changed, 20 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index b699ca81d8c4..039f0b057603 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -961,6 +961,21 @@ static int ice_set_per_vf_res(struct ice_pf *pf)
 	return 0;
 }
 
+/**
+ * ice_clear_vf_reset_trigger - enable VF to access hardware
+ * @vf: VF to enabled hardware access for
+ */
+static void ice_clear_vf_reset_trigger(struct ice_vf *vf)
+{
+	struct ice_hw *hw = &vf->pf->hw;
+	u32 reg;
+
+	reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
+	reg &= ~VPGEN_VFRTRIG_VFSWR_M;
+	wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
+	ice_flush(hw);
+}
+
 /**
  * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset
  * @vf: pointer to the VF structure
@@ -974,26 +989,20 @@ static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
 {
 	struct ice_pf *pf = vf->pf;
 	struct ice_hw *hw;
-	u32 reg;
 
 	hw = &pf->hw;
 
-	/* PF software completes the flow by notifying VF that reset flow is
-	 * completed. This is done by enabling hardware by clearing the reset
-	 * bit in the VPGEN_VFRTRIG reg and setting VFR_STATE in the VFGEN_RSTAT
-	 * register to VFR completed (done at the end of this function)
-	 * By doing this we allow HW to access VF memory at any point. If we
-	 * did it any sooner, HW could access memory while it was being freed
-	 * in ice_free_vf_res(), causing an IOMMU fault.
+	/* Allow HW to access VF memory after calling
+	 * ice_clear_vf_reset_trigger(). If we did it any sooner, HW could
+	 * access memory while it was being freed in ice_free_vf_res(), causing
+	 * an IOMMU fault.
 	 *
 	 * On the other hand, this needs to be done ASAP, because the VF driver
 	 * is waiting for this to happen and may report a timeout. It's
 	 * harmless, but it gets logged into Guest OS kernel log, so best avoid
 	 * it.
 	 */
-	reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id));
-	reg &= ~VPGEN_VFRTRIG_VFSWR_M;
-	wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg);
+	ice_clear_vf_reset_trigger(vf);
 
 	/* reallocate VF resources to finish resetting the VSI state */
 	if (!ice_alloc_vf_res(vf)) {
-- 
cgit v1.2.3


From 916c7fdf5e938052a869f78b35a0ca2214d25b12 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:10 -0700
Subject: ice: Separate VF VSI initialization/creation from reset flow

Currently the same flow is used for VF VSI initialization/creation and VF
VSI reset. This makes the initialization/creation flow unnecessarily
complicated. Fix this by separating the initialization/creation of the
VF VSI from the reset flow.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 110 ++++++++++++++++++++++-
 1 file changed, 106 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 039f0b057603..72a9da3164d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1375,6 +1375,99 @@ static void ice_vc_notify_vf_reset(struct ice_vf *vf)
 			      NULL);
 }
 
+/**
+ * ice_init_vf_vsi_res - initialize/setup VF VSI resources
+ * @vf: VF to initialize/setup the VSI for
+ *
+ * This function creates a VSI for the VF, adds a VLAN 0 filter, and sets up the
+ * VF VSI's broadcast filter and is only used during initial VF creation.
+ */
+static int ice_init_vf_vsi_res(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	u8 broadcast[ETH_ALEN];
+	enum ice_status status;
+	struct ice_vsi *vsi;
+	struct device *dev;
+	int err;
+
+	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
+
+	dev = ice_pf_to_dev(pf);
+	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
+	if (!vsi) {
+		dev_err(dev, "Failed to create VF VSI\n");
+		return -ENOMEM;
+	}
+
+	vf->lan_vsi_idx = vsi->idx;
+	vf->lan_vsi_num = vsi->vsi_num;
+
+	err = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI);
+	if (err) {
+		dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n",
+			 vf->vf_id);
+		goto release_vsi;
+	}
+
+	eth_broadcast_addr(broadcast);
+	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
+	if (status) {
+		dev_err(dev, "Failed to add broadcast MAC filter for VF %d, status %s\n",
+			vf->vf_id, ice_stat_str(status));
+		err = ice_status_to_errno(status);
+		goto release_vsi;
+	}
+
+	vf->num_mac = 1;
+
+	return 0;
+
+release_vsi:
+	ice_vsi_release(vsi);
+	return err;
+}
+
+/**
+ * ice_start_vfs - start VFs so they are ready to be used by SR-IOV
+ * @pf: PF the VFs are associated with
+ */
+static int ice_start_vfs(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	int retval, i;
+
+	ice_for_each_vf(pf, i) {
+		struct ice_vf *vf = &pf->vf[i];
+
+		ice_clear_vf_reset_trigger(vf);
+
+		retval = ice_init_vf_vsi_res(vf);
+		if (retval) {
+			dev_err(ice_pf_to_dev(pf), "Failed to initialize VSI resources for VF %d, error %d\n",
+				vf->vf_id, retval);
+			goto teardown;
+		}
+
+		set_bit(ICE_VF_STATE_INIT, vf->vf_states);
+		ice_ena_vf_mappings(vf);
+		wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
+	}
+
+	ice_flush(hw);
+	return 0;
+
+teardown:
+	for (i = i - 1; i >= 0; i--) {
+		struct ice_vf *vf = &pf->vf[i];
+
+		ice_dis_vf_mappings(vf);
+		ice_vsi_release(pf->vsi[vf->lan_vsi_idx]);
+	}
+
+	return retval;
+}
+
 /**
  * ice_alloc_vfs - Allocate and set up VFs resources
  * @pf: pointer to the PF structure
@@ -1407,6 +1500,13 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 	pf->vf = vfs;
 	pf->num_alloc_vfs = num_alloc_vfs;
 
+	if (ice_set_per_vf_res(pf)) {
+		dev_err(dev, "Not enough resources for %d VFs, try with fewer number of VFs\n",
+			num_alloc_vfs);
+		ret = -ENOSPC;
+		goto err_unroll_sriov;
+	}
+
 	/* apply default profile */
 	ice_for_each_vf(pf, i) {
 		vfs[i].pf = pf;
@@ -1416,15 +1516,17 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 		/* assign default capabilities */
 		set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
 		vfs[i].spoofchk = true;
+		vfs[i].num_vf_qs = pf->num_qps_per_vf;
 	}
 
-	/* VF resources get allocated with initialization */
-	if (!ice_config_res_vfs(pf)) {
-		ret = -EIO;
+	if (ice_start_vfs(pf)) {
+		dev_err(dev, "Failed to start VF(s)\n");
+		ret = -EAGAIN;
 		goto err_unroll_sriov;
 	}
 
-	return ret;
+	clear_bit(__ICE_VF_DIS, pf->state);
+	return 0;
 
 err_unroll_sriov:
 	pf->vf = NULL;
-- 
cgit v1.2.3


From a06325a0901a887009d28e9fa06168d05c35c941 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:11 -0700
Subject: ice: Renaming and simplification in VF init path

Some function names weren't very clear and some portions of VF creation
could be moved into functions for clarity. Fix this by renaming some
functions and move pieces of code into clearly name functions.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 83 +++++++++++++++---------
 1 file changed, 54 insertions(+), 29 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 72a9da3164d9..92a442ec7314 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1469,16 +1469,56 @@ teardown:
 }
 
 /**
- * ice_alloc_vfs - Allocate and set up VFs resources
+ * ice_set_dflt_settings - set VF defaults during initialization/creation
+ * @pf: PF holding reference to all VFs for default configuration
+ */
+static void ice_set_dflt_settings_vfs(struct ice_pf *pf)
+{
+	int i;
+
+	ice_for_each_vf(pf, i) {
+		struct ice_vf *vf = &pf->vf[i];
+
+		vf->pf = pf;
+		vf->vf_id = i;
+		vf->vf_sw_id = pf->first_sw;
+		/* assign default capabilities */
+		set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vf->vf_caps);
+		vf->spoofchk = true;
+		vf->num_vf_qs = pf->num_qps_per_vf;
+	}
+}
+
+/**
+ * ice_alloc_vfs - allocate num_vfs in the PF structure
+ * @pf: PF to store the allocated VFs in
+ * @num_vfs: number of VFs to allocate
+ */
+static int ice_alloc_vfs(struct ice_pf *pf, int num_vfs)
+{
+	struct ice_vf *vfs;
+
+	vfs = devm_kcalloc(ice_pf_to_dev(pf), num_vfs, sizeof(*vfs),
+			   GFP_KERNEL);
+	if (!vfs)
+		return -ENOMEM;
+
+	pf->vf = vfs;
+	pf->num_alloc_vfs = num_vfs;
+
+	return 0;
+}
+
+/**
+ * ice_ena_vfs - enable VFs so they are ready to be used
  * @pf: pointer to the PF structure
- * @num_alloc_vfs: number of VFs to allocate
+ * @num_vfs: number of VFs to enable
  */
-static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
+static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
-	struct ice_vf *vfs;
-	int i, ret;
+	int ret;
 
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
@@ -1486,38 +1526,24 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 	set_bit(__ICE_OICR_INTR_DIS, pf->state);
 	ice_flush(hw);
 
-	ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
+	ret = pci_enable_sriov(pf->pdev, num_vfs);
 	if (ret) {
 		pf->num_alloc_vfs = 0;
 		goto err_unroll_intr;
 	}
-	/* allocate memory */
-	vfs = devm_kcalloc(dev, num_alloc_vfs, sizeof(*vfs), GFP_KERNEL);
-	if (!vfs) {
-		ret = -ENOMEM;
+
+	ret = ice_alloc_vfs(pf, num_vfs);
+	if (ret)
 		goto err_pci_disable_sriov;
-	}
-	pf->vf = vfs;
-	pf->num_alloc_vfs = num_alloc_vfs;
 
 	if (ice_set_per_vf_res(pf)) {
 		dev_err(dev, "Not enough resources for %d VFs, try with fewer number of VFs\n",
-			num_alloc_vfs);
+			num_vfs);
 		ret = -ENOSPC;
 		goto err_unroll_sriov;
 	}
 
-	/* apply default profile */
-	ice_for_each_vf(pf, i) {
-		vfs[i].pf = pf;
-		vfs[i].vf_sw_id = pf->first_sw;
-		vfs[i].vf_id = i;
-
-		/* assign default capabilities */
-		set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
-		vfs[i].spoofchk = true;
-		vfs[i].num_vf_qs = pf->num_qps_per_vf;
-	}
+	ice_set_dflt_settings_vfs(pf);
 
 	if (ice_start_vfs(pf)) {
 		dev_err(dev, "Failed to start VF(s)\n");
@@ -1529,9 +1555,8 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 	return 0;
 
 err_unroll_sriov:
+	devm_kfree(dev, pf->vf);
 	pf->vf = NULL;
-	devm_kfree(dev, vfs);
-	vfs = NULL;
 	pf->num_alloc_vfs = 0;
 err_pci_disable_sriov:
 	pci_disable_sriov(pf->pdev);
@@ -1591,8 +1616,8 @@ static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs)
 		return -EOPNOTSUPP;
 	}
 
-	dev_info(dev, "Allocating %d VFs\n", num_vfs);
-	err = ice_alloc_vfs(pf, num_vfs);
+	dev_info(dev, "Enabling %d VFs\n", num_vfs);
+	err = ice_ena_vfs(pf, num_vfs);
 	if (err) {
 		dev_err(dev, "Failed to enable SR-IOV: %d\n", err);
 		return err;
-- 
cgit v1.2.3


From eb2af3ee94de7f493745adc34bb9d170ced8c5a9 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:12 -0700
Subject: ice: Add function to set trust mode bit on reset

As the title says, use a function to set trust mode bit on reset.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 92a442ec7314..4005a4caf2f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -610,6 +610,18 @@ ice_alloc_vsi_res_exit:
 	return status;
 }
 
+/**
+ * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value
+ * @vf: VF to configure trust setting for
+ */
+static void ice_vf_set_host_trust_cfg(struct ice_vf *vf)
+{
+	if (vf->trusted)
+		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+	else
+		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+}
+
 /**
  * ice_alloc_vf_res - Allocate VF resources
  * @vf: pointer to the VF structure
@@ -635,10 +647,7 @@ static int ice_alloc_vf_res(struct ice_vf *vf)
 	if (status)
 		goto ice_alloc_vf_res_exit;
 
-	if (vf->trusted)
-		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
-	else
-		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
+	ice_vf_set_host_trust_cfg(vf);
 
 	/* VF is now completely initialized */
 	set_bit(ICE_VF_STATE_INIT, vf->vf_states);
-- 
cgit v1.2.3


From 350e822cd54ff331bb421a59b6c096bb1739d22b Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:13 -0700
Subject: ice: Add functions to rebuild host VLAN/MAC config for a VF

When resetting a VF the VLAN and MAC filter configurations need to be
replayed. Add helper functions for this purpose.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 121 +++++++++++++++++------
 1 file changed, 89 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 4005a4caf2f0..3a714c81b5b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -540,6 +540,82 @@ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
 	return pf->sriov_base_vector + vf->vf_id * pf->num_msix_per_vf;
 }
 
+/**
+ * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN
+ * @vf: VF to add MAC filters for
+ *
+ * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
+ * always re-adds either a VLAN 0 or port VLAN based filter after reset.
+ */
+static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	u16 vlan_id = 0;
+	int err;
+
+	if (vf->port_vlan_info) {
+		err = ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true);
+		if (err) {
+			dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n",
+				vf->vf_id, err);
+			return err;
+		}
+
+		vlan_id = vf->port_vlan_info & VLAN_VID_MASK;
+	}
+
+	/* vlan_id will either be 0 or the port VLAN number */
+	err = ice_vsi_add_vlan(vsi, vlan_id, ICE_FWD_TO_VSI);
+	if (err) {
+		dev_err(dev, "failed to add %s VLAN %u filter for VF %u, error %d\n",
+			vf->port_vlan_info ? "port" : "", vlan_id, vf->vf_id,
+			err);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA
+ * @vf: VF to add MAC filters for
+ *
+ * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver
+ * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset.
+ */
+static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
+	struct device *dev = ice_pf_to_dev(vf->pf);
+	enum ice_status status;
+	u8 broadcast[ETH_ALEN];
+
+	eth_broadcast_addr(broadcast);
+	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
+	if (status) {
+		dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %s\n",
+			vf->vf_id, ice_stat_str(status));
+		return ice_status_to_errno(status);
+	}
+
+	vf->num_mac++;
+
+	if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) {
+		status = ice_fltr_add_mac(vsi, vf->dflt_lan_addr.addr,
+					  ICE_FWD_TO_VSI);
+		if (status) {
+			dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %s\n",
+				&vf->dflt_lan_addr.addr[0], vf->vf_id,
+				ice_stat_str(status));
+			return ice_status_to_errno(status);
+		}
+		vf->num_mac++;
+	}
+
+	return 0;
+}
+
 /**
  * ice_alloc_vsi_res - Setup VF VSI and its resources
  * @vf: pointer to the VF structure
@@ -549,10 +625,9 @@ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
 static int ice_alloc_vsi_res(struct ice_vf *vf)
 {
 	struct ice_pf *pf = vf->pf;
-	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
 	struct device *dev;
-	int status = 0;
+	int ret;
 
 	dev = ice_pf_to_dev(pf);
 	/* first vector index is the VFs OICR index */
@@ -567,38 +642,20 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	vf->lan_vsi_idx = vsi->idx;
 	vf->lan_vsi_num = vsi->vsi_num;
 
-	/* Check if port VLAN exist before, and restore it accordingly */
-	if (vf->port_vlan_info) {
-		ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true);
-		if (ice_vsi_add_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK,
-				     ICE_FWD_TO_VSI))
-			dev_warn(ice_pf_to_dev(pf), "Failed to add Port VLAN %d filter for VF %d\n",
-				 vf->port_vlan_info & VLAN_VID_MASK, vf->vf_id);
-	} else {
-		/* set VLAN 0 filter by default when no port VLAN is
-		 * enabled. If a port VLAN is enabled we don't want
-		 * untagged broadcast/multicast traffic seen on the VF
-		 * interface.
-		 */
-		if (ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI))
-			dev_warn(ice_pf_to_dev(pf), "Failed to add VLAN 0 filter for VF %d, MDD events will trigger. Reset the VF, disable spoofchk, or enable 8021q module on the guest\n",
-				 vf->vf_id);
+	ret = ice_vf_rebuild_host_vlan_cfg(vf);
+	if (ret) {
+		dev_err(dev, "failed to rebuild default MAC configuration for VF %d, error %d\n",
+			vf->vf_id, ret);
+		goto ice_alloc_vsi_res_exit;
 	}
 
-	if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) {
-		status = ice_fltr_add_mac(vsi, vf->dflt_lan_addr.addr,
-					  ICE_FWD_TO_VSI);
-		if (status)
-			goto ice_alloc_vsi_res_exit;
-	}
 
-	eth_broadcast_addr(broadcast);
-	status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI);
-	if (status)
-		dev_err(dev, "could not add mac filters error %d\n",
-			status);
-	else
-		vf->num_mac = 1;
+	ret = ice_vf_rebuild_host_mac_cfg(vf);
+	if (ret) {
+		dev_err(dev, "failed to rebuild default MAC configuration for VF %d, error %d\n",
+			vf->vf_id, ret);
+		goto ice_alloc_vsi_res_exit;
+	}
 
 	/* Clear this bit after VF initialization since we shouldn't reclaim
 	 * and reassign interrupts for synchronous or asynchronous VFR events.
@@ -607,7 +664,7 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	 * more vectors.
 	 */
 ice_alloc_vsi_res_exit:
-	return status;
+	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From a58e1d817475eb45471869190ff72dd1b493a936 Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Fri, 15 May 2020 17:51:14 -0700
Subject: ice: remove VM/VF disable command on CORER/GLOBR reset

Remove VM/VF disable AQC (opcode 0x0C31) when resetting all VFs.
This is not required for CORER/GLOBR reset.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 3a714c81b5b2..245310a52e1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1196,17 +1196,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	ice_for_each_vf(pf, v)
 		ice_trigger_vf_reset(&pf->vf[v], is_vflr, true);
 
-	ice_for_each_vf(pf, v) {
-		struct ice_vsi *vsi;
-
-		vf = &pf->vf[v];
-		vsi = pf->vsi[vf->lan_vsi_idx];
-		if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states))
-			ice_dis_vf_qs(vf);
-		ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
-				NULL, ICE_VF_RESET, vf->vf_id, NULL);
-	}
-
 	/* HW requires some time to make sure it can flush the FIFO for a VF
 	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
 	 * sequence to make sure that it has completed. We'll keep track of
-- 
cgit v1.2.3


From 12bb018c538c3b9a050f69f62fa09fa6c9160bca Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:15 -0700
Subject: ice: Refactor VF reset

Currently VF VSI are being reset twice during a PFR or greater. This is
causing reset, specifically resetting all VFs, to take too long. This is
causing various issues with VF drivers not being able to gracefully
handle the VF reset timeout. Fix this by refactoring how VF reset is
handled for the case mentioned previously and for the VFR/VFLR case.

The refactor was done by doing the following:

1. Removing the call to ice_vsi_rebuild_by_type for
   ICE_VSI_VF VSI, which was causing the initial VSI rebuild.

2. Adding functions for pre/post VSI rebuild functions that can be called
   in both the reset all VFs case and reset individual VF case.

3. Adding VSI rebuild functions that are specific for the reset all VFs
   case and adding functions that are specific for the reset individual
   VF case.

4. Calling the pre-rebuild function, then the specific VSI rebuild
   function based on the reset type, and then calling the post-rebuild
   function to handle VF resets.

This patch series makes some assumptions about how VSI are handling by
FW during reset:

1. During a PFR or greater all VSI in FW will be cleared.
2. During a VFR/VFLR the VSI rebuild responsibility is in the hands of
   the PF software.
3. There is code in the ice_reset_all_vfs() case to amortize operations
   if possible. This was left intact.
4. PF software should not be replaying VSI based filters that were added
   other than host configured, PF software configured, or the VF's
   default/LAA MAC. This is the VF drivers job after it has been reset.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c        |  13 +-
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 304 ++++++++++-------------
 2 files changed, 130 insertions(+), 187 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 69854b8644a6..bbf92d2f1ac1 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4897,6 +4897,11 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf)
  * ice_rebuild - rebuild after reset
  * @pf: PF to rebuild
  * @reset_type: type of reset
+ *
+ * Do not rebuild VF VSI in this flow because that is already handled via
+ * ice_reset_all_vfs(). This is because requirements for resetting a VF after a
+ * PFR/CORER/GLOBER/etc. are different than the normal flow. Also, we don't want
+ * to reset/rebuild all the VF VSI twice.
  */
 static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
@@ -4994,14 +4999,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_vsi_rebuild;
 	}
 
-	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
-		err = ice_vsi_rebuild_by_type(pf, ICE_VSI_VF);
-		if (err) {
-			dev_err(dev, "VF VSI rebuild failed: %d\n", err);
-			goto err_vsi_rebuild;
-		}
-	}
-
 	/* If Flow Director is active */
 	if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) {
 		err = ice_vsi_rebuild_by_type(pf, ICE_VSI_CTRL);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 245310a52e1b..727f371db465 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -413,10 +413,7 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 	clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
 
 	/* Disable VF's configuration API during reset. The flag is re-enabled
-	 * in ice_alloc_vf_res(), when it's safe again to access VF's VSI.
-	 * It's normally disabled in ice_free_vf_res(), but it's safer
-	 * to do it earlier to give some time to finish to any VF config
-	 * functions that may still be running at this point.
+	 * when it's safe again to access VF's VSI.
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
@@ -616,57 +613,6 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf)
 	return 0;
 }
 
-/**
- * ice_alloc_vsi_res - Setup VF VSI and its resources
- * @vf: pointer to the VF structure
- *
- * Returns 0 on success, negative value on failure
- */
-static int ice_alloc_vsi_res(struct ice_vf *vf)
-{
-	struct ice_pf *pf = vf->pf;
-	struct ice_vsi *vsi;
-	struct device *dev;
-	int ret;
-
-	dev = ice_pf_to_dev(pf);
-	/* first vector index is the VFs OICR index */
-	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
-
-	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
-	if (!vsi) {
-		dev_err(dev, "Failed to create VF VSI\n");
-		return -ENOMEM;
-	}
-
-	vf->lan_vsi_idx = vsi->idx;
-	vf->lan_vsi_num = vsi->vsi_num;
-
-	ret = ice_vf_rebuild_host_vlan_cfg(vf);
-	if (ret) {
-		dev_err(dev, "failed to rebuild default MAC configuration for VF %d, error %d\n",
-			vf->vf_id, ret);
-		goto ice_alloc_vsi_res_exit;
-	}
-
-
-	ret = ice_vf_rebuild_host_mac_cfg(vf);
-	if (ret) {
-		dev_err(dev, "failed to rebuild default MAC configuration for VF %d, error %d\n",
-			vf->vf_id, ret);
-		goto ice_alloc_vsi_res_exit;
-	}
-
-	/* Clear this bit after VF initialization since we shouldn't reclaim
-	 * and reassign interrupts for synchronous or asynchronous VFR events.
-	 * We don't want to reconfigure interrupts since AVF driver doesn't
-	 * expect vector assignment to be changed unless there is a request for
-	 * more vectors.
-	 */
-ice_alloc_vsi_res_exit:
-	return ret;
-}
-
 /**
  * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value
  * @vf: VF to configure trust setting for
@@ -679,43 +625,6 @@ static void ice_vf_set_host_trust_cfg(struct ice_vf *vf)
 		clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
 }
 
-/**
- * ice_alloc_vf_res - Allocate VF resources
- * @vf: pointer to the VF structure
- */
-static int ice_alloc_vf_res(struct ice_vf *vf)
-{
-	struct ice_pf *pf = vf->pf;
-	int tx_rx_queue_left;
-	int status;
-
-	/* Update number of VF queues, in case VF had requested for queue
-	 * changes
-	 */
-	tx_rx_queue_left = min_t(int, ice_get_avail_txq_count(pf),
-				 ice_get_avail_rxq_count(pf));
-	tx_rx_queue_left += pf->num_qps_per_vf;
-	if (vf->num_req_qs && vf->num_req_qs <= tx_rx_queue_left &&
-	    vf->num_req_qs != vf->num_vf_qs)
-		vf->num_vf_qs = vf->num_req_qs;
-
-	/* setup VF VSI and necessary resources */
-	status = ice_alloc_vsi_res(vf);
-	if (status)
-		goto ice_alloc_vf_res_exit;
-
-	ice_vf_set_host_trust_cfg(vf);
-
-	/* VF is now completely initialized */
-	set_bit(ICE_VF_STATE_INIT, vf->vf_states);
-
-	return status;
-
-ice_alloc_vf_res_exit:
-	ice_free_vf_res(vf);
-	return status;
-}
-
 /**
  * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware
  * @vf: VF to enable MSIX mappings for
@@ -1042,48 +951,6 @@ static void ice_clear_vf_reset_trigger(struct ice_vf *vf)
 	ice_flush(hw);
 }
 
-/**
- * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset
- * @vf: pointer to the VF structure
- *
- * Cleanup a VF after the hardware reset is finished. Expects the caller to
- * have verified whether the reset is finished properly, and ensure the
- * minimum amount of wait time has passed. Reallocate VF resources back to make
- * VF state active
- */
-static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
-{
-	struct ice_pf *pf = vf->pf;
-	struct ice_hw *hw;
-
-	hw = &pf->hw;
-
-	/* Allow HW to access VF memory after calling
-	 * ice_clear_vf_reset_trigger(). If we did it any sooner, HW could
-	 * access memory while it was being freed in ice_free_vf_res(), causing
-	 * an IOMMU fault.
-	 *
-	 * On the other hand, this needs to be done ASAP, because the VF driver
-	 * is waiting for this to happen and may report a timeout. It's
-	 * harmless, but it gets logged into Guest OS kernel log, so best avoid
-	 * it.
-	 */
-	ice_clear_vf_reset_trigger(vf);
-
-	/* reallocate VF resources to finish resetting the VSI state */
-	if (!ice_alloc_vf_res(vf)) {
-		ice_ena_vf_mappings(vf);
-		set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states);
-		clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
-	}
-
-	/* Tell the VF driver the reset is done. This needs to be done only
-	 * after VF has been fully initialized, because the VF driver may
-	 * request resources immediately after setting this flag.
-	 */
-	wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
-}
-
 /**
  * ice_vf_set_vsi_promisc - set given VF VSI to given promiscuous mode(s)
  * @vf: pointer to the VF info
@@ -1125,44 +992,134 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m,
 	return status;
 }
 
+static void ice_vf_clear_counters(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
+
+	vf->num_mac = 0;
+	vsi->num_vlan = 0;
+	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
+	memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events));
+}
+
 /**
- * ice_config_res_vfs - Finalize allocation of VFs resources in one go
- * @pf: pointer to the PF structure
+ * ice_vf_pre_vsi_rebuild - tasks to be done prior to VSI rebuild
+ * @vf: VF to perform pre VSI rebuild tasks
  *
- * This function is being called as last part of resetting all VFs, or when
- * configuring VFs for the first time, where there is no resource to be freed
- * Returns true if resources were properly allocated for all VFs, and false
- * otherwise.
+ * These tasks are items that don't need to be amortized since they are most
+ * likely called in a for loop with all VF(s) in the reset_all_vfs() case.
  */
-static bool ice_config_res_vfs(struct ice_pf *pf)
+static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf)
 {
-	struct device *dev = ice_pf_to_dev(pf);
-	struct ice_hw *hw = &pf->hw;
-	int v;
+	ice_vf_clear_counters(vf);
+	ice_clear_vf_reset_trigger(vf);
+}
 
-	if (ice_set_per_vf_res(pf)) {
-		dev_err(dev, "Cannot allocate VF resources, try with fewer number of VFs\n");
-		return false;
+/**
+ * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset
+ * @vf: VF to rebuild host configuration on
+ */
+static void ice_vf_rebuild_host_cfg(struct ice_vf *vf)
+{
+	struct device *dev = ice_pf_to_dev(vf->pf);
+
+	ice_vf_set_host_trust_cfg(vf);
+
+	if (ice_vf_rebuild_host_mac_cfg(vf))
+		dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n",
+			vf->vf_id);
+
+	if (ice_vf_rebuild_host_vlan_cfg(vf))
+		dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n",
+			vf->vf_id);
+}
+
+/**
+ * ice_vf_rebuild_vsi_with_release - release and setup the VF's VSI
+ * @vf: VF to release and setup the VSI for
+ *
+ * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF
+ * configuration change, etc.).
+ */
+static int ice_vf_rebuild_vsi_with_release(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+
+	vsi = pf->vsi[vf->lan_vsi_idx];
+	ice_vsi_release(vsi);
+	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
+	if (!vsi) {
+		dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n");
+		return -ENOMEM;
 	}
 
-	/* rearm global interrupts */
-	if (test_and_clear_bit(__ICE_OICR_INTR_DIS, pf->state))
-		ice_irq_dynamic_ena(hw, NULL, NULL);
+	vf->lan_vsi_idx = vsi->idx;
+	vf->lan_vsi_num = vsi->vsi_num;
 
-	/* Finish resetting each VF and allocate resources */
-	ice_for_each_vf(pf, v) {
-		struct ice_vf *vf = &pf->vf[v];
+	return 0;
+}
 
-		vf->num_vf_qs = pf->num_qps_per_vf;
-		dev_dbg(dev, "VF-id %d has %d queues configured\n", vf->vf_id,
-			vf->num_vf_qs);
-		ice_cleanup_and_realloc_vf(vf);
+/**
+ * ice_vf_rebuild_vsi - rebuild the VF's VSI
+ * @vf: VF to rebuild the VSI for
+ *
+ * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the
+ * host, PFR, CORER, etc.).
+ */
+static int ice_vf_rebuild_vsi(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+
+	vsi = pf->vsi[vf->lan_vsi_idx];
+
+	if (ice_vsi_rebuild(vsi, true)) {
+		dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n",
+			vf->vf_id);
+		return -EIO;
 	}
+	/* vsi->idx will remain the same in this case so don't update
+	 * vf->lan_vsi_idx
+	 */
+	vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx);
+	vf->lan_vsi_num = vsi->vsi_num;
 
-	ice_flush(hw);
-	clear_bit(__ICE_VF_DIS, pf->state);
+	return 0;
+}
 
-	return true;
+/**
+ * ice_vf_set_initialized - VF is ready for VIRTCHNL communication
+ * @vf: VF to set in initialized state
+ *
+ * After this function the VF will be ready to receive/handle the
+ * VIRTCHNL_OP_GET_VF_RESOURCES message
+ */
+static void ice_vf_set_initialized(struct ice_vf *vf)
+{
+	ice_set_vf_state_qs_dis(vf);
+	clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states);
+	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
+	clear_bit(ICE_VF_STATE_DIS, vf->vf_states);
+	set_bit(ICE_VF_STATE_INIT, vf->vf_states);
+}
+
+/**
+ * ice_vf_post_vsi_rebuild - tasks to do after the VF's VSI have been rebuilt
+ * @vf: VF to perform tasks on
+ */
+static void ice_vf_post_vsi_rebuild(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+	struct ice_hw *hw;
+
+	hw = &pf->hw;
+
+	ice_vf_rebuild_host_cfg(vf);
+
+	ice_vf_set_initialized(vf);
+	ice_ena_vf_mappings(vf);
+	wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE);
 }
 
 /**
@@ -1232,21 +1189,13 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	ice_for_each_vf(pf, v) {
 		vf = &pf->vf[v];
 
-		ice_free_vf_res(vf);
-
-		/* Free VF queues as well, and reallocate later.
-		 * If a given VF has different number of queues
-		 * configured, the request for update will come
-		 * via mailbox communication.
-		 */
-		vf->num_vf_qs = 0;
+		ice_vf_pre_vsi_rebuild(vf);
+		ice_vf_rebuild_vsi(vf);
+		ice_vf_post_vsi_rebuild(vf);
 	}
 
-	if (ice_sriov_free_msix_res(pf))
-		dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n");
-
-	if (!ice_config_res_vfs(pf))
-		return false;
+	ice_flush(hw);
+	clear_bit(__ICE_VF_DIS, pf->state);
 
 	return true;
 }
@@ -1358,12 +1307,9 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 			dev_err(dev, "disabling promiscuous mode failed\n");
 	}
 
-	/* free VF resources to begin resetting the VSI state */
-	ice_free_vf_res(vf);
-
-	ice_cleanup_and_realloc_vf(vf);
-
-	ice_flush(hw);
+	ice_vf_pre_vsi_rebuild(vf);
+	ice_vf_rebuild_vsi_with_release(vf);
+	ice_vf_post_vsi_rebuild(vf);
 
 	return true;
 }
-- 
cgit v1.2.3


From 3726cce258908ed6e30d52e2d4dfffe96ad2f962 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:16 -0700
Subject: ice: Refactor VF VSI release and setup functions

Currently when a VF VSI calls ice_vsi_release() and ice_vsi_setup() it
subsequently clears/sets the VF cached variables for lan_vsi_idx and
lan_vsi_num. This works fine, but can be improved by handling this in
the VF specific VSI release and setup functions.

Also, when a VF VSI is setup too many parameters are passed that can be
derived from the VF. Fix this by only calling VF VSI setup with the bare
minimum parameters.

Also, add functionality to invalidate a VF's VSI when it's released
and/or setup fails. This will make it so a VF VSI cannot be accessed via
its cached vsi_idx/vsi_num in these cases.

Finally when a VF's VSI is invalidated set the lan_vsi_idx and
lan_vsi_num to ICE_NO_VSI to clearly show that there is no valid VSI
associated with this VF.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 86 +++++++++++++++---------
 1 file changed, 55 insertions(+), 31 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 727f371db465..a126e7c7663d 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -181,6 +181,26 @@ static void ice_vc_notify_vf_link_state(struct ice_vf *vf)
 			      sizeof(pfe), NULL);
 }
 
+/**
+ * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access
+ * @vf: VF to remove access to VSI for
+ */
+static void ice_vf_invalidate_vsi(struct ice_vf *vf)
+{
+	vf->lan_vsi_idx = ICE_NO_VSI;
+	vf->lan_vsi_num = ICE_NO_VSI;
+}
+
+/**
+ * ice_vf_vsi_release - invalidate the VF's VSI after freeing it
+ * @vf: invalidate this VF's VSI after freeing it
+ */
+static void ice_vf_vsi_release(struct ice_vf *vf)
+{
+	ice_vsi_release(vf->pf->vsi[vf->lan_vsi_idx]);
+	ice_vf_invalidate_vsi(vf);
+}
+
 /**
  * ice_free_vf_res - Free a VF's resources
  * @vf: pointer to the VF info
@@ -196,10 +216,8 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
 	/* free VSI and disconnect it from the parent uplink */
-	if (vf->lan_vsi_idx) {
-		ice_vsi_release(pf->vsi[vf->lan_vsi_idx]);
-		vf->lan_vsi_idx = 0;
-		vf->lan_vsi_num = 0;
+	if (vf->lan_vsi_idx != ICE_NO_VSI) {
+		ice_vf_vsi_release(vf);
 		vf->num_mac = 0;
 	}
 
@@ -505,19 +523,40 @@ out:
 	return ret;
 }
 
+/**
+ * ice_vf_get_port_info - Get the VF's port info structure
+ * @vf: VF used to get the port info structure for
+ */
+static struct ice_port_info *ice_vf_get_port_info(struct ice_vf *vf)
+{
+	return vf->pf->hw.port_info;
+}
+
 /**
  * ice_vf_vsi_setup - Set up a VF VSI
- * @pf: board private structure
- * @pi: pointer to the port_info instance
- * @vf_id: defines VF ID to which this VSI connects.
+ * @vf: VF to setup VSI for
  *
  * Returns pointer to the successfully allocated VSI struct on success,
  * otherwise returns NULL on failure.
  */
-static struct ice_vsi *
-ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id)
+static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf)
 {
-	return ice_vsi_setup(pf, pi, ICE_VSI_VF, vf_id);
+	struct ice_port_info *pi = ice_vf_get_port_info(vf);
+	struct ice_pf *pf = vf->pf;
+	struct ice_vsi *vsi;
+
+	vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf->vf_id);
+
+	if (!vsi) {
+		dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n");
+		ice_vf_invalidate_vsi(vf);
+		return NULL;
+	}
+
+	vf->lan_vsi_idx = vsi->idx;
+	vf->lan_vsi_num = vsi->vsi_num;
+
+	return vsi;
 }
 
 /**
@@ -1043,19 +1082,9 @@ static void ice_vf_rebuild_host_cfg(struct ice_vf *vf)
  */
 static int ice_vf_rebuild_vsi_with_release(struct ice_vf *vf)
 {
-	struct ice_pf *pf = vf->pf;
-	struct ice_vsi *vsi;
-
-	vsi = pf->vsi[vf->lan_vsi_idx];
-	ice_vsi_release(vsi);
-	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
-	if (!vsi) {
-		dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n");
+	ice_vf_vsi_release(vf);
+	if (!ice_vf_vsi_setup(vf))
 		return -ENOMEM;
-	}
-
-	vf->lan_vsi_idx = vsi->idx;
-	vf->lan_vsi_num = vsi->vsi_num;
 
 	return 0;
 }
@@ -1395,14 +1424,9 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
 
 	dev = ice_pf_to_dev(pf);
-	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
-	if (!vsi) {
-		dev_err(dev, "Failed to create VF VSI\n");
+	vsi = ice_vf_vsi_setup(vf);
+	if (!vsi)
 		return -ENOMEM;
-	}
-
-	vf->lan_vsi_idx = vsi->idx;
-	vf->lan_vsi_num = vsi->vsi_num;
 
 	err = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI);
 	if (err) {
@@ -1425,7 +1449,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	return 0;
 
 release_vsi:
-	ice_vsi_release(vsi);
+	ice_vf_vsi_release(vf);
 	return err;
 }
 
@@ -1463,7 +1487,7 @@ teardown:
 		struct ice_vf *vf = &pf->vf[i];
 
 		ice_dis_vf_mappings(vf);
-		ice_vsi_release(pf->vsi[vf->lan_vsi_idx]);
+		ice_vf_vsi_release(vf);
 	}
 
 	return retval;
-- 
cgit v1.2.3


From d320692d9f8502e819e511ea5294552e0a8d3d9b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:28 +0200
Subject: net: ks8851: Factor out spi->dev in probe()/remove()

Pull out the spi->dev into one common place in the function instead of
having it repeated over and over again. This is done in preparation for
unifying ks8851 and ks8851-mll drivers. No functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 33305c9c5a62..e32ef9403803 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1413,6 +1413,7 @@ static SIMPLE_DEV_PM_OPS(ks8851_pm_ops, ks8851_suspend, ks8851_resume);
 
 static int ks8851_probe(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
 	struct net_device *ndev;
 	struct ks8851_net *ks;
 	int ret;
@@ -1431,8 +1432,7 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->spidev = spi;
 	ks->tx_space = 6144;
 
-	gpio = of_get_named_gpio_flags(spi->dev.of_node, "reset-gpios",
-				       0, NULL);
+	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
 	if (gpio == -EPROBE_DEFER) {
 		ret = gpio;
 		goto err_gpio;
@@ -1440,15 +1440,15 @@ static int ks8851_probe(struct spi_device *spi)
 
 	ks->gpio = gpio;
 	if (gpio_is_valid(gpio)) {
-		ret = devm_gpio_request_one(&spi->dev, gpio,
+		ret = devm_gpio_request_one(dev, gpio,
 					    GPIOF_OUT_INIT_LOW, "ks8851_rst_n");
 		if (ret) {
-			dev_err(&spi->dev, "reset gpio request failed\n");
+			dev_err(dev, "reset gpio request failed\n");
 			goto err_gpio;
 		}
 	}
 
-	ks->vdd_io = devm_regulator_get(&spi->dev, "vdd-io");
+	ks->vdd_io = devm_regulator_get(dev, "vdd-io");
 	if (IS_ERR(ks->vdd_io)) {
 		ret = PTR_ERR(ks->vdd_io);
 		goto err_reg_io;
@@ -1456,12 +1456,11 @@ static int ks8851_probe(struct spi_device *spi)
 
 	ret = regulator_enable(ks->vdd_io);
 	if (ret) {
-		dev_err(&spi->dev, "regulator vdd_io enable fail: %d\n",
-			ret);
+		dev_err(dev, "regulator vdd_io enable fail: %d\n", ret);
 		goto err_reg_io;
 	}
 
-	ks->vdd_reg = devm_regulator_get(&spi->dev, "vdd");
+	ks->vdd_reg = devm_regulator_get(dev, "vdd");
 	if (IS_ERR(ks->vdd_reg)) {
 		ret = PTR_ERR(ks->vdd_reg);
 		goto err_reg;
@@ -1469,8 +1468,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	ret = regulator_enable(ks->vdd_reg);
 	if (ret) {
-		dev_err(&spi->dev, "regulator vdd enable fail: %d\n",
-			ret);
+		dev_err(dev, "regulator vdd enable fail: %d\n", ret);
 		goto err_reg;
 	}
 
@@ -1509,7 +1507,7 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->mii.mdio_read	= ks8851_phy_read;
 	ks->mii.mdio_write	= ks8851_phy_write;
 
-	dev_info(&spi->dev, "message enable is %d\n", msg_enable);
+	dev_info(dev, "message enable is %d\n", msg_enable);
 
 	/* set the default message enable */
 	ks->msg_enable = netif_msg_init(msg_enable, (NETIF_MSG_DRV |
@@ -1519,7 +1517,7 @@ static int ks8851_probe(struct spi_device *spi)
 	skb_queue_head_init(&ks->txq);
 
 	ndev->ethtool_ops = &ks8851_ethtool_ops;
-	SET_NETDEV_DEV(ndev, &spi->dev);
+	SET_NETDEV_DEV(ndev, dev);
 
 	spi_set_drvdata(spi, ks);
 
@@ -1534,7 +1532,7 @@ static int ks8851_probe(struct spi_device *spi)
 	/* simple check for a valid chip being connected to the bus */
 	cider = ks8851_rdreg16(ks, KS_CIDER);
 	if ((cider & ~CIDER_REV_MASK) != CIDER_ID) {
-		dev_err(&spi->dev, "failed to read device ID\n");
+		dev_err(dev, "failed to read device ID\n");
 		ret = -ENODEV;
 		goto err_id;
 	}
@@ -1547,7 +1545,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	ret = register_netdev(ndev);
 	if (ret) {
-		dev_err(&spi->dev, "failed to register network device\n");
+		dev_err(dev, "failed to register network device\n");
 		goto err_netdev;
 	}
 
@@ -1573,9 +1571,10 @@ err_gpio:
 static int ks8851_remove(struct spi_device *spi)
 {
 	struct ks8851_net *priv = spi_get_drvdata(spi);
+	struct device *dev = &spi->dev;
 
 	if (netif_msg_drv(priv))
-		dev_info(&spi->dev, "remove\n");
+		dev_info(dev, "remove\n");
 
 	unregister_netdev(priv->netdev);
 	if (gpio_is_valid(priv->gpio))
-- 
cgit v1.2.3


From bfd1e0eb08f6ac25659e3d9bfd80b8ddffe57c94 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:29 +0200
Subject: net: ks8851: Rename ndev to netdev in probe

Rename ndev variable to netdev for the sake of consistency.

No functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index e32ef9403803..2b85072993c5 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1414,21 +1414,21 @@ static SIMPLE_DEV_PM_OPS(ks8851_pm_ops, ks8851_suspend, ks8851_resume);
 static int ks8851_probe(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
-	struct net_device *ndev;
+	struct net_device *netdev;
 	struct ks8851_net *ks;
 	int ret;
 	unsigned cider;
 	int gpio;
 
-	ndev = alloc_etherdev(sizeof(struct ks8851_net));
-	if (!ndev)
+	netdev = alloc_etherdev(sizeof(struct ks8851_net));
+	if (!netdev)
 		return -ENOMEM;
 
 	spi->bits_per_word = 8;
 
-	ks = netdev_priv(ndev);
+	ks = netdev_priv(netdev);
 
-	ks->netdev = ndev;
+	ks->netdev = netdev;
 	ks->spidev = spi;
 	ks->tx_space = 6144;
 
@@ -1500,7 +1500,7 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->eeprom.register_write = ks8851_eeprom_regwrite;
 
 	/* setup mii state */
-	ks->mii.dev		= ndev;
+	ks->mii.dev		= netdev;
 	ks->mii.phy_id		= 1,
 	ks->mii.phy_id_mask	= 1;
 	ks->mii.reg_num_mask	= 0xf;
@@ -1516,15 +1516,15 @@ static int ks8851_probe(struct spi_device *spi)
 
 	skb_queue_head_init(&ks->txq);
 
-	ndev->ethtool_ops = &ks8851_ethtool_ops;
-	SET_NETDEV_DEV(ndev, dev);
+	netdev->ethtool_ops = &ks8851_ethtool_ops;
+	SET_NETDEV_DEV(netdev, dev);
 
 	spi_set_drvdata(spi, ks);
 
 	netif_carrier_off(ks->netdev);
-	ndev->if_port = IF_PORT_100BASET;
-	ndev->netdev_ops = &ks8851_netdev_ops;
-	ndev->irq = spi->irq;
+	netdev->if_port = IF_PORT_100BASET;
+	netdev->netdev_ops = &ks8851_netdev_ops;
+	netdev->irq = spi->irq;
 
 	/* issue a global soft reset to reset the device. */
 	ks8851_soft_reset(ks, GRR_GSR);
@@ -1543,14 +1543,14 @@ static int ks8851_probe(struct spi_device *spi)
 	ks8851_read_selftest(ks);
 	ks8851_init_mac(ks);
 
-	ret = register_netdev(ndev);
+	ret = register_netdev(netdev);
 	if (ret) {
 		dev_err(dev, "failed to register network device\n");
 		goto err_netdev;
 	}
 
-	netdev_info(ndev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
-		    CIDER_REV_GET(cider), ndev->dev_addr, ndev->irq,
+	netdev_info(netdev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
+		    CIDER_REV_GET(cider), netdev->dev_addr, netdev->irq,
 		    ks->rc_ccr & CCR_EEPROM ? "has" : "no");
 
 	return 0;
@@ -1564,7 +1564,7 @@ err_reg:
 	regulator_disable(ks->vdd_io);
 err_reg_io:
 err_gpio:
-	free_netdev(ndev);
+	free_netdev(netdev);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 2f3271c952bfa9486aa3746f591788c983fc280d Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:30 +0200
Subject: net: ks8851: Replace dev_err() with netdev_err() in IRQ handler

Use netdev_err() instead of dev_err() to avoid accessing the spidev->dev
in the interrupt handler. This is the only place which uses the spidev
in this function, so replace it with netdev_err() to get rid of it. This
is done in preparation for unifying the KS8851 SPI and parallel drivers.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 2b85072993c5..0088df970ad6 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -631,7 +631,7 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 		handled |= IRQ_RXI;
 
 	if (status & IRQ_SPIBEI) {
-		dev_err(&ks->spidev->dev, "%s: spi bus error\n", __func__);
+		netdev_err(ks->netdev, "%s: spi bus error\n", __func__);
 		handled |= IRQ_SPIBEI;
 	}
 
-- 
cgit v1.2.3


From 848fc0ce6cb84430c4b1dd0a749015ad9af1b766 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:31 +0200
Subject: net: ks8851: Pass device node into ks8851_init_mac()

Since the driver probe function already has a struct device *dev pointer
and can easily derive of_node pointer from it, pass the of_node pointer as
a parameter to ks8851_init_mac() to avoid fishing it out from ks->spidev.
This is the only reference to spidev in the function, so get rid of it.
This is done in preparation for unifying the KS8851 SPI and parallel bus
drivers.

No functional change.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 0088df970ad6..582092a95afc 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -409,6 +409,7 @@ static void ks8851_read_mac_addr(struct net_device *dev)
 /**
  * ks8851_init_mac - initialise the mac address
  * @ks: The device structure
+ * @np: The device node pointer
  *
  * Get or create the initial mac address for the device and then set that
  * into the station address register. A mac address supplied in the device
@@ -416,12 +417,12 @@ static void ks8851_read_mac_addr(struct net_device *dev)
  * we try that. If no valid mac address is found we use eth_random_addr()
  * to create a new one.
  */
-static void ks8851_init_mac(struct ks8851_net *ks)
+static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
 {
 	struct net_device *dev = ks->netdev;
 	const u8 *mac_addr;
 
-	mac_addr = of_get_mac_address(ks->spidev->dev.of_node);
+	mac_addr = of_get_mac_address(np);
 	if (!IS_ERR(mac_addr)) {
 		ether_addr_copy(dev->dev_addr, mac_addr);
 		ks8851_write_mac_addr(dev);
@@ -1541,7 +1542,7 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->rc_ccr = ks8851_rdreg16(ks, KS_CCR);
 
 	ks8851_read_selftest(ks);
-	ks8851_init_mac(ks);
+	ks8851_init_mac(ks, dev->of_node);
 
 	ret = register_netdev(netdev);
 	if (ret) {
-- 
cgit v1.2.3


From b6948e1b7b094ccc86b1ae768beab734e5355ced Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:32 +0200
Subject: net: ks8851: Use devm_alloc_etherdev()

Use device managed version of alloc_etherdev() to simplify the code.
No functional change intended.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 582092a95afc..86bfe55f346d 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1421,7 +1421,7 @@ static int ks8851_probe(struct spi_device *spi)
 	unsigned cider;
 	int gpio;
 
-	netdev = alloc_etherdev(sizeof(struct ks8851_net));
+	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net));
 	if (!netdev)
 		return -ENOMEM;
 
@@ -1434,10 +1434,8 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->tx_space = 6144;
 
 	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
-	if (gpio == -EPROBE_DEFER) {
-		ret = gpio;
-		goto err_gpio;
-	}
+	if (gpio == -EPROBE_DEFER)
+		return gpio;
 
 	ks->gpio = gpio;
 	if (gpio_is_valid(gpio)) {
@@ -1445,7 +1443,7 @@ static int ks8851_probe(struct spi_device *spi)
 					    GPIOF_OUT_INIT_LOW, "ks8851_rst_n");
 		if (ret) {
 			dev_err(dev, "reset gpio request failed\n");
-			goto err_gpio;
+			return ret;
 		}
 	}
 
@@ -1564,8 +1562,6 @@ err_id:
 err_reg:
 	regulator_disable(ks->vdd_io);
 err_reg_io:
-err_gpio:
-	free_netdev(netdev);
 	return ret;
 }
 
@@ -1582,7 +1578,6 @@ static int ks8851_remove(struct spi_device *spi)
 		gpio_set_value(priv->gpio, 0);
 	regulator_disable(priv->vdd_reg);
 	regulator_disable(priv->vdd_io);
-	free_netdev(priv->netdev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 2c5b0a86ac54dae5bcf854a93dbb086191368014 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:33 +0200
Subject: net: ks8851: Use dev_{get,set}_drvdata()

Replace spi_{get,set}_drvdata() with dev_{get,set}_drvdata(), which
works for both SPI and platform drivers. This is done in preparation
for unifying the KS8851 SPI and parallel bus drivers.

There should be no functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 86bfe55f346d..fe2037e166dc 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1518,7 +1518,7 @@ static int ks8851_probe(struct spi_device *spi)
 	netdev->ethtool_ops = &ks8851_ethtool_ops;
 	SET_NETDEV_DEV(netdev, dev);
 
-	spi_set_drvdata(spi, ks);
+	dev_set_drvdata(dev, ks);
 
 	netif_carrier_off(ks->netdev);
 	netdev->if_port = IF_PORT_100BASET;
@@ -1567,8 +1567,10 @@ err_reg_io:
 
 static int ks8851_remove(struct spi_device *spi)
 {
-	struct ks8851_net *priv = spi_get_drvdata(spi);
 	struct device *dev = &spi->dev;
+	struct ks8851_net *priv;
+
+	priv = dev_get_drvdata(dev);
 
 	if (netif_msg_drv(priv))
 		dev_info(dev, "remove\n");
-- 
cgit v1.2.3


From 806f66495e791eb349cd3ea286ee411bcf1df4d0 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:34 +0200
Subject: net: ks8851: Remove ks8851_rdreg32()

The ks8851_rdreg32() is used only in one place, to read two registers
using a single read. To make it easier to support 16-bit accesses via
parallel bus later on, replace this single read with two 16-bit reads
from each of the registers and drop the ks8851_rdreg32() altogether.

If this has noticeable performance impact on the SPI variant of KS8851,
then we should consider using regmap to abstract the SPI and parallel
bus options and in case of SPI, permit regmap to merge register reads
of neighboring registers into single, longer, read.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 25 ++-----------------------
 1 file changed, 2 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index fe2037e166dc..8df130efbde1 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -296,25 +296,6 @@ static unsigned ks8851_rdreg16(struct ks8851_net *ks, unsigned reg)
 	return le16_to_cpu(rx);
 }
 
-/**
- * ks8851_rdreg32 - read 32 bit register from device
- * @ks: The chip information
- * @reg: The register address
- *
- * Read a 32bit register from the chip.
- *
- * Note, this read requires the address be aligned to 4 bytes.
-*/
-static unsigned ks8851_rdreg32(struct ks8851_net *ks, unsigned reg)
-{
-	__le32 rx = 0;
-
-	WARN_ON(reg & 3);
-
-	ks8851_rdreg(ks, MK_OP(0xf, reg), (u8 *)&rx, 4);
-	return le32_to_cpu(rx);
-}
-
 /**
  * ks8851_soft_reset - issue one of the soft reset to the device
  * @ks: The device state.
@@ -508,7 +489,6 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 	unsigned rxfc;
 	unsigned rxlen;
 	unsigned rxstat;
-	u32 rxh;
 	u8 *rxpkt;
 
 	rxfc = ks8851_rdreg8(ks, KS_RXFC);
@@ -527,9 +507,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 	 */
 
 	for (; rxfc != 0; rxfc--) {
-		rxh = ks8851_rdreg32(ks, KS_RXFHSR);
-		rxstat = rxh & 0xffff;
-		rxlen = (rxh >> 16) & 0xfff;
+		rxstat = ks8851_rdreg16(ks, KS_RXFHSR);
+		rxlen = ks8851_rdreg16(ks, KS_RXFHBCR) & RXFHBCR_CNT_MASK;
 
 		netif_dbg(ks, rx_status, ks->netdev,
 			  "rx: stat 0x%04x, len 0x%04x\n", rxstat, rxlen);
-- 
cgit v1.2.3


From 88cfedd0d7ab5ff047ac7eb8243fb9a69526fee7 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:35 +0200
Subject: net: ks8851: Use 16-bit writes to program MAC address

On the SPI variant of KS8851, the MAC address can be programmed with
either 8/16/32-bit writes. To make it easier to support the 16-bit
parallel option of KS8851 too, switch both the MAC address programming
and readout to 16-bit operations.

Remove ks8851_wrreg8() as it is not used anywhere anymore.

There should be no functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 47 ++++++++++--------------------------
 drivers/net/ethernet/micrel/ks8851.h |  2 +-
 2 files changed, 14 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 8df130efbde1..1b81340e811f 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -185,36 +185,6 @@ static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 		netdev_err(ks->netdev, "spi_sync() failed\n");
 }
 
-/**
- * ks8851_wrreg8 - write 8bit register value to chip
- * @ks: The chip state
- * @reg: The register address
- * @val: The value to write
- *
- * Issue a write to put the value @val into the register specified in @reg.
- */
-static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val)
-{
-	struct spi_transfer *xfer = &ks->spi_xfer1;
-	struct spi_message *msg = &ks->spi_msg1;
-	__le16 txb[2];
-	int ret;
-	int bit;
-
-	bit = 1 << (reg & 3);
-
-	txb[0] = cpu_to_le16(MK_OP(bit, reg) | KS_SPIOP_WR);
-	txb[1] = val;
-
-	xfer->tx_buf = txb;
-	xfer->rx_buf = NULL;
-	xfer->len = 3;
-
-	ret = spi_sync(ks->spidev, msg);
-	if (ret < 0)
-		netdev_err(ks->netdev, "spi_sync() failed\n");
-}
-
 /**
  * ks8851_rdreg - issue read register command and return the data
  * @ks: The device state
@@ -349,6 +319,7 @@ static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
 static int ks8851_write_mac_addr(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	u16 val;
 	int i;
 
 	mutex_lock(&ks->lock);
@@ -358,8 +329,12 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 	 * the first write to the MAC address does not take effect.
 	 */
 	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
-	for (i = 0; i < ETH_ALEN; i++)
-		ks8851_wrreg8(ks, KS_MAR(i), dev->dev_addr[i]);
+
+	for (i = 0; i < ETH_ALEN; i += 2) {
+		val = (dev->dev_addr[i] << 8) | dev->dev_addr[i + 1];
+		ks8851_wrreg16(ks, KS_MAR(i), val);
+	}
+
 	if (!netif_running(dev))
 		ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
 
@@ -377,12 +352,16 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 static void ks8851_read_mac_addr(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	u16 reg;
 	int i;
 
 	mutex_lock(&ks->lock);
 
-	for (i = 0; i < ETH_ALEN; i++)
-		dev->dev_addr[i] = ks8851_rdreg8(ks, KS_MAR(i));
+	for (i = 0; i < ETH_ALEN; i += 2) {
+		reg = ks8851_rdreg16(ks, KS_MAR(i));
+		dev->dev_addr[i] = reg >> 8;
+		dev->dev_addr[i + 1] = reg & 0xff;
+	}
 
 	mutex_unlock(&ks->lock);
 }
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index 8f834aef8e32..f210d18a10b5 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -19,7 +19,7 @@
 #define CCR_32PIN				(1 << 0)    /* KSZ8851SNL    */
 
 /* MAC address registers */
-#define KS_MAR(_m)				(0x15 - (_m))
+#define KS_MAR(_m)				(0x14 - (_m))
 #define KS_MARL					0x10
 #define KS_MARM					0x12
 #define KS_MARH					0x14
-- 
cgit v1.2.3


From aa39bf6730b72e495f711b0f06ca92e9673d648c Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:36 +0200
Subject: net: ks8851: Use 16-bit read of RXFC register

The RXFC register is the only one being read using 8-bit accessors.
To make it easier to support the 16-bit accesses used by the parallel
bus variant of KS8851, use 16-bit accessor to read RXFC register as
well as neighboring RXFCTR register.

Remove ks8851_rdreg8() as it is not used anywhere anymore.

There should be no functional change.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 1b81340e811f..e2e75041e931 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -236,21 +236,6 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 		memcpy(rxb, trx + 2, rxl);
 }
 
-/**
- * ks8851_rdreg8 - read 8 bit register from device
- * @ks: The chip information
- * @reg: The register address
- *
- * Read a 8bit register from the chip, returning the result
-*/
-static unsigned ks8851_rdreg8(struct ks8851_net *ks, unsigned reg)
-{
-	u8 rxb[1];
-
-	ks8851_rdreg(ks, MK_OP(1 << (reg & 3), reg), rxb, 1);
-	return rxb[0];
-}
-
 /**
  * ks8851_rdreg16 - read 16 bit register from device
  * @ks: The chip information
@@ -470,7 +455,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 	unsigned rxstat;
 	u8 *rxpkt;
 
-	rxfc = ks8851_rdreg8(ks, KS_RXFC);
+	rxfc = (ks8851_rdreg16(ks, KS_RXFCTR) >> 8) & 0xff;
 
 	netif_dbg(ks, rx_status, ks->netdev,
 		  "%s: %d packets\n", __func__, rxfc);
-- 
cgit v1.2.3


From 22726020050beacc7a164eaaafef0048d302cf41 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:37 +0200
Subject: net: ks8851: Factor out bus lock handling

Pull out bus access locking code into separate functions, this is done
in preparation for unifying the driver with the parallel bus one. The
parallel bus driver does not need heavy mutex locking of the bus and
works better with spinlocks, hence prepare these locking functions to
be overridden then.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 97 +++++++++++++++++++++++++-----------
 1 file changed, 68 insertions(+), 29 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index e2e75041e931..053d6d085539 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -151,6 +151,30 @@ static int msg_enable;
 /* turn register number and byte-enable mask into data for start of packet */
 #define MK_OP(_byteen, _reg) (BYTE_EN(_byteen) | (_reg)  << (8+2) | (_reg) >> 6)
 
+/**
+ * ks8851_lock - register access lock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Claim chip register access lock
+ */
+static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
+{
+	mutex_lock(&ks->lock);
+}
+
+/**
+ * ks8851_unlock - register access unlock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Release chip register access lock
+ */
+static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
+{
+	mutex_unlock(&ks->lock);
+}
+
 /* SPI register read/write calls.
  *
  * All these calls issue SPI transactions to access the chip's registers. They
@@ -304,10 +328,11 @@ static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
 static int ks8851_write_mac_addr(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 	u16 val;
 	int i;
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	/*
 	 * Wake up chip in case it was powered off when stopped; otherwise,
@@ -323,7 +348,7 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 	if (!netif_running(dev))
 		ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 
 	return 0;
 }
@@ -337,10 +362,11 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 static void ks8851_read_mac_addr(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 	u16 reg;
 	int i;
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	for (i = 0; i < ETH_ALEN; i += 2) {
 		reg = ks8851_rdreg16(ks, KS_MAR(i));
@@ -348,7 +374,7 @@ static void ks8851_read_mac_addr(struct net_device *dev)
 		dev->dev_addr[i + 1] = reg & 0xff;
 	}
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 }
 
 /**
@@ -534,10 +560,11 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 static irqreturn_t ks8851_irq(int irq, void *_ks)
 {
 	struct ks8851_net *ks = _ks;
-	unsigned status;
 	unsigned handled = 0;
+	unsigned long flags;
+	unsigned int status;
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	status = ks8851_rdreg16(ks, KS_ISR);
 
@@ -606,7 +633,7 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 		ks8851_wrreg16(ks, KS_RXCR1, rxc->rxcr1);
 	}
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 
 	if (status & IRQ_LCI)
 		mii_check_link(&ks->mii);
@@ -700,10 +727,11 @@ static void ks8851_done_tx(struct ks8851_net *ks, struct sk_buff *txb)
 static void ks8851_tx_work(struct work_struct *work)
 {
 	struct ks8851_net *ks = container_of(work, struct ks8851_net, tx_work);
+	unsigned long flags;
 	struct sk_buff *txb;
 	bool last = skb_queue_empty(&ks->txq);
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	while (!last) {
 		txb = skb_dequeue(&ks->txq);
@@ -719,7 +747,7 @@ static void ks8851_tx_work(struct work_struct *work)
 		}
 	}
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 }
 
 /**
@@ -732,6 +760,7 @@ static void ks8851_tx_work(struct work_struct *work)
 static int ks8851_net_open(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 	int ret;
 
 	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
@@ -744,7 +773,7 @@ static int ks8851_net_open(struct net_device *dev)
 
 	/* lock the card, even if we may not actually be doing anything
 	 * else at the moment */
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	netif_dbg(ks, ifup, ks->netdev, "opening\n");
 
@@ -804,7 +833,7 @@ static int ks8851_net_open(struct net_device *dev)
 
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 	mii_check_link(&ks->mii);
 	return 0;
 }
@@ -820,22 +849,23 @@ static int ks8851_net_open(struct net_device *dev)
 static int ks8851_net_stop(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 
 	netif_info(ks, ifdown, dev, "shutting down\n");
 
 	netif_stop_queue(dev);
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 	/* turn off the IRQs and ack any outstanding */
 	ks8851_wrreg16(ks, KS_IER, 0x0000);
 	ks8851_wrreg16(ks, KS_ISR, 0xffff);
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 
 	/* stop any outstanding work */
 	flush_work(&ks->tx_work);
 	flush_work(&ks->rxctrl_work);
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 	/* shutdown RX process */
 	ks8851_wrreg16(ks, KS_RXCR1, 0x0000);
 
@@ -844,7 +874,7 @@ static int ks8851_net_stop(struct net_device *dev)
 
 	/* set powermode to soft power down to save power */
 	ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 
 	/* ensure any queued tx buffers are dumped */
 	while (!skb_queue_empty(&ks->txq)) {
@@ -916,13 +946,14 @@ static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
 static void ks8851_rxctrl_work(struct work_struct *work)
 {
 	struct ks8851_net *ks = container_of(work, struct ks8851_net, rxctrl_work);
+	unsigned long flags;
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 
 	/* need to shutdown RXQ before modifying filter parameters */
 	ks8851_wrreg16(ks, KS_RXCR1, 0x00);
 
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 }
 
 static void ks8851_set_rx_mode(struct net_device *dev)
@@ -1104,11 +1135,6 @@ static void ks8851_eeprom_regwrite(struct eeprom_93cx6 *ee)
  */
 static int ks8851_eeprom_claim(struct ks8851_net *ks)
 {
-	if (!(ks->rc_ccr & CCR_EEPROM))
-		return -ENOENT;
-
-	mutex_lock(&ks->lock);
-
 	/* start with clock low, cs high */
 	ks8851_wrreg16(ks, KS_EEPCR, EEPCR_EESA | EEPCR_EECS);
 	return 0;
@@ -1125,7 +1151,6 @@ static void ks8851_eeprom_release(struct ks8851_net *ks)
 	unsigned val = ks8851_rdreg16(ks, KS_EEPCR);
 
 	ks8851_wrreg16(ks, KS_EEPCR, val & ~EEPCR_EESA);
-	mutex_unlock(&ks->lock);
 }
 
 #define KS_EEPROM_MAGIC (0x00008851)
@@ -1135,6 +1160,7 @@ static int ks8851_set_eeprom(struct net_device *dev,
 {
 	struct ks8851_net *ks = netdev_priv(dev);
 	int offset = ee->offset;
+	unsigned long flags;
 	int len = ee->len;
 	u16 tmp;
 
@@ -1145,9 +1171,13 @@ static int ks8851_set_eeprom(struct net_device *dev,
 	if (ee->magic != KS_EEPROM_MAGIC)
 		return -EINVAL;
 
-	if (ks8851_eeprom_claim(ks))
+	if (!(ks->rc_ccr & CCR_EEPROM))
 		return -ENOENT;
 
+	ks8851_lock(ks, &flags);
+
+	ks8851_eeprom_claim(ks);
+
 	eeprom_93cx6_wren(&ks->eeprom, true);
 
 	/* ethtool currently only supports writing bytes, which means
@@ -1167,6 +1197,7 @@ static int ks8851_set_eeprom(struct net_device *dev,
 	eeprom_93cx6_wren(&ks->eeprom, false);
 
 	ks8851_eeprom_release(ks);
+	ks8851_unlock(ks, &flags);
 
 	return 0;
 }
@@ -1176,19 +1207,25 @@ static int ks8851_get_eeprom(struct net_device *dev,
 {
 	struct ks8851_net *ks = netdev_priv(dev);
 	int offset = ee->offset;
+	unsigned long flags;
 	int len = ee->len;
 
 	/* must be 2 byte aligned */
 	if (len & 1 || offset & 1)
 		return -EINVAL;
 
-	if (ks8851_eeprom_claim(ks))
+	if (!(ks->rc_ccr & CCR_EEPROM))
 		return -ENOENT;
 
+	ks8851_lock(ks, &flags);
+
+	ks8851_eeprom_claim(ks);
+
 	ee->magic = KS_EEPROM_MAGIC;
 
 	eeprom_93cx6_multiread(&ks->eeprom, offset/2, (__le16 *)data, len/2);
 	ks8851_eeprom_release(ks);
+	ks8851_unlock(ks, &flags);
 
 	return 0;
 }
@@ -1262,6 +1299,7 @@ static int ks8851_phy_reg(int reg)
 static int ks8851_phy_read(struct net_device *dev, int phy_addr, int reg)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 	int ksreg;
 	int result;
 
@@ -1269,9 +1307,9 @@ static int ks8851_phy_read(struct net_device *dev, int phy_addr, int reg)
 	if (!ksreg)
 		return 0x0;	/* no error return allowed, so use zero */
 
-	mutex_lock(&ks->lock);
+	ks8851_lock(ks, &flags);
 	result = ks8851_rdreg16(ks, ksreg);
-	mutex_unlock(&ks->lock);
+	ks8851_unlock(ks, &flags);
 
 	return result;
 }
@@ -1280,13 +1318,14 @@ static void ks8851_phy_write(struct net_device *dev,
 			     int phy, int reg, int value)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
 	int ksreg;
 
 	ksreg = ks8851_phy_reg(reg);
 	if (ksreg) {
-		mutex_lock(&ks->lock);
+		ks8851_lock(ks, &flags);
 		ks8851_wrreg16(ks, ksreg, value);
-		mutex_unlock(&ks->lock);
+		ks8851_unlock(ks, &flags);
 	}
 }
 
-- 
cgit v1.2.3


From 18a3df73093287ed5ccf650e5d700b6afc3e0663 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:38 +0200
Subject: net: ks8851: Factor out SKB receive function

Factor out this netif_rx_ni(), so it could be overridden by the parallel
bus variant of the KS8851 driver.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 053d6d085539..087d2a39cdce 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -465,6 +465,15 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
 		   rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]);
 }
 
+/**
+ * ks8851_rx_skb - receive skbuff
+ * @skb: The skbuff
+ */
+static void ks8851_rx_skb(struct sk_buff *skb)
+{
+	netif_rx_ni(skb);
+}
+
 /**
  * ks8851_rx_pkts - receive packets from the host
  * @ks: The device information.
@@ -533,7 +542,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 					ks8851_dbg_dumpkkt(ks, rxpkt);
 
 				skb->protocol = eth_type_trans(skb, ks->netdev);
-				netif_rx_ni(skb);
+				ks8851_rx_skb(skb);
 
 				ks->netdev->stats.rx_packets++;
 				ks->netdev->stats.rx_bytes += rxlen;
-- 
cgit v1.2.3


From d48b7634c692bc3df1aec413b4b4c823d55d7899 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:39 +0200
Subject: net: ks8851: Split out SPI specific entries in struct ks8851_net

Add a new struct ks8851_net_spi, which embeds the original
struct ks8851_net and contains the entries specific only to
the SPI variant of KS8851.

There should be no functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 128 +++++++++++++++++++++--------------
 1 file changed, 79 insertions(+), 49 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 087d2a39cdce..482c65b1accf 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -64,16 +64,11 @@ union ks8851_tx_hdr {
 /**
  * struct ks8851_net - KS8851 driver private data
  * @netdev: The network device we're bound to
- * @spidev: The spi device we're bound to.
- * @lock: Lock to ensure that the device is not accessed when busy.
  * @statelock: Lock on this structure for tx list.
  * @mii: The MII state information for the mii calls.
  * @rxctrl: RX settings for @rxctrl_work.
- * @tx_work: Work queue for tx packets
  * @rxctrl_work: Work queue for updating RX mode and multicast lists
  * @txq: Queue of packets for transmission.
- * @spi_msg1: pre-setup SPI transfer with one message, @spi_xfer1.
- * @spi_msg2: pre-setup SPI transfer with two messages, @spi_xfer2.
  * @txh: Space for generating packet TX header in DMA-able data
  * @rxd: Space for receiving SPI data, in DMA-able space.
  * @txd: Space for transmitting SPI data, in DMA-able space.
@@ -87,11 +82,6 @@ union ks8851_tx_hdr {
  * @vdd_io: Optional digital power supply for IO
  * @gpio: Optional reset_n gpio
  *
- * The @lock ensures that the chip is protected when certain operations are
- * in progress. When the read or write packet transfer is in progress, most
- * of the chip registers are not ccessible until the transfer is finished and
- * the DMA has been de-asserted.
- *
  * The @statelock is used to protect information in the structure which may
  * need to be accessed via several sources, such as the network driver layer
  * or one of the work queues.
@@ -102,8 +92,6 @@ union ks8851_tx_hdr {
  */
 struct ks8851_net {
 	struct net_device	*netdev;
-	struct spi_device	*spidev;
-	struct mutex		lock;
 	spinlock_t		statelock;
 
 	union ks8851_tx_hdr	txh ____cacheline_aligned;
@@ -121,22 +109,43 @@ struct ks8851_net {
 	struct mii_if_info	mii;
 	struct ks8851_rxctrl	rxctrl;
 
-	struct work_struct	tx_work;
 	struct work_struct	rxctrl_work;
 
 	struct sk_buff_head	txq;
 
-	struct spi_message	spi_msg1;
-	struct spi_message	spi_msg2;
-	struct spi_transfer	spi_xfer1;
-	struct spi_transfer	spi_xfer2[2];
-
 	struct eeprom_93cx6	eeprom;
 	struct regulator	*vdd_reg;
 	struct regulator	*vdd_io;
 	int			gpio;
 };
 
+/**
+ * struct ks8851_net_spi - KS8851 SPI driver private data
+ * @ks8851: KS8851 driver common private data
+ * @lock: Lock to ensure that the device is not accessed when busy.
+ * @tx_work: Work queue for tx packets
+ * @spidev: The spi device we're bound to.
+ * @spi_msg1: pre-setup SPI transfer with one message, @spi_xfer1.
+ * @spi_msg2: pre-setup SPI transfer with two messages, @spi_xfer2.
+ *
+ * The @lock ensures that the chip is protected when certain operations are
+ * in progress. When the read or write packet transfer is in progress, most
+ * of the chip registers are not ccessible until the transfer is finished and
+ * the DMA has been de-asserted.
+ */
+struct ks8851_net_spi {
+	struct ks8851_net	ks8851;
+	struct mutex		lock;
+	struct work_struct	tx_work;
+	struct spi_device	*spidev;
+	struct spi_message	spi_msg1;
+	struct spi_message	spi_msg2;
+	struct spi_transfer	spi_xfer1;
+	struct spi_transfer	spi_xfer2[2];
+};
+
+#define to_ks8851_spi(ks) container_of((ks), struct ks8851_net_spi, ks8851)
+
 static int msg_enable;
 
 /* SPI frame opcodes */
@@ -160,7 +169,9 @@ static int msg_enable;
  */
 static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
 {
-	mutex_lock(&ks->lock);
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	mutex_lock(&kss->lock);
 }
 
 /**
@@ -172,7 +183,9 @@ static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
  */
 static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
 {
-	mutex_unlock(&ks->lock);
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	mutex_unlock(&kss->lock);
 }
 
 /* SPI register read/write calls.
@@ -192,8 +205,9 @@ static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
  */
 static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 {
-	struct spi_transfer *xfer = &ks->spi_xfer1;
-	struct spi_message *msg = &ks->spi_msg1;
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = &kss->spi_xfer1;
+	struct spi_message *msg = &kss->spi_msg1;
 	__le16 txb[2];
 	int ret;
 
@@ -204,7 +218,7 @@ static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 	xfer->rx_buf = NULL;
 	xfer->len = 4;
 
-	ret = spi_sync(ks->spidev, msg);
+	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "spi_sync() failed\n");
 }
@@ -222,6 +236,7 @@ static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 			 u8 *rxb, unsigned rxl)
 {
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 	struct spi_transfer *xfer;
 	struct spi_message *msg;
 	__le16 *txb = (__le16 *)ks->txd;
@@ -230,9 +245,9 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 
 	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
 
-	if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
-		msg = &ks->spi_msg2;
-		xfer = ks->spi_xfer2;
+	if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
+		msg = &kss->spi_msg2;
+		xfer = kss->spi_xfer2;
 
 		xfer->tx_buf = txb;
 		xfer->rx_buf = NULL;
@@ -243,18 +258,18 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 		xfer->rx_buf = trx;
 		xfer->len = rxl;
 	} else {
-		msg = &ks->spi_msg1;
-		xfer = &ks->spi_xfer1;
+		msg = &kss->spi_msg1;
+		xfer = &kss->spi_xfer1;
 
 		xfer->tx_buf = txb;
 		xfer->rx_buf = trx;
 		xfer->len = rxl + 2;
 	}
 
-	ret = spi_sync(ks->spidev, msg);
+	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
+	else if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
 		memcpy(rxb, trx, rxl);
 	else
 		memcpy(rxb, trx + 2, rxl);
@@ -424,8 +439,9 @@ static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
  */
 static void ks8851_rdfifo(struct ks8851_net *ks, u8 *buff, unsigned len)
 {
-	struct spi_transfer *xfer = ks->spi_xfer2;
-	struct spi_message *msg = &ks->spi_msg2;
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = kss->spi_xfer2;
+	struct spi_message *msg = &kss->spi_msg2;
 	u8 txb[1];
 	int ret;
 
@@ -444,7 +460,7 @@ static void ks8851_rdfifo(struct ks8851_net *ks, u8 *buff, unsigned len)
 	xfer->tx_buf = NULL;
 	xfer->len = len;
 
-	ret = spi_sync(ks->spidev, msg);
+	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
 }
@@ -678,8 +694,9 @@ static inline unsigned calc_txlen(unsigned len)
  */
 static void ks8851_wrpkt(struct ks8851_net *ks, struct sk_buff *txp, bool irq)
 {
-	struct spi_transfer *xfer = ks->spi_xfer2;
-	struct spi_message *msg = &ks->spi_msg2;
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = kss->spi_xfer2;
+	struct spi_message *msg = &kss->spi_msg2;
 	unsigned fid = 0;
 	int ret;
 
@@ -706,7 +723,7 @@ static void ks8851_wrpkt(struct ks8851_net *ks, struct sk_buff *txp, bool irq)
 	xfer->rx_buf = NULL;
 	xfer->len = ALIGN(txp->len, 4);
 
-	ret = spi_sync(ks->spidev, msg);
+	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
 }
@@ -735,10 +752,15 @@ static void ks8851_done_tx(struct ks8851_net *ks, struct sk_buff *txb)
  */
 static void ks8851_tx_work(struct work_struct *work)
 {
-	struct ks8851_net *ks = container_of(work, struct ks8851_net, tx_work);
+	struct ks8851_net_spi *kss;
+	struct ks8851_net *ks;
 	unsigned long flags;
 	struct sk_buff *txb;
-	bool last = skb_queue_empty(&ks->txq);
+	bool last;
+
+	kss = container_of(work, struct ks8851_net_spi, tx_work);
+	ks = &kss->ks8851;
+	last = skb_queue_empty(&ks->txq);
 
 	ks8851_lock(ks, &flags);
 
@@ -858,8 +880,11 @@ static int ks8851_net_open(struct net_device *dev)
 static int ks8851_net_stop(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	struct ks8851_net_spi *kss;
 	unsigned long flags;
 
+	kss = to_ks8851_spi(ks);
+
 	netif_info(ks, ifdown, dev, "shutting down\n");
 
 	netif_stop_queue(dev);
@@ -871,7 +896,7 @@ static int ks8851_net_stop(struct net_device *dev)
 	ks8851_unlock(ks, &flags);
 
 	/* stop any outstanding work */
-	flush_work(&ks->tx_work);
+	flush_work(&kss->tx_work);
 	flush_work(&ks->rxctrl_work);
 
 	ks8851_lock(ks, &flags);
@@ -919,6 +944,9 @@ static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
 	struct ks8851_net *ks = netdev_priv(dev);
 	unsigned needed = calc_txlen(skb->len);
 	netdev_tx_t ret = NETDEV_TX_OK;
+	struct ks8851_net_spi *kss;
+
+	kss = to_ks8851_spi(ks);
 
 	netif_dbg(ks, tx_queued, ks->netdev,
 		  "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data);
@@ -934,7 +962,7 @@ static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
 	}
 
 	spin_unlock(&ks->statelock);
-	schedule_work(&ks->tx_work);
+	schedule_work(&kss->tx_work);
 
 	return ret;
 }
@@ -1406,22 +1434,24 @@ static SIMPLE_DEV_PM_OPS(ks8851_pm_ops, ks8851_suspend, ks8851_resume);
 static int ks8851_probe(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
+	struct ks8851_net_spi *kss;
 	struct net_device *netdev;
 	struct ks8851_net *ks;
 	int ret;
 	unsigned cider;
 	int gpio;
 
-	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net));
+	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_spi));
 	if (!netdev)
 		return -ENOMEM;
 
 	spi->bits_per_word = 8;
 
 	ks = netdev_priv(netdev);
+	kss = to_ks8851_spi(ks);
 
 	ks->netdev = netdev;
-	ks->spidev = spi;
+	kss->spidev = spi;
 	ks->tx_space = 6144;
 
 	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
@@ -1467,20 +1497,20 @@ static int ks8851_probe(struct spi_device *spi)
 		gpio_set_value(gpio, 1);
 	}
 
-	mutex_init(&ks->lock);
+	mutex_init(&kss->lock);
 	spin_lock_init(&ks->statelock);
 
-	INIT_WORK(&ks->tx_work, ks8851_tx_work);
+	INIT_WORK(&kss->tx_work, ks8851_tx_work);
 	INIT_WORK(&ks->rxctrl_work, ks8851_rxctrl_work);
 
 	/* initialise pre-made spi transfer messages */
 
-	spi_message_init(&ks->spi_msg1);
-	spi_message_add_tail(&ks->spi_xfer1, &ks->spi_msg1);
+	spi_message_init(&kss->spi_msg1);
+	spi_message_add_tail(&kss->spi_xfer1, &kss->spi_msg1);
 
-	spi_message_init(&ks->spi_msg2);
-	spi_message_add_tail(&ks->spi_xfer2[0], &ks->spi_msg2);
-	spi_message_add_tail(&ks->spi_xfer2[1], &ks->spi_msg2);
+	spi_message_init(&kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[0], &kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[1], &kss->spi_msg2);
 
 	/* setup EEPROM state */
 
-- 
cgit v1.2.3


From 24be72632c68e616c23ae01b08722d38242e552b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:40 +0200
Subject: net: ks8851: Split out SPI specific code from probe() and remove()

Factor out common code into ks8851_probe_common() and
ks8851_remove_common() to permit both SPI and parallel
bus driver variants to use the common code path for
both probing and removal.

There should be no functional change.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 86 ++++++++++++++++++++----------------
 1 file changed, 48 insertions(+), 38 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 482c65b1accf..4283ba5bee81 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1431,27 +1431,15 @@ static int ks8851_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(ks8851_pm_ops, ks8851_suspend, ks8851_resume);
 
-static int ks8851_probe(struct spi_device *spi)
+static int ks8851_probe_common(struct net_device *netdev, struct device *dev,
+			       int msg_en)
 {
-	struct device *dev = &spi->dev;
-	struct ks8851_net_spi *kss;
-	struct net_device *netdev;
-	struct ks8851_net *ks;
-	int ret;
+	struct ks8851_net *ks = netdev_priv(netdev);
 	unsigned cider;
 	int gpio;
-
-	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_spi));
-	if (!netdev)
-		return -ENOMEM;
-
-	spi->bits_per_word = 8;
-
-	ks = netdev_priv(netdev);
-	kss = to_ks8851_spi(ks);
+	int ret;
 
 	ks->netdev = netdev;
-	kss->spidev = spi;
 	ks->tx_space = 6144;
 
 	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
@@ -1497,23 +1485,11 @@ static int ks8851_probe(struct spi_device *spi)
 		gpio_set_value(gpio, 1);
 	}
 
-	mutex_init(&kss->lock);
 	spin_lock_init(&ks->statelock);
 
-	INIT_WORK(&kss->tx_work, ks8851_tx_work);
 	INIT_WORK(&ks->rxctrl_work, ks8851_rxctrl_work);
 
-	/* initialise pre-made spi transfer messages */
-
-	spi_message_init(&kss->spi_msg1);
-	spi_message_add_tail(&kss->spi_xfer1, &kss->spi_msg1);
-
-	spi_message_init(&kss->spi_msg2);
-	spi_message_add_tail(&kss->spi_xfer2[0], &kss->spi_msg2);
-	spi_message_add_tail(&kss->spi_xfer2[1], &kss->spi_msg2);
-
 	/* setup EEPROM state */
-
 	ks->eeprom.data = ks;
 	ks->eeprom.width = PCI_EEPROM_WIDTH_93C46;
 	ks->eeprom.register_read = ks8851_eeprom_regread;
@@ -1527,12 +1503,12 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->mii.mdio_read	= ks8851_phy_read;
 	ks->mii.mdio_write	= ks8851_phy_write;
 
-	dev_info(dev, "message enable is %d\n", msg_enable);
+	dev_info(dev, "message enable is %d\n", msg_en);
 
 	/* set the default message enable */
-	ks->msg_enable = netif_msg_init(msg_enable, (NETIF_MSG_DRV |
-						     NETIF_MSG_PROBE |
-						     NETIF_MSG_LINK));
+	ks->msg_enable = netif_msg_init(msg_en, NETIF_MSG_DRV |
+						NETIF_MSG_PROBE |
+						NETIF_MSG_LINK);
 
 	skb_queue_head_init(&ks->txq);
 
@@ -1544,7 +1520,6 @@ static int ks8851_probe(struct spi_device *spi)
 	netif_carrier_off(ks->netdev);
 	netdev->if_port = IF_PORT_100BASET;
 	netdev->netdev_ops = &ks8851_netdev_ops;
-	netdev->irq = spi->irq;
 
 	/* issue a global soft reset to reset the device. */
 	ks8851_soft_reset(ks, GRR_GSR);
@@ -1586,12 +1561,9 @@ err_reg_io:
 	return ret;
 }
 
-static int ks8851_remove(struct spi_device *spi)
+static int ks8851_remove_common(struct device *dev)
 {
-	struct device *dev = &spi->dev;
-	struct ks8851_net *priv;
-
-	priv = dev_get_drvdata(dev);
+	struct ks8851_net *priv = dev_get_drvdata(dev);
 
 	if (netif_msg_drv(priv))
 		dev_info(dev, "remove\n");
@@ -1605,6 +1577,44 @@ static int ks8851_remove(struct spi_device *spi)
 	return 0;
 }
 
+static int ks8851_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct ks8851_net_spi *kss;
+	struct net_device *netdev;
+	struct ks8851_net *ks;
+
+	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_spi));
+	if (!netdev)
+		return -ENOMEM;
+
+	spi->bits_per_word = 8;
+
+	ks = netdev_priv(netdev);
+	kss = to_ks8851_spi(ks);
+
+	kss->spidev = spi;
+	mutex_init(&kss->lock);
+	INIT_WORK(&kss->tx_work, ks8851_tx_work);
+
+	/* initialise pre-made spi transfer messages */
+	spi_message_init(&kss->spi_msg1);
+	spi_message_add_tail(&kss->spi_xfer1, &kss->spi_msg1);
+
+	spi_message_init(&kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[0], &kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[1], &kss->spi_msg2);
+
+	netdev->irq = spi->irq;
+
+	return ks8851_probe_common(netdev, dev, msg_enable);
+}
+
+static int ks8851_remove(struct spi_device *spi)
+{
+	return ks8851_remove_common(&spi->dev);
+}
+
 static const struct of_device_id ks8851_match_table[] = {
 	{ .compatible = "micrel,ks8851" },
 	{ }
-- 
cgit v1.2.3


From 144ad36c3d3b53045a2b3f334bd735f469cb8ea8 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:41 +0200
Subject: net: ks8851: Factor out TX work flush function

While the SPI version of the KS8851 requires a TX worker thread to pump
data via SPI, the parallel bus version can write data into the TX FIFO
directly in .ndo_start_xmit, as the parallel bus access is much faster
and does not sleep. Factor out this TX work flush part, so it can be
overridden by the parallel bus driver.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 4283ba5bee81..458c86903ac0 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -781,6 +781,17 @@ static void ks8851_tx_work(struct work_struct *work)
 	ks8851_unlock(ks, &flags);
 }
 
+/**
+ * ks8851_flush_tx_work - flush outstanding TX work
+ * @ks: The device state
+ */
+static void ks8851_flush_tx_work(struct ks8851_net *ks)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	flush_work(&kss->tx_work);
+}
+
 /**
  * ks8851_net_open - open network device
  * @dev: The network device being opened.
@@ -880,11 +891,8 @@ static int ks8851_net_open(struct net_device *dev)
 static int ks8851_net_stop(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
-	struct ks8851_net_spi *kss;
 	unsigned long flags;
 
-	kss = to_ks8851_spi(ks);
-
 	netif_info(ks, ifdown, dev, "shutting down\n");
 
 	netif_stop_queue(dev);
@@ -896,7 +904,7 @@ static int ks8851_net_stop(struct net_device *dev)
 	ks8851_unlock(ks, &flags);
 
 	/* stop any outstanding work */
-	flush_work(&kss->tx_work);
+	ks8851_flush_tx_work(ks);
 	flush_work(&ks->rxctrl_work);
 
 	ks8851_lock(ks, &flags);
-- 
cgit v1.2.3


From d2a1c643a00e881de3ceae7ebe70e90f791dbb22 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:42 +0200
Subject: net: ks8851: Permit overridding interrupt enable register

The parallel bus variant does not need to use the TX interrupt at all
as it writes the TX FIFO directly with in .ndo_start_xmit, permit the
drivers to configure the interrupt enable bits.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 458c86903ac0..baf424f9893b 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -859,17 +859,8 @@ static int ks8851_net_open(struct net_device *dev)
 	ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 
 	/* clear then enable interrupts */
-
-#define STD_IRQ (IRQ_LCI |	/* Link Change */	\
-		 IRQ_TXI |	/* TX done */		\
-		 IRQ_RXI |	/* RX done */		\
-		 IRQ_SPIBEI |	/* SPI bus error */	\
-		 IRQ_TXPSI |	/* TX process stop */	\
-		 IRQ_RXPSI)	/* RX process stop */
-
-	ks->rc_ier = STD_IRQ;
-	ks8851_wrreg16(ks, KS_ISR, STD_IRQ);
-	ks8851_wrreg16(ks, KS_IER, STD_IRQ);
+	ks8851_wrreg16(ks, KS_ISR, ks->rc_ier);
+	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
 
 	netif_start_queue(ks->netdev);
 
@@ -1599,6 +1590,15 @@ static int ks8851_probe(struct spi_device *spi)
 	spi->bits_per_word = 8;
 
 	ks = netdev_priv(netdev);
+
+#define STD_IRQ (IRQ_LCI |	/* Link Change */	\
+		 IRQ_TXI |	/* TX done */		\
+		 IRQ_RXI |	/* RX done */		\
+		 IRQ_SPIBEI |	/* SPI bus error */	\
+		 IRQ_TXPSI |	/* TX process stop */	\
+		 IRQ_RXPSI)	/* RX process stop */
+	ks->rc_ier = STD_IRQ;
+
 	kss = to_ks8851_spi(ks);
 
 	kss->spidev = spi;
-- 
cgit v1.2.3


From 7a552c850c4581d698b8d47d9d03196fe572f32d Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:43 +0200
Subject: net: ks8851: Implement register, FIFO, lock accessor callbacks

The register and FIFO accessors are bus specific, so is locking.
Implement callbacks so that each variant of the KS8851 can implement
matching accessors and locking, and use the rest of the common code.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851.c | 178 ++++++++++++++++++++++++++++++-----
 1 file changed, 156 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index baf424f9893b..1fa907d5dd5b 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -81,6 +81,15 @@ union ks8851_tx_hdr {
  * @vdd_reg:	Optional regulator supplying the chip
  * @vdd_io: Optional digital power supply for IO
  * @gpio: Optional reset_n gpio
+ * @lock: Bus access lock callback
+ * @unlock: Bus access unlock callback
+ * @rdreg16: 16bit register read callback
+ * @wrreg16: 16bit register write callback
+ * @rdfifo: FIFO read callback
+ * @wrfifo: FIFO write callback
+ * @start_xmit: start_xmit() implementation callback
+ * @rx_skb: rx_skb() implementation callback
+ * @flush_tx_work: flush_tx_work() implementation callback
  *
  * The @statelock is used to protect information in the structure which may
  * need to be accessed via several sources, such as the network driver layer
@@ -117,6 +126,24 @@ struct ks8851_net {
 	struct regulator	*vdd_reg;
 	struct regulator	*vdd_io;
 	int			gpio;
+
+	void			(*lock)(struct ks8851_net *ks,
+					unsigned long *flags);
+	void			(*unlock)(struct ks8851_net *ks,
+					  unsigned long *flags);
+	unsigned int		(*rdreg16)(struct ks8851_net *ks,
+					   unsigned int reg);
+	void			(*wrreg16)(struct ks8851_net *ks,
+					   unsigned int reg, unsigned int val);
+	void			(*rdfifo)(struct ks8851_net *ks, u8 *buff,
+					  unsigned int len);
+	void			(*wrfifo)(struct ks8851_net *ks,
+					  struct sk_buff *txp, bool irq);
+	netdev_tx_t		(*start_xmit)(struct sk_buff *skb,
+					      struct net_device *dev);
+	void			(*rx_skb)(struct ks8851_net *ks,
+					  struct sk_buff *skb);
+	void			(*flush_tx_work)(struct ks8851_net *ks);
 };
 
 /**
@@ -161,13 +188,13 @@ static int msg_enable;
 #define MK_OP(_byteen, _reg) (BYTE_EN(_byteen) | (_reg)  << (8+2) | (_reg) >> 6)
 
 /**
- * ks8851_lock - register access lock
+ * ks8851_lock_spi - register access lock for SPI
  * @ks: The chip state
  * @flags: Spinlock flags
  *
  * Claim chip register access lock
  */
-static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
+static void ks8851_lock_spi(struct ks8851_net *ks, unsigned long *flags)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 
@@ -175,19 +202,43 @@ static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
 }
 
 /**
- * ks8851_unlock - register access unlock
+ * ks8851_unlock_spi - register access unlock for SPI
  * @ks: The chip state
  * @flags: Spinlock flags
  *
  * Release chip register access lock
  */
-static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
+static void ks8851_unlock_spi(struct ks8851_net *ks, unsigned long *flags)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 
 	mutex_unlock(&kss->lock);
 }
 
+/**
+ * ks8851_lock - register access lock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Claim chip register access lock
+ */
+static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
+{
+	ks->lock(ks, flags);
+}
+
+/**
+ * ks8851_unlock - register access unlock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Release chip register access lock
+ */
+static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
+{
+	ks->unlock(ks, flags);
+}
+
 /* SPI register read/write calls.
  *
  * All these calls issue SPI transactions to access the chip's registers. They
@@ -196,14 +247,15 @@ static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
  */
 
 /**
- * ks8851_wrreg16 - write 16bit register value to chip
+ * ks8851_wrreg16_spi - write 16bit register value to chip via SPI
  * @ks: The chip state
  * @reg: The register address
  * @val: The value to write
  *
  * Issue a write to put the value @val into the register specified in @reg.
  */
-static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
+static void ks8851_wrreg16_spi(struct ks8851_net *ks, unsigned int reg,
+			       unsigned int val)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 	struct spi_transfer *xfer = &kss->spi_xfer1;
@@ -223,6 +275,20 @@ static void ks8851_wrreg16(struct ks8851_net *ks, unsigned reg, unsigned val)
 		netdev_err(ks->netdev, "spi_sync() failed\n");
 }
 
+/**
+ * ks8851_wrreg16 - write 16bit register value to chip
+ * @ks: The chip state
+ * @reg: The register address
+ * @val: The value to write
+ *
+ * Issue a write to put the value @val into the register specified in @reg.
+ */
+static void ks8851_wrreg16(struct ks8851_net *ks, unsigned int reg,
+			   unsigned int val)
+{
+	ks->wrreg16(ks, reg, val);
+}
+
 /**
  * ks8851_rdreg - issue read register command and return the data
  * @ks: The device state
@@ -276,13 +342,14 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
 }
 
 /**
- * ks8851_rdreg16 - read 16 bit register from device
+ * ks8851_rdreg16_spi - read 16 bit register from device via SPI
  * @ks: The chip information
  * @reg: The register address
  *
  * Read a 16bit register from the chip, returning the result
 */
-static unsigned ks8851_rdreg16(struct ks8851_net *ks, unsigned reg)
+static unsigned int ks8851_rdreg16_spi(struct ks8851_net *ks,
+				       unsigned int reg)
 {
 	__le16 rx = 0;
 
@@ -290,6 +357,19 @@ static unsigned ks8851_rdreg16(struct ks8851_net *ks, unsigned reg)
 	return le16_to_cpu(rx);
 }
 
+/**
+ * ks8851_rdreg16 - read 16 bit register from device
+ * @ks: The chip information
+ * @reg: The register address
+ *
+ * Read a 16bit register from the chip, returning the result
+ */
+static unsigned int ks8851_rdreg16(struct ks8851_net *ks,
+				   unsigned int reg)
+{
+	return ks->rdreg16(ks, reg);
+}
+
 /**
  * ks8851_soft_reset - issue one of the soft reset to the device
  * @ks: The device state.
@@ -429,7 +509,7 @@ static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
 }
 
 /**
- * ks8851_rdfifo - read data from the receive fifo
+ * ks8851_rdfifo_spi - read data from the receive fifo via SPI
  * @ks: The device state.
  * @buff: The buffer address
  * @len: The length of the data to read
@@ -437,7 +517,8 @@ static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
  * Issue an RXQ FIFO read command and read the @len amount of data from
  * the FIFO into the buffer specified by @buff.
  */
-static void ks8851_rdfifo(struct ks8851_net *ks, u8 *buff, unsigned len)
+static void ks8851_rdfifo_spi(struct ks8851_net *ks, u8 *buff,
+			      unsigned int len)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 	struct spi_transfer *xfer = kss->spi_xfer2;
@@ -482,14 +563,25 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
 }
 
 /**
- * ks8851_rx_skb - receive skbuff
+ * ks8851_rx_skb_spi - receive skbuff for SPI
+ * @ks: The device state
  * @skb: The skbuff
  */
-static void ks8851_rx_skb(struct sk_buff *skb)
+static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
 {
 	netif_rx_ni(skb);
 }
 
+/**
+ * ks8851_rx_skb - receive skbuff
+ * @ks: The device state
+ * @skb: The skbuff
+ */
+static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb)
+{
+	ks->rx_skb(ks, skb);
+}
+
 /**
  * ks8851_rx_pkts - receive packets from the host
  * @ks: The device information.
@@ -552,13 +644,13 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 
 				rxpkt = skb_put(skb, rxlen) - 8;
 
-				ks8851_rdfifo(ks, rxpkt, rxalign + 8);
+				ks->rdfifo(ks, rxpkt, rxalign + 8);
 
 				if (netif_msg_pktdata(ks))
 					ks8851_dbg_dumpkkt(ks, rxpkt);
 
 				skb->protocol = eth_type_trans(skb, ks->netdev);
-				ks8851_rx_skb(skb);
+				ks8851_rx_skb(ks, skb);
 
 				ks->netdev->stats.rx_packets++;
 				ks->netdev->stats.rx_bytes += rxlen;
@@ -682,7 +774,7 @@ static inline unsigned calc_txlen(unsigned len)
 }
 
 /**
- * ks8851_wrpkt - write packet to TX FIFO
+ * ks8851_wrpkt_spi - write packet to TX FIFO via SPI
  * @ks: The device state.
  * @txp: The sk_buff to transmit.
  * @irq: IRQ on completion of the packet.
@@ -692,7 +784,8 @@ static inline unsigned calc_txlen(unsigned len)
  * needs, such as IRQ on completion. Send the header and the packet data to
  * the device.
  */
-static void ks8851_wrpkt(struct ks8851_net *ks, struct sk_buff *txp, bool irq)
+static void ks8851_wrpkt_spi(struct ks8851_net *ks, struct sk_buff *txp,
+			     bool irq)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 	struct spi_transfer *xfer = kss->spi_xfer2;
@@ -770,7 +863,7 @@ static void ks8851_tx_work(struct work_struct *work)
 
 		if (txb != NULL) {
 			ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
-			ks8851_wrpkt(ks, txb, last);
+			ks->wrfifo(ks, txb, last);
 			ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 			ks8851_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
 
@@ -782,16 +875,26 @@ static void ks8851_tx_work(struct work_struct *work)
 }
 
 /**
- * ks8851_flush_tx_work - flush outstanding TX work
+ * ks8851_flush_tx_work_spi - flush outstanding TX work for SPI
  * @ks: The device state
  */
-static void ks8851_flush_tx_work(struct ks8851_net *ks)
+static void ks8851_flush_tx_work_spi(struct ks8851_net *ks)
 {
 	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
 
 	flush_work(&kss->tx_work);
 }
 
+/**
+ * ks8851_flush_tx_work - flush outstanding TX work
+ * @ks: The device state
+ */
+static void ks8851_flush_tx_work(struct ks8851_net *ks)
+{
+	if (ks->flush_tx_work)
+		ks->flush_tx_work(ks);
+}
+
 /**
  * ks8851_net_open - open network device
  * @dev: The network device being opened.
@@ -925,7 +1028,7 @@ static int ks8851_net_stop(struct net_device *dev)
 }
 
 /**
- * ks8851_start_xmit - transmit packet
+ * ks8851_start_xmit_spi - transmit packet using SPI
  * @skb: The buffer to transmit
  * @dev: The device used to transmit the packet.
  *
@@ -937,8 +1040,8 @@ static int ks8851_net_stop(struct net_device *dev)
  * and secondly so we can round up more than one packet to transmit which
  * means we can try and avoid generating too many transmit done interrupts.
  */
-static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
-				     struct net_device *dev)
+static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb,
+					 struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
 	unsigned needed = calc_txlen(skb->len);
@@ -966,6 +1069,27 @@ static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
 	return ret;
 }
 
+/**
+ * ks8851_start_xmit - transmit packet
+ * @skb: The buffer to transmit
+ * @dev: The device used to transmit the packet.
+ *
+ * Called by the network layer to transmit the @skb. Queue the packet for
+ * the device and schedule the necessary work to transmit the packet when
+ * it is free.
+ *
+ * We do this to firstly avoid sleeping with the network device locked,
+ * and secondly so we can round up more than one packet to transmit which
+ * means we can try and avoid generating too many transmit done interrupts.
+ */
+static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
+				     struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	return ks->start_xmit(skb, dev);
+}
+
 /**
  * ks8851_rxctrl_work - work handler to change rx mode
  * @work: The work structure this belongs to.
@@ -1591,6 +1715,16 @@ static int ks8851_probe(struct spi_device *spi)
 
 	ks = netdev_priv(netdev);
 
+	ks->lock = ks8851_lock_spi;
+	ks->unlock = ks8851_unlock_spi;
+	ks->rdreg16 = ks8851_rdreg16_spi;
+	ks->wrreg16 = ks8851_wrreg16_spi;
+	ks->rdfifo = ks8851_rdfifo_spi;
+	ks->wrfifo = ks8851_wrpkt_spi;
+	ks->start_xmit = ks8851_start_xmit_spi;
+	ks->rx_skb = ks8851_rx_skb_spi;
+	ks->flush_tx_work = ks8851_flush_tx_work_spi;
+
 #define STD_IRQ (IRQ_LCI |	/* Link Change */	\
 		 IRQ_TXI |	/* TX done */		\
 		 IRQ_RXI |	/* RX done */		\
-- 
cgit v1.2.3


From b07f987a8d773c5c7dd5e5714e0468729abf132c Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:44 +0200
Subject: net: ks8851: Separate SPI operations into separate file

Pull all the SPI bus specific code into a separate file, so that it is
not mixed with the common code. Rename ks8851.c to ks8851_common.c. The
ks8851_common.c is linked with ks8851_spi.c now, so it can call the
accessors in the ks8851_spi.c without any pointer indirection.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/Makefile        |    1 +
 drivers/net/ethernet/micrel/ks8851.c        | 1783 ---------------------------
 drivers/net/ethernet/micrel/ks8851.h        |  149 +++
 drivers/net/ethernet/micrel/ks8851_common.c | 1193 ++++++++++++++++++
 drivers/net/ethernet/micrel/ks8851_spi.c    |  485 ++++++++
 5 files changed, 1828 insertions(+), 1783 deletions(-)
 delete mode 100644 drivers/net/ethernet/micrel/ks8851.c
 create mode 100644 drivers/net/ethernet/micrel/ks8851_common.c
 create mode 100644 drivers/net/ethernet/micrel/ks8851_spi.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/Makefile b/drivers/net/ethernet/micrel/Makefile
index 6d8ac5527aef..c7a4725c2e95 100644
--- a/drivers/net/ethernet/micrel/Makefile
+++ b/drivers/net/ethernet/micrel/Makefile
@@ -5,5 +5,6 @@
 
 obj-$(CONFIG_KS8842) += ks8842.o
 obj-$(CONFIG_KS8851) += ks8851.o
+ks8851-objs = ks8851_common.o ks8851_spi.o
 obj-$(CONFIG_KS8851_MLL) += ks8851_mll.o
 obj-$(CONFIG_KSZ884X_PCI) += ksz884x.o
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
deleted file mode 100644
index 1fa907d5dd5b..000000000000
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ /dev/null
@@ -1,1783 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* drivers/net/ethernet/micrel/ks8851.c
- *
- * Copyright 2009 Simtec Electronics
- *	http://www.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#define DEBUG
-
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/cache.h>
-#include <linux/crc32.h>
-#include <linux/mii.h>
-#include <linux/eeprom_93cx6.h>
-#include <linux/regulator/consumer.h>
-
-#include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
-#include <linux/of_net.h>
-
-#include "ks8851.h"
-
-/**
- * struct ks8851_rxctrl - KS8851 driver rx control
- * @mchash: Multicast hash-table data.
- * @rxcr1: KS_RXCR1 register setting
- * @rxcr2: KS_RXCR2 register setting
- *
- * Representation of the settings needs to control the receive filtering
- * such as the multicast hash-filter and the receive register settings. This
- * is used to make the job of working out if the receive settings change and
- * then issuing the new settings to the worker that will send the necessary
- * commands.
- */
-struct ks8851_rxctrl {
-	u16	mchash[4];
-	u16	rxcr1;
-	u16	rxcr2;
-};
-
-/**
- * union ks8851_tx_hdr - tx header data
- * @txb: The header as bytes
- * @txw: The header as 16bit, little-endian words
- *
- * A dual representation of the tx header data to allow
- * access to individual bytes, and to allow 16bit accesses
- * with 16bit alignment.
- */
-union ks8851_tx_hdr {
-	u8	txb[6];
-	__le16	txw[3];
-};
-
-/**
- * struct ks8851_net - KS8851 driver private data
- * @netdev: The network device we're bound to
- * @statelock: Lock on this structure for tx list.
- * @mii: The MII state information for the mii calls.
- * @rxctrl: RX settings for @rxctrl_work.
- * @rxctrl_work: Work queue for updating RX mode and multicast lists
- * @txq: Queue of packets for transmission.
- * @txh: Space for generating packet TX header in DMA-able data
- * @rxd: Space for receiving SPI data, in DMA-able space.
- * @txd: Space for transmitting SPI data, in DMA-able space.
- * @msg_enable: The message flags controlling driver output (see ethtool).
- * @fid: Incrementing frame id tag.
- * @rc_ier: Cached copy of KS_IER.
- * @rc_ccr: Cached copy of KS_CCR.
- * @rc_rxqcr: Cached copy of KS_RXQCR.
- * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
- * @vdd_reg:	Optional regulator supplying the chip
- * @vdd_io: Optional digital power supply for IO
- * @gpio: Optional reset_n gpio
- * @lock: Bus access lock callback
- * @unlock: Bus access unlock callback
- * @rdreg16: 16bit register read callback
- * @wrreg16: 16bit register write callback
- * @rdfifo: FIFO read callback
- * @wrfifo: FIFO write callback
- * @start_xmit: start_xmit() implementation callback
- * @rx_skb: rx_skb() implementation callback
- * @flush_tx_work: flush_tx_work() implementation callback
- *
- * The @statelock is used to protect information in the structure which may
- * need to be accessed via several sources, such as the network driver layer
- * or one of the work queues.
- *
- * We align the buffers we may use for rx/tx to ensure that if the SPI driver
- * wants to DMA map them, it will not have any problems with data the driver
- * modifies.
- */
-struct ks8851_net {
-	struct net_device	*netdev;
-	spinlock_t		statelock;
-
-	union ks8851_tx_hdr	txh ____cacheline_aligned;
-	u8			rxd[8];
-	u8			txd[8];
-
-	u32			msg_enable ____cacheline_aligned;
-	u16			tx_space;
-	u8			fid;
-
-	u16			rc_ier;
-	u16			rc_rxqcr;
-	u16			rc_ccr;
-
-	struct mii_if_info	mii;
-	struct ks8851_rxctrl	rxctrl;
-
-	struct work_struct	rxctrl_work;
-
-	struct sk_buff_head	txq;
-
-	struct eeprom_93cx6	eeprom;
-	struct regulator	*vdd_reg;
-	struct regulator	*vdd_io;
-	int			gpio;
-
-	void			(*lock)(struct ks8851_net *ks,
-					unsigned long *flags);
-	void			(*unlock)(struct ks8851_net *ks,
-					  unsigned long *flags);
-	unsigned int		(*rdreg16)(struct ks8851_net *ks,
-					   unsigned int reg);
-	void			(*wrreg16)(struct ks8851_net *ks,
-					   unsigned int reg, unsigned int val);
-	void			(*rdfifo)(struct ks8851_net *ks, u8 *buff,
-					  unsigned int len);
-	void			(*wrfifo)(struct ks8851_net *ks,
-					  struct sk_buff *txp, bool irq);
-	netdev_tx_t		(*start_xmit)(struct sk_buff *skb,
-					      struct net_device *dev);
-	void			(*rx_skb)(struct ks8851_net *ks,
-					  struct sk_buff *skb);
-	void			(*flush_tx_work)(struct ks8851_net *ks);
-};
-
-/**
- * struct ks8851_net_spi - KS8851 SPI driver private data
- * @ks8851: KS8851 driver common private data
- * @lock: Lock to ensure that the device is not accessed when busy.
- * @tx_work: Work queue for tx packets
- * @spidev: The spi device we're bound to.
- * @spi_msg1: pre-setup SPI transfer with one message, @spi_xfer1.
- * @spi_msg2: pre-setup SPI transfer with two messages, @spi_xfer2.
- *
- * The @lock ensures that the chip is protected when certain operations are
- * in progress. When the read or write packet transfer is in progress, most
- * of the chip registers are not ccessible until the transfer is finished and
- * the DMA has been de-asserted.
- */
-struct ks8851_net_spi {
-	struct ks8851_net	ks8851;
-	struct mutex		lock;
-	struct work_struct	tx_work;
-	struct spi_device	*spidev;
-	struct spi_message	spi_msg1;
-	struct spi_message	spi_msg2;
-	struct spi_transfer	spi_xfer1;
-	struct spi_transfer	spi_xfer2[2];
-};
-
-#define to_ks8851_spi(ks) container_of((ks), struct ks8851_net_spi, ks8851)
-
-static int msg_enable;
-
-/* SPI frame opcodes */
-#define KS_SPIOP_RD	(0x00)
-#define KS_SPIOP_WR	(0x40)
-#define KS_SPIOP_RXFIFO	(0x80)
-#define KS_SPIOP_TXFIFO	(0xC0)
-
-/* shift for byte-enable data */
-#define BYTE_EN(_x)	((_x) << 2)
-
-/* turn register number and byte-enable mask into data for start of packet */
-#define MK_OP(_byteen, _reg) (BYTE_EN(_byteen) | (_reg)  << (8+2) | (_reg) >> 6)
-
-/**
- * ks8851_lock_spi - register access lock for SPI
- * @ks: The chip state
- * @flags: Spinlock flags
- *
- * Claim chip register access lock
- */
-static void ks8851_lock_spi(struct ks8851_net *ks, unsigned long *flags)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-
-	mutex_lock(&kss->lock);
-}
-
-/**
- * ks8851_unlock_spi - register access unlock for SPI
- * @ks: The chip state
- * @flags: Spinlock flags
- *
- * Release chip register access lock
- */
-static void ks8851_unlock_spi(struct ks8851_net *ks, unsigned long *flags)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-
-	mutex_unlock(&kss->lock);
-}
-
-/**
- * ks8851_lock - register access lock
- * @ks: The chip state
- * @flags: Spinlock flags
- *
- * Claim chip register access lock
- */
-static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
-{
-	ks->lock(ks, flags);
-}
-
-/**
- * ks8851_unlock - register access unlock
- * @ks: The chip state
- * @flags: Spinlock flags
- *
- * Release chip register access lock
- */
-static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
-{
-	ks->unlock(ks, flags);
-}
-
-/* SPI register read/write calls.
- *
- * All these calls issue SPI transactions to access the chip's registers. They
- * all require that the necessary lock is held to prevent accesses when the
- * chip is busy transferring packet data (RX/TX FIFO accesses).
- */
-
-/**
- * ks8851_wrreg16_spi - write 16bit register value to chip via SPI
- * @ks: The chip state
- * @reg: The register address
- * @val: The value to write
- *
- * Issue a write to put the value @val into the register specified in @reg.
- */
-static void ks8851_wrreg16_spi(struct ks8851_net *ks, unsigned int reg,
-			       unsigned int val)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-	struct spi_transfer *xfer = &kss->spi_xfer1;
-	struct spi_message *msg = &kss->spi_msg1;
-	__le16 txb[2];
-	int ret;
-
-	txb[0] = cpu_to_le16(MK_OP(reg & 2 ? 0xC : 0x03, reg) | KS_SPIOP_WR);
-	txb[1] = cpu_to_le16(val);
-
-	xfer->tx_buf = txb;
-	xfer->rx_buf = NULL;
-	xfer->len = 4;
-
-	ret = spi_sync(kss->spidev, msg);
-	if (ret < 0)
-		netdev_err(ks->netdev, "spi_sync() failed\n");
-}
-
-/**
- * ks8851_wrreg16 - write 16bit register value to chip
- * @ks: The chip state
- * @reg: The register address
- * @val: The value to write
- *
- * Issue a write to put the value @val into the register specified in @reg.
- */
-static void ks8851_wrreg16(struct ks8851_net *ks, unsigned int reg,
-			   unsigned int val)
-{
-	ks->wrreg16(ks, reg, val);
-}
-
-/**
- * ks8851_rdreg - issue read register command and return the data
- * @ks: The device state
- * @op: The register address and byte enables in message format.
- * @rxb: The RX buffer to return the result into
- * @rxl: The length of data expected.
- *
- * This is the low level read call that issues the necessary spi message(s)
- * to read data from the register specified in @op.
- */
-static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
-			 u8 *rxb, unsigned rxl)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-	struct spi_transfer *xfer;
-	struct spi_message *msg;
-	__le16 *txb = (__le16 *)ks->txd;
-	u8 *trx = ks->rxd;
-	int ret;
-
-	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
-
-	if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
-		msg = &kss->spi_msg2;
-		xfer = kss->spi_xfer2;
-
-		xfer->tx_buf = txb;
-		xfer->rx_buf = NULL;
-		xfer->len = 2;
-
-		xfer++;
-		xfer->tx_buf = NULL;
-		xfer->rx_buf = trx;
-		xfer->len = rxl;
-	} else {
-		msg = &kss->spi_msg1;
-		xfer = &kss->spi_xfer1;
-
-		xfer->tx_buf = txb;
-		xfer->rx_buf = trx;
-		xfer->len = rxl + 2;
-	}
-
-	ret = spi_sync(kss->spidev, msg);
-	if (ret < 0)
-		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
-		memcpy(rxb, trx, rxl);
-	else
-		memcpy(rxb, trx + 2, rxl);
-}
-
-/**
- * ks8851_rdreg16_spi - read 16 bit register from device via SPI
- * @ks: The chip information
- * @reg: The register address
- *
- * Read a 16bit register from the chip, returning the result
-*/
-static unsigned int ks8851_rdreg16_spi(struct ks8851_net *ks,
-				       unsigned int reg)
-{
-	__le16 rx = 0;
-
-	ks8851_rdreg(ks, MK_OP(reg & 2 ? 0xC : 0x3, reg), (u8 *)&rx, 2);
-	return le16_to_cpu(rx);
-}
-
-/**
- * ks8851_rdreg16 - read 16 bit register from device
- * @ks: The chip information
- * @reg: The register address
- *
- * Read a 16bit register from the chip, returning the result
- */
-static unsigned int ks8851_rdreg16(struct ks8851_net *ks,
-				   unsigned int reg)
-{
-	return ks->rdreg16(ks, reg);
-}
-
-/**
- * ks8851_soft_reset - issue one of the soft reset to the device
- * @ks: The device state.
- * @op: The bit(s) to set in the GRR
- *
- * Issue the relevant soft-reset command to the device's GRR register
- * specified by @op.
- *
- * Note, the delays are in there as a caution to ensure that the reset
- * has time to take effect and then complete. Since the datasheet does
- * not currently specify the exact sequence, we have chosen something
- * that seems to work with our device.
- */
-static void ks8851_soft_reset(struct ks8851_net *ks, unsigned op)
-{
-	ks8851_wrreg16(ks, KS_GRR, op);
-	mdelay(1);	/* wait a short time to effect reset */
-	ks8851_wrreg16(ks, KS_GRR, 0);
-	mdelay(1);	/* wait for condition to clear */
-}
-
-/**
- * ks8851_set_powermode - set power mode of the device
- * @ks: The device state
- * @pwrmode: The power mode value to write to KS_PMECR.
- *
- * Change the power mode of the chip.
- */
-static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
-{
-	unsigned pmecr;
-
-	netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
-
-	pmecr = ks8851_rdreg16(ks, KS_PMECR);
-	pmecr &= ~PMECR_PM_MASK;
-	pmecr |= pwrmode;
-
-	ks8851_wrreg16(ks, KS_PMECR, pmecr);
-}
-
-/**
- * ks8851_write_mac_addr - write mac address to device registers
- * @dev: The network device
- *
- * Update the KS8851 MAC address registers from the address in @dev.
- *
- * This call assumes that the chip is not running, so there is no need to
- * shutdown the RXQ process whilst setting this.
-*/
-static int ks8851_write_mac_addr(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-	u16 val;
-	int i;
-
-	ks8851_lock(ks, &flags);
-
-	/*
-	 * Wake up chip in case it was powered off when stopped; otherwise,
-	 * the first write to the MAC address does not take effect.
-	 */
-	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
-
-	for (i = 0; i < ETH_ALEN; i += 2) {
-		val = (dev->dev_addr[i] << 8) | dev->dev_addr[i + 1];
-		ks8851_wrreg16(ks, KS_MAR(i), val);
-	}
-
-	if (!netif_running(dev))
-		ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
-
-	ks8851_unlock(ks, &flags);
-
-	return 0;
-}
-
-/**
- * ks8851_read_mac_addr - read mac address from device registers
- * @dev: The network device
- *
- * Update our copy of the KS8851 MAC address from the registers of @dev.
-*/
-static void ks8851_read_mac_addr(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-	u16 reg;
-	int i;
-
-	ks8851_lock(ks, &flags);
-
-	for (i = 0; i < ETH_ALEN; i += 2) {
-		reg = ks8851_rdreg16(ks, KS_MAR(i));
-		dev->dev_addr[i] = reg >> 8;
-		dev->dev_addr[i + 1] = reg & 0xff;
-	}
-
-	ks8851_unlock(ks, &flags);
-}
-
-/**
- * ks8851_init_mac - initialise the mac address
- * @ks: The device structure
- * @np: The device node pointer
- *
- * Get or create the initial mac address for the device and then set that
- * into the station address register. A mac address supplied in the device
- * tree takes precedence. Otherwise, if there is an EEPROM present, then
- * we try that. If no valid mac address is found we use eth_random_addr()
- * to create a new one.
- */
-static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
-{
-	struct net_device *dev = ks->netdev;
-	const u8 *mac_addr;
-
-	mac_addr = of_get_mac_address(np);
-	if (!IS_ERR(mac_addr)) {
-		ether_addr_copy(dev->dev_addr, mac_addr);
-		ks8851_write_mac_addr(dev);
-		return;
-	}
-
-	if (ks->rc_ccr & CCR_EEPROM) {
-		ks8851_read_mac_addr(dev);
-		if (is_valid_ether_addr(dev->dev_addr))
-			return;
-
-		netdev_err(ks->netdev, "invalid mac address read %pM\n",
-				dev->dev_addr);
-	}
-
-	eth_hw_addr_random(dev);
-	ks8851_write_mac_addr(dev);
-}
-
-/**
- * ks8851_rdfifo_spi - read data from the receive fifo via SPI
- * @ks: The device state.
- * @buff: The buffer address
- * @len: The length of the data to read
- *
- * Issue an RXQ FIFO read command and read the @len amount of data from
- * the FIFO into the buffer specified by @buff.
- */
-static void ks8851_rdfifo_spi(struct ks8851_net *ks, u8 *buff,
-			      unsigned int len)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-	struct spi_transfer *xfer = kss->spi_xfer2;
-	struct spi_message *msg = &kss->spi_msg2;
-	u8 txb[1];
-	int ret;
-
-	netif_dbg(ks, rx_status, ks->netdev,
-		  "%s: %d@%p\n", __func__, len, buff);
-
-	/* set the operation we're issuing */
-	txb[0] = KS_SPIOP_RXFIFO;
-
-	xfer->tx_buf = txb;
-	xfer->rx_buf = NULL;
-	xfer->len = 1;
-
-	xfer++;
-	xfer->rx_buf = buff;
-	xfer->tx_buf = NULL;
-	xfer->len = len;
-
-	ret = spi_sync(kss->spidev, msg);
-	if (ret < 0)
-		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
-}
-
-/**
- * ks8851_dbg_dumpkkt - dump initial packet contents to debug
- * @ks: The device state
- * @rxpkt: The data for the received packet
- *
- * Dump the initial data from the packet to dev_dbg().
-*/
-static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
-{
-	netdev_dbg(ks->netdev,
-		   "pkt %02x%02x%02x%02x %02x%02x%02x%02x %02x%02x%02x%02x\n",
-		   rxpkt[4], rxpkt[5], rxpkt[6], rxpkt[7],
-		   rxpkt[8], rxpkt[9], rxpkt[10], rxpkt[11],
-		   rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]);
-}
-
-/**
- * ks8851_rx_skb_spi - receive skbuff for SPI
- * @ks: The device state
- * @skb: The skbuff
- */
-static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
-{
-	netif_rx_ni(skb);
-}
-
-/**
- * ks8851_rx_skb - receive skbuff
- * @ks: The device state
- * @skb: The skbuff
- */
-static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb)
-{
-	ks->rx_skb(ks, skb);
-}
-
-/**
- * ks8851_rx_pkts - receive packets from the host
- * @ks: The device information.
- *
- * This is called from the IRQ work queue when the system detects that there
- * are packets in the receive queue. Find out how many packets there are and
- * read them from the FIFO.
- */
-static void ks8851_rx_pkts(struct ks8851_net *ks)
-{
-	struct sk_buff *skb;
-	unsigned rxfc;
-	unsigned rxlen;
-	unsigned rxstat;
-	u8 *rxpkt;
-
-	rxfc = (ks8851_rdreg16(ks, KS_RXFCTR) >> 8) & 0xff;
-
-	netif_dbg(ks, rx_status, ks->netdev,
-		  "%s: %d packets\n", __func__, rxfc);
-
-	/* Currently we're issuing a read per packet, but we could possibly
-	 * improve the code by issuing a single read, getting the receive
-	 * header, allocating the packet and then reading the packet data
-	 * out in one go.
-	 *
-	 * This form of operation would require us to hold the SPI bus'
-	 * chipselect low during the entie transaction to avoid any
-	 * reset to the data stream coming from the chip.
-	 */
-
-	for (; rxfc != 0; rxfc--) {
-		rxstat = ks8851_rdreg16(ks, KS_RXFHSR);
-		rxlen = ks8851_rdreg16(ks, KS_RXFHBCR) & RXFHBCR_CNT_MASK;
-
-		netif_dbg(ks, rx_status, ks->netdev,
-			  "rx: stat 0x%04x, len 0x%04x\n", rxstat, rxlen);
-
-		/* the length of the packet includes the 32bit CRC */
-
-		/* set dma read address */
-		ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00);
-
-		/* start DMA access */
-		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
-
-		if (rxlen > 4) {
-			unsigned int rxalign;
-
-			rxlen -= 4;
-			rxalign = ALIGN(rxlen, 4);
-			skb = netdev_alloc_skb_ip_align(ks->netdev, rxalign);
-			if (skb) {
-
-				/* 4 bytes of status header + 4 bytes of
-				 * garbage: we put them before ethernet
-				 * header, so that they are copied,
-				 * but ignored.
-				 */
-
-				rxpkt = skb_put(skb, rxlen) - 8;
-
-				ks->rdfifo(ks, rxpkt, rxalign + 8);
-
-				if (netif_msg_pktdata(ks))
-					ks8851_dbg_dumpkkt(ks, rxpkt);
-
-				skb->protocol = eth_type_trans(skb, ks->netdev);
-				ks8851_rx_skb(ks, skb);
-
-				ks->netdev->stats.rx_packets++;
-				ks->netdev->stats.rx_bytes += rxlen;
-			}
-		}
-
-		/* end DMA access and dequeue packet */
-		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF);
-	}
-}
-
-/**
- * ks8851_irq - IRQ handler for dealing with interrupt requests
- * @irq: IRQ number
- * @_ks: cookie
- *
- * This handler is invoked when the IRQ line asserts to find out what happened.
- * As we cannot allow ourselves to sleep in HARDIRQ context, this handler runs
- * in thread context.
- *
- * Read the interrupt status, work out what needs to be done and then clear
- * any of the interrupts that are not needed.
- */
-static irqreturn_t ks8851_irq(int irq, void *_ks)
-{
-	struct ks8851_net *ks = _ks;
-	unsigned handled = 0;
-	unsigned long flags;
-	unsigned int status;
-
-	ks8851_lock(ks, &flags);
-
-	status = ks8851_rdreg16(ks, KS_ISR);
-
-	netif_dbg(ks, intr, ks->netdev,
-		  "%s: status 0x%04x\n", __func__, status);
-
-	if (status & IRQ_LCI)
-		handled |= IRQ_LCI;
-
-	if (status & IRQ_LDI) {
-		u16 pmecr = ks8851_rdreg16(ks, KS_PMECR);
-		pmecr &= ~PMECR_WKEVT_MASK;
-		ks8851_wrreg16(ks, KS_PMECR, pmecr | PMECR_WKEVT_LINK);
-
-		handled |= IRQ_LDI;
-	}
-
-	if (status & IRQ_RXPSI)
-		handled |= IRQ_RXPSI;
-
-	if (status & IRQ_TXI) {
-		handled |= IRQ_TXI;
-
-		/* no lock here, tx queue should have been stopped */
-
-		/* update our idea of how much tx space is available to the
-		 * system */
-		ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
-
-		netif_dbg(ks, intr, ks->netdev,
-			  "%s: txspace %d\n", __func__, ks->tx_space);
-	}
-
-	if (status & IRQ_RXI)
-		handled |= IRQ_RXI;
-
-	if (status & IRQ_SPIBEI) {
-		netdev_err(ks->netdev, "%s: spi bus error\n", __func__);
-		handled |= IRQ_SPIBEI;
-	}
-
-	ks8851_wrreg16(ks, KS_ISR, handled);
-
-	if (status & IRQ_RXI) {
-		/* the datasheet says to disable the rx interrupt during
-		 * packet read-out, however we're masking the interrupt
-		 * from the device so do not bother masking just the RX
-		 * from the device. */
-
-		ks8851_rx_pkts(ks);
-	}
-
-	/* if something stopped the rx process, probably due to wanting
-	 * to change the rx settings, then do something about restarting
-	 * it. */
-	if (status & IRQ_RXPSI) {
-		struct ks8851_rxctrl *rxc = &ks->rxctrl;
-
-		/* update the multicast hash table */
-		ks8851_wrreg16(ks, KS_MAHTR0, rxc->mchash[0]);
-		ks8851_wrreg16(ks, KS_MAHTR1, rxc->mchash[1]);
-		ks8851_wrreg16(ks, KS_MAHTR2, rxc->mchash[2]);
-		ks8851_wrreg16(ks, KS_MAHTR3, rxc->mchash[3]);
-
-		ks8851_wrreg16(ks, KS_RXCR2, rxc->rxcr2);
-		ks8851_wrreg16(ks, KS_RXCR1, rxc->rxcr1);
-	}
-
-	ks8851_unlock(ks, &flags);
-
-	if (status & IRQ_LCI)
-		mii_check_link(&ks->mii);
-
-	if (status & IRQ_TXI)
-		netif_wake_queue(ks->netdev);
-
-	return IRQ_HANDLED;
-}
-
-/**
- * calc_txlen - calculate size of message to send packet
- * @len: Length of data
- *
- * Returns the size of the TXFIFO message needed to send
- * this packet.
- */
-static inline unsigned calc_txlen(unsigned len)
-{
-	return ALIGN(len + 4, 4);
-}
-
-/**
- * ks8851_wrpkt_spi - write packet to TX FIFO via SPI
- * @ks: The device state.
- * @txp: The sk_buff to transmit.
- * @irq: IRQ on completion of the packet.
- *
- * Send the @txp to the chip. This means creating the relevant packet header
- * specifying the length of the packet and the other information the chip
- * needs, such as IRQ on completion. Send the header and the packet data to
- * the device.
- */
-static void ks8851_wrpkt_spi(struct ks8851_net *ks, struct sk_buff *txp,
-			     bool irq)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-	struct spi_transfer *xfer = kss->spi_xfer2;
-	struct spi_message *msg = &kss->spi_msg2;
-	unsigned fid = 0;
-	int ret;
-
-	netif_dbg(ks, tx_queued, ks->netdev, "%s: skb %p, %d@%p, irq %d\n",
-		  __func__, txp, txp->len, txp->data, irq);
-
-	fid = ks->fid++;
-	fid &= TXFR_TXFID_MASK;
-
-	if (irq)
-		fid |= TXFR_TXIC;	/* irq on completion */
-
-	/* start header at txb[1] to align txw entries */
-	ks->txh.txb[1] = KS_SPIOP_TXFIFO;
-	ks->txh.txw[1] = cpu_to_le16(fid);
-	ks->txh.txw[2] = cpu_to_le16(txp->len);
-
-	xfer->tx_buf = &ks->txh.txb[1];
-	xfer->rx_buf = NULL;
-	xfer->len = 5;
-
-	xfer++;
-	xfer->tx_buf = txp->data;
-	xfer->rx_buf = NULL;
-	xfer->len = ALIGN(txp->len, 4);
-
-	ret = spi_sync(kss->spidev, msg);
-	if (ret < 0)
-		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
-}
-
-/**
- * ks8851_done_tx - update and then free skbuff after transmitting
- * @ks: The device state
- * @txb: The buffer transmitted
- */
-static void ks8851_done_tx(struct ks8851_net *ks, struct sk_buff *txb)
-{
-	struct net_device *dev = ks->netdev;
-
-	dev->stats.tx_bytes += txb->len;
-	dev->stats.tx_packets++;
-
-	dev_kfree_skb(txb);
-}
-
-/**
- * ks8851_tx_work - process tx packet(s)
- * @work: The work strucutre what was scheduled.
- *
- * This is called when a number of packets have been scheduled for
- * transmission and need to be sent to the device.
- */
-static void ks8851_tx_work(struct work_struct *work)
-{
-	struct ks8851_net_spi *kss;
-	struct ks8851_net *ks;
-	unsigned long flags;
-	struct sk_buff *txb;
-	bool last;
-
-	kss = container_of(work, struct ks8851_net_spi, tx_work);
-	ks = &kss->ks8851;
-	last = skb_queue_empty(&ks->txq);
-
-	ks8851_lock(ks, &flags);
-
-	while (!last) {
-		txb = skb_dequeue(&ks->txq);
-		last = skb_queue_empty(&ks->txq);
-
-		if (txb != NULL) {
-			ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
-			ks->wrfifo(ks, txb, last);
-			ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
-			ks8851_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
-
-			ks8851_done_tx(ks, txb);
-		}
-	}
-
-	ks8851_unlock(ks, &flags);
-}
-
-/**
- * ks8851_flush_tx_work_spi - flush outstanding TX work for SPI
- * @ks: The device state
- */
-static void ks8851_flush_tx_work_spi(struct ks8851_net *ks)
-{
-	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
-
-	flush_work(&kss->tx_work);
-}
-
-/**
- * ks8851_flush_tx_work - flush outstanding TX work
- * @ks: The device state
- */
-static void ks8851_flush_tx_work(struct ks8851_net *ks)
-{
-	if (ks->flush_tx_work)
-		ks->flush_tx_work(ks);
-}
-
-/**
- * ks8851_net_open - open network device
- * @dev: The network device being opened.
- *
- * Called when the network device is marked active, such as a user executing
- * 'ifconfig up' on the device.
- */
-static int ks8851_net_open(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-	int ret;
-
-	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
-				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				   dev->name, ks);
-	if (ret < 0) {
-		netdev_err(dev, "failed to get irq\n");
-		return ret;
-	}
-
-	/* lock the card, even if we may not actually be doing anything
-	 * else at the moment */
-	ks8851_lock(ks, &flags);
-
-	netif_dbg(ks, ifup, ks->netdev, "opening\n");
-
-	/* bring chip out of any power saving mode it was in */
-	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
-
-	/* issue a soft reset to the RX/TX QMU to put it into a known
-	 * state. */
-	ks8851_soft_reset(ks, GRR_QMU);
-
-	/* setup transmission parameters */
-
-	ks8851_wrreg16(ks, KS_TXCR, (TXCR_TXE | /* enable transmit process */
-				     TXCR_TXPE | /* pad to min length */
-				     TXCR_TXCRC | /* add CRC */
-				     TXCR_TXFCE)); /* enable flow control */
-
-	/* auto-increment tx data, reset tx pointer */
-	ks8851_wrreg16(ks, KS_TXFDPR, TXFDPR_TXFPAI);
-
-	/* setup receiver control */
-
-	ks8851_wrreg16(ks, KS_RXCR1, (RXCR1_RXPAFMA | /*  from mac filter */
-				      RXCR1_RXFCE | /* enable flow control */
-				      RXCR1_RXBE | /* broadcast enable */
-				      RXCR1_RXUE | /* unicast enable */
-				      RXCR1_RXE)); /* enable rx block */
-
-	/* transfer entire frames out in one go */
-	ks8851_wrreg16(ks, KS_RXCR2, RXCR2_SRDBL_FRAME);
-
-	/* set receive counter timeouts */
-	ks8851_wrreg16(ks, KS_RXDTTR, 1000); /* 1ms after first frame to IRQ */
-	ks8851_wrreg16(ks, KS_RXDBCTR, 4096); /* >4Kbytes in buffer to IRQ */
-	ks8851_wrreg16(ks, KS_RXFCTR, 10);  /* 10 frames to IRQ */
-
-	ks->rc_rxqcr = (RXQCR_RXFCTE |  /* IRQ on frame count exceeded */
-			RXQCR_RXDBCTE | /* IRQ on byte count exceeded */
-			RXQCR_RXDTTE);  /* IRQ on time exceeded */
-
-	ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
-
-	/* clear then enable interrupts */
-	ks8851_wrreg16(ks, KS_ISR, ks->rc_ier);
-	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
-
-	netif_start_queue(ks->netdev);
-
-	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
-
-	ks8851_unlock(ks, &flags);
-	mii_check_link(&ks->mii);
-	return 0;
-}
-
-/**
- * ks8851_net_stop - close network device
- * @dev: The device being closed.
- *
- * Called to close down a network device which has been active. Cancell any
- * work, shutdown the RX and TX process and then place the chip into a low
- * power state whilst it is not being used.
- */
-static int ks8851_net_stop(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-
-	netif_info(ks, ifdown, dev, "shutting down\n");
-
-	netif_stop_queue(dev);
-
-	ks8851_lock(ks, &flags);
-	/* turn off the IRQs and ack any outstanding */
-	ks8851_wrreg16(ks, KS_IER, 0x0000);
-	ks8851_wrreg16(ks, KS_ISR, 0xffff);
-	ks8851_unlock(ks, &flags);
-
-	/* stop any outstanding work */
-	ks8851_flush_tx_work(ks);
-	flush_work(&ks->rxctrl_work);
-
-	ks8851_lock(ks, &flags);
-	/* shutdown RX process */
-	ks8851_wrreg16(ks, KS_RXCR1, 0x0000);
-
-	/* shutdown TX process */
-	ks8851_wrreg16(ks, KS_TXCR, 0x0000);
-
-	/* set powermode to soft power down to save power */
-	ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
-	ks8851_unlock(ks, &flags);
-
-	/* ensure any queued tx buffers are dumped */
-	while (!skb_queue_empty(&ks->txq)) {
-		struct sk_buff *txb = skb_dequeue(&ks->txq);
-
-		netif_dbg(ks, ifdown, ks->netdev,
-			  "%s: freeing txb %p\n", __func__, txb);
-
-		dev_kfree_skb(txb);
-	}
-
-	free_irq(dev->irq, ks);
-
-	return 0;
-}
-
-/**
- * ks8851_start_xmit_spi - transmit packet using SPI
- * @skb: The buffer to transmit
- * @dev: The device used to transmit the packet.
- *
- * Called by the network layer to transmit the @skb. Queue the packet for
- * the device and schedule the necessary work to transmit the packet when
- * it is free.
- *
- * We do this to firstly avoid sleeping with the network device locked,
- * and secondly so we can round up more than one packet to transmit which
- * means we can try and avoid generating too many transmit done interrupts.
- */
-static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb,
-					 struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned needed = calc_txlen(skb->len);
-	netdev_tx_t ret = NETDEV_TX_OK;
-	struct ks8851_net_spi *kss;
-
-	kss = to_ks8851_spi(ks);
-
-	netif_dbg(ks, tx_queued, ks->netdev,
-		  "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data);
-
-	spin_lock(&ks->statelock);
-
-	if (needed > ks->tx_space) {
-		netif_stop_queue(dev);
-		ret = NETDEV_TX_BUSY;
-	} else {
-		ks->tx_space -= needed;
-		skb_queue_tail(&ks->txq, skb);
-	}
-
-	spin_unlock(&ks->statelock);
-	schedule_work(&kss->tx_work);
-
-	return ret;
-}
-
-/**
- * ks8851_start_xmit - transmit packet
- * @skb: The buffer to transmit
- * @dev: The device used to transmit the packet.
- *
- * Called by the network layer to transmit the @skb. Queue the packet for
- * the device and schedule the necessary work to transmit the packet when
- * it is free.
- *
- * We do this to firstly avoid sleeping with the network device locked,
- * and secondly so we can round up more than one packet to transmit which
- * means we can try and avoid generating too many transmit done interrupts.
- */
-static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
-				     struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-
-	return ks->start_xmit(skb, dev);
-}
-
-/**
- * ks8851_rxctrl_work - work handler to change rx mode
- * @work: The work structure this belongs to.
- *
- * Lock the device and issue the necessary changes to the receive mode from
- * the network device layer. This is done so that we can do this without
- * having to sleep whilst holding the network device lock.
- *
- * Since the recommendation from Micrel is that the RXQ is shutdown whilst the
- * receive parameters are programmed, we issue a write to disable the RXQ and
- * then wait for the interrupt handler to be triggered once the RXQ shutdown is
- * complete. The interrupt handler then writes the new values into the chip.
- */
-static void ks8851_rxctrl_work(struct work_struct *work)
-{
-	struct ks8851_net *ks = container_of(work, struct ks8851_net, rxctrl_work);
-	unsigned long flags;
-
-	ks8851_lock(ks, &flags);
-
-	/* need to shutdown RXQ before modifying filter parameters */
-	ks8851_wrreg16(ks, KS_RXCR1, 0x00);
-
-	ks8851_unlock(ks, &flags);
-}
-
-static void ks8851_set_rx_mode(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	struct ks8851_rxctrl rxctrl;
-
-	memset(&rxctrl, 0, sizeof(rxctrl));
-
-	if (dev->flags & IFF_PROMISC) {
-		/* interface to receive everything */
-
-		rxctrl.rxcr1 = RXCR1_RXAE | RXCR1_RXINVF;
-	} else if (dev->flags & IFF_ALLMULTI) {
-		/* accept all multicast packets */
-
-		rxctrl.rxcr1 = (RXCR1_RXME | RXCR1_RXAE |
-				RXCR1_RXPAFMA | RXCR1_RXMAFMA);
-	} else if (dev->flags & IFF_MULTICAST && !netdev_mc_empty(dev)) {
-		struct netdev_hw_addr *ha;
-		u32 crc;
-
-		/* accept some multicast */
-
-		netdev_for_each_mc_addr(ha, dev) {
-			crc = ether_crc(ETH_ALEN, ha->addr);
-			crc >>= (32 - 6);  /* get top six bits */
-
-			rxctrl.mchash[crc >> 4] |= (1 << (crc & 0xf));
-		}
-
-		rxctrl.rxcr1 = RXCR1_RXME | RXCR1_RXPAFMA;
-	} else {
-		/* just accept broadcast / unicast */
-		rxctrl.rxcr1 = RXCR1_RXPAFMA;
-	}
-
-	rxctrl.rxcr1 |= (RXCR1_RXUE | /* unicast enable */
-			 RXCR1_RXBE | /* broadcast enable */
-			 RXCR1_RXE | /* RX process enable */
-			 RXCR1_RXFCE); /* enable flow control */
-
-	rxctrl.rxcr2 |= RXCR2_SRDBL_FRAME;
-
-	/* schedule work to do the actual set of the data if needed */
-
-	spin_lock(&ks->statelock);
-
-	if (memcmp(&rxctrl, &ks->rxctrl, sizeof(rxctrl)) != 0) {
-		memcpy(&ks->rxctrl, &rxctrl, sizeof(ks->rxctrl));
-		schedule_work(&ks->rxctrl_work);
-	}
-
-	spin_unlock(&ks->statelock);
-}
-
-static int ks8851_set_mac_address(struct net_device *dev, void *addr)
-{
-	struct sockaddr *sa = addr;
-
-	if (netif_running(dev))
-		return -EBUSY;
-
-	if (!is_valid_ether_addr(sa->sa_data))
-		return -EADDRNOTAVAIL;
-
-	memcpy(dev->dev_addr, sa->sa_data, ETH_ALEN);
-	return ks8851_write_mac_addr(dev);
-}
-
-static int ks8851_net_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	return generic_mii_ioctl(&ks->mii, if_mii(req), cmd, NULL);
-}
-
-static const struct net_device_ops ks8851_netdev_ops = {
-	.ndo_open		= ks8851_net_open,
-	.ndo_stop		= ks8851_net_stop,
-	.ndo_do_ioctl		= ks8851_net_ioctl,
-	.ndo_start_xmit		= ks8851_start_xmit,
-	.ndo_set_mac_address	= ks8851_set_mac_address,
-	.ndo_set_rx_mode	= ks8851_set_rx_mode,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-/* ethtool support */
-
-static void ks8851_get_drvinfo(struct net_device *dev,
-			       struct ethtool_drvinfo *di)
-{
-	strlcpy(di->driver, "KS8851", sizeof(di->driver));
-	strlcpy(di->version, "1.00", sizeof(di->version));
-	strlcpy(di->bus_info, dev_name(dev->dev.parent), sizeof(di->bus_info));
-}
-
-static u32 ks8851_get_msglevel(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	return ks->msg_enable;
-}
-
-static void ks8851_set_msglevel(struct net_device *dev, u32 to)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	ks->msg_enable = to;
-}
-
-static int ks8851_get_link_ksettings(struct net_device *dev,
-				     struct ethtool_link_ksettings *cmd)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-
-	mii_ethtool_get_link_ksettings(&ks->mii, cmd);
-
-	return 0;
-}
-
-static int ks8851_set_link_ksettings(struct net_device *dev,
-				     const struct ethtool_link_ksettings *cmd)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	return mii_ethtool_set_link_ksettings(&ks->mii, cmd);
-}
-
-static u32 ks8851_get_link(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	return mii_link_ok(&ks->mii);
-}
-
-static int ks8851_nway_reset(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	return mii_nway_restart(&ks->mii);
-}
-
-/* EEPROM support */
-
-static void ks8851_eeprom_regread(struct eeprom_93cx6 *ee)
-{
-	struct ks8851_net *ks = ee->data;
-	unsigned val;
-
-	val = ks8851_rdreg16(ks, KS_EEPCR);
-
-	ee->reg_data_out = (val & EEPCR_EESB) ? 1 : 0;
-	ee->reg_data_clock = (val & EEPCR_EESCK) ? 1 : 0;
-	ee->reg_chip_select = (val & EEPCR_EECS) ? 1 : 0;
-}
-
-static void ks8851_eeprom_regwrite(struct eeprom_93cx6 *ee)
-{
-	struct ks8851_net *ks = ee->data;
-	unsigned val = EEPCR_EESA;	/* default - eeprom access on */
-
-	if (ee->drive_data)
-		val |= EEPCR_EESRWA;
-	if (ee->reg_data_in)
-		val |= EEPCR_EEDO;
-	if (ee->reg_data_clock)
-		val |= EEPCR_EESCK;
-	if (ee->reg_chip_select)
-		val |= EEPCR_EECS;
-
-	ks8851_wrreg16(ks, KS_EEPCR, val);
-}
-
-/**
- * ks8851_eeprom_claim - claim device EEPROM and activate the interface
- * @ks: The network device state.
- *
- * Check for the presence of an EEPROM, and then activate software access
- * to the device.
- */
-static int ks8851_eeprom_claim(struct ks8851_net *ks)
-{
-	/* start with clock low, cs high */
-	ks8851_wrreg16(ks, KS_EEPCR, EEPCR_EESA | EEPCR_EECS);
-	return 0;
-}
-
-/**
- * ks8851_eeprom_release - release the EEPROM interface
- * @ks: The device state
- *
- * Release the software access to the device EEPROM
- */
-static void ks8851_eeprom_release(struct ks8851_net *ks)
-{
-	unsigned val = ks8851_rdreg16(ks, KS_EEPCR);
-
-	ks8851_wrreg16(ks, KS_EEPCR, val & ~EEPCR_EESA);
-}
-
-#define KS_EEPROM_MAGIC (0x00008851)
-
-static int ks8851_set_eeprom(struct net_device *dev,
-			     struct ethtool_eeprom *ee, u8 *data)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	int offset = ee->offset;
-	unsigned long flags;
-	int len = ee->len;
-	u16 tmp;
-
-	/* currently only support byte writing */
-	if (len != 1)
-		return -EINVAL;
-
-	if (ee->magic != KS_EEPROM_MAGIC)
-		return -EINVAL;
-
-	if (!(ks->rc_ccr & CCR_EEPROM))
-		return -ENOENT;
-
-	ks8851_lock(ks, &flags);
-
-	ks8851_eeprom_claim(ks);
-
-	eeprom_93cx6_wren(&ks->eeprom, true);
-
-	/* ethtool currently only supports writing bytes, which means
-	 * we have to read/modify/write our 16bit EEPROMs */
-
-	eeprom_93cx6_read(&ks->eeprom, offset/2, &tmp);
-
-	if (offset & 1) {
-		tmp &= 0xff;
-		tmp |= *data << 8;
-	} else {
-		tmp &= 0xff00;
-		tmp |= *data;
-	}
-
-	eeprom_93cx6_write(&ks->eeprom, offset/2, tmp);
-	eeprom_93cx6_wren(&ks->eeprom, false);
-
-	ks8851_eeprom_release(ks);
-	ks8851_unlock(ks, &flags);
-
-	return 0;
-}
-
-static int ks8851_get_eeprom(struct net_device *dev,
-			     struct ethtool_eeprom *ee, u8 *data)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	int offset = ee->offset;
-	unsigned long flags;
-	int len = ee->len;
-
-	/* must be 2 byte aligned */
-	if (len & 1 || offset & 1)
-		return -EINVAL;
-
-	if (!(ks->rc_ccr & CCR_EEPROM))
-		return -ENOENT;
-
-	ks8851_lock(ks, &flags);
-
-	ks8851_eeprom_claim(ks);
-
-	ee->magic = KS_EEPROM_MAGIC;
-
-	eeprom_93cx6_multiread(&ks->eeprom, offset/2, (__le16 *)data, len/2);
-	ks8851_eeprom_release(ks);
-	ks8851_unlock(ks, &flags);
-
-	return 0;
-}
-
-static int ks8851_get_eeprom_len(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-
-	/* currently, we assume it is an 93C46 attached, so return 128 */
-	return ks->rc_ccr & CCR_EEPROM ? 128 : 0;
-}
-
-static const struct ethtool_ops ks8851_ethtool_ops = {
-	.get_drvinfo	= ks8851_get_drvinfo,
-	.get_msglevel	= ks8851_get_msglevel,
-	.set_msglevel	= ks8851_set_msglevel,
-	.get_link	= ks8851_get_link,
-	.nway_reset	= ks8851_nway_reset,
-	.get_eeprom_len	= ks8851_get_eeprom_len,
-	.get_eeprom	= ks8851_get_eeprom,
-	.set_eeprom	= ks8851_set_eeprom,
-	.get_link_ksettings = ks8851_get_link_ksettings,
-	.set_link_ksettings = ks8851_set_link_ksettings,
-};
-
-/* MII interface controls */
-
-/**
- * ks8851_phy_reg - convert MII register into a KS8851 register
- * @reg: MII register number.
- *
- * Return the KS8851 register number for the corresponding MII PHY register
- * if possible. Return zero if the MII register has no direct mapping to the
- * KS8851 register set.
- */
-static int ks8851_phy_reg(int reg)
-{
-	switch (reg) {
-	case MII_BMCR:
-		return KS_P1MBCR;
-	case MII_BMSR:
-		return KS_P1MBSR;
-	case MII_PHYSID1:
-		return KS_PHY1ILR;
-	case MII_PHYSID2:
-		return KS_PHY1IHR;
-	case MII_ADVERTISE:
-		return KS_P1ANAR;
-	case MII_LPA:
-		return KS_P1ANLPR;
-	}
-
-	return 0x0;
-}
-
-/**
- * ks8851_phy_read - MII interface PHY register read.
- * @dev: The network device the PHY is on.
- * @phy_addr: Address of PHY (ignored as we only have one)
- * @reg: The register to read.
- *
- * This call reads data from the PHY register specified in @reg. Since the
- * device does not support all the MII registers, the non-existent values
- * are always returned as zero.
- *
- * We return zero for unsupported registers as the MII code does not check
- * the value returned for any error status, and simply returns it to the
- * caller. The mii-tool that the driver was tested with takes any -ve error
- * as real PHY capabilities, thus displaying incorrect data to the user.
- */
-static int ks8851_phy_read(struct net_device *dev, int phy_addr, int reg)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-	int ksreg;
-	int result;
-
-	ksreg = ks8851_phy_reg(reg);
-	if (!ksreg)
-		return 0x0;	/* no error return allowed, so use zero */
-
-	ks8851_lock(ks, &flags);
-	result = ks8851_rdreg16(ks, ksreg);
-	ks8851_unlock(ks, &flags);
-
-	return result;
-}
-
-static void ks8851_phy_write(struct net_device *dev,
-			     int phy, int reg, int value)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	unsigned long flags;
-	int ksreg;
-
-	ksreg = ks8851_phy_reg(reg);
-	if (ksreg) {
-		ks8851_lock(ks, &flags);
-		ks8851_wrreg16(ks, ksreg, value);
-		ks8851_unlock(ks, &flags);
-	}
-}
-
-/**
- * ks8851_read_selftest - read the selftest memory info.
- * @ks: The device state
- *
- * Read and check the TX/RX memory selftest information.
- */
-static int ks8851_read_selftest(struct ks8851_net *ks)
-{
-	unsigned both_done = MBIR_TXMBF | MBIR_RXMBF;
-	int ret = 0;
-	unsigned rd;
-
-	rd = ks8851_rdreg16(ks, KS_MBIR);
-
-	if ((rd & both_done) != both_done) {
-		netdev_warn(ks->netdev, "Memory selftest not finished\n");
-		return 0;
-	}
-
-	if (rd & MBIR_TXMBFA) {
-		netdev_err(ks->netdev, "TX memory selftest fail\n");
-		ret |= 1;
-	}
-
-	if (rd & MBIR_RXMBFA) {
-		netdev_err(ks->netdev, "RX memory selftest fail\n");
-		ret |= 2;
-	}
-
-	return 0;
-}
-
-/* driver bus management functions */
-
-#ifdef CONFIG_PM_SLEEP
-
-static int ks8851_suspend(struct device *dev)
-{
-	struct ks8851_net *ks = dev_get_drvdata(dev);
-	struct net_device *netdev = ks->netdev;
-
-	if (netif_running(netdev)) {
-		netif_device_detach(netdev);
-		ks8851_net_stop(netdev);
-	}
-
-	return 0;
-}
-
-static int ks8851_resume(struct device *dev)
-{
-	struct ks8851_net *ks = dev_get_drvdata(dev);
-	struct net_device *netdev = ks->netdev;
-
-	if (netif_running(netdev)) {
-		ks8851_net_open(netdev);
-		netif_device_attach(netdev);
-	}
-
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(ks8851_pm_ops, ks8851_suspend, ks8851_resume);
-
-static int ks8851_probe_common(struct net_device *netdev, struct device *dev,
-			       int msg_en)
-{
-	struct ks8851_net *ks = netdev_priv(netdev);
-	unsigned cider;
-	int gpio;
-	int ret;
-
-	ks->netdev = netdev;
-	ks->tx_space = 6144;
-
-	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
-	if (gpio == -EPROBE_DEFER)
-		return gpio;
-
-	ks->gpio = gpio;
-	if (gpio_is_valid(gpio)) {
-		ret = devm_gpio_request_one(dev, gpio,
-					    GPIOF_OUT_INIT_LOW, "ks8851_rst_n");
-		if (ret) {
-			dev_err(dev, "reset gpio request failed\n");
-			return ret;
-		}
-	}
-
-	ks->vdd_io = devm_regulator_get(dev, "vdd-io");
-	if (IS_ERR(ks->vdd_io)) {
-		ret = PTR_ERR(ks->vdd_io);
-		goto err_reg_io;
-	}
-
-	ret = regulator_enable(ks->vdd_io);
-	if (ret) {
-		dev_err(dev, "regulator vdd_io enable fail: %d\n", ret);
-		goto err_reg_io;
-	}
-
-	ks->vdd_reg = devm_regulator_get(dev, "vdd");
-	if (IS_ERR(ks->vdd_reg)) {
-		ret = PTR_ERR(ks->vdd_reg);
-		goto err_reg;
-	}
-
-	ret = regulator_enable(ks->vdd_reg);
-	if (ret) {
-		dev_err(dev, "regulator vdd enable fail: %d\n", ret);
-		goto err_reg;
-	}
-
-	if (gpio_is_valid(gpio)) {
-		usleep_range(10000, 11000);
-		gpio_set_value(gpio, 1);
-	}
-
-	spin_lock_init(&ks->statelock);
-
-	INIT_WORK(&ks->rxctrl_work, ks8851_rxctrl_work);
-
-	/* setup EEPROM state */
-	ks->eeprom.data = ks;
-	ks->eeprom.width = PCI_EEPROM_WIDTH_93C46;
-	ks->eeprom.register_read = ks8851_eeprom_regread;
-	ks->eeprom.register_write = ks8851_eeprom_regwrite;
-
-	/* setup mii state */
-	ks->mii.dev		= netdev;
-	ks->mii.phy_id		= 1,
-	ks->mii.phy_id_mask	= 1;
-	ks->mii.reg_num_mask	= 0xf;
-	ks->mii.mdio_read	= ks8851_phy_read;
-	ks->mii.mdio_write	= ks8851_phy_write;
-
-	dev_info(dev, "message enable is %d\n", msg_en);
-
-	/* set the default message enable */
-	ks->msg_enable = netif_msg_init(msg_en, NETIF_MSG_DRV |
-						NETIF_MSG_PROBE |
-						NETIF_MSG_LINK);
-
-	skb_queue_head_init(&ks->txq);
-
-	netdev->ethtool_ops = &ks8851_ethtool_ops;
-	SET_NETDEV_DEV(netdev, dev);
-
-	dev_set_drvdata(dev, ks);
-
-	netif_carrier_off(ks->netdev);
-	netdev->if_port = IF_PORT_100BASET;
-	netdev->netdev_ops = &ks8851_netdev_ops;
-
-	/* issue a global soft reset to reset the device. */
-	ks8851_soft_reset(ks, GRR_GSR);
-
-	/* simple check for a valid chip being connected to the bus */
-	cider = ks8851_rdreg16(ks, KS_CIDER);
-	if ((cider & ~CIDER_REV_MASK) != CIDER_ID) {
-		dev_err(dev, "failed to read device ID\n");
-		ret = -ENODEV;
-		goto err_id;
-	}
-
-	/* cache the contents of the CCR register for EEPROM, etc. */
-	ks->rc_ccr = ks8851_rdreg16(ks, KS_CCR);
-
-	ks8851_read_selftest(ks);
-	ks8851_init_mac(ks, dev->of_node);
-
-	ret = register_netdev(netdev);
-	if (ret) {
-		dev_err(dev, "failed to register network device\n");
-		goto err_netdev;
-	}
-
-	netdev_info(netdev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
-		    CIDER_REV_GET(cider), netdev->dev_addr, netdev->irq,
-		    ks->rc_ccr & CCR_EEPROM ? "has" : "no");
-
-	return 0;
-
-err_netdev:
-err_id:
-	if (gpio_is_valid(gpio))
-		gpio_set_value(gpio, 0);
-	regulator_disable(ks->vdd_reg);
-err_reg:
-	regulator_disable(ks->vdd_io);
-err_reg_io:
-	return ret;
-}
-
-static int ks8851_remove_common(struct device *dev)
-{
-	struct ks8851_net *priv = dev_get_drvdata(dev);
-
-	if (netif_msg_drv(priv))
-		dev_info(dev, "remove\n");
-
-	unregister_netdev(priv->netdev);
-	if (gpio_is_valid(priv->gpio))
-		gpio_set_value(priv->gpio, 0);
-	regulator_disable(priv->vdd_reg);
-	regulator_disable(priv->vdd_io);
-
-	return 0;
-}
-
-static int ks8851_probe(struct spi_device *spi)
-{
-	struct device *dev = &spi->dev;
-	struct ks8851_net_spi *kss;
-	struct net_device *netdev;
-	struct ks8851_net *ks;
-
-	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_spi));
-	if (!netdev)
-		return -ENOMEM;
-
-	spi->bits_per_word = 8;
-
-	ks = netdev_priv(netdev);
-
-	ks->lock = ks8851_lock_spi;
-	ks->unlock = ks8851_unlock_spi;
-	ks->rdreg16 = ks8851_rdreg16_spi;
-	ks->wrreg16 = ks8851_wrreg16_spi;
-	ks->rdfifo = ks8851_rdfifo_spi;
-	ks->wrfifo = ks8851_wrpkt_spi;
-	ks->start_xmit = ks8851_start_xmit_spi;
-	ks->rx_skb = ks8851_rx_skb_spi;
-	ks->flush_tx_work = ks8851_flush_tx_work_spi;
-
-#define STD_IRQ (IRQ_LCI |	/* Link Change */	\
-		 IRQ_TXI |	/* TX done */		\
-		 IRQ_RXI |	/* RX done */		\
-		 IRQ_SPIBEI |	/* SPI bus error */	\
-		 IRQ_TXPSI |	/* TX process stop */	\
-		 IRQ_RXPSI)	/* RX process stop */
-	ks->rc_ier = STD_IRQ;
-
-	kss = to_ks8851_spi(ks);
-
-	kss->spidev = spi;
-	mutex_init(&kss->lock);
-	INIT_WORK(&kss->tx_work, ks8851_tx_work);
-
-	/* initialise pre-made spi transfer messages */
-	spi_message_init(&kss->spi_msg1);
-	spi_message_add_tail(&kss->spi_xfer1, &kss->spi_msg1);
-
-	spi_message_init(&kss->spi_msg2);
-	spi_message_add_tail(&kss->spi_xfer2[0], &kss->spi_msg2);
-	spi_message_add_tail(&kss->spi_xfer2[1], &kss->spi_msg2);
-
-	netdev->irq = spi->irq;
-
-	return ks8851_probe_common(netdev, dev, msg_enable);
-}
-
-static int ks8851_remove(struct spi_device *spi)
-{
-	return ks8851_remove_common(&spi->dev);
-}
-
-static const struct of_device_id ks8851_match_table[] = {
-	{ .compatible = "micrel,ks8851" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, ks8851_match_table);
-
-static struct spi_driver ks8851_driver = {
-	.driver = {
-		.name = "ks8851",
-		.of_match_table = ks8851_match_table,
-		.pm = &ks8851_pm_ops,
-	},
-	.probe = ks8851_probe,
-	.remove = ks8851_remove,
-};
-module_spi_driver(ks8851_driver);
-
-MODULE_DESCRIPTION("KS8851 Network driver");
-MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
-MODULE_LICENSE("GPL");
-
-module_param_named(message, msg_enable, int, 0);
-MODULE_PARM_DESC(message, "Message verbosity level (0=none, 31=all)");
-MODULE_ALIAS("spi:ks8851");
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index f210d18a10b5..2b319e451121 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -7,6 +7,11 @@
  * KS8851 register definitions
 */
 
+#ifndef __KS8851_H__
+#define __KS8851_H__
+
+#include <linux/eeprom_93cx6.h>
+
 #define KS_CCR					0x08
 #define CCR_LE					(1 << 10)   /* KSZ8851-16MLL */
 #define CCR_EEPROM				(1 << 9)
@@ -300,3 +305,147 @@
 #define TXFR_TXIC				(1 << 15)
 #define TXFR_TXFID_MASK				(0x3f << 0)
 #define TXFR_TXFID_SHIFT			(0)
+
+/**
+ * struct ks8851_rxctrl - KS8851 driver rx control
+ * @mchash: Multicast hash-table data.
+ * @rxcr1: KS_RXCR1 register setting
+ * @rxcr2: KS_RXCR2 register setting
+ *
+ * Representation of the settings needs to control the receive filtering
+ * such as the multicast hash-filter and the receive register settings. This
+ * is used to make the job of working out if the receive settings change and
+ * then issuing the new settings to the worker that will send the necessary
+ * commands.
+ */
+struct ks8851_rxctrl {
+	u16	mchash[4];
+	u16	rxcr1;
+	u16	rxcr2;
+};
+
+/**
+ * union ks8851_tx_hdr - tx header data
+ * @txb: The header as bytes
+ * @txw: The header as 16bit, little-endian words
+ *
+ * A dual representation of the tx header data to allow
+ * access to individual bytes, and to allow 16bit accesses
+ * with 16bit alignment.
+ */
+union ks8851_tx_hdr {
+	u8	txb[6];
+	__le16	txw[3];
+};
+
+/**
+ * struct ks8851_net - KS8851 driver private data
+ * @netdev: The network device we're bound to
+ * @statelock: Lock on this structure for tx list.
+ * @mii: The MII state information for the mii calls.
+ * @rxctrl: RX settings for @rxctrl_work.
+ * @rxctrl_work: Work queue for updating RX mode and multicast lists
+ * @txq: Queue of packets for transmission.
+ * @txh: Space for generating packet TX header in DMA-able data
+ * @rxd: Space for receiving SPI data, in DMA-able space.
+ * @txd: Space for transmitting SPI data, in DMA-able space.
+ * @msg_enable: The message flags controlling driver output (see ethtool).
+ * @fid: Incrementing frame id tag.
+ * @rc_ier: Cached copy of KS_IER.
+ * @rc_ccr: Cached copy of KS_CCR.
+ * @rc_rxqcr: Cached copy of KS_RXQCR.
+ * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
+ * @vdd_reg:	Optional regulator supplying the chip
+ * @vdd_io: Optional digital power supply for IO
+ * @gpio: Optional reset_n gpio
+ * @lock: Bus access lock callback
+ * @unlock: Bus access unlock callback
+ * @rdreg16: 16bit register read callback
+ * @wrreg16: 16bit register write callback
+ * @rdfifo: FIFO read callback
+ * @wrfifo: FIFO write callback
+ * @start_xmit: start_xmit() implementation callback
+ * @rx_skb: rx_skb() implementation callback
+ * @flush_tx_work: flush_tx_work() implementation callback
+ *
+ * The @statelock is used to protect information in the structure which may
+ * need to be accessed via several sources, such as the network driver layer
+ * or one of the work queues.
+ *
+ * We align the buffers we may use for rx/tx to ensure that if the SPI driver
+ * wants to DMA map them, it will not have any problems with data the driver
+ * modifies.
+ */
+struct ks8851_net {
+	struct net_device	*netdev;
+	spinlock_t		statelock;
+
+	union ks8851_tx_hdr	txh ____cacheline_aligned;
+	u8			rxd[8];
+	u8			txd[8];
+
+	u32			msg_enable ____cacheline_aligned;
+	u16			tx_space;
+	u8			fid;
+
+	u16			rc_ier;
+	u16			rc_rxqcr;
+	u16			rc_ccr;
+
+	struct mii_if_info	mii;
+	struct ks8851_rxctrl	rxctrl;
+
+	struct work_struct	rxctrl_work;
+
+	struct sk_buff_head	txq;
+
+	struct eeprom_93cx6	eeprom;
+	struct regulator	*vdd_reg;
+	struct regulator	*vdd_io;
+	int			gpio;
+
+	void			(*lock)(struct ks8851_net *ks,
+					unsigned long *flags);
+	void			(*unlock)(struct ks8851_net *ks,
+					  unsigned long *flags);
+	unsigned int		(*rdreg16)(struct ks8851_net *ks,
+					   unsigned int reg);
+	void			(*wrreg16)(struct ks8851_net *ks,
+					   unsigned int reg, unsigned int val);
+	void			(*rdfifo)(struct ks8851_net *ks, u8 *buff,
+					  unsigned int len);
+	void			(*wrfifo)(struct ks8851_net *ks,
+					  struct sk_buff *txp, bool irq);
+	netdev_tx_t		(*start_xmit)(struct sk_buff *skb,
+					      struct net_device *dev);
+	void			(*rx_skb)(struct ks8851_net *ks,
+					  struct sk_buff *skb);
+	void			(*flush_tx_work)(struct ks8851_net *ks);
+};
+
+int ks8851_probe_common(struct net_device *netdev, struct device *dev,
+			int msg_en);
+int ks8851_remove_common(struct device *dev);
+int ks8851_suspend(struct device *dev);
+int ks8851_resume(struct device *dev);
+
+static __maybe_unused SIMPLE_DEV_PM_OPS(ks8851_pm_ops,
+					ks8851_suspend, ks8851_resume);
+
+/**
+ * ks8851_done_tx - update and then free skbuff after transmitting
+ * @ks: The device state
+ * @txb: The buffer transmitted
+ */
+static void __maybe_unused ks8851_done_tx(struct ks8851_net *ks,
+					  struct sk_buff *txb)
+{
+	struct net_device *dev = ks->netdev;
+
+	dev->stats.tx_bytes += txb->len;
+	dev->stats.tx_packets++;
+
+	dev_kfree_skb(txb);
+}
+
+#endif /* __KS8851_H__ */
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
new file mode 100644
index 000000000000..d65872172229
--- /dev/null
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -0,0 +1,1193 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* drivers/net/ethernet/micrel/ks8851.c
+ *
+ * Copyright 2009 Simtec Electronics
+ *	http://www.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define DEBUG
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/cache.h>
+#include <linux/crc32.h>
+#include <linux/mii.h>
+#include <linux/regulator/consumer.h>
+
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_net.h>
+
+#include "ks8851.h"
+
+/**
+ * ks8851_lock - register access lock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Claim chip register access lock
+ */
+static void ks8851_lock(struct ks8851_net *ks, unsigned long *flags)
+{
+	ks->lock(ks, flags);
+}
+
+/**
+ * ks8851_unlock - register access unlock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Release chip register access lock
+ */
+static void ks8851_unlock(struct ks8851_net *ks, unsigned long *flags)
+{
+	ks->unlock(ks, flags);
+}
+
+/**
+ * ks8851_wrreg16 - write 16bit register value to chip
+ * @ks: The chip state
+ * @reg: The register address
+ * @val: The value to write
+ *
+ * Issue a write to put the value @val into the register specified in @reg.
+ */
+static void ks8851_wrreg16(struct ks8851_net *ks, unsigned int reg,
+			   unsigned int val)
+{
+	ks->wrreg16(ks, reg, val);
+}
+
+/**
+ * ks8851_rdreg16 - read 16 bit register from device
+ * @ks: The chip information
+ * @reg: The register address
+ *
+ * Read a 16bit register from the chip, returning the result
+ */
+static unsigned int ks8851_rdreg16(struct ks8851_net *ks,
+				   unsigned int reg)
+{
+	return ks->rdreg16(ks, reg);
+}
+
+/**
+ * ks8851_soft_reset - issue one of the soft reset to the device
+ * @ks: The device state.
+ * @op: The bit(s) to set in the GRR
+ *
+ * Issue the relevant soft-reset command to the device's GRR register
+ * specified by @op.
+ *
+ * Note, the delays are in there as a caution to ensure that the reset
+ * has time to take effect and then complete. Since the datasheet does
+ * not currently specify the exact sequence, we have chosen something
+ * that seems to work with our device.
+ */
+static void ks8851_soft_reset(struct ks8851_net *ks, unsigned op)
+{
+	ks8851_wrreg16(ks, KS_GRR, op);
+	mdelay(1);	/* wait a short time to effect reset */
+	ks8851_wrreg16(ks, KS_GRR, 0);
+	mdelay(1);	/* wait for condition to clear */
+}
+
+/**
+ * ks8851_set_powermode - set power mode of the device
+ * @ks: The device state
+ * @pwrmode: The power mode value to write to KS_PMECR.
+ *
+ * Change the power mode of the chip.
+ */
+static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
+{
+	unsigned pmecr;
+
+	netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
+
+	pmecr = ks8851_rdreg16(ks, KS_PMECR);
+	pmecr &= ~PMECR_PM_MASK;
+	pmecr |= pwrmode;
+
+	ks8851_wrreg16(ks, KS_PMECR, pmecr);
+}
+
+/**
+ * ks8851_write_mac_addr - write mac address to device registers
+ * @dev: The network device
+ *
+ * Update the KS8851 MAC address registers from the address in @dev.
+ *
+ * This call assumes that the chip is not running, so there is no need to
+ * shutdown the RXQ process whilst setting this.
+*/
+static int ks8851_write_mac_addr(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+	u16 val;
+	int i;
+
+	ks8851_lock(ks, &flags);
+
+	/*
+	 * Wake up chip in case it was powered off when stopped; otherwise,
+	 * the first write to the MAC address does not take effect.
+	 */
+	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
+
+	for (i = 0; i < ETH_ALEN; i += 2) {
+		val = (dev->dev_addr[i] << 8) | dev->dev_addr[i + 1];
+		ks8851_wrreg16(ks, KS_MAR(i), val);
+	}
+
+	if (!netif_running(dev))
+		ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
+
+	ks8851_unlock(ks, &flags);
+
+	return 0;
+}
+
+/**
+ * ks8851_read_mac_addr - read mac address from device registers
+ * @dev: The network device
+ *
+ * Update our copy of the KS8851 MAC address from the registers of @dev.
+*/
+static void ks8851_read_mac_addr(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+	u16 reg;
+	int i;
+
+	ks8851_lock(ks, &flags);
+
+	for (i = 0; i < ETH_ALEN; i += 2) {
+		reg = ks8851_rdreg16(ks, KS_MAR(i));
+		dev->dev_addr[i] = reg >> 8;
+		dev->dev_addr[i + 1] = reg & 0xff;
+	}
+
+	ks8851_unlock(ks, &flags);
+}
+
+/**
+ * ks8851_init_mac - initialise the mac address
+ * @ks: The device structure
+ * @np: The device node pointer
+ *
+ * Get or create the initial mac address for the device and then set that
+ * into the station address register. A mac address supplied in the device
+ * tree takes precedence. Otherwise, if there is an EEPROM present, then
+ * we try that. If no valid mac address is found we use eth_random_addr()
+ * to create a new one.
+ */
+static void ks8851_init_mac(struct ks8851_net *ks, struct device_node *np)
+{
+	struct net_device *dev = ks->netdev;
+	const u8 *mac_addr;
+
+	mac_addr = of_get_mac_address(np);
+	if (!IS_ERR(mac_addr)) {
+		ether_addr_copy(dev->dev_addr, mac_addr);
+		ks8851_write_mac_addr(dev);
+		return;
+	}
+
+	if (ks->rc_ccr & CCR_EEPROM) {
+		ks8851_read_mac_addr(dev);
+		if (is_valid_ether_addr(dev->dev_addr))
+			return;
+
+		netdev_err(ks->netdev, "invalid mac address read %pM\n",
+				dev->dev_addr);
+	}
+
+	eth_hw_addr_random(dev);
+	ks8851_write_mac_addr(dev);
+}
+
+/**
+ * ks8851_dbg_dumpkkt - dump initial packet contents to debug
+ * @ks: The device state
+ * @rxpkt: The data for the received packet
+ *
+ * Dump the initial data from the packet to dev_dbg().
+ */
+static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
+{
+	netdev_dbg(ks->netdev,
+		   "pkt %02x%02x%02x%02x %02x%02x%02x%02x %02x%02x%02x%02x\n",
+		   rxpkt[4], rxpkt[5], rxpkt[6], rxpkt[7],
+		   rxpkt[8], rxpkt[9], rxpkt[10], rxpkt[11],
+		   rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]);
+}
+
+/**
+ * ks8851_rx_skb - receive skbuff
+ * @ks: The device state.
+ * @skb: The skbuff
+ */
+static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb)
+{
+	ks->rx_skb(ks, skb);
+}
+
+/**
+ * ks8851_rx_pkts - receive packets from the host
+ * @ks: The device information.
+ *
+ * This is called from the IRQ work queue when the system detects that there
+ * are packets in the receive queue. Find out how many packets there are and
+ * read them from the FIFO.
+ */
+static void ks8851_rx_pkts(struct ks8851_net *ks)
+{
+	struct sk_buff *skb;
+	unsigned rxfc;
+	unsigned rxlen;
+	unsigned rxstat;
+	u8 *rxpkt;
+
+	rxfc = (ks8851_rdreg16(ks, KS_RXFCTR) >> 8) & 0xff;
+
+	netif_dbg(ks, rx_status, ks->netdev,
+		  "%s: %d packets\n", __func__, rxfc);
+
+	/* Currently we're issuing a read per packet, but we could possibly
+	 * improve the code by issuing a single read, getting the receive
+	 * header, allocating the packet and then reading the packet data
+	 * out in one go.
+	 *
+	 * This form of operation would require us to hold the SPI bus'
+	 * chipselect low during the entie transaction to avoid any
+	 * reset to the data stream coming from the chip.
+	 */
+
+	for (; rxfc != 0; rxfc--) {
+		rxstat = ks8851_rdreg16(ks, KS_RXFHSR);
+		rxlen = ks8851_rdreg16(ks, KS_RXFHBCR) & RXFHBCR_CNT_MASK;
+
+		netif_dbg(ks, rx_status, ks->netdev,
+			  "rx: stat 0x%04x, len 0x%04x\n", rxstat, rxlen);
+
+		/* the length of the packet includes the 32bit CRC */
+
+		/* set dma read address */
+		ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00);
+
+		/* start DMA access */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
+
+		if (rxlen > 4) {
+			unsigned int rxalign;
+
+			rxlen -= 4;
+			rxalign = ALIGN(rxlen, 4);
+			skb = netdev_alloc_skb_ip_align(ks->netdev, rxalign);
+			if (skb) {
+
+				/* 4 bytes of status header + 4 bytes of
+				 * garbage: we put them before ethernet
+				 * header, so that they are copied,
+				 * but ignored.
+				 */
+
+				rxpkt = skb_put(skb, rxlen) - 8;
+
+				ks->rdfifo(ks, rxpkt, rxalign + 8);
+
+				if (netif_msg_pktdata(ks))
+					ks8851_dbg_dumpkkt(ks, rxpkt);
+
+				skb->protocol = eth_type_trans(skb, ks->netdev);
+				ks8851_rx_skb(ks, skb);
+
+				ks->netdev->stats.rx_packets++;
+				ks->netdev->stats.rx_bytes += rxlen;
+			}
+		}
+
+		/* end DMA access and dequeue packet */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF);
+	}
+}
+
+/**
+ * ks8851_irq - IRQ handler for dealing with interrupt requests
+ * @irq: IRQ number
+ * @_ks: cookie
+ *
+ * This handler is invoked when the IRQ line asserts to find out what happened.
+ * As we cannot allow ourselves to sleep in HARDIRQ context, this handler runs
+ * in thread context.
+ *
+ * Read the interrupt status, work out what needs to be done and then clear
+ * any of the interrupts that are not needed.
+ */
+static irqreturn_t ks8851_irq(int irq, void *_ks)
+{
+	struct ks8851_net *ks = _ks;
+	unsigned handled = 0;
+	unsigned long flags;
+	unsigned int status;
+
+	ks8851_lock(ks, &flags);
+
+	status = ks8851_rdreg16(ks, KS_ISR);
+
+	netif_dbg(ks, intr, ks->netdev,
+		  "%s: status 0x%04x\n", __func__, status);
+
+	if (status & IRQ_LCI)
+		handled |= IRQ_LCI;
+
+	if (status & IRQ_LDI) {
+		u16 pmecr = ks8851_rdreg16(ks, KS_PMECR);
+		pmecr &= ~PMECR_WKEVT_MASK;
+		ks8851_wrreg16(ks, KS_PMECR, pmecr | PMECR_WKEVT_LINK);
+
+		handled |= IRQ_LDI;
+	}
+
+	if (status & IRQ_RXPSI)
+		handled |= IRQ_RXPSI;
+
+	if (status & IRQ_TXI) {
+		handled |= IRQ_TXI;
+
+		/* no lock here, tx queue should have been stopped */
+
+		/* update our idea of how much tx space is available to the
+		 * system */
+		ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
+
+		netif_dbg(ks, intr, ks->netdev,
+			  "%s: txspace %d\n", __func__, ks->tx_space);
+	}
+
+	if (status & IRQ_RXI)
+		handled |= IRQ_RXI;
+
+	if (status & IRQ_SPIBEI) {
+		netdev_err(ks->netdev, "%s: spi bus error\n", __func__);
+		handled |= IRQ_SPIBEI;
+	}
+
+	ks8851_wrreg16(ks, KS_ISR, handled);
+
+	if (status & IRQ_RXI) {
+		/* the datasheet says to disable the rx interrupt during
+		 * packet read-out, however we're masking the interrupt
+		 * from the device so do not bother masking just the RX
+		 * from the device. */
+
+		ks8851_rx_pkts(ks);
+	}
+
+	/* if something stopped the rx process, probably due to wanting
+	 * to change the rx settings, then do something about restarting
+	 * it. */
+	if (status & IRQ_RXPSI) {
+		struct ks8851_rxctrl *rxc = &ks->rxctrl;
+
+		/* update the multicast hash table */
+		ks8851_wrreg16(ks, KS_MAHTR0, rxc->mchash[0]);
+		ks8851_wrreg16(ks, KS_MAHTR1, rxc->mchash[1]);
+		ks8851_wrreg16(ks, KS_MAHTR2, rxc->mchash[2]);
+		ks8851_wrreg16(ks, KS_MAHTR3, rxc->mchash[3]);
+
+		ks8851_wrreg16(ks, KS_RXCR2, rxc->rxcr2);
+		ks8851_wrreg16(ks, KS_RXCR1, rxc->rxcr1);
+	}
+
+	ks8851_unlock(ks, &flags);
+
+	if (status & IRQ_LCI)
+		mii_check_link(&ks->mii);
+
+	if (status & IRQ_TXI)
+		netif_wake_queue(ks->netdev);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ks8851_flush_tx_work - flush outstanding TX work
+ * @ks: The device state
+ */
+static void ks8851_flush_tx_work(struct ks8851_net *ks)
+{
+	if (ks->flush_tx_work)
+		ks->flush_tx_work(ks);
+}
+
+/**
+ * ks8851_net_open - open network device
+ * @dev: The network device being opened.
+ *
+ * Called when the network device is marked active, such as a user executing
+ * 'ifconfig up' on the device.
+ */
+static int ks8851_net_open(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+	int ret;
+
+	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
+				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				   dev->name, ks);
+	if (ret < 0) {
+		netdev_err(dev, "failed to get irq\n");
+		return ret;
+	}
+
+	/* lock the card, even if we may not actually be doing anything
+	 * else at the moment */
+	ks8851_lock(ks, &flags);
+
+	netif_dbg(ks, ifup, ks->netdev, "opening\n");
+
+	/* bring chip out of any power saving mode it was in */
+	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
+
+	/* issue a soft reset to the RX/TX QMU to put it into a known
+	 * state. */
+	ks8851_soft_reset(ks, GRR_QMU);
+
+	/* setup transmission parameters */
+
+	ks8851_wrreg16(ks, KS_TXCR, (TXCR_TXE | /* enable transmit process */
+				     TXCR_TXPE | /* pad to min length */
+				     TXCR_TXCRC | /* add CRC */
+				     TXCR_TXFCE)); /* enable flow control */
+
+	/* auto-increment tx data, reset tx pointer */
+	ks8851_wrreg16(ks, KS_TXFDPR, TXFDPR_TXFPAI);
+
+	/* setup receiver control */
+
+	ks8851_wrreg16(ks, KS_RXCR1, (RXCR1_RXPAFMA | /*  from mac filter */
+				      RXCR1_RXFCE | /* enable flow control */
+				      RXCR1_RXBE | /* broadcast enable */
+				      RXCR1_RXUE | /* unicast enable */
+				      RXCR1_RXE)); /* enable rx block */
+
+	/* transfer entire frames out in one go */
+	ks8851_wrreg16(ks, KS_RXCR2, RXCR2_SRDBL_FRAME);
+
+	/* set receive counter timeouts */
+	ks8851_wrreg16(ks, KS_RXDTTR, 1000); /* 1ms after first frame to IRQ */
+	ks8851_wrreg16(ks, KS_RXDBCTR, 4096); /* >4Kbytes in buffer to IRQ */
+	ks8851_wrreg16(ks, KS_RXFCTR, 10);  /* 10 frames to IRQ */
+
+	ks->rc_rxqcr = (RXQCR_RXFCTE |  /* IRQ on frame count exceeded */
+			RXQCR_RXDBCTE | /* IRQ on byte count exceeded */
+			RXQCR_RXDTTE);  /* IRQ on time exceeded */
+
+	ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
+
+	/* clear then enable interrupts */
+	ks8851_wrreg16(ks, KS_ISR, ks->rc_ier);
+	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
+
+	netif_start_queue(ks->netdev);
+
+	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
+
+	ks8851_unlock(ks, &flags);
+	mii_check_link(&ks->mii);
+	return 0;
+}
+
+/**
+ * ks8851_net_stop - close network device
+ * @dev: The device being closed.
+ *
+ * Called to close down a network device which has been active. Cancell any
+ * work, shutdown the RX and TX process and then place the chip into a low
+ * power state whilst it is not being used.
+ */
+static int ks8851_net_stop(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+
+	netif_info(ks, ifdown, dev, "shutting down\n");
+
+	netif_stop_queue(dev);
+
+	ks8851_lock(ks, &flags);
+	/* turn off the IRQs and ack any outstanding */
+	ks8851_wrreg16(ks, KS_IER, 0x0000);
+	ks8851_wrreg16(ks, KS_ISR, 0xffff);
+	ks8851_unlock(ks, &flags);
+
+	/* stop any outstanding work */
+	ks8851_flush_tx_work(ks);
+	flush_work(&ks->rxctrl_work);
+
+	ks8851_lock(ks, &flags);
+	/* shutdown RX process */
+	ks8851_wrreg16(ks, KS_RXCR1, 0x0000);
+
+	/* shutdown TX process */
+	ks8851_wrreg16(ks, KS_TXCR, 0x0000);
+
+	/* set powermode to soft power down to save power */
+	ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
+	ks8851_unlock(ks, &flags);
+
+	/* ensure any queued tx buffers are dumped */
+	while (!skb_queue_empty(&ks->txq)) {
+		struct sk_buff *txb = skb_dequeue(&ks->txq);
+
+		netif_dbg(ks, ifdown, ks->netdev,
+			  "%s: freeing txb %p\n", __func__, txb);
+
+		dev_kfree_skb(txb);
+	}
+
+	free_irq(dev->irq, ks);
+
+	return 0;
+}
+
+/**
+ * ks8851_start_xmit - transmit packet
+ * @skb: The buffer to transmit
+ * @dev: The device used to transmit the packet.
+ *
+ * Called by the network layer to transmit the @skb. Queue the packet for
+ * the device and schedule the necessary work to transmit the packet when
+ * it is free.
+ *
+ * We do this to firstly avoid sleeping with the network device locked,
+ * and secondly so we can round up more than one packet to transmit which
+ * means we can try and avoid generating too many transmit done interrupts.
+ */
+static netdev_tx_t ks8851_start_xmit(struct sk_buff *skb,
+				     struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	return ks->start_xmit(skb, dev);
+}
+
+/**
+ * ks8851_rxctrl_work - work handler to change rx mode
+ * @work: The work structure this belongs to.
+ *
+ * Lock the device and issue the necessary changes to the receive mode from
+ * the network device layer. This is done so that we can do this without
+ * having to sleep whilst holding the network device lock.
+ *
+ * Since the recommendation from Micrel is that the RXQ is shutdown whilst the
+ * receive parameters are programmed, we issue a write to disable the RXQ and
+ * then wait for the interrupt handler to be triggered once the RXQ shutdown is
+ * complete. The interrupt handler then writes the new values into the chip.
+ */
+static void ks8851_rxctrl_work(struct work_struct *work)
+{
+	struct ks8851_net *ks = container_of(work, struct ks8851_net, rxctrl_work);
+	unsigned long flags;
+
+	ks8851_lock(ks, &flags);
+
+	/* need to shutdown RXQ before modifying filter parameters */
+	ks8851_wrreg16(ks, KS_RXCR1, 0x00);
+
+	ks8851_unlock(ks, &flags);
+}
+
+static void ks8851_set_rx_mode(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	struct ks8851_rxctrl rxctrl;
+
+	memset(&rxctrl, 0, sizeof(rxctrl));
+
+	if (dev->flags & IFF_PROMISC) {
+		/* interface to receive everything */
+
+		rxctrl.rxcr1 = RXCR1_RXAE | RXCR1_RXINVF;
+	} else if (dev->flags & IFF_ALLMULTI) {
+		/* accept all multicast packets */
+
+		rxctrl.rxcr1 = (RXCR1_RXME | RXCR1_RXAE |
+				RXCR1_RXPAFMA | RXCR1_RXMAFMA);
+	} else if (dev->flags & IFF_MULTICAST && !netdev_mc_empty(dev)) {
+		struct netdev_hw_addr *ha;
+		u32 crc;
+
+		/* accept some multicast */
+
+		netdev_for_each_mc_addr(ha, dev) {
+			crc = ether_crc(ETH_ALEN, ha->addr);
+			crc >>= (32 - 6);  /* get top six bits */
+
+			rxctrl.mchash[crc >> 4] |= (1 << (crc & 0xf));
+		}
+
+		rxctrl.rxcr1 = RXCR1_RXME | RXCR1_RXPAFMA;
+	} else {
+		/* just accept broadcast / unicast */
+		rxctrl.rxcr1 = RXCR1_RXPAFMA;
+	}
+
+	rxctrl.rxcr1 |= (RXCR1_RXUE | /* unicast enable */
+			 RXCR1_RXBE | /* broadcast enable */
+			 RXCR1_RXE | /* RX process enable */
+			 RXCR1_RXFCE); /* enable flow control */
+
+	rxctrl.rxcr2 |= RXCR2_SRDBL_FRAME;
+
+	/* schedule work to do the actual set of the data if needed */
+
+	spin_lock(&ks->statelock);
+
+	if (memcmp(&rxctrl, &ks->rxctrl, sizeof(rxctrl)) != 0) {
+		memcpy(&ks->rxctrl, &rxctrl, sizeof(ks->rxctrl));
+		schedule_work(&ks->rxctrl_work);
+	}
+
+	spin_unlock(&ks->statelock);
+}
+
+static int ks8851_set_mac_address(struct net_device *dev, void *addr)
+{
+	struct sockaddr *sa = addr;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	if (!is_valid_ether_addr(sa->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(dev->dev_addr, sa->sa_data, ETH_ALEN);
+	return ks8851_write_mac_addr(dev);
+}
+
+static int ks8851_net_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	return generic_mii_ioctl(&ks->mii, if_mii(req), cmd, NULL);
+}
+
+static const struct net_device_ops ks8851_netdev_ops = {
+	.ndo_open		= ks8851_net_open,
+	.ndo_stop		= ks8851_net_stop,
+	.ndo_do_ioctl		= ks8851_net_ioctl,
+	.ndo_start_xmit		= ks8851_start_xmit,
+	.ndo_set_mac_address	= ks8851_set_mac_address,
+	.ndo_set_rx_mode	= ks8851_set_rx_mode,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+/* ethtool support */
+
+static void ks8851_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *di)
+{
+	strlcpy(di->driver, "KS8851", sizeof(di->driver));
+	strlcpy(di->version, "1.00", sizeof(di->version));
+	strlcpy(di->bus_info, dev_name(dev->dev.parent), sizeof(di->bus_info));
+}
+
+static u32 ks8851_get_msglevel(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	return ks->msg_enable;
+}
+
+static void ks8851_set_msglevel(struct net_device *dev, u32 to)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	ks->msg_enable = to;
+}
+
+static int ks8851_get_link_ksettings(struct net_device *dev,
+				     struct ethtool_link_ksettings *cmd)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	mii_ethtool_get_link_ksettings(&ks->mii, cmd);
+
+	return 0;
+}
+
+static int ks8851_set_link_ksettings(struct net_device *dev,
+				     const struct ethtool_link_ksettings *cmd)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	return mii_ethtool_set_link_ksettings(&ks->mii, cmd);
+}
+
+static u32 ks8851_get_link(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	return mii_link_ok(&ks->mii);
+}
+
+static int ks8851_nway_reset(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	return mii_nway_restart(&ks->mii);
+}
+
+/* EEPROM support */
+
+static void ks8851_eeprom_regread(struct eeprom_93cx6 *ee)
+{
+	struct ks8851_net *ks = ee->data;
+	unsigned val;
+
+	val = ks8851_rdreg16(ks, KS_EEPCR);
+
+	ee->reg_data_out = (val & EEPCR_EESB) ? 1 : 0;
+	ee->reg_data_clock = (val & EEPCR_EESCK) ? 1 : 0;
+	ee->reg_chip_select = (val & EEPCR_EECS) ? 1 : 0;
+}
+
+static void ks8851_eeprom_regwrite(struct eeprom_93cx6 *ee)
+{
+	struct ks8851_net *ks = ee->data;
+	unsigned val = EEPCR_EESA;	/* default - eeprom access on */
+
+	if (ee->drive_data)
+		val |= EEPCR_EESRWA;
+	if (ee->reg_data_in)
+		val |= EEPCR_EEDO;
+	if (ee->reg_data_clock)
+		val |= EEPCR_EESCK;
+	if (ee->reg_chip_select)
+		val |= EEPCR_EECS;
+
+	ks8851_wrreg16(ks, KS_EEPCR, val);
+}
+
+/**
+ * ks8851_eeprom_claim - claim device EEPROM and activate the interface
+ * @ks: The network device state.
+ *
+ * Check for the presence of an EEPROM, and then activate software access
+ * to the device.
+ */
+static int ks8851_eeprom_claim(struct ks8851_net *ks)
+{
+	/* start with clock low, cs high */
+	ks8851_wrreg16(ks, KS_EEPCR, EEPCR_EESA | EEPCR_EECS);
+	return 0;
+}
+
+/**
+ * ks8851_eeprom_release - release the EEPROM interface
+ * @ks: The device state
+ *
+ * Release the software access to the device EEPROM
+ */
+static void ks8851_eeprom_release(struct ks8851_net *ks)
+{
+	unsigned val = ks8851_rdreg16(ks, KS_EEPCR);
+
+	ks8851_wrreg16(ks, KS_EEPCR, val & ~EEPCR_EESA);
+}
+
+#define KS_EEPROM_MAGIC (0x00008851)
+
+static int ks8851_set_eeprom(struct net_device *dev,
+			     struct ethtool_eeprom *ee, u8 *data)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	int offset = ee->offset;
+	unsigned long flags;
+	int len = ee->len;
+	u16 tmp;
+
+	/* currently only support byte writing */
+	if (len != 1)
+		return -EINVAL;
+
+	if (ee->magic != KS_EEPROM_MAGIC)
+		return -EINVAL;
+
+	if (!(ks->rc_ccr & CCR_EEPROM))
+		return -ENOENT;
+
+	ks8851_lock(ks, &flags);
+
+	ks8851_eeprom_claim(ks);
+
+	eeprom_93cx6_wren(&ks->eeprom, true);
+
+	/* ethtool currently only supports writing bytes, which means
+	 * we have to read/modify/write our 16bit EEPROMs */
+
+	eeprom_93cx6_read(&ks->eeprom, offset/2, &tmp);
+
+	if (offset & 1) {
+		tmp &= 0xff;
+		tmp |= *data << 8;
+	} else {
+		tmp &= 0xff00;
+		tmp |= *data;
+	}
+
+	eeprom_93cx6_write(&ks->eeprom, offset/2, tmp);
+	eeprom_93cx6_wren(&ks->eeprom, false);
+
+	ks8851_eeprom_release(ks);
+	ks8851_unlock(ks, &flags);
+
+	return 0;
+}
+
+static int ks8851_get_eeprom(struct net_device *dev,
+			     struct ethtool_eeprom *ee, u8 *data)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	int offset = ee->offset;
+	unsigned long flags;
+	int len = ee->len;
+
+	/* must be 2 byte aligned */
+	if (len & 1 || offset & 1)
+		return -EINVAL;
+
+	if (!(ks->rc_ccr & CCR_EEPROM))
+		return -ENOENT;
+
+	ks8851_lock(ks, &flags);
+
+	ks8851_eeprom_claim(ks);
+
+	ee->magic = KS_EEPROM_MAGIC;
+
+	eeprom_93cx6_multiread(&ks->eeprom, offset/2, (__le16 *)data, len/2);
+	ks8851_eeprom_release(ks);
+	ks8851_unlock(ks, &flags);
+
+	return 0;
+}
+
+static int ks8851_get_eeprom_len(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	/* currently, we assume it is an 93C46 attached, so return 128 */
+	return ks->rc_ccr & CCR_EEPROM ? 128 : 0;
+}
+
+static const struct ethtool_ops ks8851_ethtool_ops = {
+	.get_drvinfo	= ks8851_get_drvinfo,
+	.get_msglevel	= ks8851_get_msglevel,
+	.set_msglevel	= ks8851_set_msglevel,
+	.get_link	= ks8851_get_link,
+	.nway_reset	= ks8851_nway_reset,
+	.get_eeprom_len	= ks8851_get_eeprom_len,
+	.get_eeprom	= ks8851_get_eeprom,
+	.set_eeprom	= ks8851_set_eeprom,
+	.get_link_ksettings = ks8851_get_link_ksettings,
+	.set_link_ksettings = ks8851_set_link_ksettings,
+};
+
+/* MII interface controls */
+
+/**
+ * ks8851_phy_reg - convert MII register into a KS8851 register
+ * @reg: MII register number.
+ *
+ * Return the KS8851 register number for the corresponding MII PHY register
+ * if possible. Return zero if the MII register has no direct mapping to the
+ * KS8851 register set.
+ */
+static int ks8851_phy_reg(int reg)
+{
+	switch (reg) {
+	case MII_BMCR:
+		return KS_P1MBCR;
+	case MII_BMSR:
+		return KS_P1MBSR;
+	case MII_PHYSID1:
+		return KS_PHY1ILR;
+	case MII_PHYSID2:
+		return KS_PHY1IHR;
+	case MII_ADVERTISE:
+		return KS_P1ANAR;
+	case MII_LPA:
+		return KS_P1ANLPR;
+	}
+
+	return 0x0;
+}
+
+/**
+ * ks8851_phy_read - MII interface PHY register read.
+ * @dev: The network device the PHY is on.
+ * @phy_addr: Address of PHY (ignored as we only have one)
+ * @reg: The register to read.
+ *
+ * This call reads data from the PHY register specified in @reg. Since the
+ * device does not support all the MII registers, the non-existent values
+ * are always returned as zero.
+ *
+ * We return zero for unsupported registers as the MII code does not check
+ * the value returned for any error status, and simply returns it to the
+ * caller. The mii-tool that the driver was tested with takes any -ve error
+ * as real PHY capabilities, thus displaying incorrect data to the user.
+ */
+static int ks8851_phy_read(struct net_device *dev, int phy_addr, int reg)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+	int ksreg;
+	int result;
+
+	ksreg = ks8851_phy_reg(reg);
+	if (!ksreg)
+		return 0x0;	/* no error return allowed, so use zero */
+
+	ks8851_lock(ks, &flags);
+	result = ks8851_rdreg16(ks, ksreg);
+	ks8851_unlock(ks, &flags);
+
+	return result;
+}
+
+static void ks8851_phy_write(struct net_device *dev,
+			     int phy, int reg, int value)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	unsigned long flags;
+	int ksreg;
+
+	ksreg = ks8851_phy_reg(reg);
+	if (ksreg) {
+		ks8851_lock(ks, &flags);
+		ks8851_wrreg16(ks, ksreg, value);
+		ks8851_unlock(ks, &flags);
+	}
+}
+
+/**
+ * ks8851_read_selftest - read the selftest memory info.
+ * @ks: The device state
+ *
+ * Read and check the TX/RX memory selftest information.
+ */
+static int ks8851_read_selftest(struct ks8851_net *ks)
+{
+	unsigned both_done = MBIR_TXMBF | MBIR_RXMBF;
+	int ret = 0;
+	unsigned rd;
+
+	rd = ks8851_rdreg16(ks, KS_MBIR);
+
+	if ((rd & both_done) != both_done) {
+		netdev_warn(ks->netdev, "Memory selftest not finished\n");
+		return 0;
+	}
+
+	if (rd & MBIR_TXMBFA) {
+		netdev_err(ks->netdev, "TX memory selftest fail\n");
+		ret |= 1;
+	}
+
+	if (rd & MBIR_RXMBFA) {
+		netdev_err(ks->netdev, "RX memory selftest fail\n");
+		ret |= 2;
+	}
+
+	return 0;
+}
+
+/* driver bus management functions */
+
+#ifdef CONFIG_PM_SLEEP
+
+int ks8851_suspend(struct device *dev)
+{
+	struct ks8851_net *ks = dev_get_drvdata(dev);
+	struct net_device *netdev = ks->netdev;
+
+	if (netif_running(netdev)) {
+		netif_device_detach(netdev);
+		ks8851_net_stop(netdev);
+	}
+
+	return 0;
+}
+
+int ks8851_resume(struct device *dev)
+{
+	struct ks8851_net *ks = dev_get_drvdata(dev);
+	struct net_device *netdev = ks->netdev;
+
+	if (netif_running(netdev)) {
+		ks8851_net_open(netdev);
+		netif_device_attach(netdev);
+	}
+
+	return 0;
+}
+#endif
+
+int ks8851_probe_common(struct net_device *netdev, struct device *dev,
+			int msg_en)
+{
+	struct ks8851_net *ks = netdev_priv(netdev);
+	unsigned cider;
+	int gpio;
+	int ret;
+
+	ks->netdev = netdev;
+	ks->tx_space = 6144;
+
+	gpio = of_get_named_gpio_flags(dev->of_node, "reset-gpios", 0, NULL);
+	if (gpio == -EPROBE_DEFER)
+		return gpio;
+
+	ks->gpio = gpio;
+	if (gpio_is_valid(gpio)) {
+		ret = devm_gpio_request_one(dev, gpio,
+					    GPIOF_OUT_INIT_LOW, "ks8851_rst_n");
+		if (ret) {
+			dev_err(dev, "reset gpio request failed\n");
+			return ret;
+		}
+	}
+
+	ks->vdd_io = devm_regulator_get(dev, "vdd-io");
+	if (IS_ERR(ks->vdd_io)) {
+		ret = PTR_ERR(ks->vdd_io);
+		goto err_reg_io;
+	}
+
+	ret = regulator_enable(ks->vdd_io);
+	if (ret) {
+		dev_err(dev, "regulator vdd_io enable fail: %d\n", ret);
+		goto err_reg_io;
+	}
+
+	ks->vdd_reg = devm_regulator_get(dev, "vdd");
+	if (IS_ERR(ks->vdd_reg)) {
+		ret = PTR_ERR(ks->vdd_reg);
+		goto err_reg;
+	}
+
+	ret = regulator_enable(ks->vdd_reg);
+	if (ret) {
+		dev_err(dev, "regulator vdd enable fail: %d\n", ret);
+		goto err_reg;
+	}
+
+	if (gpio_is_valid(gpio)) {
+		usleep_range(10000, 11000);
+		gpio_set_value(gpio, 1);
+	}
+
+	spin_lock_init(&ks->statelock);
+
+	INIT_WORK(&ks->rxctrl_work, ks8851_rxctrl_work);
+
+	/* setup EEPROM state */
+	ks->eeprom.data = ks;
+	ks->eeprom.width = PCI_EEPROM_WIDTH_93C46;
+	ks->eeprom.register_read = ks8851_eeprom_regread;
+	ks->eeprom.register_write = ks8851_eeprom_regwrite;
+
+	/* setup mii state */
+	ks->mii.dev		= netdev;
+	ks->mii.phy_id		= 1,
+	ks->mii.phy_id_mask	= 1;
+	ks->mii.reg_num_mask	= 0xf;
+	ks->mii.mdio_read	= ks8851_phy_read;
+	ks->mii.mdio_write	= ks8851_phy_write;
+
+	dev_info(dev, "message enable is %d\n", msg_en);
+
+	/* set the default message enable */
+	ks->msg_enable = netif_msg_init(msg_en, NETIF_MSG_DRV |
+						NETIF_MSG_PROBE |
+						NETIF_MSG_LINK);
+
+	skb_queue_head_init(&ks->txq);
+
+	netdev->ethtool_ops = &ks8851_ethtool_ops;
+	SET_NETDEV_DEV(netdev, dev);
+
+	dev_set_drvdata(dev, ks);
+
+	netif_carrier_off(ks->netdev);
+	netdev->if_port = IF_PORT_100BASET;
+	netdev->netdev_ops = &ks8851_netdev_ops;
+
+	/* issue a global soft reset to reset the device. */
+	ks8851_soft_reset(ks, GRR_GSR);
+
+	/* simple check for a valid chip being connected to the bus */
+	cider = ks8851_rdreg16(ks, KS_CIDER);
+	if ((cider & ~CIDER_REV_MASK) != CIDER_ID) {
+		dev_err(dev, "failed to read device ID\n");
+		ret = -ENODEV;
+		goto err_id;
+	}
+
+	/* cache the contents of the CCR register for EEPROM, etc. */
+	ks->rc_ccr = ks8851_rdreg16(ks, KS_CCR);
+
+	ks8851_read_selftest(ks);
+	ks8851_init_mac(ks, dev->of_node);
+
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(dev, "failed to register network device\n");
+		goto err_netdev;
+	}
+
+	netdev_info(netdev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
+		    CIDER_REV_GET(cider), netdev->dev_addr, netdev->irq,
+		    ks->rc_ccr & CCR_EEPROM ? "has" : "no");
+
+	return 0;
+
+err_netdev:
+err_id:
+	if (gpio_is_valid(gpio))
+		gpio_set_value(gpio, 0);
+	regulator_disable(ks->vdd_reg);
+err_reg:
+	regulator_disable(ks->vdd_io);
+err_reg_io:
+	return ret;
+}
+
+int ks8851_remove_common(struct device *dev)
+{
+	struct ks8851_net *priv = dev_get_drvdata(dev);
+
+	if (netif_msg_drv(priv))
+		dev_info(dev, "remove\n");
+
+	unregister_netdev(priv->netdev);
+	if (gpio_is_valid(priv->gpio))
+		gpio_set_value(priv->gpio, 0);
+	regulator_disable(priv->vdd_reg);
+	regulator_disable(priv->vdd_io);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
new file mode 100644
index 000000000000..4ec7f1615977
--- /dev/null
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -0,0 +1,485 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* drivers/net/ethernet/micrel/ks8851.c
+ *
+ * Copyright 2009 Simtec Electronics
+ *	http://www.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define DEBUG
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/cache.h>
+#include <linux/crc32.h>
+#include <linux/mii.h>
+#include <linux/regulator/consumer.h>
+
+#include <linux/spi/spi.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_net.h>
+
+#include "ks8851.h"
+
+static int msg_enable;
+
+/**
+ * struct ks8851_net_spi - KS8851 SPI driver private data
+ * @lock: Lock to ensure that the device is not accessed when busy.
+ * @tx_work: Work queue for tx packets
+ * @ks8851: KS8851 driver common private data
+ * @spidev: The spi device we're bound to.
+ * @spi_msg1: pre-setup SPI transfer with one message, @spi_xfer1.
+ * @spi_msg2: pre-setup SPI transfer with two messages, @spi_xfer2.
+ * @spi_xfer1: @spi_msg1 SPI transfer structure
+ * @spi_xfer2: @spi_msg2 SPI transfer structure
+ *
+ * The @lock ensures that the chip is protected when certain operations are
+ * in progress. When the read or write packet transfer is in progress, most
+ * of the chip registers are not ccessible until the transfer is finished and
+ * the DMA has been de-asserted.
+ */
+struct ks8851_net_spi {
+	struct ks8851_net	ks8851;
+	struct mutex		lock;
+	struct work_struct	tx_work;
+	struct spi_device	*spidev;
+	struct spi_message	spi_msg1;
+	struct spi_message	spi_msg2;
+	struct spi_transfer	spi_xfer1;
+	struct spi_transfer	spi_xfer2[2];
+};
+
+#define to_ks8851_spi(ks) container_of((ks), struct ks8851_net_spi, ks8851)
+
+/* SPI frame opcodes */
+#define KS_SPIOP_RD	0x00
+#define KS_SPIOP_WR	0x40
+#define KS_SPIOP_RXFIFO	0x80
+#define KS_SPIOP_TXFIFO	0xC0
+
+/* shift for byte-enable data */
+#define BYTE_EN(_x)	((_x) << 2)
+
+/* turn register number and byte-enable mask into data for start of packet */
+#define MK_OP(_byteen, _reg)	\
+	(BYTE_EN(_byteen) | (_reg) << (8 + 2) | (_reg) >> 6)
+
+/**
+ * ks8851_lock_spi - register access lock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Claim chip register access lock
+ */
+static void ks8851_lock_spi(struct ks8851_net *ks, unsigned long *flags)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	mutex_lock(&kss->lock);
+}
+
+/**
+ * ks8851_unlock_spi - register access unlock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Release chip register access lock
+ */
+static void ks8851_unlock_spi(struct ks8851_net *ks, unsigned long *flags)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	mutex_unlock(&kss->lock);
+}
+
+/* SPI register read/write calls.
+ *
+ * All these calls issue SPI transactions to access the chip's registers. They
+ * all require that the necessary lock is held to prevent accesses when the
+ * chip is busy transferring packet data (RX/TX FIFO accesses).
+ */
+
+/**
+ * ks8851_wrreg16_spi - write 16bit register value to chip via SPI
+ * @ks: The chip state
+ * @reg: The register address
+ * @val: The value to write
+ *
+ * Issue a write to put the value @val into the register specified in @reg.
+ */
+static void ks8851_wrreg16_spi(struct ks8851_net *ks, unsigned int reg,
+			       unsigned int val)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = &kss->spi_xfer1;
+	struct spi_message *msg = &kss->spi_msg1;
+	__le16 txb[2];
+	int ret;
+
+	txb[0] = cpu_to_le16(MK_OP(reg & 2 ? 0xC : 0x03, reg) | KS_SPIOP_WR);
+	txb[1] = cpu_to_le16(val);
+
+	xfer->tx_buf = txb;
+	xfer->rx_buf = NULL;
+	xfer->len = 4;
+
+	ret = spi_sync(kss->spidev, msg);
+	if (ret < 0)
+		netdev_err(ks->netdev, "spi_sync() failed\n");
+}
+
+/**
+ * ks8851_rdreg - issue read register command and return the data
+ * @ks: The device state
+ * @op: The register address and byte enables in message format.
+ * @rxb: The RX buffer to return the result into
+ * @rxl: The length of data expected.
+ *
+ * This is the low level read call that issues the necessary spi message(s)
+ * to read data from the register specified in @op.
+ */
+static void ks8851_rdreg(struct ks8851_net *ks, unsigned int op,
+			 u8 *rxb, unsigned int rxl)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer;
+	struct spi_message *msg;
+	__le16 *txb = (__le16 *)ks->txd;
+	u8 *trx = ks->rxd;
+	int ret;
+
+	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
+
+	if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
+		msg = &kss->spi_msg2;
+		xfer = kss->spi_xfer2;
+
+		xfer->tx_buf = txb;
+		xfer->rx_buf = NULL;
+		xfer->len = 2;
+
+		xfer++;
+		xfer->tx_buf = NULL;
+		xfer->rx_buf = trx;
+		xfer->len = rxl;
+	} else {
+		msg = &kss->spi_msg1;
+		xfer = &kss->spi_xfer1;
+
+		xfer->tx_buf = txb;
+		xfer->rx_buf = trx;
+		xfer->len = rxl + 2;
+	}
+
+	ret = spi_sync(kss->spidev, msg);
+	if (ret < 0)
+		netdev_err(ks->netdev, "read: spi_sync() failed\n");
+	else if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
+		memcpy(rxb, trx, rxl);
+	else
+		memcpy(rxb, trx + 2, rxl);
+}
+
+/**
+ * ks8851_rdreg16_spi - read 16 bit register from device via SPI
+ * @ks: The chip information
+ * @reg: The register address
+ *
+ * Read a 16bit register from the chip, returning the result
+ */
+static unsigned int ks8851_rdreg16_spi(struct ks8851_net *ks, unsigned int reg)
+{
+	__le16 rx = 0;
+
+	ks8851_rdreg(ks, MK_OP(reg & 2 ? 0xC : 0x3, reg), (u8 *)&rx, 2);
+	return le16_to_cpu(rx);
+}
+
+/**
+ * ks8851_rdfifo_spi - read data from the receive fifo via SPI
+ * @ks: The device state.
+ * @buff: The buffer address
+ * @len: The length of the data to read
+ *
+ * Issue an RXQ FIFO read command and read the @len amount of data from
+ * the FIFO into the buffer specified by @buff.
+ */
+static void ks8851_rdfifo_spi(struct ks8851_net *ks, u8 *buff, unsigned int len)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = kss->spi_xfer2;
+	struct spi_message *msg = &kss->spi_msg2;
+	u8 txb[1];
+	int ret;
+
+	netif_dbg(ks, rx_status, ks->netdev,
+		  "%s: %d@%p\n", __func__, len, buff);
+
+	/* set the operation we're issuing */
+	txb[0] = KS_SPIOP_RXFIFO;
+
+	xfer->tx_buf = txb;
+	xfer->rx_buf = NULL;
+	xfer->len = 1;
+
+	xfer++;
+	xfer->rx_buf = buff;
+	xfer->tx_buf = NULL;
+	xfer->len = len;
+
+	ret = spi_sync(kss->spidev, msg);
+	if (ret < 0)
+		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
+}
+
+/**
+ * ks8851_wrfifo_spi - write packet to TX FIFO via SPI
+ * @ks: The device state.
+ * @txp: The sk_buff to transmit.
+ * @irq: IRQ on completion of the packet.
+ *
+ * Send the @txp to the chip. This means creating the relevant packet header
+ * specifying the length of the packet and the other information the chip
+ * needs, such as IRQ on completion. Send the header and the packet data to
+ * the device.
+ */
+static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp,
+			      bool irq)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+	struct spi_transfer *xfer = kss->spi_xfer2;
+	struct spi_message *msg = &kss->spi_msg2;
+	unsigned int fid = 0;
+	int ret;
+
+	netif_dbg(ks, tx_queued, ks->netdev, "%s: skb %p, %d@%p, irq %d\n",
+		  __func__, txp, txp->len, txp->data, irq);
+
+	fid = ks->fid++;
+	fid &= TXFR_TXFID_MASK;
+
+	if (irq)
+		fid |= TXFR_TXIC;	/* irq on completion */
+
+	/* start header at txb[1] to align txw entries */
+	ks->txh.txb[1] = KS_SPIOP_TXFIFO;
+	ks->txh.txw[1] = cpu_to_le16(fid);
+	ks->txh.txw[2] = cpu_to_le16(txp->len);
+
+	xfer->tx_buf = &ks->txh.txb[1];
+	xfer->rx_buf = NULL;
+	xfer->len = 5;
+
+	xfer++;
+	xfer->tx_buf = txp->data;
+	xfer->rx_buf = NULL;
+	xfer->len = ALIGN(txp->len, 4);
+
+	ret = spi_sync(kss->spidev, msg);
+	if (ret < 0)
+		netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__);
+}
+
+/**
+ * ks8851_rx_skb_spi - receive skbuff
+ * @ks: The device state
+ * @skb: The skbuff
+ */
+static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
+{
+	netif_rx_ni(skb);
+}
+
+/**
+ * ks8851_tx_work - process tx packet(s)
+ * @work: The work strucutre what was scheduled.
+ *
+ * This is called when a number of packets have been scheduled for
+ * transmission and need to be sent to the device.
+ */
+static void ks8851_tx_work(struct work_struct *work)
+{
+	struct ks8851_net_spi *kss;
+	struct ks8851_net *ks;
+	unsigned long flags;
+	struct sk_buff *txb;
+	bool last;
+
+	kss = container_of(work, struct ks8851_net_spi, tx_work);
+	ks = &kss->ks8851;
+	last = skb_queue_empty(&ks->txq);
+
+	ks8851_lock_spi(ks, &flags);
+
+	while (!last) {
+		txb = skb_dequeue(&ks->txq);
+		last = skb_queue_empty(&ks->txq);
+
+		if (txb) {
+			ks8851_wrreg16_spi(ks, KS_RXQCR,
+					   ks->rc_rxqcr | RXQCR_SDA);
+			ks8851_wrfifo_spi(ks, txb, last);
+			ks8851_wrreg16_spi(ks, KS_RXQCR, ks->rc_rxqcr);
+			ks8851_wrreg16_spi(ks, KS_TXQCR, TXQCR_METFE);
+
+			ks8851_done_tx(ks, txb);
+		}
+	}
+
+	ks8851_unlock_spi(ks, &flags);
+}
+
+/**
+ * ks8851_flush_tx_work_spi - flush outstanding TX work
+ * @ks: The device state
+ */
+static void ks8851_flush_tx_work_spi(struct ks8851_net *ks)
+{
+	struct ks8851_net_spi *kss = to_ks8851_spi(ks);
+
+	flush_work(&kss->tx_work);
+}
+
+/**
+ * calc_txlen - calculate size of message to send packet
+ * @len: Length of data
+ *
+ * Returns the size of the TXFIFO message needed to send
+ * this packet.
+ */
+static unsigned int calc_txlen(unsigned int len)
+{
+	return ALIGN(len + 4, 4);
+}
+
+/**
+ * ks8851_start_xmit_spi - transmit packet using SPI
+ * @skb: The buffer to transmit
+ * @dev: The device used to transmit the packet.
+ *
+ * Called by the network layer to transmit the @skb. Queue the packet for
+ * the device and schedule the necessary work to transmit the packet when
+ * it is free.
+ *
+ * We do this to firstly avoid sleeping with the network device locked,
+ * and secondly so we can round up more than one packet to transmit which
+ * means we can try and avoid generating too many transmit done interrupts.
+ */
+static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb,
+					 struct net_device *dev)
+{
+	unsigned int needed = calc_txlen(skb->len);
+	struct ks8851_net *ks = netdev_priv(dev);
+	netdev_tx_t ret = NETDEV_TX_OK;
+	struct ks8851_net_spi *kss;
+
+	kss = to_ks8851_spi(ks);
+
+	netif_dbg(ks, tx_queued, ks->netdev,
+		  "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data);
+
+	spin_lock(&ks->statelock);
+
+	if (needed > ks->tx_space) {
+		netif_stop_queue(dev);
+		ret = NETDEV_TX_BUSY;
+	} else {
+		ks->tx_space -= needed;
+		skb_queue_tail(&ks->txq, skb);
+	}
+
+	spin_unlock(&ks->statelock);
+	schedule_work(&kss->tx_work);
+
+	return ret;
+}
+
+static int ks8851_probe_spi(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct ks8851_net_spi *kss;
+	struct net_device *netdev;
+	struct ks8851_net *ks;
+
+	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_spi));
+	if (!netdev)
+		return -ENOMEM;
+
+	spi->bits_per_word = 8;
+
+	ks = netdev_priv(netdev);
+
+	ks->lock = ks8851_lock_spi;
+	ks->unlock = ks8851_unlock_spi;
+	ks->rdreg16 = ks8851_rdreg16_spi;
+	ks->wrreg16 = ks8851_wrreg16_spi;
+	ks->rdfifo = ks8851_rdfifo_spi;
+	ks->wrfifo = ks8851_wrfifo_spi;
+	ks->start_xmit = ks8851_start_xmit_spi;
+	ks->rx_skb = ks8851_rx_skb_spi;
+	ks->flush_tx_work = ks8851_flush_tx_work_spi;
+
+#define STD_IRQ (IRQ_LCI |	/* Link Change */	\
+		 IRQ_TXI |	/* TX done */		\
+		 IRQ_RXI |	/* RX done */		\
+		 IRQ_SPIBEI |	/* SPI bus error */	\
+		 IRQ_TXPSI |	/* TX process stop */	\
+		 IRQ_RXPSI)	/* RX process stop */
+	ks->rc_ier = STD_IRQ;
+
+	kss = to_ks8851_spi(ks);
+
+	kss->spidev = spi;
+	mutex_init(&kss->lock);
+	INIT_WORK(&kss->tx_work, ks8851_tx_work);
+
+	/* initialise pre-made spi transfer messages */
+	spi_message_init(&kss->spi_msg1);
+	spi_message_add_tail(&kss->spi_xfer1, &kss->spi_msg1);
+
+	spi_message_init(&kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[0], &kss->spi_msg2);
+	spi_message_add_tail(&kss->spi_xfer2[1], &kss->spi_msg2);
+
+	netdev->irq = spi->irq;
+
+	return ks8851_probe_common(netdev, dev, msg_enable);
+}
+
+static int ks8851_remove_spi(struct spi_device *spi)
+{
+	return ks8851_remove_common(&spi->dev);
+}
+
+static const struct of_device_id ks8851_match_table[] = {
+	{ .compatible = "micrel,ks8851" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ks8851_match_table);
+
+static struct spi_driver ks8851_driver = {
+	.driver = {
+		.name = "ks8851",
+		.of_match_table = ks8851_match_table,
+		.pm = &ks8851_pm_ops,
+	},
+	.probe = ks8851_probe_spi,
+	.remove = ks8851_remove_spi,
+};
+module_spi_driver(ks8851_driver);
+
+MODULE_DESCRIPTION("KS8851 Network driver");
+MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
+MODULE_LICENSE("GPL");
+
+module_param_named(message, msg_enable, int, 0);
+MODULE_PARM_DESC(message, "Message verbosity level (0=none, 31=all)");
+MODULE_ALIAS("spi:ks8851");
-- 
cgit v1.2.3


From 797047f875b5463719cc70ba213eb691d453c946 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:45 +0200
Subject: net: ks8851: Implement Parallel bus operations

Implement accessors for KS8851-16MLL/MLLI/MLLU parallel bus variant of
the KS8851. This is based off the ks8851_mll.c , which is a driver for
exactly the same hardware, however the ks8851.c code is much higher
quality. Hence, this patch pulls out the relevant information from the
ks8851_mll.c on how to access the bus, but uses the common ks8851.c
code. To make this patch reviewable, instead of rewriting ks8851_mll.c,
ks8851_mll.c is removed in a separate subsequent patch.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/Kconfig      |   2 +
 drivers/net/ethernet/micrel/Makefile     |   1 +
 drivers/net/ethernet/micrel/ks8851_par.c | 357 +++++++++++++++++++++++++++++++
 3 files changed, 360 insertions(+)
 create mode 100644 drivers/net/ethernet/micrel/ks8851_par.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig
index b9c4d48e28e4..09f35209d43d 100644
--- a/drivers/net/ethernet/micrel/Kconfig
+++ b/drivers/net/ethernet/micrel/Kconfig
@@ -38,6 +38,8 @@ config KS8851_MLL
 	tristate "Micrel KS8851 MLL"
 	depends on HAS_IOMEM
 	select MII
+	select CRC32
+	select EEPROM_93CX6
 	---help---
 	  This platform driver is for Micrel KS8851 Address/data bus
 	  multiplexed network chip.
diff --git a/drivers/net/ethernet/micrel/Makefile b/drivers/net/ethernet/micrel/Makefile
index c7a4725c2e95..5cc00d22c708 100644
--- a/drivers/net/ethernet/micrel/Makefile
+++ b/drivers/net/ethernet/micrel/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_KS8842) += ks8842.o
 obj-$(CONFIG_KS8851) += ks8851.o
 ks8851-objs = ks8851_common.o ks8851_spi.o
 obj-$(CONFIG_KS8851_MLL) += ks8851_mll.o
+ks8851_mll-objs = ks8851_common.o ks8851_par.o
 obj-$(CONFIG_KSZ884X_PCI) += ksz884x.o
diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c
new file mode 100644
index 000000000000..3bab0cb2b1a5
--- /dev/null
+++ b/drivers/net/ethernet/micrel/ks8851_par.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* drivers/net/ethernet/micrel/ks8851.c
+ *
+ * Copyright 2009 Simtec Electronics
+ *	http://www.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define DEBUG
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/iopoll.h>
+#include <linux/mii.h>
+
+#include <linux/platform_device.h>
+#include <linux/of_net.h>
+
+#include "ks8851.h"
+
+static int msg_enable;
+
+#define BE3             0x8000      /* Byte Enable 3 */
+#define BE2             0x4000      /* Byte Enable 2 */
+#define BE1             0x2000      /* Byte Enable 1 */
+#define BE0             0x1000      /* Byte Enable 0 */
+
+/**
+ * struct ks8851_net_par - KS8851 Parallel driver private data
+ * @ks8851: KS8851 driver common private data
+ * @lock: Lock to ensure that the device is not accessed when busy.
+ * @hw_addr	: start address of data register.
+ * @hw_addr_cmd	: start address of command register.
+ * @cmd_reg_cache	: command register cached.
+ *
+ * The @lock ensures that the chip is protected when certain operations are
+ * in progress. When the read or write packet transfer is in progress, most
+ * of the chip registers are not accessible until the transfer is finished
+ * and the DMA has been de-asserted.
+ */
+struct ks8851_net_par {
+	struct ks8851_net	ks8851;
+	spinlock_t		lock;
+	void __iomem		*hw_addr;
+	void __iomem		*hw_addr_cmd;
+	u16			cmd_reg_cache;
+};
+
+#define to_ks8851_par(ks) container_of((ks), struct ks8851_net_par, ks8851)
+
+/**
+ * ks8851_lock_par - register access lock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Claim chip register access lock
+ */
+static void ks8851_lock_par(struct ks8851_net *ks, unsigned long *flags)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+
+	spin_lock_irqsave(&ksp->lock, *flags);
+}
+
+/**
+ * ks8851_unlock_par - register access unlock
+ * @ks: The chip state
+ * @flags: Spinlock flags
+ *
+ * Release chip register access lock
+ */
+static void ks8851_unlock_par(struct ks8851_net *ks, unsigned long *flags)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+
+	spin_unlock_irqrestore(&ksp->lock, *flags);
+}
+
+/**
+ * ks_check_endian - Check whether endianness of the bus is correct
+ * @ks	  : The chip information
+ *
+ * The KS8851-16MLL EESK pin allows selecting the endianness of the 16bit
+ * bus. To maintain optimum performance, the bus endianness should be set
+ * such that it matches the endianness of the CPU.
+ */
+static int ks_check_endian(struct ks8851_net *ks)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+	u16 cider;
+
+	/*
+	 * Read CIDER register first, however read it the "wrong" way around.
+	 * If the endian strap on the KS8851-16MLL in incorrect and the chip
+	 * is operating in different endianness than the CPU, then the meaning
+	 * of BE[3:0] byte-enable bits is also swapped such that:
+	 *    BE[3,2,1,0] becomes BE[1,0,3,2]
+	 *
+	 * Luckily for us, the byte-enable bits are the top four MSbits of
+	 * the address register and the CIDER register is at offset 0xc0.
+	 * Hence, by reading address 0xc0c0, which is not impacted by endian
+	 * swapping, we assert either BE[3:2] or BE[1:0] while reading the
+	 * CIDER register.
+	 *
+	 * If the bus configuration is correct, reading 0xc0c0 asserts
+	 * BE[3:2] and this read returns 0x0000, because to read register
+	 * with bottom two LSbits of address set to 0, BE[1:0] must be
+	 * asserted.
+	 *
+	 * If the bus configuration is NOT correct, reading 0xc0c0 asserts
+	 * BE[1:0] and this read returns non-zero 0x8872 value.
+	 */
+	iowrite16(BE3 | BE2 | KS_CIDER, ksp->hw_addr_cmd);
+	cider = ioread16(ksp->hw_addr);
+	if (!cider)
+		return 0;
+
+	netdev_err(ks->netdev, "incorrect EESK endian strap setting\n");
+
+	return -EINVAL;
+}
+
+/**
+ * ks8851_wrreg16_par - write 16bit register value to chip
+ * @ks: The chip state
+ * @reg: The register address
+ * @val: The value to write
+ *
+ * Issue a write to put the value @val into the register specified in @reg.
+ */
+static void ks8851_wrreg16_par(struct ks8851_net *ks, unsigned int reg,
+			       unsigned int val)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+
+	ksp->cmd_reg_cache = (u16)reg | ((BE1 | BE0) << (reg & 0x02));
+	iowrite16(ksp->cmd_reg_cache, ksp->hw_addr_cmd);
+	iowrite16(val, ksp->hw_addr);
+}
+
+/**
+ * ks8851_rdreg16_par - read 16 bit register from chip
+ * @ks: The chip information
+ * @reg: The register address
+ *
+ * Read a 16bit register from the chip, returning the result
+ */
+static unsigned int ks8851_rdreg16_par(struct ks8851_net *ks, unsigned int reg)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+
+	ksp->cmd_reg_cache = (u16)reg | ((BE1 | BE0) << (reg & 0x02));
+	iowrite16(ksp->cmd_reg_cache, ksp->hw_addr_cmd);
+	return ioread16(ksp->hw_addr);
+}
+
+/**
+ * ks8851_rdfifo_par - read data from the receive fifo
+ * @ks: The device state.
+ * @buff: The buffer address
+ * @len: The length of the data to read
+ *
+ * Issue an RXQ FIFO read command and read the @len amount of data from
+ * the FIFO into the buffer specified by @buff.
+ */
+static void ks8851_rdfifo_par(struct ks8851_net *ks, u8 *buff, unsigned int len)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+
+	netif_dbg(ks, rx_status, ks->netdev,
+		  "%s: %d@%p\n", __func__, len, buff);
+
+	ioread16_rep(ksp->hw_addr, (u16 *)buff + 1, len / 2);
+}
+
+/**
+ * ks8851_wrfifo_par - write packet to TX FIFO
+ * @ks: The device state.
+ * @txp: The sk_buff to transmit.
+ * @irq: IRQ on completion of the packet.
+ *
+ * Send the @txp to the chip. This means creating the relevant packet header
+ * specifying the length of the packet and the other information the chip
+ * needs, such as IRQ on completion. Send the header and the packet data to
+ * the device.
+ */
+static void ks8851_wrfifo_par(struct ks8851_net *ks, struct sk_buff *txp,
+			      bool irq)
+{
+	struct ks8851_net_par *ksp = to_ks8851_par(ks);
+	unsigned int len = ALIGN(txp->len, 4);
+	unsigned int fid = 0;
+
+	netif_dbg(ks, tx_queued, ks->netdev, "%s: skb %p, %d@%p, irq %d\n",
+		  __func__, txp, txp->len, txp->data, irq);
+
+	fid = ks->fid++;
+	fid &= TXFR_TXFID_MASK;
+
+	if (irq)
+		fid |= TXFR_TXIC;	/* irq on completion */
+
+	iowrite16(fid, ksp->hw_addr);
+	iowrite16(txp->len, ksp->hw_addr);
+
+	iowrite16_rep(ksp->hw_addr, txp->data, len / 2);
+}
+
+/**
+ * ks8851_rx_skb_par - receive skbuff
+ * @ks: The device state.
+ * @skb: The skbuff
+ */
+static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb)
+{
+	netif_rx(skb);
+}
+
+static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks)
+{
+	return ks8851_rdreg16_par(ks, KS_TXQCR);
+}
+
+/**
+ * ks8851_start_xmit_par - transmit packet
+ * @skb: The buffer to transmit
+ * @dev: The device used to transmit the packet.
+ *
+ * Called by the network layer to transmit the @skb. Queue the packet for
+ * the device and schedule the necessary work to transmit the packet when
+ * it is free.
+ *
+ * We do this to firstly avoid sleeping with the network device locked,
+ * and secondly so we can round up more than one packet to transmit which
+ * means we can try and avoid generating too many transmit done interrupts.
+ */
+static netdev_tx_t ks8851_start_xmit_par(struct sk_buff *skb,
+					 struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	netdev_tx_t ret = NETDEV_TX_OK;
+	unsigned long flags;
+	unsigned int txqcr;
+	u16 txmir;
+	int err;
+
+	netif_dbg(ks, tx_queued, ks->netdev,
+		  "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data);
+
+	ks8851_lock_par(ks, &flags);
+
+	txmir = ks8851_rdreg16_par(ks, KS_TXMIR) & 0x1fff;
+
+	if (likely(txmir >= skb->len + 12)) {
+		ks8851_wrreg16_par(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
+		ks8851_wrfifo_par(ks, skb, false);
+		ks8851_wrreg16_par(ks, KS_RXQCR, ks->rc_rxqcr);
+		ks8851_wrreg16_par(ks, KS_TXQCR, TXQCR_METFE);
+
+		err = readx_poll_timeout_atomic(ks8851_rdreg16_par_txqcr, ks,
+						txqcr, !(txqcr & TXQCR_METFE),
+						5, 1000000);
+		if (err)
+			ret = NETDEV_TX_BUSY;
+
+		ks8851_done_tx(ks, skb);
+	} else {
+		ret = NETDEV_TX_BUSY;
+	}
+
+	ks8851_unlock_par(ks, &flags);
+
+	return ret;
+}
+
+static int ks8851_probe_par(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ks8851_net_par *ksp;
+	struct net_device *netdev;
+	struct ks8851_net *ks;
+	int ret;
+
+	netdev = devm_alloc_etherdev(dev, sizeof(struct ks8851_net_par));
+	if (!netdev)
+		return -ENOMEM;
+
+	ks = netdev_priv(netdev);
+
+	ks->lock = ks8851_lock_par;
+	ks->unlock = ks8851_unlock_par;
+	ks->rdreg16 = ks8851_rdreg16_par;
+	ks->wrreg16 = ks8851_wrreg16_par;
+	ks->rdfifo = ks8851_rdfifo_par;
+	ks->wrfifo = ks8851_wrfifo_par;
+	ks->start_xmit = ks8851_start_xmit_par;
+	ks->rx_skb = ks8851_rx_skb_par;
+
+#define STD_IRQ (IRQ_LCI |	/* Link Change */	\
+		 IRQ_RXI |	/* RX done */		\
+		 IRQ_RXPSI)	/* RX process stop */
+	ks->rc_ier = STD_IRQ;
+
+	ksp = to_ks8851_par(ks);
+	spin_lock_init(&ksp->lock);
+
+	ksp->hw_addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ksp->hw_addr))
+		return PTR_ERR(ksp->hw_addr);
+
+	ksp->hw_addr_cmd = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(ksp->hw_addr_cmd))
+		return PTR_ERR(ksp->hw_addr_cmd);
+
+	ret = ks_check_endian(ks);
+	if (ret)
+		return ret;
+
+	netdev->irq = platform_get_irq(pdev, 0);
+
+	return ks8851_probe_common(netdev, dev, msg_enable);
+}
+
+static int ks8851_remove_par(struct platform_device *pdev)
+{
+	return ks8851_remove_common(&pdev->dev);
+}
+
+static const struct of_device_id ks8851_match_table[] = {
+	{ .compatible = "micrel,ks8851-mll" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ks8851_match_table);
+
+static struct platform_driver ks8851_driver = {
+	.driver = {
+		.name = "ks8851",
+		.of_match_table = ks8851_match_table,
+		.pm = &ks8851_pm_ops,
+	},
+	.probe = ks8851_probe_par,
+	.remove = ks8851_remove_par,
+};
+module_platform_driver(ks8851_driver);
+
+MODULE_DESCRIPTION("KS8851 Network driver");
+MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
+MODULE_LICENSE("GPL");
+
+module_param_named(message, msg_enable, int, 0);
+MODULE_PARM_DESC(message, "Message verbosity level (0=none, 31=all)");
-- 
cgit v1.2.3


From 72628da6d63413299a6369e71f5c97f0edea6a8b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 29 May 2020 00:21:46 +0200
Subject: net: ks8851: Remove ks8851_mll.c

The ks8851_mll.c is replaced by ks8851_par.c, which is using common code
from ks8851.c, just like ks8851_spi.c . Remove this old ad-hoc driver.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Petr Stetiar <ynezz@true.cz>
Cc: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ks8851_mll.c | 1393 ------------------------------
 1 file changed, 1393 deletions(-)
 delete mode 100644 drivers/net/ethernet/micrel/ks8851_mll.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
deleted file mode 100644
index 45cc840d8e2e..000000000000
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ /dev/null
@@ -1,1393 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/**
- * drivers/net/ethernet/micrel/ks8851_mll.c
- * Copyright (c) 2009 Micrel Inc.
- */
-
-/* Supports:
- * KS8851 16bit MLL chip from Micrel Inc.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/cache.h>
-#include <linux/crc32.h>
-#include <linux/crc32poly.h>
-#include <linux/mii.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/ks8851_mll.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_net.h>
-
-#include "ks8851.h"
-
-#define	DRV_NAME	"ks8851_mll"
-
-static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
-#define MAX_RECV_FRAMES			255
-#define MAX_BUF_SIZE			2048
-#define TX_BUF_SIZE			2000
-#define RX_BUF_SIZE			2000
-
-#define RXCR1_FILTER_MASK    		(RXCR1_RXINVF | RXCR1_RXAE | \
-					 RXCR1_RXMAFMA | RXCR1_RXPAFMA)
-#define RXQCR_CMD_CNTL                	(RXQCR_RXFCTE|RXQCR_ADRFE)
-
-#define	ENUM_BUS_NONE			0
-#define	ENUM_BUS_8BIT			1
-#define	ENUM_BUS_16BIT			2
-#define	ENUM_BUS_32BIT			3
-
-#define MAX_MCAST_LST			32
-#define HW_MCAST_SIZE			8
-
-/**
- * union ks_tx_hdr - tx header data
- * @txb: The header as bytes
- * @txw: The header as 16bit, little-endian words
- *
- * A dual representation of the tx header data to allow
- * access to individual bytes, and to allow 16bit accesses
- * with 16bit alignment.
- */
-union ks_tx_hdr {
-	u8      txb[4];
-	__le16  txw[2];
-};
-
-/**
- * struct ks_net - KS8851 driver private data
- * @net_device 	: The network device we're bound to
- * @hw_addr	: start address of data register.
- * @hw_addr_cmd	: start address of command register.
- * @txh    	: temporaly buffer to save status/length.
- * @lock	: Lock to ensure that the device is not accessed when busy.
- * @pdev	: Pointer to platform device.
- * @mii		: The MII state information for the mii calls.
- * @frame_head_info   	: frame header information for multi-pkt rx.
- * @statelock	: Lock on this structure for tx list.
- * @msg_enable	: The message flags controlling driver output (see ethtool).
- * @frame_cnt  	: number of frames received.
- * @bus_width  	: i/o bus width.
- * @rc_rxqcr	: Cached copy of KS_RXQCR.
- * @rc_txcr	: Cached copy of KS_TXCR.
- * @rc_ier	: Cached copy of KS_IER.
- * @sharedbus  	: Multipex(addr and data bus) mode indicator.
- * @cmd_reg_cache	: command register cached.
- * @cmd_reg_cache_int	: command register cached. Used in the irq handler.
- * @promiscuous	: promiscuous mode indicator.
- * @all_mcast  	: mutlicast indicator.
- * @mcast_lst_size   	: size of multicast list.
- * @mcast_lst    	: multicast list.
- * @mcast_bits    	: multicast enabed.
- * @mac_addr   		: MAC address assigned to this device.
- * @fid    		: frame id.
- * @extra_byte    	: number of extra byte prepended rx pkt.
- * @enabled    		: indicator this device works.
- *
- * The @lock ensures that the chip is protected when certain operations are
- * in progress. When the read or write packet transfer is in progress, most
- * of the chip registers are not accessible until the transfer is finished and
- * the DMA has been de-asserted.
- *
- * The @statelock is used to protect information in the structure which may
- * need to be accessed via several sources, such as the network driver layer
- * or one of the work queues.
- *
- */
-
-/* Receive multiplex framer header info */
-struct type_frame_head {
-	u16	sts;         /* Frame status */
-	u16	len;         /* Byte count */
-};
-
-struct ks_net {
-	struct net_device	*netdev;
-	void __iomem    	*hw_addr;
-	void __iomem    	*hw_addr_cmd;
-	union ks_tx_hdr		txh ____cacheline_aligned;
-	struct mutex      	lock; /* spinlock to be interrupt safe */
-	struct platform_device *pdev;
-	struct mii_if_info	mii;
-	struct type_frame_head	*frame_head_info;
-	spinlock_t		statelock;
-	u32			msg_enable;
-	u32			frame_cnt;
-	int			bus_width;
-
-	u16			rc_rxqcr;
-	u16			rc_txcr;
-	u16			rc_ier;
-	u16			sharedbus;
-	u16			cmd_reg_cache;
-	u16			cmd_reg_cache_int;
-	u16			promiscuous;
-	u16			all_mcast;
-	u16			mcast_lst_size;
-	u8			mcast_lst[MAX_MCAST_LST][ETH_ALEN];
-	u8			mcast_bits[HW_MCAST_SIZE];
-	u8			mac_addr[6];
-	u8                      fid;
-	u8			extra_byte;
-	u8			enabled;
-};
-
-static int msg_enable;
-
-#define BE3             0x8000      /* Byte Enable 3 */
-#define BE2             0x4000      /* Byte Enable 2 */
-#define BE1             0x2000      /* Byte Enable 1 */
-#define BE0             0x1000      /* Byte Enable 0 */
-
-/* register read/write calls.
- *
- * All these calls issue transactions to access the chip's registers. They
- * all require that the necessary lock is held to prevent accesses when the
- * chip is busy transferring packet data (RX/TX FIFO accesses).
- */
-
-/**
- * ks_check_endian - Check whether endianness of the bus is correct
- * @ks	  : The chip information
- *
- * The KS8851-16MLL EESK pin allows selecting the endianness of the 16bit
- * bus. To maintain optimum performance, the bus endianness should be set
- * such that it matches the endianness of the CPU.
- */
-
-static int ks_check_endian(struct ks_net *ks)
-{
-	u16 cider;
-
-	/*
-	 * Read CIDER register first, however read it the "wrong" way around.
-	 * If the endian strap on the KS8851-16MLL in incorrect and the chip
-	 * is operating in different endianness than the CPU, then the meaning
-	 * of BE[3:0] byte-enable bits is also swapped such that:
-	 *    BE[3,2,1,0] becomes BE[1,0,3,2]
-	 *
-	 * Luckily for us, the byte-enable bits are the top four MSbits of
-	 * the address register and the CIDER register is at offset 0xc0.
-	 * Hence, by reading address 0xc0c0, which is not impacted by endian
-	 * swapping, we assert either BE[3:2] or BE[1:0] while reading the
-	 * CIDER register.
-	 *
-	 * If the bus configuration is correct, reading 0xc0c0 asserts
-	 * BE[3:2] and this read returns 0x0000, because to read register
-	 * with bottom two LSbits of address set to 0, BE[1:0] must be
-	 * asserted.
-	 *
-	 * If the bus configuration is NOT correct, reading 0xc0c0 asserts
-	 * BE[1:0] and this read returns non-zero 0x8872 value.
-	 */
-	iowrite16(BE3 | BE2 | KS_CIDER, ks->hw_addr_cmd);
-	cider = ioread16(ks->hw_addr);
-	if (!cider)
-		return 0;
-
-	netdev_err(ks->netdev, "incorrect EESK endian strap setting\n");
-
-	return -EINVAL;
-}
-
-/**
- * ks_rdreg16 - read 16 bit register from device
- * @ks	  : The chip information
- * @offset: The register address
- *
- * Read a 16bit register from the chip, returning the result
- */
-
-static u16 ks_rdreg16(struct ks_net *ks, int offset)
-{
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	return ioread16(ks->hw_addr);
-}
-
-/**
- * ks_wrreg16 - write 16bit register value to chip
- * @ks: The chip information
- * @offset: The register address
- * @value: The value to write
- *
- */
-
-static void ks_wrreg16(struct ks_net *ks, int offset, u16 value)
-{
-	ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	iowrite16(value, ks->hw_addr);
-}
-
-/**
- * ks_inblk - read a block of data from QMU. This is called after sudo DMA mode enabled.
- * @ks: The chip state
- * @wptr: buffer address to save data
- * @len: length in byte to read
- *
- */
-static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len)
-{
-	len >>= 1;
-	while (len--)
-		*wptr++ = (u16)ioread16(ks->hw_addr);
-}
-
-/**
- * ks_outblk - write data to QMU. This is called after sudo DMA mode enabled.
- * @ks: The chip information
- * @wptr: buffer address
- * @len: length in byte to write
- *
- */
-static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len)
-{
-	len >>= 1;
-	while (len--)
-		iowrite16(*wptr++, ks->hw_addr);
-}
-
-static void ks_disable_int(struct ks_net *ks)
-{
-	ks_wrreg16(ks, KS_IER, 0x0000);
-}  /* ks_disable_int */
-
-static void ks_enable_int(struct ks_net *ks)
-{
-	ks_wrreg16(ks, KS_IER, ks->rc_ier);
-}  /* ks_enable_int */
-
-/**
- * ks_tx_fifo_space - return the available hardware buffer size.
- * @ks: The chip information
- *
- */
-static inline u16 ks_tx_fifo_space(struct ks_net *ks)
-{
-	return ks_rdreg16(ks, KS_TXMIR) & 0x1fff;
-}
-
-/**
- * ks_save_cmd_reg - save the command register from the cache.
- * @ks: The chip information
- *
- */
-static inline void ks_save_cmd_reg(struct ks_net *ks)
-{
-	/*ks8851 MLL has a bug to read back the command register.
-	* So rely on software to save the content of command register.
-	*/
-	ks->cmd_reg_cache_int = ks->cmd_reg_cache;
-}
-
-/**
- * ks_restore_cmd_reg - restore the command register from the cache and
- * 	write to hardware register.
- * @ks: The chip information
- *
- */
-static inline void ks_restore_cmd_reg(struct ks_net *ks)
-{
-	ks->cmd_reg_cache = ks->cmd_reg_cache_int;
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-}
-
-/**
- * ks_set_powermode - set power mode of the device
- * @ks: The chip information
- * @pwrmode: The power mode value to write to KS_PMECR.
- *
- * Change the power mode of the chip.
- */
-static void ks_set_powermode(struct ks_net *ks, unsigned pwrmode)
-{
-	unsigned pmecr;
-
-	netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
-
-	ks_rdreg16(ks, KS_GRR);
-	pmecr = ks_rdreg16(ks, KS_PMECR);
-	pmecr &= ~PMECR_PM_MASK;
-	pmecr |= pwrmode;
-
-	ks_wrreg16(ks, KS_PMECR, pmecr);
-}
-
-/**
- * ks_read_config - read chip configuration of bus width.
- * @ks: The chip information
- *
- */
-static void ks_read_config(struct ks_net *ks)
-{
-	u16 reg_data = 0;
-
-	/* Regardless of bus width, 8 bit read should always work.*/
-	reg_data = ks_rdreg16(ks, KS_CCR);
-
-	/* addr/data bus are multiplexed */
-	ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
-
-	/* There are garbage data when reading data from QMU,
-	depending on bus-width.
-	*/
-
-	if (reg_data & CCR_8BIT) {
-		ks->bus_width = ENUM_BUS_8BIT;
-		ks->extra_byte = 1;
-	} else if (reg_data & CCR_16BIT) {
-		ks->bus_width = ENUM_BUS_16BIT;
-		ks->extra_byte = 2;
-	} else {
-		ks->bus_width = ENUM_BUS_32BIT;
-		ks->extra_byte = 4;
-	}
-}
-
-/**
- * ks_soft_reset - issue one of the soft reset to the device
- * @ks: The device state.
- * @op: The bit(s) to set in the GRR
- *
- * Issue the relevant soft-reset command to the device's GRR register
- * specified by @op.
- *
- * Note, the delays are in there as a caution to ensure that the reset
- * has time to take effect and then complete. Since the datasheet does
- * not currently specify the exact sequence, we have chosen something
- * that seems to work with our device.
- */
-static void ks_soft_reset(struct ks_net *ks, unsigned op)
-{
-	/* Disable interrupt first */
-	ks_wrreg16(ks, KS_IER, 0x0000);
-	ks_wrreg16(ks, KS_GRR, op);
-	mdelay(10);	/* wait a short time to effect reset */
-	ks_wrreg16(ks, KS_GRR, 0);
-	mdelay(1);	/* wait for condition to clear */
-}
-
-
-static void ks_enable_qmu(struct ks_net *ks)
-{
-	u16 w;
-
-	w = ks_rdreg16(ks, KS_TXCR);
-	/* Enables QMU Transmit (TXCR). */
-	ks_wrreg16(ks, KS_TXCR, w | TXCR_TXE);
-
-	/*
-	 * RX Frame Count Threshold Enable and Auto-Dequeue RXQ Frame
-	 * Enable
-	 */
-
-	w = ks_rdreg16(ks, KS_RXQCR);
-	ks_wrreg16(ks, KS_RXQCR, w | RXQCR_RXFCTE);
-
-	/* Enables QMU Receive (RXCR1). */
-	w = ks_rdreg16(ks, KS_RXCR1);
-	ks_wrreg16(ks, KS_RXCR1, w | RXCR1_RXE);
-	ks->enabled = true;
-}  /* ks_enable_qmu */
-
-static void ks_disable_qmu(struct ks_net *ks)
-{
-	u16	w;
-
-	w = ks_rdreg16(ks, KS_TXCR);
-
-	/* Disables QMU Transmit (TXCR). */
-	w  &= ~TXCR_TXE;
-	ks_wrreg16(ks, KS_TXCR, w);
-
-	/* Disables QMU Receive (RXCR1). */
-	w = ks_rdreg16(ks, KS_RXCR1);
-	w &= ~RXCR1_RXE ;
-	ks_wrreg16(ks, KS_RXCR1, w);
-
-	ks->enabled = false;
-
-}  /* ks_disable_qmu */
-
-/**
- * ks_read_qmu - read 1 pkt data from the QMU.
- * @ks: The chip information
- * @buf: buffer address to save 1 pkt
- * @len: Pkt length
- * Here is the sequence to read 1 pkt:
- *	1. set sudo DMA mode
- *	2. read prepend data
- *	3. read pkt data
- *	4. reset sudo DMA Mode
- */
-static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len)
-{
-	u32 r =  ks->extra_byte & 0x1 ;
-	u32 w = ks->extra_byte - r;
-
-	/* 1. set sudo DMA mode */
-	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
-	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
-
-	/* 2. read prepend data */
-	/**
-	 * read 4 + extra bytes and discard them.
-	 * extra bytes for dummy, 2 for status, 2 for len
-	 */
-
-	/* use likely(r) for 8 bit access for performance */
-	if (unlikely(r))
-		ioread8(ks->hw_addr);
-	ks_inblk(ks, buf, w + 2 + 2);
-
-	/* 3. read pkt data */
-	ks_inblk(ks, buf, ALIGN(len, 4));
-
-	/* 4. reset sudo DMA Mode */
-	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
-}
-
-/**
- * ks_rcv - read multiple pkts data from the QMU.
- * @ks: The chip information
- * @netdev: The network device being opened.
- *
- * Read all of header information before reading pkt content.
- * It is not allowed only port of pkts in QMU after issuing
- * interrupt ack.
- */
-static void ks_rcv(struct ks_net *ks, struct net_device *netdev)
-{
-	u32	i;
-	struct type_frame_head *frame_hdr = ks->frame_head_info;
-	struct sk_buff *skb;
-
-	ks->frame_cnt = ks_rdreg16(ks, KS_RXFCTR) >> 8;
-
-	/* read all header information */
-	for (i = 0; i < ks->frame_cnt; i++) {
-		/* Checking Received packet status */
-		frame_hdr->sts = ks_rdreg16(ks, KS_RXFHSR);
-		/* Get packet len from hardware */
-		frame_hdr->len = ks_rdreg16(ks, KS_RXFHBCR);
-		frame_hdr++;
-	}
-
-	frame_hdr = ks->frame_head_info;
-	while (ks->frame_cnt--) {
-		if (unlikely(!(frame_hdr->sts & RXFSHR_RXFV) ||
-			     frame_hdr->len >= RX_BUF_SIZE ||
-			     frame_hdr->len <= 0)) {
-
-			/* discard an invalid packet */
-			ks_wrreg16(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_RRXEF));
-			netdev->stats.rx_dropped++;
-			if (!(frame_hdr->sts & RXFSHR_RXFV))
-				netdev->stats.rx_frame_errors++;
-			else
-				netdev->stats.rx_length_errors++;
-			frame_hdr++;
-			continue;
-		}
-
-		skb = netdev_alloc_skb(netdev, frame_hdr->len + 16);
-		if (likely(skb)) {
-			skb_reserve(skb, 2);
-			/* read data block including CRC 4 bytes */
-			ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len);
-			skb_put(skb, frame_hdr->len - 4);
-			skb->protocol = eth_type_trans(skb, netdev);
-			netif_rx(skb);
-			/* exclude CRC size */
-			netdev->stats.rx_bytes += frame_hdr->len - 4;
-			netdev->stats.rx_packets++;
-		} else {
-			ks_wrreg16(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_RRXEF));
-			netdev->stats.rx_dropped++;
-		}
-		frame_hdr++;
-	}
-}
-
-/**
- * ks_update_link_status - link status update.
- * @netdev: The network device being opened.
- * @ks: The chip information
- *
- */
-
-static void ks_update_link_status(struct net_device *netdev, struct ks_net *ks)
-{
-	/* check the status of the link */
-	u32 link_up_status;
-	if (ks_rdreg16(ks, KS_P1SR) & P1SR_LINK_GOOD) {
-		netif_carrier_on(netdev);
-		link_up_status = true;
-	} else {
-		netif_carrier_off(netdev);
-		link_up_status = false;
-	}
-	netif_dbg(ks, link, ks->netdev,
-		  "%s: %s\n", __func__, link_up_status ? "UP" : "DOWN");
-}
-
-/**
- * ks_irq - device interrupt handler
- * @irq: Interrupt number passed from the IRQ handler.
- * @pw: The private word passed to register_irq(), our struct ks_net.
- *
- * This is the handler invoked to find out what happened
- *
- * Read the interrupt status, work out what needs to be done and then clear
- * any of the interrupts that are not needed.
- */
-
-static irqreturn_t ks_irq(int irq, void *pw)
-{
-	struct net_device *netdev = pw;
-	struct ks_net *ks = netdev_priv(netdev);
-	unsigned long flags;
-	u16 status;
-
-	spin_lock_irqsave(&ks->statelock, flags);
-	/*this should be the first in IRQ handler */
-	ks_save_cmd_reg(ks);
-
-	status = ks_rdreg16(ks, KS_ISR);
-	if (unlikely(!status)) {
-		ks_restore_cmd_reg(ks);
-		spin_unlock_irqrestore(&ks->statelock, flags);
-		return IRQ_NONE;
-	}
-
-	ks_wrreg16(ks, KS_ISR, status);
-
-	if (likely(status & IRQ_RXI))
-		ks_rcv(ks, netdev);
-
-	if (unlikely(status & IRQ_LCI))
-		ks_update_link_status(netdev, ks);
-
-	if (unlikely(status & IRQ_TXI))
-		netif_wake_queue(netdev);
-
-	if (unlikely(status & IRQ_LDI)) {
-
-		u16 pmecr = ks_rdreg16(ks, KS_PMECR);
-		pmecr &= ~PMECR_WKEVT_MASK;
-		ks_wrreg16(ks, KS_PMECR, pmecr | PMECR_WKEVT_LINK);
-	}
-
-	if (unlikely(status & IRQ_RXOI))
-		ks->netdev->stats.rx_over_errors++;
-	/* this should be the last in IRQ handler*/
-	ks_restore_cmd_reg(ks);
-	spin_unlock_irqrestore(&ks->statelock, flags);
-	return IRQ_HANDLED;
-}
-
-
-/**
- * ks_net_open - open network device
- * @netdev: The network device being opened.
- *
- * Called when the network device is marked active, such as a user executing
- * 'ifconfig up' on the device.
- */
-static int ks_net_open(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	int err;
-
-#define	KS_INT_FLAGS	IRQF_TRIGGER_LOW
-	/* lock the card, even if we may not actually do anything
-	 * else at the moment.
-	 */
-
-	netif_dbg(ks, ifup, ks->netdev, "%s - entry\n", __func__);
-
-	/* reset the HW */
-	err = request_irq(netdev->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, netdev);
-
-	if (err) {
-		pr_err("Failed to request IRQ: %d: %d\n", netdev->irq, err);
-		return err;
-	}
-
-	/* wake up powermode to normal mode */
-	ks_set_powermode(ks, PMECR_PM_NORMAL);
-	mdelay(1);	/* wait for normal mode to take effect */
-
-	ks_wrreg16(ks, KS_ISR, 0xffff);
-	ks_enable_int(ks);
-	ks_enable_qmu(ks);
-	netif_start_queue(ks->netdev);
-
-	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
-
-	return 0;
-}
-
-/**
- * ks_net_stop - close network device
- * @netdev: The device being closed.
- *
- * Called to close down a network device which has been active. Cancell any
- * work, shutdown the RX and TX process and then place the chip into a low
- * power state whilst it is not being used.
- */
-static int ks_net_stop(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-
-	netif_info(ks, ifdown, netdev, "shutting down\n");
-
-	netif_stop_queue(netdev);
-
-	mutex_lock(&ks->lock);
-
-	/* turn off the IRQs and ack any outstanding */
-	ks_wrreg16(ks, KS_IER, 0x0000);
-	ks_wrreg16(ks, KS_ISR, 0xffff);
-
-	/* shutdown RX/TX QMU */
-	ks_disable_qmu(ks);
-	ks_disable_int(ks);
-
-	/* set powermode to soft power down to save power */
-	ks_set_powermode(ks, PMECR_PM_SOFTDOWN);
-	free_irq(netdev->irq, netdev);
-	mutex_unlock(&ks->lock);
-	return 0;
-}
-
-
-/**
- * ks_write_qmu - write 1 pkt data to the QMU.
- * @ks: The chip information
- * @pdata: buffer address to save 1 pkt
- * @len: Pkt length in byte
- * Here is the sequence to write 1 pkt:
- *	1. set sudo DMA mode
- *	2. write status/length
- *	3. write pkt data
- *	4. reset sudo DMA Mode
- *	5. reset sudo DMA mode
- *	6. Wait until pkt is out
- */
-static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len)
-{
-	/* start header at txb[0] to align txw entries */
-	ks->txh.txw[0] = 0;
-	ks->txh.txw[1] = cpu_to_le16(len);
-
-	/* 1. set sudo-DMA mode */
-	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
-	/* 2. write status/lenth info */
-	ks_outblk(ks, ks->txh.txw, 4);
-	/* 3. write pkt data */
-	ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4));
-	/* 4. reset sudo-DMA mode */
-	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
-	/* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */
-	ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
-	/* 6. wait until TXQCR_METFE is auto-cleared */
-	while (ks_rdreg16(ks, KS_TXQCR) & TXQCR_METFE)
-		;
-}
-
-/**
- * ks_start_xmit - transmit packet
- * @skb		: The buffer to transmit
- * @netdev	: The device used to transmit the packet.
- *
- * Called by the network layer to transmit the @skb.
- * spin_lock_irqsave is required because tx and rx should be mutual exclusive.
- * So while tx is in-progress, prevent IRQ interrupt from happenning.
- */
-static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev)
-{
-	netdev_tx_t retv = NETDEV_TX_OK;
-	struct ks_net *ks = netdev_priv(netdev);
-	unsigned long flags;
-
-	spin_lock_irqsave(&ks->statelock, flags);
-
-	/* Extra space are required:
-	*  4 byte for alignment, 4 for status/length, 4 for CRC
-	*/
-
-	if (likely(ks_tx_fifo_space(ks) >= skb->len + 12)) {
-		ks_write_qmu(ks, skb->data, skb->len);
-		/* add tx statistics */
-		netdev->stats.tx_bytes += skb->len;
-		netdev->stats.tx_packets++;
-		dev_kfree_skb(skb);
-	} else
-		retv = NETDEV_TX_BUSY;
-	spin_unlock_irqrestore(&ks->statelock, flags);
-	return retv;
-}
-
-/**
- * ks_start_rx - ready to serve pkts
- * @ks		: The chip information
- *
- */
-static void ks_start_rx(struct ks_net *ks)
-{
-	u16 cntl;
-
-	/* Enables QMU Receive (RXCR1). */
-	cntl = ks_rdreg16(ks, KS_RXCR1);
-	cntl |= RXCR1_RXE ;
-	ks_wrreg16(ks, KS_RXCR1, cntl);
-}  /* ks_start_rx */
-
-/**
- * ks_stop_rx - stop to serve pkts
- * @ks		: The chip information
- *
- */
-static void ks_stop_rx(struct ks_net *ks)
-{
-	u16 cntl;
-
-	/* Disables QMU Receive (RXCR1). */
-	cntl = ks_rdreg16(ks, KS_RXCR1);
-	cntl &= ~RXCR1_RXE ;
-	ks_wrreg16(ks, KS_RXCR1, cntl);
-
-}  /* ks_stop_rx */
-
-static unsigned long const ethernet_polynomial = CRC32_POLY_BE;
-
-static unsigned long ether_gen_crc(int length, u8 *data)
-{
-	long crc = -1;
-	while (--length >= 0) {
-		u8 current_octet = *data++;
-		int bit;
-
-		for (bit = 0; bit < 8; bit++, current_octet >>= 1) {
-			crc = (crc << 1) ^
-				((crc < 0) ^ (current_octet & 1) ?
-			ethernet_polynomial : 0);
-		}
-	}
-	return (unsigned long)crc;
-}  /* ether_gen_crc */
-
-/**
-* ks_set_grpaddr - set multicast information
-* @ks : The chip information
-*/
-
-static void ks_set_grpaddr(struct ks_net *ks)
-{
-	u8	i;
-	u32	index, position, value;
-
-	memset(ks->mcast_bits, 0, sizeof(u8) * HW_MCAST_SIZE);
-
-	for (i = 0; i < ks->mcast_lst_size; i++) {
-		position = (ether_gen_crc(6, ks->mcast_lst[i]) >> 26) & 0x3f;
-		index = position >> 3;
-		value = 1 << (position & 7);
-		ks->mcast_bits[index] |= (u8)value;
-	}
-
-	for (i  = 0; i < HW_MCAST_SIZE; i++) {
-		if (i & 1) {
-			ks_wrreg16(ks, (u16)((KS_MAHTR0 + i) & ~1),
-				(ks->mcast_bits[i] << 8) |
-				ks->mcast_bits[i - 1]);
-		}
-	}
-}  /* ks_set_grpaddr */
-
-/**
-* ks_clear_mcast - clear multicast information
-*
-* @ks : The chip information
-* This routine removes all mcast addresses set in the hardware.
-*/
-
-static void ks_clear_mcast(struct ks_net *ks)
-{
-	u16	i, mcast_size;
-	for (i = 0; i < HW_MCAST_SIZE; i++)
-		ks->mcast_bits[i] = 0;
-
-	mcast_size = HW_MCAST_SIZE >> 2;
-	for (i = 0; i < mcast_size; i++)
-		ks_wrreg16(ks, KS_MAHTR0 + (2*i), 0);
-}
-
-static void ks_set_promis(struct ks_net *ks, u16 promiscuous_mode)
-{
-	u16		cntl;
-	ks->promiscuous = promiscuous_mode;
-	ks_stop_rx(ks);  /* Stop receiving for reconfiguration */
-	cntl = ks_rdreg16(ks, KS_RXCR1);
-
-	cntl &= ~RXCR1_FILTER_MASK;
-	if (promiscuous_mode)
-		/* Enable Promiscuous mode */
-		cntl |= RXCR1_RXAE | RXCR1_RXINVF;
-	else
-		/* Disable Promiscuous mode (default normal mode) */
-		cntl |= RXCR1_RXPAFMA;
-
-	ks_wrreg16(ks, KS_RXCR1, cntl);
-
-	if (ks->enabled)
-		ks_start_rx(ks);
-
-}  /* ks_set_promis */
-
-static void ks_set_mcast(struct ks_net *ks, u16 mcast)
-{
-	u16	cntl;
-
-	ks->all_mcast = mcast;
-	ks_stop_rx(ks);  /* Stop receiving for reconfiguration */
-	cntl = ks_rdreg16(ks, KS_RXCR1);
-	cntl &= ~RXCR1_FILTER_MASK;
-	if (mcast)
-		/* Enable "Perfect with Multicast address passed mode" */
-		cntl |= (RXCR1_RXAE | RXCR1_RXMAFMA | RXCR1_RXPAFMA);
-	else
-		/**
-		 * Disable "Perfect with Multicast address passed
-		 * mode" (normal mode).
-		 */
-		cntl |= RXCR1_RXPAFMA;
-
-	ks_wrreg16(ks, KS_RXCR1, cntl);
-
-	if (ks->enabled)
-		ks_start_rx(ks);
-}  /* ks_set_mcast */
-
-static void ks_set_rx_mode(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	struct netdev_hw_addr *ha;
-
-	/* Turn on/off promiscuous mode. */
-	if ((netdev->flags & IFF_PROMISC) == IFF_PROMISC)
-		ks_set_promis(ks,
-			(u16)((netdev->flags & IFF_PROMISC) == IFF_PROMISC));
-	/* Turn on/off all mcast mode. */
-	else if ((netdev->flags & IFF_ALLMULTI) == IFF_ALLMULTI)
-		ks_set_mcast(ks,
-			(u16)((netdev->flags & IFF_ALLMULTI) == IFF_ALLMULTI));
-	else
-		ks_set_promis(ks, false);
-
-	if ((netdev->flags & IFF_MULTICAST) && netdev_mc_count(netdev)) {
-		if (netdev_mc_count(netdev) <= MAX_MCAST_LST) {
-			int i = 0;
-
-			netdev_for_each_mc_addr(ha, netdev) {
-				if (i >= MAX_MCAST_LST)
-					break;
-				memcpy(ks->mcast_lst[i++], ha->addr, ETH_ALEN);
-			}
-			ks->mcast_lst_size = (u8)i;
-			ks_set_grpaddr(ks);
-		} else {
-			/**
-			 * List too big to support so
-			 * turn on all mcast mode.
-			 */
-			ks->mcast_lst_size = MAX_MCAST_LST;
-			ks_set_mcast(ks, true);
-		}
-	} else {
-		ks->mcast_lst_size = 0;
-		ks_clear_mcast(ks);
-	}
-} /* ks_set_rx_mode */
-
-static void ks_set_mac(struct ks_net *ks, u8 *data)
-{
-	u16 *pw = (u16 *)data;
-	u16 w, u;
-
-	ks_stop_rx(ks);  /* Stop receiving for reconfiguration */
-
-	u = *pw++;
-	w = ((u & 0xFF) << 8) | ((u >> 8) & 0xFF);
-	ks_wrreg16(ks, KS_MARH, w);
-
-	u = *pw++;
-	w = ((u & 0xFF) << 8) | ((u >> 8) & 0xFF);
-	ks_wrreg16(ks, KS_MARM, w);
-
-	u = *pw;
-	w = ((u & 0xFF) << 8) | ((u >> 8) & 0xFF);
-	ks_wrreg16(ks, KS_MARL, w);
-
-	memcpy(ks->mac_addr, data, ETH_ALEN);
-
-	if (ks->enabled)
-		ks_start_rx(ks);
-}
-
-static int ks_set_mac_address(struct net_device *netdev, void *paddr)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	struct sockaddr *addr = paddr;
-	u8 *da;
-
-	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
-
-	da = (u8 *)netdev->dev_addr;
-
-	ks_set_mac(ks, da);
-	return 0;
-}
-
-static int ks_net_ioctl(struct net_device *netdev, struct ifreq *req, int cmd)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-
-	if (!netif_running(netdev))
-		return -EINVAL;
-
-	return generic_mii_ioctl(&ks->mii, if_mii(req), cmd, NULL);
-}
-
-static const struct net_device_ops ks_netdev_ops = {
-	.ndo_open		= ks_net_open,
-	.ndo_stop		= ks_net_stop,
-	.ndo_do_ioctl		= ks_net_ioctl,
-	.ndo_start_xmit		= ks_start_xmit,
-	.ndo_set_mac_address	= ks_set_mac_address,
-	.ndo_set_rx_mode	= ks_set_rx_mode,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-/* ethtool support */
-
-static void ks_get_drvinfo(struct net_device *netdev,
-			       struct ethtool_drvinfo *di)
-{
-	strlcpy(di->driver, DRV_NAME, sizeof(di->driver));
-	strlcpy(di->version, "1.00", sizeof(di->version));
-	strlcpy(di->bus_info, dev_name(netdev->dev.parent),
-		sizeof(di->bus_info));
-}
-
-static u32 ks_get_msglevel(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	return ks->msg_enable;
-}
-
-static void ks_set_msglevel(struct net_device *netdev, u32 to)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	ks->msg_enable = to;
-}
-
-static int ks_get_link_ksettings(struct net_device *netdev,
-				 struct ethtool_link_ksettings *cmd)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-
-	mii_ethtool_get_link_ksettings(&ks->mii, cmd);
-
-	return 0;
-}
-
-static int ks_set_link_ksettings(struct net_device *netdev,
-				 const struct ethtool_link_ksettings *cmd)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	return mii_ethtool_set_link_ksettings(&ks->mii, cmd);
-}
-
-static u32 ks_get_link(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	return mii_link_ok(&ks->mii);
-}
-
-static int ks_nway_reset(struct net_device *netdev)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	return mii_nway_restart(&ks->mii);
-}
-
-static const struct ethtool_ops ks_ethtool_ops = {
-	.get_drvinfo	= ks_get_drvinfo,
-	.get_msglevel	= ks_get_msglevel,
-	.set_msglevel	= ks_set_msglevel,
-	.get_link	= ks_get_link,
-	.nway_reset	= ks_nway_reset,
-	.get_link_ksettings = ks_get_link_ksettings,
-	.set_link_ksettings = ks_set_link_ksettings,
-};
-
-/* MII interface controls */
-
-/**
- * ks_phy_reg - convert MII register into a KS8851 register
- * @reg: MII register number.
- *
- * Return the KS8851 register number for the corresponding MII PHY register
- * if possible. Return zero if the MII register has no direct mapping to the
- * KS8851 register set.
- */
-static int ks_phy_reg(int reg)
-{
-	switch (reg) {
-	case MII_BMCR:
-		return KS_P1MBCR;
-	case MII_BMSR:
-		return KS_P1MBSR;
-	case MII_PHYSID1:
-		return KS_PHY1ILR;
-	case MII_PHYSID2:
-		return KS_PHY1IHR;
-	case MII_ADVERTISE:
-		return KS_P1ANAR;
-	case MII_LPA:
-		return KS_P1ANLPR;
-	}
-
-	return 0x0;
-}
-
-/**
- * ks_phy_read - MII interface PHY register read.
- * @netdev: The network device the PHY is on.
- * @phy_addr: Address of PHY (ignored as we only have one)
- * @reg: The register to read.
- *
- * This call reads data from the PHY register specified in @reg. Since the
- * device does not support all the MII registers, the non-existent values
- * are always returned as zero.
- *
- * We return zero for unsupported registers as the MII code does not check
- * the value returned for any error status, and simply returns it to the
- * caller. The mii-tool that the driver was tested with takes any -ve error
- * as real PHY capabilities, thus displaying incorrect data to the user.
- */
-static int ks_phy_read(struct net_device *netdev, int phy_addr, int reg)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	int ksreg;
-	int result;
-
-	ksreg = ks_phy_reg(reg);
-	if (!ksreg)
-		return 0x0;	/* no error return allowed, so use zero */
-
-	mutex_lock(&ks->lock);
-	result = ks_rdreg16(ks, ksreg);
-	mutex_unlock(&ks->lock);
-
-	return result;
-}
-
-static void ks_phy_write(struct net_device *netdev,
-			     int phy, int reg, int value)
-{
-	struct ks_net *ks = netdev_priv(netdev);
-	int ksreg;
-
-	ksreg = ks_phy_reg(reg);
-	if (ksreg) {
-		mutex_lock(&ks->lock);
-		ks_wrreg16(ks, ksreg, value);
-		mutex_unlock(&ks->lock);
-	}
-}
-
-/**
- * ks_read_selftest - read the selftest memory info.
- * @ks: The device state
- *
- * Read and check the TX/RX memory selftest information.
- */
-static int ks_read_selftest(struct ks_net *ks)
-{
-	unsigned both_done = MBIR_TXMBF | MBIR_RXMBF;
-	int ret = 0;
-	unsigned rd;
-
-	rd = ks_rdreg16(ks, KS_MBIR);
-
-	if ((rd & both_done) != both_done) {
-		netdev_warn(ks->netdev, "Memory selftest not finished\n");
-		return 0;
-	}
-
-	if (rd & MBIR_TXMBFA) {
-		netdev_err(ks->netdev, "TX memory selftest fails\n");
-		ret |= 1;
-	}
-
-	if (rd & MBIR_RXMBFA) {
-		netdev_err(ks->netdev, "RX memory selftest fails\n");
-		ret |= 2;
-	}
-
-	netdev_info(ks->netdev, "the selftest passes\n");
-	return ret;
-}
-
-static void ks_setup(struct ks_net *ks)
-{
-	u16	w;
-
-	/**
-	 * Configure QMU Transmit
-	 */
-
-	/* Setup Transmit Frame Data Pointer Auto-Increment (TXFDPR) */
-	ks_wrreg16(ks, KS_TXFDPR, TXFDPR_TXFPAI);
-
-	/* Setup Receive Frame Data Pointer Auto-Increment */
-	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
-
-	/* Setup Receive Frame Threshold - 1 frame (RXFCTFC) */
-	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_RXFCT_MASK);
-
-	/* Setup RxQ Command Control (RXQCR) */
-	ks->rc_rxqcr = RXQCR_CMD_CNTL;
-	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
-
-	/**
-	 * set the force mode to half duplex, default is full duplex
-	 *  because if the auto-negotiation fails, most switch uses
-	 *  half-duplex.
-	 */
-
-	w = ks_rdreg16(ks, KS_P1MBCR);
-	w &= ~BMCR_FULLDPLX;
-	ks_wrreg16(ks, KS_P1MBCR, w);
-
-	w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP;
-	ks_wrreg16(ks, KS_TXCR, w);
-
-	w = RXCR1_RXFCE | RXCR1_RXBE | RXCR1_RXUE | RXCR1_RXME | RXCR1_RXIPFCC;
-
-	if (ks->promiscuous)         /* bPromiscuous */
-		w |= (RXCR1_RXAE | RXCR1_RXINVF);
-	else if (ks->all_mcast) /* Multicast address passed mode */
-		w |= (RXCR1_RXAE | RXCR1_RXMAFMA | RXCR1_RXPAFMA);
-	else                                   /* Normal mode */
-		w |= RXCR1_RXPAFMA;
-
-	ks_wrreg16(ks, KS_RXCR1, w);
-}  /*ks_setup */
-
-
-static void ks_setup_int(struct ks_net *ks)
-{
-	ks->rc_ier = 0x00;
-	/* Clear the interrupts status of the hardware. */
-	ks_wrreg16(ks, KS_ISR, 0xffff);
-
-	/* Enables the interrupts of the hardware. */
-	ks->rc_ier = (IRQ_LCI | IRQ_TXI | IRQ_RXI);
-}  /* ks_setup_int */
-
-static int ks_hw_init(struct ks_net *ks)
-{
-#define	MHEADER_SIZE	(sizeof(struct type_frame_head) * MAX_RECV_FRAMES)
-	ks->promiscuous = 0;
-	ks->all_mcast = 0;
-	ks->mcast_lst_size = 0;
-
-	ks->frame_head_info = devm_kmalloc(&ks->pdev->dev, MHEADER_SIZE,
-					   GFP_KERNEL);
-	if (!ks->frame_head_info)
-		return false;
-
-	ks_set_mac(ks, KS_DEFAULT_MAC_ADDRESS);
-	return true;
-}
-
-#if defined(CONFIG_OF)
-static const struct of_device_id ks8851_ml_dt_ids[] = {
-	{ .compatible = "micrel,ks8851-mll" },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, ks8851_ml_dt_ids);
-#endif
-
-static int ks8851_probe(struct platform_device *pdev)
-{
-	int err;
-	struct net_device *netdev;
-	struct ks_net *ks;
-	u16 id, data;
-	const char *mac;
-
-	netdev = alloc_etherdev(sizeof(struct ks_net));
-	if (!netdev)
-		return -ENOMEM;
-
-	SET_NETDEV_DEV(netdev, &pdev->dev);
-
-	ks = netdev_priv(netdev);
-	ks->netdev = netdev;
-
-	ks->hw_addr = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(ks->hw_addr)) {
-		err = PTR_ERR(ks->hw_addr);
-		goto err_free;
-	}
-
-	ks->hw_addr_cmd = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(ks->hw_addr_cmd)) {
-		err = PTR_ERR(ks->hw_addr_cmd);
-		goto err_free;
-	}
-
-	err = ks_check_endian(ks);
-	if (err)
-		goto err_free;
-
-	netdev->irq = platform_get_irq(pdev, 0);
-
-	if ((int)netdev->irq < 0) {
-		err = netdev->irq;
-		goto err_free;
-	}
-
-	ks->pdev = pdev;
-
-	mutex_init(&ks->lock);
-	spin_lock_init(&ks->statelock);
-
-	netdev->netdev_ops = &ks_netdev_ops;
-	netdev->ethtool_ops = &ks_ethtool_ops;
-
-	/* setup mii state */
-	ks->mii.dev             = netdev;
-	ks->mii.phy_id          = 1,
-	ks->mii.phy_id_mask     = 1;
-	ks->mii.reg_num_mask    = 0xf;
-	ks->mii.mdio_read       = ks_phy_read;
-	ks->mii.mdio_write      = ks_phy_write;
-
-	netdev_info(netdev, "message enable is %d\n", msg_enable);
-	/* set the default message enable */
-	ks->msg_enable = netif_msg_init(msg_enable, (NETIF_MSG_DRV |
-						     NETIF_MSG_PROBE |
-						     NETIF_MSG_LINK));
-	ks_read_config(ks);
-
-	/* simple check for a valid chip being connected to the bus */
-	if ((ks_rdreg16(ks, KS_CIDER) & ~CIDER_REV_MASK) != CIDER_ID) {
-		netdev_err(netdev, "failed to read device ID\n");
-		err = -ENODEV;
-		goto err_free;
-	}
-
-	if (ks_read_selftest(ks)) {
-		netdev_err(netdev, "failed to read device ID\n");
-		err = -ENODEV;
-		goto err_free;
-	}
-
-	err = register_netdev(netdev);
-	if (err)
-		goto err_free;
-
-	platform_set_drvdata(pdev, netdev);
-
-	ks_soft_reset(ks, GRR_GSR);
-	ks_hw_init(ks);
-	ks_disable_qmu(ks);
-	ks_setup(ks);
-	ks_setup_int(ks);
-
-	data = ks_rdreg16(ks, KS_OBCR);
-	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16mA);
-
-	/* overwriting the default MAC address */
-	if (pdev->dev.of_node) {
-		mac = of_get_mac_address(pdev->dev.of_node);
-		if (!IS_ERR(mac))
-			ether_addr_copy(ks->mac_addr, mac);
-	} else {
-		struct ks8851_mll_platform_data *pdata;
-
-		pdata = dev_get_platdata(&pdev->dev);
-		if (!pdata) {
-			netdev_err(netdev, "No platform data\n");
-			err = -ENODEV;
-			goto err_pdata;
-		}
-		memcpy(ks->mac_addr, pdata->mac_addr, ETH_ALEN);
-	}
-	if (!is_valid_ether_addr(ks->mac_addr)) {
-		/* Use random MAC address if none passed */
-		eth_random_addr(ks->mac_addr);
-		netdev_info(netdev, "Using random mac address\n");
-	}
-	netdev_info(netdev, "Mac address is: %pM\n", ks->mac_addr);
-
-	memcpy(netdev->dev_addr, ks->mac_addr, ETH_ALEN);
-
-	ks_set_mac(ks, netdev->dev_addr);
-
-	id = ks_rdreg16(ks, KS_CIDER);
-
-	netdev_info(netdev, "Found chip, family: 0x%x, id: 0x%x, rev: 0x%x\n",
-		    (id >> 8) & 0xff, (id >> 4) & 0xf, (id >> 1) & 0x7);
-	return 0;
-
-err_pdata:
-	unregister_netdev(netdev);
-err_free:
-	free_netdev(netdev);
-	return err;
-}
-
-static int ks8851_remove(struct platform_device *pdev)
-{
-	struct net_device *netdev = platform_get_drvdata(pdev);
-
-	unregister_netdev(netdev);
-	free_netdev(netdev);
-	return 0;
-
-}
-
-static struct platform_driver ks8851_platform_driver = {
-	.driver = {
-		.name = DRV_NAME,
-		.of_match_table	= of_match_ptr(ks8851_ml_dt_ids),
-	},
-	.probe = ks8851_probe,
-	.remove = ks8851_remove,
-};
-
-module_platform_driver(ks8851_platform_driver);
-
-MODULE_DESCRIPTION("KS8851 MLL Network driver");
-MODULE_AUTHOR("David Choi <david.choi@micrel.com>");
-MODULE_LICENSE("GPL");
-module_param_named(message, msg_enable, int, 0);
-MODULE_PARM_DESC(message, "Message verbosity level (0=none, 31=all)");
-
-- 
cgit v1.2.3


From 2421ee24777e9f7effc4b6db29276eced7ca2114 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:08 +0800
Subject: net: hns3: remove an unnecessary 'goto' in hclge_init_ae_dev()

Remove the redundant 'goto' and return -ENOMEM directly, when
allocating memory for 'hdev' fails in hclge_init_ae_dev().

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 7c9f2ba1f272..0e36f037f69c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -9928,10 +9928,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	int ret;
 
 	hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL);
-	if (!hdev) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!hdev)
+		return -ENOMEM;
 
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
-- 
cgit v1.2.3


From 9516352150c0cb896b3de3997b1dfe43fb96d8a5 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:09 +0800
Subject: net: hns3: add a missing mutex destroy in hclge_init_ad_dev()

Add a mutex destroy call in hclge_init_ae_dev() when fails.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0e36f037f69c..7d5c304bd6b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -10108,6 +10108,7 @@ err_pci_uninit:
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 out:
+	mutex_destroy(&hdev->vport_lock);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 9f5a9816065f92683fd5f23cd8ec98719f20144f Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:10 +0800
Subject: net: hns3: refactor hclge_config_tso()

Since parameters 'tso_mss_min' and 'tso_mss_max' only indicate
the minimum and maximum MSS, the hnae3_set_field() calls are
meaningless, remove them and change the type of these two
parameters to u16.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 7d5c304bd6b1..35e5cb87f48c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1429,26 +1429,17 @@ static int hclge_configure(struct hclge_dev *hdev)
 	return ret;
 }
 
-static int hclge_config_tso(struct hclge_dev *hdev, unsigned int tso_mss_min,
-			    unsigned int tso_mss_max)
+static int hclge_config_tso(struct hclge_dev *hdev, u16 tso_mss_min,
+			    u16 tso_mss_max)
 {
 	struct hclge_cfg_tso_status_cmd *req;
 	struct hclge_desc desc;
-	u16 tso_mss;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false);
 
 	req = (struct hclge_cfg_tso_status_cmd *)desc.data;
-
-	tso_mss = 0;
-	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-			HCLGE_TSO_MSS_MIN_S, tso_mss_min);
-	req->tso_mss_min = cpu_to_le16(tso_mss);
-
-	tso_mss = 0;
-	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-			HCLGE_TSO_MSS_MIN_S, tso_mss_max);
-	req->tso_mss_max = cpu_to_le16(tso_mss);
+	req->tso_mss_min = cpu_to_le16(tso_mss_min);
+	req->tso_mss_max = cpu_to_le16(tso_mss_max);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
-- 
cgit v1.2.3


From 5caa039f320d023fb2a40c8c7ededfca3ce85501 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:11 +0800
Subject: net: hns3: refactor hclge_query_bd_num_cmd_send()

In order to improve code maintainability and readability, rewrite
the process of BDs' initialization in hclge_query_bd_num_cmd_send().

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 35e5cb87f48c..e9b0e1c00970 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -10723,16 +10723,19 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 
 int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc)
 {
-	/*prepare 4 commands to query DFX BD number*/
-	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
-	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
+	int i;
+
+	/* initialize command BD except the last one */
+	for (i = 0; i < HCLGE_GET_DFX_REG_TYPE_CNT - 1; i++) {
+		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM,
+					   true);
+		desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	}
+
+	/* initialize the last command BD */
+	hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_DFX_BD_NUM, true);
 
-	return hclge_cmd_send(&hdev->hw, desc, 4);
+	return hclge_cmd_send(&hdev->hw, desc, HCLGE_GET_DFX_REG_TYPE_CNT);
 }
 
 static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev,
-- 
cgit v1.2.3


From 639d84d0c4281e6d8814bb2cc230bfe7ccf5019d Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:12 +0800
Subject: net: hns3: modify an incorrect type in struct
 hclge_cfg_gro_status_cmd

Modify field .gro_en in struct hclge_cfg_gro_status_cmd to u8
according to the UM, otherwise, it will overwrite the reserved
byte which may be used for other purpose.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index e3bab8f3847f..463f29151ef0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -884,8 +884,8 @@ struct hclge_cfg_tso_status_cmd {
 
 #define HCLGE_GRO_EN_B		0
 struct hclge_cfg_gro_status_cmd {
-	__le16 gro_en;
-	u8 rsv[22];
+	u8 gro_en;
+	u8 rsv[23];
 };
 
 #define HCLGE_TSO_MSS_MIN	256
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e9b0e1c00970..1e4f28518d69 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1456,7 +1456,7 @@ static int hclge_config_gro(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GRO_GENERIC_CONFIG, false);
 	req = (struct hclge_cfg_gro_status_cmd *)desc.data;
 
-	req->gro_en = cpu_to_le16(en ? 1 : 0);
+	req->gro_en = en ? 1 : 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
-- 
cgit v1.2.3


From fb9e44d63dc33b455a50b772a37faf43e793da91 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:13 +0800
Subject: net: hns3: modify an incorrect type in struct
 hclgevf_cfg_gro_status_cmd

Modify field .gro_en in struct hclgevf_cfg_gro_status_cmd to u8
according to the UM, otherwise, it will overwrite the reserved
byte which may be used for other purpose.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h  | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index f830eef02e5c..40d6e602ab51 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -161,8 +161,8 @@ struct hclgevf_query_res_cmd {
 
 #define HCLGEVF_GRO_EN_B               0
 struct hclgevf_cfg_gro_status_cmd {
-	__le16 gro_en;
-	u8 rsv[22];
+	u8 gro_en;
+	u8 rsv[23];
 };
 
 #define HCLGEVF_RSS_DEFAULT_OUTPORT_B	4
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 59fcb80671c8..be5789bb5ddd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2403,7 +2403,7 @@ static int hclgevf_config_gro(struct hclgevf_dev *hdev, bool en)
 				     false);
 	req = (struct hclgevf_cfg_gro_status_cmd *)desc.data;
 
-	req->gro_en = cpu_to_le16(en ? 1 : 0);
+	req->gro_en = en ? 1 : 0;
 
 	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
-- 
cgit v1.2.3


From 5e86178dcead4941fcdadc963f31ed4e859e58ce Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:14 +0800
Subject: net: hns3: remove some unused fields in struct hns3_nic_priv

Remove some fileds which defined in struct hns3_nic_priv,
but not used, and remove the related definition of struct
hns3_udp_tunnel and enum hns3_udp_tnl_type.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 22 ----------------------
 1 file changed, 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 60f82ad89957..66cd4395f781 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -469,21 +469,8 @@ struct hns3_enet_tqp_vector {
 	unsigned long last_jiffies;
 } ____cacheline_internodealigned_in_smp;
 
-enum hns3_udp_tnl_type {
-	HNS3_UDP_TNL_VXLAN,
-	HNS3_UDP_TNL_GENEVE,
-	HNS3_UDP_TNL_MAX,
-};
-
-struct hns3_udp_tunnel {
-	u16 dst_port;
-	int used;
-};
-
 struct hns3_nic_priv {
 	struct hnae3_handle *ae_handle;
-	u32 enet_ver;
-	u32 port_id;
 	struct net_device *netdev;
 	struct device *dev;
 
@@ -495,19 +482,10 @@ struct hns3_nic_priv {
 	struct hns3_enet_tqp_vector *tqp_vector;
 	u16 vector_num;
 
-	/* The most recently read link state */
-	int link;
 	u64 tx_timeout_count;
 
 	unsigned long state;
 
-	struct timer_list service_timer;
-
-	struct work_struct service_task;
-
-	struct notifier_block notifier_block;
-	/* Vxlan/Geneve information */
-	struct hns3_udp_tunnel udp_tnl[HNS3_UDP_TNL_MAX];
 	struct hns3_enet_coalesce tx_coal;
 	struct hns3_enet_coalesce rx_coal;
 };
-- 
cgit v1.2.3


From c496299e0677fe8c12af8fd233783df1c8aa9c4e Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:15 +0800
Subject: net: hns3; remove unused HNAE3_RESTORE_CLIENT in enum
 hnae3_reset_notify_type

Remove HNAE3_RESTORE_CLIENT which is not needed now.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 7506cabaa16e..0a4aac44efa5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -145,7 +145,6 @@ enum hnae3_reset_notify_type {
 	HNAE3_DOWN_CLIENT,
 	HNAE3_INIT_CLIENT,
 	HNAE3_UNINIT_CLIENT,
-	HNAE3_RESTORE_CLIENT,
 };
 
 enum hnae3_hw_error_type {
-- 
cgit v1.2.3


From 4828b5766a69e93ca76b15f820c97f03ebd3a48c Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:16 +0800
Subject: net: hns3: remove unused struct hnae3_unic_private_info

Since field .uinfo in struct hnae3_handle never be used,
so remove it and its structure definition.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 0a4aac44efa5..d041cac9a487 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -621,16 +621,6 @@ struct hnae3_roce_private_info {
 	unsigned long state;
 };
 
-struct hnae3_unic_private_info {
-	struct net_device *netdev;
-	u16 rx_buf_len;
-	u16 num_tx_desc;
-	u16 num_rx_desc;
-
-	u16 num_tqps;	/* total number of tqps in this handle */
-	struct hnae3_queue **tqp;  /* array base of all TQPs of this instance */
-};
-
 #define HNAE3_SUPPORT_APP_LOOPBACK    BIT(0)
 #define HNAE3_SUPPORT_PHY_LOOPBACK    BIT(1)
 #define HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK	BIT(2)
@@ -656,7 +646,6 @@ struct hnae3_handle {
 	union {
 		struct net_device *netdev; /* first member */
 		struct hnae3_knic_private_info kinfo;
-		struct hnae3_unic_private_info uinfo;
 		struct hnae3_roce_private_info rinfo;
 	};
 
-- 
cgit v1.2.3


From 9cee2e8d303940a413d20c5d275bdaf418b09b17 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:17 +0800
Subject: net: hns3: remove two duplicated register macros in hclgevf_main.h

HCLGEVF_CMDQ_INTR_SRC_REG and HCLGEVF_CMDQ_INTR_STS_REG are same
as HCLGEVF_VECTOR0_CMDQ_SRC_REG and HCLGEVF_VECTOR0_CMDQ_STAT_REG,
replace the former with the latter, and rename macro
HCLGEVF_VECTOR0_CMDQ_STAT_REG since 'stat' is not abbreviation of
'state'.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 6 +++---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 4 +---
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index be5789bb5ddd..a8c0e79901f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -46,7 +46,7 @@ static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG,
 					 HCLGEVF_CMDQ_RX_TAIL_REG,
 					 HCLGEVF_CMDQ_RX_HEAD_REG,
 					 HCLGEVF_VECTOR0_CMDQ_SRC_REG,
-					 HCLGEVF_CMDQ_INTR_STS_REG,
+					 HCLGEVF_VECTOR0_CMDQ_STATE_REG,
 					 HCLGEVF_CMDQ_INTR_EN_REG,
 					 HCLGEVF_CMDQ_INTR_GEN_REG};
 
@@ -1826,7 +1826,7 @@ static void hclgevf_dump_rst_info(struct hclgevf_dev *hdev)
 	dev_info(&hdev->pdev->dev, "vector0 interrupt enable status: 0x%x\n",
 		 hclgevf_read_dev(&hdev->hw, HCLGEVF_MISC_VECTOR_REG_BASE));
 	dev_info(&hdev->pdev->dev, "vector0 interrupt status: 0x%x\n",
-		 hclgevf_read_dev(&hdev->hw, HCLGEVF_VECTOR0_CMDQ_STAT_REG));
+		 hclgevf_read_dev(&hdev->hw, HCLGEVF_VECTOR0_CMDQ_STATE_REG));
 	dev_info(&hdev->pdev->dev, "handshake status: 0x%x\n",
 		 hclgevf_read_dev(&hdev->hw, HCLGEVF_CMDQ_TX_DEPTH_REG));
 	dev_info(&hdev->pdev->dev, "function reset status: 0x%x\n",
@@ -2250,7 +2250,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 
 	/* fetch the events from their corresponding regs */
 	cmdq_stat_reg = hclgevf_read_dev(&hdev->hw,
-					 HCLGEVF_VECTOR0_CMDQ_STAT_REG);
+					 HCLGEVF_VECTOR0_CMDQ_STATE_REG);
 
 	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) {
 		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index f19583c4bc9b..738de124cfc4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -42,8 +42,6 @@
 #define HCLGEVF_CMDQ_RX_DEPTH_REG		0x27020
 #define HCLGEVF_CMDQ_RX_TAIL_REG		0x27024
 #define HCLGEVF_CMDQ_RX_HEAD_REG		0x27028
-#define HCLGEVF_CMDQ_INTR_SRC_REG		0x27100
-#define HCLGEVF_CMDQ_INTR_STS_REG		0x27104
 #define HCLGEVF_CMDQ_INTR_EN_REG		0x27108
 #define HCLGEVF_CMDQ_INTR_GEN_REG		0x2710C
 
@@ -88,7 +86,7 @@
 /* Vector0 interrupt CMDQ event source register(RW) */
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
 /* Vector0 interrupt CMDQ event status register(RO) */
-#define HCLGEVF_VECTOR0_CMDQ_STAT_REG	0x27104
+#define HCLGEVF_VECTOR0_CMDQ_STATE_REG	0x27104
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B	1
 /* RST register bits for RESET event */
-- 
cgit v1.2.3


From 7c6643cac0ed78395ec10fe5b3b279e61b0ee51f Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:18 +0800
Subject: net: hns3: remove some unused fields in struct hclge_dev

Remove some fields in struct hclge_dev which have not been used.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 913c4f677404..46e6e0fef3ba 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -771,12 +771,6 @@ struct hclge_dev {
 	u16 num_roce_msi;	/* Num of roce vectors for this PF */
 	int roce_base_vector;
 
-	u16 pending_udp_bitmap;
-
-	u16 rx_itr_default;
-	u16 tx_itr_default;
-
-	u16 adminq_work_limit; /* Num of admin receive queue desc to process */
 	unsigned long service_timer_period;
 	unsigned long service_timer_previous;
 	struct timer_list reset_timer;
-- 
cgit v1.2.3


From ead38a8537bf87228917f23c2131c7a020fe0951 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 May 2020 21:48:19 +0800
Subject: net: hns3: print out speed info when parsing speed fails

When calling hclge_parse_speed() fails, printing out the speed is
helpful for debugging.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 1e4f28518d69..96bfad52630d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1387,7 +1387,8 @@ static int hclge_configure(struct hclge_dev *hdev)
 
 	ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
 	if (ret) {
-		dev_err(&hdev->pdev->dev, "Get wrong speed ret=%d.\n", ret);
+		dev_err(&hdev->pdev->dev, "failed to parse speed %u, ret = %d\n",
+			cfg.default_speed, ret);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From c28481a88cb38a3e1b7b533f53eb82e5e34f7597 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 11 Mar 2020 09:37:40 +0100
Subject: i40e: Use scnprintf() for avoiding potential buffer overflow

Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit.  Fix it by replacing with scnprintf().

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ea7395b391e5..5d807c8004f8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -14486,29 +14486,29 @@ static void i40e_print_features(struct i40e_pf *pf)
 
 	i = snprintf(buf, INFO_STRING_LEN, "Features: PF-id[%d]", hw->pf_id);
 #ifdef CONFIG_PCI_IOV
-	i += snprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs);
+	i += scnprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs);
 #endif
-	i += snprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
+	i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
 		      pf->hw.func_caps.num_vsis,
 		      pf->vsi[pf->lan_vsi]->num_queue_pairs);
 	if (pf->flags & I40E_FLAG_RSS_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " RSS");
+		i += scnprintf(&buf[i], REMAIN(i), " RSS");
 	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " FD_ATR");
+		i += scnprintf(&buf[i], REMAIN(i), " FD_ATR");
 	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
-		i += snprintf(&buf[i], REMAIN(i), " FD_SB");
-		i += snprintf(&buf[i], REMAIN(i), " NTUPLE");
+		i += scnprintf(&buf[i], REMAIN(i), " FD_SB");
+		i += scnprintf(&buf[i], REMAIN(i), " NTUPLE");
 	}
 	if (pf->flags & I40E_FLAG_DCB_CAPABLE)
-		i += snprintf(&buf[i], REMAIN(i), " DCB");
-	i += snprintf(&buf[i], REMAIN(i), " VxLAN");
-	i += snprintf(&buf[i], REMAIN(i), " Geneve");
+		i += scnprintf(&buf[i], REMAIN(i), " DCB");
+	i += scnprintf(&buf[i], REMAIN(i), " VxLAN");
+	i += scnprintf(&buf[i], REMAIN(i), " Geneve");
 	if (pf->flags & I40E_FLAG_PTP)
-		i += snprintf(&buf[i], REMAIN(i), " PTP");
+		i += scnprintf(&buf[i], REMAIN(i), " PTP");
 	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
-		i += snprintf(&buf[i], REMAIN(i), " VEB");
+		i += scnprintf(&buf[i], REMAIN(i), " VEB");
 	else
-		i += snprintf(&buf[i], REMAIN(i), " VEPA");
+		i += scnprintf(&buf[i], REMAIN(i), " VEPA");
 
 	dev_info(&pf->pdev->dev, "%s\n", buf);
 	kfree(buf);
-- 
cgit v1.2.3


From e92c0e0235c204a4787d186b541b33814a393d7f Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 16 Mar 2020 11:16:38 +0100
Subject: i40e: trivial fixup of comments in i40e_xsk.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The comment above i40e_run_xdp_zc() was clearly copy-pasted from
function i40e_xsk_umem_setup, which is just above.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index f3953744c505..7276580cbe64 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -139,8 +139,6 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
  *
- * This function enables or disables a UMEM to a certain ring.
- *
  * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
  **/
 static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
@@ -224,7 +222,7 @@ no_buffers:
 }
 
 /**
- * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
+ * i40e_construct_skb_zc - Create skbuff from zero-copy Rx buffer
  * @rx_ring: Rx ring
  * @xdp: xdp_buff
  *
-- 
cgit v1.2.3


From 3b70683fc4d68f5d915d9dc7e5ba72c732c7315c Mon Sep 17 00:00:00 2001
From: Xie XiuQi <xiexiuqi@huawei.com>
Date: Tue, 5 May 2020 10:45:21 +0800
Subject: ixgbe: fix signed-integer-overflow warning

ubsan report this warning, fix it by adding a unsigned suffix.

UBSAN: signed-integer-overflow in
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c:2246:26
65535 * 65537 cannot be represented in type 'int'
CPU: 21 PID: 7 Comm: kworker/u256:0 Not tainted 5.7.0-rc3-debug+ #39
Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 03/27/2020
Workqueue: ixgbe ixgbe_service_task [ixgbe]
Call trace:
 dump_backtrace+0x0/0x3f0
 show_stack+0x28/0x38
 dump_stack+0x154/0x1e4
 ubsan_epilogue+0x18/0x60
 handle_overflow+0xf8/0x148
 __ubsan_handle_mul_overflow+0x34/0x48
 ixgbe_fc_enable_generic+0x4d0/0x590 [ixgbe]
 ixgbe_service_task+0xc20/0x1f78 [ixgbe]
 process_one_work+0x8f0/0xf18
 worker_thread+0x430/0x6d0
 kthread+0x218/0x238
 ret_from_fork+0x10/0x18

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 0bd1294ba517..39c5e6fdb72c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2243,7 +2243,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 	}
 
 	/* Configure pause time (2 TCs per register) */
-	reg = hw->fc.pause_time * 0x00010001;
+	reg = hw->fc.pause_time * 0x00010001U;
 	for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++)
 		IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg);
 
-- 
cgit v1.2.3


From 85c41c5b16ee5a4939a22ec833c6a76753e3d428 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:41:57 +0800
Subject: ixgbe: Remove conversion to bool in
 ixgbe_device_supports_autoneg_fc()

No need to convert '==' expression to bool. This fixes the following
coccicheck warning:

drivers/net/ethernet/intel/ixgbe/ixgbe_common.c:68:11-16: WARNING:
conversion to bool not needed here

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 39c5e6fdb72c..17357a12cbdc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -64,8 +64,7 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 			hw->mac.ops.check_link(hw, &speed, &link_up, false);
 			/* if link is down, assume supported */
 			if (link_up)
-				supported = speed == IXGBE_LINK_SPEED_1GB_FULL ?
-				true : false;
+				supported = speed == IXGBE_LINK_SPEED_1GB_FULL;
 			else
 				supported = true;
 		}
-- 
cgit v1.2.3


From c2d77e598b1b7170a091b25e32710a0a9f9e4169 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Tue, 5 May 2020 15:43:37 +0800
Subject: ixgbe: Use true, false for bool variable in __ixgbe_enable_sriov()

Fix the following coccicheck warning:

drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c:105:2-38: WARNING:
Assignment of 0/1 to bool variable

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 537dfff585e0..d05a5690e66b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -102,7 +102,7 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
 		 * indirection table and RSS hash key with PF therefore
 		 * we want to disable the querying by default.
 		 */
-		adapter->vfinfo[i].rss_query_enabled = 0;
+		adapter->vfinfo[i].rss_query_enabled = false;
 
 		/* Untrust all VFs */
 		adapter->vfinfo[i].trusted = false;
-- 
cgit v1.2.3


From f2d9f294120fddec48e38e50d420c1d0a247661d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 5 May 2020 16:35:54 +0800
Subject: ixgbe: Remove unused inline function ixgbe_irq_disable_queues

commit b5f69ccf6765 ("ixgbe: avoid bringing rings up/down as macvlans are added/removed")
left behind this, remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 29 ---------------------------
 1 file changed, 29 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 45fc7ce1a543..a59c166f794f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2973,35 +2973,6 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 	/* skip the flush */
 }
 
-static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
-					    u64 qmask)
-{
-	u32 mask;
-	struct ixgbe_hw *hw = &adapter->hw;
-
-	switch (hw->mac.type) {
-	case ixgbe_mac_82598EB:
-		mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
-		IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask);
-		break;
-	case ixgbe_mac_82599EB:
-	case ixgbe_mac_X540:
-	case ixgbe_mac_X550:
-	case ixgbe_mac_X550EM_x:
-	case ixgbe_mac_x550em_a:
-		mask = (qmask & 0xFFFFFFFF);
-		if (mask)
-			IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask);
-		mask = (qmask >> 32);
-		if (mask)
-			IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask);
-		break;
-	default:
-		break;
-	}
-	/* skip the flush */
-}
-
 /**
  * ixgbe_irq_enable - Enable default interrupt generation settings
  * @adapter: board private structure
-- 
cgit v1.2.3


From 49c65e95f331201d431386dcb7c652bf02b306d1 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 7 May 2020 19:09:15 +0800
Subject: igb: make igb_set_fc_watermarks() return void

This function always return 0 now, we can make it return void to
simplify the code. This fixes the following coccicheck warning:

drivers/net/ethernet/intel/igb/e1000_mac.c:728:5-12: Unneeded variable:
"ret_val". Return "0" on line 751

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/e1000_mac.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index 79ee0a747260..3254737c07a3 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -12,7 +12,7 @@
 #include "igb.h"
 
 static s32 igb_set_default_fc(struct e1000_hw *hw);
-static s32 igb_set_fc_watermarks(struct e1000_hw *hw);
+static void igb_set_fc_watermarks(struct e1000_hw *hw);
 
 /**
  *  igb_get_bus_info_pcie - Get PCIe bus information
@@ -687,7 +687,7 @@ s32 igb_setup_link(struct e1000_hw *hw)
 
 	wr32(E1000_FCTTV, hw->fc.pause_time);
 
-	ret_val = igb_set_fc_watermarks(hw);
+	igb_set_fc_watermarks(hw);
 
 out:
 
@@ -723,9 +723,8 @@ void igb_config_collision_dist(struct e1000_hw *hw)
  *  flow control XON frame transmission is enabled, then set XON frame
  *  tansmission as well.
  **/
-static s32 igb_set_fc_watermarks(struct e1000_hw *hw)
+static void igb_set_fc_watermarks(struct e1000_hw *hw)
 {
-	s32 ret_val = 0;
 	u32 fcrtl = 0, fcrth = 0;
 
 	/* Set the flow control receive threshold registers.  Normally,
@@ -747,8 +746,6 @@ static s32 igb_set_fc_watermarks(struct e1000_hw *hw)
 	}
 	wr32(E1000_FCRTL, fcrtl);
 	wr32(E1000_FCRTH, fcrth);
-
-	return ret_val;
 }
 
 /**
-- 
cgit v1.2.3


From 2c3076f5ed3c17e06c2e09a442035906c99311b2 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 10 May 2020 18:52:00 +0300
Subject: igc: Remove unused flags

Transmit underrun, late and excess collision flags not in use.
This patch comes to clean up these flags.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 3d8d40d6fa3f..186deb1d9375 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -269,13 +269,9 @@
 #define IGC_TXD_CMD_DEXT	0x20000000 /* Desc extension (0 = legacy) */
 #define IGC_TXD_CMD_VLE		0x40000000 /* Add VLAN tag */
 #define IGC_TXD_STAT_DD		0x00000001 /* Descriptor Done */
-#define IGC_TXD_STAT_EC		0x00000002 /* Excess Collisions */
-#define IGC_TXD_STAT_LC		0x00000004 /* Late Collisions */
-#define IGC_TXD_STAT_TU		0x00000008 /* Transmit underrun */
 #define IGC_TXD_CMD_TCP		0x01000000 /* TCP packet */
 #define IGC_TXD_CMD_IP		0x02000000 /* IP packet */
 #define IGC_TXD_CMD_TSE		0x04000000 /* TCP Seg enable */
-#define IGC_TXD_STAT_TC		0x00000004 /* Tx Underrun */
 #define IGC_TXD_EXTCMD_TSTAMP	0x00000010 /* IEEE1588 Timestamp packet */
 
 /* IPSec Encrypt Enable */
-- 
cgit v1.2.3


From 3d3e9b6b6a878d01c04629eae8787de132056533 Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 12 May 2020 10:35:52 -0700
Subject: igc: Reject NFC rules with multiple matches

The way Rx queue assignment based on mac address, Ethertype and VLAN
priority filtering operates in I225 doesn't allow us to properly support
NFC rules with multiple matches.

Consider the following example which assigns to queue 2 frames matching
the address MACADDR *and* Ethertype ETYPE.

$ ethtool -N eth0 flow-type ether dst <MACADDR> proto <ETYPE> queue 2

When such rule is applied, we have 2 unwanted behaviors:

    1) Any frame matching MACADDR will be assigned to queue 2. It
       doesn't matter the ETYPE value.

    2) Any accepted frame that has Ethertype equals to ETYPE, no matter
       the mac address, will be assigned to queue 2 as well.

In current code, multiple-match filters are accepted by the driver, even
though it doesn't support them properly. This patch adds a check for
multiple-match rules in igc_ethtool_is_nfc_rule_valid() so they are
rejected.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 946e775e34ae..a938ec8db681 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1222,8 +1222,8 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule,
  * @adapter: Pointer to adapter
  * @rule: Rule under evaluation
  *
- * Rules with both destination and source MAC addresses are considered invalid
- * since the driver doesn't support them.
+ * The driver doesn't support rules with multiple matches so if more than
+ * one bit in filter flags is set, @rule is considered invalid.
  *
  * Also, if there is already another rule with the same filter in a different
  * location, @rule is considered invalid.
@@ -1244,9 +1244,8 @@ static int igc_ethtool_check_nfc_rule(struct igc_adapter *adapter,
 		return -EINVAL;
 	}
 
-	if (flags & IGC_FILTER_FLAG_DST_MAC_ADDR &&
-	    flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
-		netdev_dbg(dev, "Filters with both dst and src are not supported\n");
+	if (flags & (flags - 1)) {
+		netdev_dbg(dev, "Rule with multiple matches not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-- 
cgit v1.2.3


From e087d3bbc4bfb1458b28f77caa0eed092f632b2b Mon Sep 17 00:00:00 2001
From: Andre Guedes <andre.guedes@intel.com>
Date: Tue, 12 May 2020 10:35:53 -0700
Subject: igc: Fix IGC_MAX_RXNFC_RULES

IGC supports a total of 32 rules. 16 MAC address based, 8 VLAN priority
based, and 8 Ethertype based. This patch fixes IGC_MAX_RXNFC_RULES
accordingly.

Signed-off-by: Andre Guedes <andre.guedes@intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 14f9edaaaf83..5dbc5a156626 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -457,7 +457,10 @@ struct igc_nfc_rule {
 	u16 action;
 };
 
-#define IGC_MAX_RXNFC_RULES		16
+/* IGC supports a total of 32 NFC rules: 16 MAC address based,, 8 VLAN priority
+ * based, and 8 ethertype based.
+ */
+#define IGC_MAX_RXNFC_RULES		32
 
 /* igc_desc_unused - calculate if we have unused descriptors */
 static inline u16 igc_desc_unused(const struct igc_ring *ring)
-- 
cgit v1.2.3


From d601afcae2febc49665008e9a79e701248d56c50 Mon Sep 17 00:00:00 2001
From: Punit Agrawal <punit1.agrawal@toshiba.co.jp>
Date: Fri, 15 May 2020 13:31:27 +0900
Subject: e1000e: Relax condition to trigger reset for ME workaround

It's an error if the value of the RX/TX tail descriptor does not match
what was written. The error condition is true regardless the duration
of the interference from ME. But the driver only performs the reset if
E1000_ICH_FWSM_PCIM2PCI_COUNT (2000) iterations of 50us delay have
transpired. The extra condition can lead to inconsistency between the
state of hardware as expected by the driver.

Fix this by dropping the check for number of delay iterations.

While at it, also make __ew32_prepare() static as it's not used
anywhere else.

CC: stable <stable@vger.kernel.org>
Signed-off-by: Punit Agrawal <punit1.agrawal@toshiba.co.jp>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000e/e1000.h  |  1 -
 drivers/net/ethernet/intel/e1000e/netdev.c | 12 +++++-------
 2 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 37a2314d3e6b..944abd5eae11 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -576,7 +576,6 @@ static inline u32 __er32(struct e1000_hw *hw, unsigned long reg)
 
 #define er32(reg)	__er32(hw, E1000_##reg)
 
-s32 __ew32_prepare(struct e1000_hw *hw);
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val);
 
 #define ew32(reg, val)	__ew32(hw, E1000_##reg, (val))
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 32f23a15ff64..444532292588 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -158,14 +158,12 @@ static bool e1000e_check_me(u16 device_id)
  * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
  * and try again a number of times.
  **/
-s32 __ew32_prepare(struct e1000_hw *hw)
+static void __ew32_prepare(struct e1000_hw *hw)
 {
 	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
 
 	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
 		udelay(50);
-
-	return i;
 }
 
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
@@ -646,11 +644,11 @@ static void e1000e_update_rdt_wa(struct e1000_ring *rx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = rx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, rx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(rx_ring->tail)))) {
+	if (unlikely(i != readl(rx_ring->tail))) {
 		u32 rctl = er32(RCTL);
 
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
@@ -663,11 +661,11 @@ static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, tx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(tx_ring->tail)))) {
+	if (unlikely(i != readl(tx_ring->tail))) {
 		u32 tctl = er32(TCTL);
 
 		ew32(TCTL, tctl & ~E1000_TCTL_EN);
-- 
cgit v1.2.3


From 3f6023f77ad044a1a3e1b57ccaaff79432910a57 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Wed, 6 May 2020 14:18:35 +0800
Subject: i40e: Make i40e_shutdown_adminq() return void

Fix the following coccicheck warning:

drivers/net/ethernet/intel/i40e/i40e_adminq.c:699:13-21: Unneeded
variable: "ret_code". Return "0" on line 710

Signed-off-by: Jason Yan <yanaijie@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c    | 6 +-----
 drivers/net/ethernet/intel/i40e/i40e_prototype.h | 2 +-
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 37514a75f928..6a089848c857 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -694,10 +694,8 @@ init_adminq_exit:
  *  i40e_shutdown_adminq - shutdown routine for the Admin Queue
  *  @hw: pointer to the hardware structure
  **/
-i40e_status i40e_shutdown_adminq(struct i40e_hw *hw)
+void i40e_shutdown_adminq(struct i40e_hw *hw)
 {
-	i40e_status ret_code = 0;
-
 	if (i40e_check_asq_alive(hw))
 		i40e_aq_queue_shutdown(hw, true);
 
@@ -706,8 +704,6 @@ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw)
 
 	if (hw->nvm_buff.va)
 		i40e_free_virt_mem(hw, &hw->nvm_buff);
-
-	return ret_code;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index bbb478f09093..5c1378641b3b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -17,7 +17,7 @@
 
 /* adminq functions */
 i40e_status i40e_init_adminq(struct i40e_hw *hw);
-i40e_status i40e_shutdown_adminq(struct i40e_hw *hw);
+void i40e_shutdown_adminq(struct i40e_hw *hw);
 void i40e_adminq_init_ring_data(struct i40e_hw *hw);
 i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 					     struct i40e_arq_event_info *e,
-- 
cgit v1.2.3


From 758b51e1e71e38257dfcb753edaf07d417611786 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 19 May 2020 17:36:34 +0300
Subject: igc: Remove symbol error counter

Accordance to the i225 datasheet symbol error counter does not
applicable to the i225 device.
This patch comes to clean up this counter.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.c  | 1 -
 drivers/net/ethernet/intel/igc/igc_main.c | 1 -
 drivers/net/ethernet/intel/igc/igc_regs.h | 1 -
 3 files changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index 89445ab02a98..9de70a24cb9e 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -235,7 +235,6 @@ out:
 void igc_clear_hw_cntrs_base(struct igc_hw *hw)
 {
 	rd32(IGC_CRCERRS);
-	rd32(IGC_SYMERRS);
 	rd32(IGC_MPC);
 	rd32(IGC_SCC);
 	rd32(IGC_ECOL);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 97d26991c87e..662f06a647e6 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3701,7 +3701,6 @@ void igc_update_stats(struct igc_adapter *adapter)
 	adapter->stats.prc511 += rd32(IGC_PRC511);
 	adapter->stats.prc1023 += rd32(IGC_PRC1023);
 	adapter->stats.prc1522 += rd32(IGC_PRC1522);
-	adapter->stats.symerrs += rd32(IGC_SYMERRS);
 	adapter->stats.sec += rd32(IGC_SEC);
 
 	mpc = rd32(IGC_MPC);
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 7f999cfc9b39..a3e4ec922948 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -127,7 +127,6 @@
 /* Statistics Register Descriptions */
 #define IGC_CRCERRS	0x04000  /* CRC Error Count - R/clr */
 #define IGC_ALGNERRC	0x04004  /* Alignment Error Count - R/clr */
-#define IGC_SYMERRS	0x04008  /* Symbol Error Count - R/clr */
 #define IGC_RXERRC	0x0400C  /* Receive Error Count - R/clr */
 #define IGC_MPC		0x04010  /* Missed Packet Count - R/clr */
 #define IGC_SCC		0x04014  /* Single Collision Count - R/clr */
-- 
cgit v1.2.3


From 51c657b42f58fcf061dfd6d01df26ff1701ae72c Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Tue, 19 May 2020 17:55:42 +0300
Subject: igc: Add Receive Error Counter

Receive error counter reflect total number of non-filtered
packets received with errors. This includes: CRC error,
symbol error, Rx data error and carrier extend error.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.c  | 1 +
 drivers/net/ethernet/intel/igc/igc_main.c | 1 +
 drivers/net/ethernet/intel/igc/igc_regs.h | 1 +
 3 files changed, 3 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index 9de70a24cb9e..a5a087e1ac02 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -241,6 +241,7 @@ void igc_clear_hw_cntrs_base(struct igc_hw *hw)
 	rd32(IGC_MCC);
 	rd32(IGC_LATECOL);
 	rd32(IGC_COLC);
+	rd32(IGC_RERC);
 	rd32(IGC_DC);
 	rd32(IGC_SEC);
 	rd32(IGC_RLEC);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 662f06a647e6..e0c45ffa12c4 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3740,6 +3740,7 @@ void igc_update_stats(struct igc_adapter *adapter)
 
 	adapter->stats.tpt += rd32(IGC_TPT);
 	adapter->stats.colc += rd32(IGC_COLC);
+	adapter->stats.colc += rd32(IGC_RERC);
 
 	adapter->stats.algnerrc += rd32(IGC_ALGNERRC);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index a3e4ec922948..7ac3b611708c 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -134,6 +134,7 @@
 #define IGC_MCC		0x0401C  /* Multiple Collision Count - R/clr */
 #define IGC_LATECOL	0x04020  /* Late Collision Count - R/clr */
 #define IGC_COLC	0x04028  /* Collision Count - R/clr */
+#define IGC_RERC	0x0402C  /* Receive Error Count - R/clr */
 #define IGC_DC		0x04030  /* Defer Count - R/clr */
 #define IGC_TNCRS	0x04034  /* Tx-No CRS - R/clr */
 #define IGC_SEC		0x04038  /* Sequence Error Count - R/clr */
-- 
cgit v1.2.3


From e2d0f2031effc8b08a162e6db64d2c97da4cf9f5 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 28 May 2020 10:11:11 +0300
Subject: igc: Remove Sequence Error Counter

Accordance to the i225 datasheet sequence error counter does not
applicable to the i225 device.
This patch comes to clean up this counter.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.c  | 1 -
 drivers/net/ethernet/intel/igc/igc_main.c | 1 -
 drivers/net/ethernet/intel/igc/igc_regs.h | 1 -
 3 files changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index a5a087e1ac02..fb496617e8e1 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -243,7 +243,6 @@ void igc_clear_hw_cntrs_base(struct igc_hw *hw)
 	rd32(IGC_COLC);
 	rd32(IGC_RERC);
 	rd32(IGC_DC);
-	rd32(IGC_SEC);
 	rd32(IGC_RLEC);
 	rd32(IGC_XONRXC);
 	rd32(IGC_XONTXC);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e0c45ffa12c4..43fcabb5c023 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3701,7 +3701,6 @@ void igc_update_stats(struct igc_adapter *adapter)
 	adapter->stats.prc511 += rd32(IGC_PRC511);
 	adapter->stats.prc1023 += rd32(IGC_PRC1023);
 	adapter->stats.prc1522 += rd32(IGC_PRC1522);
-	adapter->stats.sec += rd32(IGC_SEC);
 
 	mpc = rd32(IGC_MPC);
 	adapter->stats.mpc += mpc;
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 7ac3b611708c..2b7a877dadac 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -137,7 +137,6 @@
 #define IGC_RERC	0x0402C  /* Receive Error Count - R/clr */
 #define IGC_DC		0x04030  /* Defer Count - R/clr */
 #define IGC_TNCRS	0x04034  /* Tx-No CRS - R/clr */
-#define IGC_SEC		0x04038  /* Sequence Error Count - R/clr */
 #define IGC_CEXTERR	0x0403C  /* Carrier Extension Error Count - R/clr */
 #define IGC_RLEC	0x04040  /* Receive Length Error Count - R/clr */
 #define IGC_XONRXC	0x04048  /* XON Rx Count - R/clr */
-- 
cgit v1.2.3


From 480b7a5a3fdb99afaf9a59681616bc70c1fbfe2f Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Thu, 28 May 2020 10:25:21 +0300
Subject: igc: Fix wrong register name

Accordance to the i225 datasheet this register address
used by Host Transmit Discarded Packet by MAC counter
and not by not applicable Carrier Extension Error counter.
This patch comes to fix this wrong definition.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_mac.c  | 2 +-
 drivers/net/ethernet/intel/igc/igc_regs.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index fb496617e8e1..410aeb01de5c 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -287,7 +287,7 @@ void igc_clear_hw_cntrs_base(struct igc_hw *hw)
 	rd32(IGC_ALGNERRC);
 	rd32(IGC_RXERRC);
 	rd32(IGC_TNCRS);
-	rd32(IGC_CEXTERR);
+	rd32(IGC_HTDPMC);
 	rd32(IGC_TSCTC);
 	rd32(IGC_TSCTFC);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index 2b7a877dadac..232e82dec62e 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -137,7 +137,7 @@
 #define IGC_RERC	0x0402C  /* Receive Error Count - R/clr */
 #define IGC_DC		0x04030  /* Defer Count - R/clr */
 #define IGC_TNCRS	0x04034  /* Tx-No CRS - R/clr */
-#define IGC_CEXTERR	0x0403C  /* Carrier Extension Error Count - R/clr */
+#define IGC_HTDPMC	0x0403C  /* Host Transmit Discarded by MAC - R/clr */
 #define IGC_RLEC	0x04040  /* Receive Length Error Count - R/clr */
 #define IGC_XONRXC	0x04048  /* XON Rx Count - R/clr */
 #define IGC_XONTXC	0x0404C  /* XON Tx Count - R/clr */
-- 
cgit v1.2.3


From 6a3faa4d7e013af13fa0230f7537640dcb3abc38 Mon Sep 17 00:00:00 2001
From: Hari <harichandrakanthan@gmail.com>
Date: Sat, 23 May 2020 18:43:26 +0530
Subject: e1000: Fix typo in the comment

Continuous Double "the" in a comment. Changed it to single "the"

Signed-off-by: Hari <harichandrakanthan@gmail.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index 48428d6a00be..623e516a9630 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -3960,7 +3960,7 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words,
  * @hw: Struct containing variables accessed by shared code
  *
  * Reads the first 64 16 bit words of the EEPROM and sums the values read.
- * If the the sum of the 64 16 bit words is 0xBABA, the EEPROM's checksum is
+ * If the sum of the 64 16 bit words is 0xBABA, the EEPROM's checksum is
  * valid.
  */
 s32 e1000_validate_eeprom_checksum(struct e1000_hw *hw)
-- 
cgit v1.2.3


From 09b547a7996e77d4141de27c1657d7c3adcb478e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 29 May 2020 10:26:48 +0200
Subject: net: ethernet: mtk-star-emac: remove unused variable

The desc pointer is set but not used. Remove it.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: 8c7bd5a454ff ("net: ethernet: mtk-star-emac: new driver")
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 8596ca0e60eb..7df35872c107 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -746,15 +746,12 @@ mtk_star_ring_free_skbs(struct mtk_star_priv *priv, struct mtk_star_ring *ring,
 					   struct mtk_star_ring_desc_data *))
 {
 	struct mtk_star_ring_desc_data desc_data;
-	struct mtk_star_ring_desc *desc;
 	int i;
 
 	for (i = 0; i < MTK_STAR_RING_NUM_DESCS; i++) {
 		if (!ring->dma_addrs[i])
 			continue;
 
-		desc = &ring->descs[i];
-
 		desc_data.dma_addr = ring->dma_addrs[i];
 		desc_data.skb = ring->skbs[i];
 
-- 
cgit v1.2.3


From 139df98bdfef62868df3d626d27f1db9edd9830f Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Thu, 28 May 2020 16:26:23 +0800
Subject: stmmac: platform: add "snps, dwmac-5.10a" IP compatible string

Add "snps,dwmac-5.10a" compatible string for 5.10a version that can
avoid to define some plat data in glue layer.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index bcda49dcf619..f32317fa75c8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -507,7 +507,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 
 	if (of_device_is_compatible(np, "snps,dwmac-4.00") ||
 	    of_device_is_compatible(np, "snps,dwmac-4.10a") ||
-	    of_device_is_compatible(np, "snps,dwmac-4.20a")) {
+	    of_device_is_compatible(np, "snps,dwmac-4.20a") ||
+	    of_device_is_compatible(np, "snps,dwmac-5.10a")) {
 		plat->has_gmac4 = 1;
 		plat->has_gmac = 0;
 		plat->pmt = 1;
-- 
cgit v1.2.3


From 94abdad6974a5e108d921df2c38e35cae6179bb2 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Thu, 28 May 2020 16:26:24 +0800
Subject: net: ethernet: dwmac: add ethernet glue logic for NXP imx8 chip

NXP imx8 family like imx8mp/imx8dxl chips support Synopsys MAC 5.10a IP.
This patch adds settings for NXP imx8 glue layer:
- clocks
- dwmac address width
- phy interface mode selection
- adjust rgmii txclk rate

v2:
- adjust code sequences in order to have reverse christmas
  tree local variable ordering.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig     |  13 +
 drivers/net/ethernet/stmicro/stmmac/Makefile    |   1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 315 ++++++++++++++++++++++++
 3 files changed, 329 insertions(+)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index b46f8d2ae6d7..36bd2e18f23b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -196,6 +196,19 @@ config DWMAC_SUN8I
 	  This selects Allwinner SoC glue layer support for the
 	  stmmac device driver. This driver is used for H3/A83T/A64
 	  EMAC ethernet controller.
+
+config DWMAC_IMX8
+	tristate "NXP IMX8 DWMAC support"
+	default ARCH_MXC
+	depends on OF && (ARCH_MXC || COMPILE_TEST)
+	select MFD_SYSCON
+	---help---
+	  Support for ethernet controller on NXP i.MX8 SOCs.
+
+	  This selects NXP SoC glue layer support for the stmmac
+	  device driver. This driver is used for i.MX8 series like
+	  iMX8MP/iMX8DXL GMAC ethernet controller.
+
 endif
 
 config DWMAC_INTEL
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index f9d024d6b69b..295615ab36a7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_DWMAC_SUNXI)	+= dwmac-sunxi.o
 obj-$(CONFIG_DWMAC_SUN8I)	+= dwmac-sun8i.o
 obj-$(CONFIG_DWMAC_DWC_QOS_ETH)	+= dwmac-dwc-qos-eth.o
 obj-$(CONFIG_DWMAC_GENERIC)	+= dwmac-generic.o
+obj-$(CONFIG_DWMAC_IMX8)	+= dwmac-imx.o
 stmmac-platform-objs:= stmmac_platform.o
 dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
new file mode 100644
index 000000000000..5010af7dab4a
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dwmac-imx.c - DWMAC Specific Glue layer for NXP imx8
+ *
+ * Copyright 2020 NXP
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/pm_wakeirq.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/stmmac.h>
+
+#include "stmmac_platform.h"
+
+#define GPR_ENET_QOS_INTF_MODE_MASK	GENMASK(21, 16)
+#define GPR_ENET_QOS_INTF_SEL_MII	(0x0 << 16)
+#define GPR_ENET_QOS_INTF_SEL_RMII	(0x4 << 16)
+#define GPR_ENET_QOS_INTF_SEL_RGMII	(0x1 << 16)
+#define GPR_ENET_QOS_CLK_GEN_EN		(0x1 << 19)
+#define GPR_ENET_QOS_CLK_TX_CLK_SEL	(0x1 << 20)
+#define GPR_ENET_QOS_RGMII_EN		(0x1 << 21)
+
+struct imx_dwmac_ops {
+	u32 addr_width;
+	bool mac_rgmii_txclk_auto_adj;
+
+	int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat);
+};
+
+struct imx_priv_data {
+	struct device *dev;
+	struct clk *clk_tx;
+	struct clk *clk_mem;
+	struct regmap *intf_regmap;
+	u32 intf_reg_off;
+	bool rmii_refclk_ext;
+
+	const struct imx_dwmac_ops *ops;
+	struct plat_stmmacenet_data *plat_dat;
+};
+
+static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	struct imx_priv_data *dwmac = plat_dat->bsp_priv;
+	int val;
+
+	switch (plat_dat->interface) {
+	case PHY_INTERFACE_MODE_MII:
+		val = GPR_ENET_QOS_INTF_SEL_MII;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		val = GPR_ENET_QOS_INTF_SEL_RMII;
+		val |= (dwmac->rmii_refclk_ext ? 0 : GPR_ENET_QOS_CLK_TX_CLK_SEL);
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		val = GPR_ENET_QOS_INTF_SEL_RGMII |
+		      GPR_ENET_QOS_RGMII_EN;
+		break;
+	default:
+		pr_debug("imx dwmac doesn't support %d interface\n",
+			 plat_dat->interface);
+		return -EINVAL;
+	}
+
+	val |= GPR_ENET_QOS_CLK_GEN_EN;
+	return regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off,
+				  GPR_ENET_QOS_INTF_MODE_MASK, val);
+};
+
+static int
+imx8dxl_set_intf_mode(struct plat_stmmacenet_data *plat_dat)
+{
+	int ret = 0;
+
+	/* TBD: depends on imx8dxl scu interfaces to be upstreamed */
+	return ret;
+}
+
+static int imx_dwmac_init(struct platform_device *pdev, void *priv)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct imx_priv_data *dwmac = priv;
+	int ret;
+
+	plat_dat = dwmac->plat_dat;
+
+	ret = clk_prepare_enable(dwmac->clk_mem);
+	if (ret) {
+		dev_err(&pdev->dev, "mem clock enable failed\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(dwmac->clk_tx);
+	if (ret) {
+		dev_err(&pdev->dev, "tx clock enable failed\n");
+		goto clk_tx_en_failed;
+	}
+
+	if (dwmac->ops->set_intf_mode) {
+		ret = dwmac->ops->set_intf_mode(plat_dat);
+		if (ret)
+			goto intf_mode_failed;
+	}
+
+	return 0;
+
+intf_mode_failed:
+	clk_disable_unprepare(dwmac->clk_tx);
+clk_tx_en_failed:
+	clk_disable_unprepare(dwmac->clk_mem);
+	return ret;
+}
+
+static void imx_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct imx_priv_data *dwmac = priv;
+
+	if (dwmac->clk_tx)
+		clk_disable_unprepare(dwmac->clk_tx);
+	clk_disable_unprepare(dwmac->clk_mem);
+}
+
+static void imx_dwmac_fix_speed(void *priv, unsigned int speed)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct imx_priv_data *dwmac = priv;
+	unsigned long rate;
+	int err;
+
+	plat_dat = dwmac->plat_dat;
+
+	if (dwmac->ops->mac_rgmii_txclk_auto_adj ||
+	    (plat_dat->interface == PHY_INTERFACE_MODE_RMII) ||
+	    (plat_dat->interface == PHY_INTERFACE_MODE_MII))
+		return;
+
+	switch (speed) {
+	case SPEED_1000:
+		rate = 125000000;
+		break;
+	case SPEED_100:
+		rate = 25000000;
+		break;
+	case SPEED_10:
+		rate = 2500000;
+		break;
+	default:
+		dev_err(dwmac->dev, "invalid speed %u\n", speed);
+		return;
+	}
+
+	err = clk_set_rate(dwmac->clk_tx, rate);
+	if (err < 0)
+		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
+}
+
+static int
+imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	int err = 0;
+
+	if (of_get_property(np, "snps,rmii_refclk_ext", NULL))
+		dwmac->rmii_refclk_ext = true;
+
+	dwmac->clk_tx = devm_clk_get(dev, "tx");
+	if (IS_ERR(dwmac->clk_tx)) {
+		dev_err(dev, "failed to get tx clock\n");
+		return PTR_ERR(dwmac->clk_tx);
+	}
+
+	dwmac->clk_mem = NULL;
+	if (of_machine_is_compatible("fsl,imx8dxl")) {
+		dwmac->clk_mem = devm_clk_get(dev, "mem");
+		if (IS_ERR(dwmac->clk_mem)) {
+			dev_err(dev, "failed to get mem clock\n");
+			return PTR_ERR(dwmac->clk_mem);
+		}
+	}
+
+	if (of_machine_is_compatible("fsl,imx8mp")) {
+		/* Binding doc describes the propety:
+		   is required by i.MX8MP.
+		   is optinoal for i.MX8DXL.
+		 */
+		dwmac->intf_regmap = syscon_regmap_lookup_by_phandle(np, "intf_mode");
+		if (IS_ERR(dwmac->intf_regmap))
+			return PTR_ERR(dwmac->intf_regmap);
+
+		err = of_property_read_u32_index(np, "intf_mode", 1, &dwmac->intf_reg_off);
+		if (err) {
+			dev_err(dev, "Can't get intf mode reg offset (%d)\n", err);
+			return err;
+		}
+	}
+
+	return err;
+}
+
+static int imx_dwmac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct imx_priv_data *dwmac;
+	const struct imx_dwmac_ops *data;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+	if (!dwmac)
+		return PTR_ERR(dwmac);
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
+
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data) {
+		dev_err(&pdev->dev, "failed to get match data\n");
+		ret = -EINVAL;
+		goto err_match_data;
+	}
+
+	dwmac->ops = data;
+	dwmac->dev = &pdev->dev;
+
+	ret = imx_dwmac_parse_dt(dwmac, &pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to parse OF data\n");
+		goto err_parse_dt;
+	}
+
+	ret = dma_set_mask_and_coherent(&pdev->dev,
+					DMA_BIT_MASK(dwmac->ops->addr_width));
+	if (ret) {
+		dev_err(&pdev->dev, "DMA mask set failed\n");
+		goto err_dma_mask;
+	}
+
+	plat_dat->init = imx_dwmac_init;
+	plat_dat->exit = imx_dwmac_exit;
+	plat_dat->fix_mac_speed = imx_dwmac_fix_speed;
+	plat_dat->bsp_priv = dwmac;
+	dwmac->plat_dat = plat_dat;
+
+	ret = imx_dwmac_init(pdev, dwmac);
+	if (ret)
+		goto err_dwmac_init;
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret)
+		goto err_drv_probe;
+
+	return 0;
+
+err_dwmac_init:
+err_drv_probe:
+	imx_dwmac_exit(pdev, plat_dat->bsp_priv);
+err_dma_mask:
+err_parse_dt:
+err_match_data:
+	stmmac_remove_config_dt(pdev, plat_dat);
+	return ret;
+}
+
+static struct imx_dwmac_ops imx8mp_dwmac_data = {
+	.addr_width = 34,
+	.mac_rgmii_txclk_auto_adj = false,
+	.set_intf_mode = imx8mp_set_intf_mode,
+};
+
+static struct imx_dwmac_ops imx8dxl_dwmac_data = {
+	.addr_width = 32,
+	.mac_rgmii_txclk_auto_adj = true,
+	.set_intf_mode = imx8dxl_set_intf_mode,
+};
+
+static const struct of_device_id imx_dwmac_match[] = {
+	{ .compatible = "nxp,imx8mp-dwmac-eqos", .data = &imx8mp_dwmac_data },
+	{ .compatible = "nxp,imx8dxl-dwmac-eqos", .data = &imx8dxl_dwmac_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, imx_dwmac_match);
+
+static struct platform_driver imx_dwmac_driver = {
+	.probe  = imx_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "imx-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = imx_dwmac_match,
+	},
+};
+module_platform_driver(imx_dwmac_driver);
+
+MODULE_AUTHOR("NXP");
+MODULE_DESCRIPTION("NXP imx8 DWMAC Specific Glue layer");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From f0b37fa613989dacbaba57010681218ed91e989b Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@netronome.com>
Date: Thu, 28 May 2020 16:18:46 +0200
Subject: nfp: flower: fix incorrect flag assignment

A previous refactoring missed some locations the flags were renamed
but not moved from the previous flower_ext_feats to the new flower_en_feats
variable. This lead to the FLOW_MERGE and LAG features not being enabled.

Fixes: e09303d3c4d9 ("nfp: flower: renaming of feature bits")
Signed-off-by: Louis Peens <louis.peens@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index d054553c75e0..ca7032d22196 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -708,7 +708,7 @@ static int nfp_flower_sync_feature_bits(struct nfp_app *app)
 	err = nfp_rtsym_write_le(app->pf->rtbl,
 				 "_abi_flower_balance_sync_enable", 1);
 	if (!err) {
-		app_priv->flower_ext_feats |= NFP_FL_ENABLE_LAG;
+		app_priv->flower_en_feats |= NFP_FL_ENABLE_LAG;
 		nfp_flower_lag_init(&app_priv->nfp_lag);
 	} else if (err == -ENOENT) {
 		nfp_warn(app->cpp, "LAG not supported by FW.\n");
@@ -721,7 +721,7 @@ static int nfp_flower_sync_feature_bits(struct nfp_app *app)
 		err = nfp_rtsym_write_le(app->pf->rtbl,
 					 "_abi_flower_merge_hint_enable", 1);
 		if (!err) {
-			app_priv->flower_ext_feats |= NFP_FL_ENABLE_FLOW_MERGE;
+			app_priv->flower_en_feats |= NFP_FL_ENABLE_FLOW_MERGE;
 			nfp_flower_internal_port_init(app_priv);
 		} else if (err == -ENOENT) {
 			nfp_warn(app->cpp,
@@ -840,7 +840,7 @@ static int nfp_flower_init(struct nfp_app *app)
 	return 0;
 
 err_cleanup:
-	if (app_priv->flower_ext_feats & NFP_FL_ENABLE_LAG)
+	if (app_priv->flower_en_feats & NFP_FL_ENABLE_LAG)
 		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
 	nfp_flower_metadata_cleanup(app);
 err_free_app_priv:
-- 
cgit v1.2.3


From 56e2287b4110fbb81456a346b1d4c12bee7cf044 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Wed, 27 May 2020 15:44:09 +0200
Subject: mlx5: fix xdp data_meta setup in mlx5e_fill_xdp_buff

The helper function xdp_set_data_meta_invalid() must be called after
setting xdp->data as it depends on it.

The bug was introduced in the cited patch below, and cause the kernel
to crash when using BPF helper bpf_xdp_adjust_head() on mlx5 driver.

Fixes: 39d6443c8daf ("mlx5, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL")
Reported-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6b3c82da199c..dbb1c6323967 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1056,8 +1056,8 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom,
 				u32 len, struct xdp_buff *xdp)
 {
 	xdp->data_hard_start = va;
-	xdp_set_data_meta_invalid(xdp);
 	xdp->data = va + headroom;
+	xdp_set_data_meta_invalid(xdp);
 	xdp->data_end = xdp->data + len;
 	xdp->rxq = &rq->xdp_rxq;
 	xdp->frame_sz = rq->buff.frame0_sz;
-- 
cgit v1.2.3


From 2950d1d64fd035726b4b060313f931ed52e3615f Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 26 May 2020 22:09:09 -0700
Subject: net/mlx5: Kconfig: Fix spelling typo

"mdoe"->"mode"

Fixes: d956873f908c ("net/mlx5e: Introduce kconfig var for TC support")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reported-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 4256d59eca2b..b6ffd1622cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -84,7 +84,7 @@ config MLX5_CLS_ACT
 	default y
 	help
 	  mlx5 ConnectX offloads support for TC classifier action (NET_CLS_ACT),
-	  works in both native NIC mdoe and Switchdev SRIOV mode.
+	  works in both native NIC mode and Switchdev SRIOV mode.
 	  Actions get attached to a Hardware offloaded classifiers and are
 	  invoked after a successful classification. Actions are used to
 	  overwrite the classification result, instantly drop or redirect and/or
-- 
cgit v1.2.3


From 2861904697de587c5b92c65a18a44ca3bbfd00ed Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Wed, 27 May 2020 00:50:22 -0700
Subject: net/mlx5e: Don't use err uninitialized in mlx5e_attach_decap

Clang warns:

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:3712:6: warning:
variable 'err' is used uninitialized whenever 'if' condition is false
[-Wsometimes-uninitialized]
        if (IS_ERR(d->pkt_reformat)) {
            ^~~~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:3718:6: note:
uninitialized use occurs here
        if (err)
            ^~~
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:3712:2: note: remove the
'if' if its condition is always true
        if (IS_ERR(d->pkt_reformat)) {
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:3670:9: note: initialize
the variable 'err' to silence this warning
        int err;
               ^
                = 0
1 warning generated.

It is not wrong, err is only ever initialized in if statements but this
one is not in one. Initialize err to 0 to fix this.

Fixes: 14e6b038afa0 ("net/mlx5e: Add support for hw decapsulation of MPLS over UDP")
Link: https://github.com/ClangBuiltLinux/linux/issues/1037
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0f119c08b835..ac19a61c5cbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3667,7 +3667,7 @@ static int mlx5e_attach_decap(struct mlx5e_priv *priv,
 	struct mlx5e_decap_entry *d;
 	struct mlx5e_decap_key key;
 	uintptr_t hash_key;
-	int err;
+	int err = 0;
 
 	parse_attr = attr->parse_attr;
 	if (sizeof(parse_attr->eth) > MLX5_CAP_ESW(priv->mdev, max_encap_header_size)) {
-- 
cgit v1.2.3


From e1167e16114f78f948078749aa1608a785f65807 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 28 Apr 2020 23:23:47 +0200
Subject: net/mlx5: reduce stack usage in qp_read_field

Moving the mlx5_ifc_query_qp_out_bits structure on the stack was a bit
excessive and now causes the compiler to complain on 32-bit architectures:

drivers/net/ethernet/mellanox/mlx5/core/debugfs.c: In function 'qp_read_field':
drivers/net/ethernet/mellanox/mlx5/core/debugfs.c:274:1: error: the frame size of 1104 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

Revert the previous patch partially to use dynamically allocation as
the code did before. Unfortunately there is no good error handling
in case the allocation fails.

Fixes: 57a6c5e992f5 ("net/mlx5: Replace hand written QP context struct with automatic getters")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 6409090b3ec5..d2d57213511b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -202,18 +202,23 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev)
 static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 			 int index, int *is_str)
 {
-	u32 out[MLX5_ST_SZ_BYTES(query_qp_out)] = {};
+	int outlen = MLX5_ST_SZ_BYTES(query_qp_out);
 	u32 in[MLX5_ST_SZ_DW(query_qp_in)] = {};
 	u64 param = 0;
+	u32 *out;
 	int state;
 	u32 *qpc;
 	int err;
 
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return 0;
+
 	MLX5_SET(query_qp_in, in, opcode, MLX5_CMD_OP_QUERY_QP);
 	MLX5_SET(query_qp_in, in, qpn, qp->qpn);
 	err = mlx5_cmd_exec_inout(dev, query_qp, in, out);
 	if (err)
-		return 0;
+		goto out;
 
 	*is_str = 0;
 
@@ -269,7 +274,8 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 		param = MLX5_GET(qpc, qpc, remote_qpn);
 		break;
 	}
-
+out:
+	kfree(out);
 	return param;
 }
 
-- 
cgit v1.2.3


From f7e3ac424a2b3fc6fb3b490106cd874adb62ae4a Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 27 May 2020 08:38:03 +0300
Subject: net/mlx5e: Use generic API to build MPLS label

Make use of generic API mpls_entry_encode() to build mpls label and get
rid of local function.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c | 20 +++-----------------
 1 file changed, 3 insertions(+), 17 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
index b4a3c96d34fd..1f9526244222 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c
@@ -25,35 +25,21 @@ static int init_encap_attr(struct net_device *tunnel_dev,
 	return 0;
 }
 
-static inline __be32 mpls_label_id_field(__be32 label, u8 tos, u8 ttl)
-{
-	u32 res;
-
-	/* mpls label is 32 bits long and construction as follows:
-	 * 20 bits label
-	 * 3 bits tos
-	 * 1 bit bottom of stack. Since we support only one label, this bit is
-	 *       always set.
-	 * 8 bits TTL
-	 */
-	res = be32_to_cpu(label) << 12 | 1 << 8 | (tos & 7) <<  9 | ttl;
-	return cpu_to_be32(res);
-}
-
 static int generate_ip_tun_hdr(char buf[],
 			       __u8 *ip_proto,
 			       struct mlx5e_encap_entry *r)
 {
 	const struct ip_tunnel_key *tun_key = &r->tun_info->key;
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
 	struct udphdr *udp = (struct udphdr *)(buf);
 	struct mpls_shim_hdr *mpls;
+	u32 tun_id;
 
+	tun_id = be32_to_cpu(tunnel_id_to_key32(tun_key->tun_id));
 	mpls = (struct mpls_shim_hdr *)(udp + 1);
 	*ip_proto = IPPROTO_UDP;
 
 	udp->dest = tun_key->tp_dst;
-	mpls->label_stack_entry = mpls_label_id_field(tun_id, tun_key->tos, tun_key->ttl);
+	*mpls = mpls_entry_encode(tun_id, tun_key->ttl, tun_key->tos, true);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 618f88c4c40a9621a3105f3ff957a91a148e7d94 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 28 May 2020 01:02:08 -0700
Subject: net/mlx5: DR: Fix incorrect type in argument

HW spec objects should receive a void ptr to work on, the MLX5_SET/GET
macro will know how to handle it.

No need to provide explicit or wrong pointer type in this case.

warning: incorrect type in argument 1 (different base types)
    expected unsigned long long const [usertype] *sw_action
    got restricted __be64 [usertype] *[assigned] sw_action

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 554811de4c9d..df1363a34a42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -1662,7 +1662,7 @@ dr_action_modify_check_field_limitation(struct mlx5dr_action *action,
 }
 
 static bool
-dr_action_modify_check_is_ttl_modify(const u64 *sw_action)
+dr_action_modify_check_is_ttl_modify(const void *sw_action)
 {
 	u16 sw_field = MLX5_GET(set_action_in, sw_action, field);
 
-- 
cgit v1.2.3


From c2ba2c2287698bac36bf71e5c4f3be423371bee0 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 28 May 2020 01:11:37 -0700
Subject: net/mlx5: DR: Fix cast to restricted __be32

raw_ip actual type is __be32 and not u32.
Fix that and get rid of the warning.

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c:906:31:
warning: cast to restricted __be32

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 78c884911ceb..470895016693 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -869,7 +869,7 @@ static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec)
 
 static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec)
 {
-	u32 raw_ip[4];
+	__be32 raw_ip[4];
 
 	spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16);
 
-- 
cgit v1.2.3


From 9ff2e92c466dc1aa4d970e5027dfd66b1f32b7bc Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 28 May 2020 01:14:31 -0700
Subject: net/mlx5: DR: Fix incorrect type in return expression

dr_ste_crc32_calc() calculates crc32 and should return it in HW format.
It is being used to calculate a u32 index, hence we force the return value
of u32 to avoid the sparse warning:

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c:115:16:
warning: incorrect type in return expression (different base types)
    expected unsigned int
    got restricted __be32 [usertype]

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 470895016693..00c2f598f034 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -112,7 +112,7 @@ static u32 dr_ste_crc32_calc(const void *input_data, size_t length)
 {
 	u32 crc = crc32(0, input_data, length);
 
-	return htonl(crc);
+	return (__force u32)htonl(crc);
 }
 
 u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
-- 
cgit v1.2.3


From 2553f421f44f4db7579f202b79b69046b579c7b5 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 27 May 2020 23:16:02 -0700
Subject: net/mlx5: cmd: Fix memset with byte count warning

Fix sparse warning:
drivers/net/ethernet/mellanox/mlx5/core/cmd.c:1949:15:
warning: memset with byte count of 271720

mlx5_cmd_stats array is too big to be held inline in mlx5_cmd.
Allocate it separately.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c     | 20 ++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c |  2 +-
 include/linux/mlx5/driver.h                       |  2 +-
 3 files changed, 16 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index eca159e8e123..1d91a0d0ab1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1072,7 +1072,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
-	if (op < ARRAY_SIZE(cmd->stats)) {
+	if (op < MLX5_CMD_OP_MAX) {
 		stats = &cmd->stats[op];
 		spin_lock_irq(&stats->lock);
 		stats->sum += ds;
@@ -1551,7 +1551,7 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;
-				if (ent->op < ARRAY_SIZE(cmd->stats)) {
+				if (ent->op < MLX5_CMD_OP_MAX) {
 					stats = &cmd->stats[ent->op];
 					spin_lock_irqsave(&stats->lock, flags);
 					stats->sum += ds;
@@ -1960,10 +1960,16 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		return -EINVAL;
 	}
 
-	cmd->pool = dma_pool_create("mlx5_cmd", dev->device, size, align, 0);
-	if (!cmd->pool)
+	cmd->stats = kvzalloc(MLX5_CMD_OP_MAX * sizeof(*cmd->stats), GFP_KERNEL);
+	if (!cmd->stats)
 		return -ENOMEM;
 
+	cmd->pool = dma_pool_create("mlx5_cmd", dev->device, size, align, 0);
+	if (!cmd->pool) {
+		err = -ENOMEM;
+		goto dma_pool_err;
+	}
+
 	err = alloc_cmd_page(dev, cmd);
 	if (err)
 		goto err_free_pool;
@@ -1999,7 +2005,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	spin_lock_init(&cmd->alloc_lock);
 	spin_lock_init(&cmd->token_lock);
-	for (i = 0; i < ARRAY_SIZE(cmd->stats); i++)
+	for (i = 0; i < MLX5_CMD_OP_MAX; i++)
 		spin_lock_init(&cmd->stats[i].lock);
 
 	sema_init(&cmd->sem, cmd->max_reg_cmds);
@@ -2046,7 +2052,8 @@ err_free_page:
 
 err_free_pool:
 	dma_pool_destroy(cmd->pool);
-
+dma_pool_err:
+	kvfree(cmd->stats);
 	return err;
 }
 EXPORT_SYMBOL(mlx5_cmd_init);
@@ -2060,6 +2067,7 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	destroy_msg_cache(dev);
 	free_cmd_page(dev, cmd);
 	dma_pool_destroy(cmd->pool);
+	kvfree(cmd->stats);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index d2d57213511b..07c8d9811bc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -171,7 +171,7 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev)
 	cmd = &dev->priv.cmdif_debugfs;
 	*cmd = debugfs_create_dir("commands", dev->priv.dbg_root);
 
-	for (i = 0; i < ARRAY_SIZE(dev->cmd.stats); i++) {
+	for (i = 0; i < MLX5_CMD_OP_MAX; i++) {
 		stats = &dev->cmd.stats[i];
 		namep = mlx5_command_str(i);
 		if (strcmp(namep, "unknown command opcode")) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6aa6bbd60559..13c0e4556eda 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -298,7 +298,7 @@ struct mlx5_cmd {
 	struct mlx5_cmd_debug dbg;
 	struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
 	int checksum_disabled;
-	struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
+	struct mlx5_cmd_stats *stats;
 };
 
 struct mlx5_port_caps {
-- 
cgit v1.2.3


From aee3e9c457f172870bdb87e675faf6c4528190b1 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 28 May 2020 18:42:40 -0700
Subject: net/mlx5: Accel: fpga tls fix cast to __be64 and incorrect argument
 types

tls handle and rcd_sn are actually big endian and not in host format.
Fix that.

Fix the following sparse warnings:
drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c:177:21:
warning: cast to restricted __be64

drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c:178:52:
warning: incorrect type in argument 2 (different base types)
    expected unsigned int [usertype] handle
    got restricted __be32 [usertype] handle

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c    | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h    | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c     | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h     | 4 ++--
 5 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index cab708af3422..cbf3d76c05a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -56,8 +56,8 @@ void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
 }
 
-int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
-			     u64 rcd_sn)
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
+			     u32 seq, __be64 rcd_sn)
 {
 	return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index e09bc3858d57..aefea467f7b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -109,8 +109,8 @@ int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
 			    bool direction_sx);
 void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 			     bool direction_sx);
-int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
-			     u64 rcd_sn);
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
+			     u32 seq, __be64 rcd_sn);
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
 u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
 int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
@@ -125,8 +125,8 @@ mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
 			bool direction_sx) { return -ENOTSUPP; }
 static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 					   bool direction_sx) { }
-static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
-					   u32 seq, u64 rcd_sn) { return 0; }
+static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
+					   u32 seq, __be64 rcd_sn) { return 0; }
 static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
 {
 	return mlx5_accel_is_ktls_device(mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index c27e9a609d51..1fbb5a90cb38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -167,7 +167,7 @@ static int mlx5e_tls_resync(struct net_device *netdev, struct sock *sk,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_tls_offload_context_rx *rx_ctx;
-	u64 rcd_sn = *(u64 *)rcd_sn_data;
+	__be64 rcd_sn = *(__be64 *)rcd_sn_data;
 
 	if (WARN_ON_ONCE(direction != TLS_OFFLOAD_CTX_DIR_RX))
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 22a2ef111514..29b7339ebfa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -194,8 +194,8 @@ static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
 		 MLX5_GET(tls_flow, flow, direction_sx));
 }
 
-int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
-			    u64 rcd_sn)
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
+			    u32 seq, __be64 rcd_sn)
 {
 	struct mlx5_fpga_dma_buf *buf;
 	int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
index 3b2e37bf76fe..5714cf391d1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
@@ -68,7 +68,7 @@ static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
 	return mdev->fpga->tls->caps;
 }
 
-int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
-			    u64 rcd_sn);
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, __be32 handle,
+			    u32 seq, __be64 rcd_sn);
 
 #endif /* __MLX5_FPGA_TLS_H__ */
-- 
cgit v1.2.3


From c51323ee7ab4132c80db198b7d0956fef957e6ab Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 27 May 2020 23:41:03 -0700
Subject: net/mlx5e: en_tc: Fix incorrect type in initializer warnings

Fix some trivial warnings of the type:
warning: incorrect type in initializer (different base types)

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ac19a61c5cbc..e866f209f252 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1873,7 +1873,7 @@ enc_opts_is_dont_care_or_full_match(struct mlx5e_priv *priv,
 		    memchr_inv(opt->opt_data, 0, opt->length * 4)) {
 			*dont_care = false;
 
-			if (opt->opt_class != U16_MAX ||
+			if (opt->opt_class != htons(U16_MAX) ||
 			    opt->type != U8_MAX) {
 				NL_SET_ERR_MSG(extack,
 					       "Partial match of tunnel options in chain > 0 isn't supported");
-- 
cgit v1.2.3


From 58ff18e12c9b3bb860b32e9cac4dc8e12aec2695 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 28 May 2020 00:22:12 -0700
Subject: net/mlx5e: en_tc: Fix cast to restricted __be32 warning

Fixes sparse warnings:
warning: cast to restricted __be32
warning: restricted __be32 degrades to integer

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e866f209f252..3ce177c24d52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -210,8 +210,8 @@ mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec,
 	fmask = headers_c + soffset;
 	fval = headers_v + soffset;
 
-	mask = cpu_to_be32(mask) >> (32 - (match_len * 8));
-	data = cpu_to_be32(data) >> (32 - (match_len * 8));
+	mask = (__force u32)(cpu_to_be32(mask)) >> (32 - (match_len * 8));
+	data = (__force u32)(cpu_to_be32(data)) >> (32 - (match_len * 8));
 
 	memcpy(fmask, &mask, match_len);
 	memcpy(fval, &data, match_len);
@@ -2815,10 +2815,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 			continue;
 
 		if (f->field_bsize == 32) {
-			mask_be32 = (__be32)mask;
+			mask_be32 = (__force __be32)(mask);
 			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
 		} else if (f->field_bsize == 16) {
-			mask_be32 = (__be32)mask;
+			mask_be32 = (__force __be32)(mask);
 			mask_be16 = *(__be16 *)&mask_be32;
 			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
 		}
-- 
cgit v1.2.3


From eb24387183d37f2f4f456654ef92679b1556f8df Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 29 May 2020 00:36:10 -0700
Subject: net/mlx5e: Make mlx5e_dcbnl_ops static

Fix sparse warning:
drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c:988:29:
error: symbol 'mlx5e_dcbnl_ops' was not declared. Should it be static?

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index ec7b332d74c2..bc102d094bbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -985,7 +985,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	return err;
 }
 
-const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = {
+static const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = {
 	.ieee_getets	= mlx5e_dcbnl_ieee_getets,
 	.ieee_setets	= mlx5e_dcbnl_ieee_setets,
 	.ieee_getmaxrate = mlx5e_dcbnl_ieee_getmaxrate,
-- 
cgit v1.2.3


From 1f4982ef56f794101cae7ec0fa3b7605f78bd25f Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:27 +0800
Subject: net: hns3: fix a print format issue in hclge_mac_mdio_config()

Use %d to print int variable 'ret' in hclge_mac_mdio_config().

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 696c5ae922e3..e89820702540 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -155,7 +155,7 @@ int hclge_mac_mdio_config(struct hclge_dev *hdev)
 	ret = mdiobus_register(mdio_bus);
 	if (ret) {
 		dev_err(mdio_bus->parent,
-			"Failed to register MDIO bus ret = %#x\n", ret);
+			"failed to register MDIO bus, ret = %d\n", ret);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From d62805087e7fbbd7582403b972dd75581256e585 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:28 +0800
Subject: net: hns3: remove an unused macro hclge_is_csq

Macro hclge_is_csq defined in hcgle_cmd.c has not been used,
so remove it.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 64a1d0bdd7d1..1d6c328bd9fb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -11,8 +11,6 @@
 #include "hnae3.h"
 #include "hclge_main.h"
 
-#define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ)
-
 #define cmq_ring_to_dev(ring)   (&(ring)->dev->pdev->dev)
 
 static int hclge_ring_space(struct hclge_cmq_ring *ring)
-- 
cgit v1.2.3


From fc68aed15648c70db0377a6abd2b34ec328dd12a Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:29 +0800
Subject: net: hns3: remove two unused macros in hclgevf_cmd.c

Macro hclgevf_ring_to_dma_dir and hclgevf_is_csq defined in
hclgevf_cmd.c, but not used, so remove them.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index f38d236ebf4f..fec65239a3c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -11,9 +11,6 @@
 #include "hclgevf_main.h"
 #include "hnae3.h"
 
-#define hclgevf_is_csq(ring) ((ring)->flag & HCLGEVF_TYPE_CSQ)
-#define hclgevf_ring_to_dma_dir(ring) (hclgevf_is_csq(ring) ? \
-					DMA_TO_DEVICE : DMA_FROM_DEVICE)
 #define cmq_ring_to_dev(ring)   (&(ring)->dev->pdev->dev)
 
 static int hclgevf_ring_space(struct hclgevf_cmq_ring *ring)
-- 
cgit v1.2.3


From ec4d9392207aad5db32cc518c4a5c8b7f1057fa1 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:30 +0800
Subject: net: hns3: fix an incorrect comment for num_tqps in struct
 hclgevf_dev

struct hclgevf_dev stands for VF device, its field num_tqps
indicates the number of VF's task queue pairs, so the comment
is incorrect, replace 'PF' with 'VF'.

Reported-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 738de124cfc4..c1fac8920ae3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -278,7 +278,7 @@ struct hclgevf_dev {
 	struct semaphore reset_sem;	/* protect reset process */
 
 	u32 fw_version;
-	u16 num_tqps;		/* num task queue pairs of this PF */
+	u16 num_tqps;		/* num task queue pairs of this VF */
 
 	u16 alloc_rss_size;	/* allocated RSS task queue */
 	u16 rss_size_max;	/* HW defined max RSS task queue */
-- 
cgit v1.2.3


From 2adb8187e5439e5066c9893586e5079e89f9060a Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:31 +0800
Subject: net: hns3: fix two coding style issues in hclgevf_main.c

Remove a redundant blank line in hclgevf_cmd_set_promisc_mode(),
and fix a reverse xmas tree coding style issue in
hclgevf_set_rss_tc_mode().

Reported-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a8c0e79901f5..1b9578d0bd80 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -669,8 +669,8 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	u16 tc_size[HCLGEVF_MAX_TC_NUM];
 	struct hclgevf_desc desc;
 	u16 roundup_size;
-	int status;
 	unsigned int i;
+	int status;
 
 	req = (struct hclgevf_rss_tc_mode_cmd *)desc.data;
 
@@ -1143,7 +1143,6 @@ static int hclgevf_cmd_set_promisc_mode(struct hclgevf_dev *hdev,
 	send_msg.en_mc = en_mc_pmc ? 1 : 0;
 
 	ret = hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0);
-
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set promisc mode fail, status is %d.\n", ret);
-- 
cgit v1.2.3


From 996aade998ac0e9f6f0bf09531c32f1106d9d559 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Sat, 30 May 2020 09:08:32 +0800
Subject: net: hns3: remove some unused codes in hns3_nic_set_features()

NETIF_F_HW_VLAN_CTAG_FILTER is not set in netdev->hw_feature for
the HNS3 driver, so the handler of NETIF_F_HW_VLAN_CTAG_FILTER
in hns3_nic_set_features() won't be called, remove it.

Reported-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 9fe40c7773b4..b14f2abc2425 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1544,12 +1544,6 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			return ret;
 	}
 
-	if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-	    h->ae_algo->ops->enable_vlan_filter) {
-		enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER);
-		h->ae_algo->ops->enable_vlan_filter(h, enable);
-	}
-
 	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    h->ae_algo->ops->enable_hw_strip_rxvtag) {
 		enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
-- 
cgit v1.2.3


From 27dc36aefc73ce50a485c9d32c33b18832289203 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:54:36 +0200
Subject: r8169: change driver data type

Change driver private data type to struct rtl8169_private * to avoid
some overhead.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 60 +++++++++++++------------------
 1 file changed, 25 insertions(+), 35 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index d672ae77c644..810398ef7186 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4816,15 +4816,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	pm_runtime_put_noidle(&pdev->dev);
 }
 
-static void rtl8169_net_suspend(struct net_device *dev)
+static void rtl8169_net_suspend(struct rtl8169_private *tp)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	if (!netif_running(dev))
+	if (!netif_running(tp->dev))
 		return;
 
 	phy_stop(tp->phydev);
-	netif_device_detach(dev);
+	netif_device_detach(tp->dev);
 
 	rtl_lock_work(tp);
 	napi_disable(&tp->napi);
@@ -4840,20 +4838,17 @@ static void rtl8169_net_suspend(struct net_device *dev)
 
 static int rtl8169_suspend(struct device *device)
 {
-	struct net_device *dev = dev_get_drvdata(device);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	rtl8169_net_suspend(dev);
+	rtl8169_net_suspend(tp);
 	clk_disable_unprepare(tp->clk);
 
 	return 0;
 }
 
-static void __rtl8169_resume(struct net_device *dev)
+static void __rtl8169_resume(struct rtl8169_private *tp)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	netif_device_attach(dev);
+	netif_device_attach(tp->dev);
 
 	rtl_pll_power_up(tp);
 	rtl8169_init_phy(tp);
@@ -4869,23 +4864,21 @@ static void __rtl8169_resume(struct net_device *dev)
 
 static int rtl8169_resume(struct device *device)
 {
-	struct net_device *dev = dev_get_drvdata(device);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	rtl_rar_set(tp, dev->dev_addr);
+	rtl_rar_set(tp, tp->dev->dev_addr);
 
 	clk_prepare_enable(tp->clk);
 
-	if (netif_running(dev))
-		__rtl8169_resume(dev);
+	if (netif_running(tp->dev))
+		__rtl8169_resume(tp);
 
 	return 0;
 }
 
 static int rtl8169_runtime_suspend(struct device *device)
 {
-	struct net_device *dev = dev_get_drvdata(device);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = dev_get_drvdata(device);
 
 	if (!tp->TxDescArray)
 		return 0;
@@ -4894,7 +4887,7 @@ static int rtl8169_runtime_suspend(struct device *device)
 	__rtl8169_set_wol(tp, WAKE_ANY);
 	rtl_unlock_work(tp);
 
-	rtl8169_net_suspend(dev);
+	rtl8169_net_suspend(tp);
 
 	/* Update counters before going runtime suspend */
 	rtl8169_update_counters(tp);
@@ -4904,10 +4897,9 @@ static int rtl8169_runtime_suspend(struct device *device)
 
 static int rtl8169_runtime_resume(struct device *device)
 {
-	struct net_device *dev = dev_get_drvdata(device);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	rtl_rar_set(tp, dev->dev_addr);
+	rtl_rar_set(tp, tp->dev->dev_addr);
 
 	if (!tp->TxDescArray)
 		return 0;
@@ -4916,16 +4908,16 @@ static int rtl8169_runtime_resume(struct device *device)
 	__rtl8169_set_wol(tp, tp->saved_wolopts);
 	rtl_unlock_work(tp);
 
-	__rtl8169_resume(dev);
+	__rtl8169_resume(tp);
 
 	return 0;
 }
 
 static int rtl8169_runtime_idle(struct device *device)
 {
-	struct net_device *dev = dev_get_drvdata(device);
+	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	if (!netif_running(dev) || !netif_carrier_ok(dev))
+	if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev))
 		pm_schedule_suspend(device, 10000);
 
 	return -EBUSY;
@@ -4970,13 +4962,12 @@ static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp)
 
 static void rtl_shutdown(struct pci_dev *pdev)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = pci_get_drvdata(pdev);
 
-	rtl8169_net_suspend(dev);
+	rtl8169_net_suspend(tp);
 
 	/* Restore original MAC address */
-	rtl_rar_set(tp, dev->perm_addr);
+	rtl_rar_set(tp, tp->dev->perm_addr);
 
 	rtl8169_hw_reset(tp);
 
@@ -4993,13 +4984,12 @@ static void rtl_shutdown(struct pci_dev *pdev)
 
 static void rtl_remove_one(struct pci_dev *pdev)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
-	struct rtl8169_private *tp = netdev_priv(dev);
+	struct rtl8169_private *tp = pci_get_drvdata(pdev);
 
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_get_noresume(&pdev->dev);
 
-	unregister_netdev(dev);
+	unregister_netdev(tp->dev);
 
 	if (r8168_check_dash(tp))
 		rtl8168_driver_stop(tp);
@@ -5007,7 +4997,7 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	rtl_release_firmware(tp);
 
 	/* restore original MAC address */
-	rtl_rar_set(tp, dev->perm_addr);
+	rtl_rar_set(tp, tp->dev->perm_addr);
 }
 
 static const struct net_device_ops rtl_netdev_ops = {
@@ -5446,7 +5436,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!tp->counters)
 		return -ENOMEM;
 
-	pci_set_drvdata(pdev, dev);
+	pci_set_drvdata(pdev, tp);
 
 	rc = r8169_mdio_register(tp);
 	if (rc)
-- 
cgit v1.2.3


From 01bd753d039553cf63830823d1dcc8a864174afc Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:55:30 +0200
Subject: r8169: enable WAKE_PHY as only WoL source when runtime-suspending

We go to runtime-suspend few secs after cable removal. As cable is
removed "physical link up" is the only meaningful WoL source.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 810398ef7186..6fcd35ac8110 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4884,7 +4884,7 @@ static int rtl8169_runtime_suspend(struct device *device)
 		return 0;
 
 	rtl_lock_work(tp);
-	__rtl8169_set_wol(tp, WAKE_ANY);
+	__rtl8169_set_wol(tp, WAKE_PHY);
 	rtl_unlock_work(tp);
 
 	rtl8169_net_suspend(tp);
-- 
cgit v1.2.3


From 9fdd50c579802adad09028eba86e5a7ef7c9b738 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:56:14 +0200
Subject: r8169: don't reset tx ring indexes in rtl8169_tx_clear

In places where the indexes have to be reset, we call
rtl8169_init_ring_indexes() anyway after rtl8169_tx_clear().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 6fcd35ac8110..43652c450892 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3955,7 +3955,6 @@ static void rtl8169_tx_clear_range(struct rtl8169_private *tp, u32 start,
 static void rtl8169_tx_clear(struct rtl8169_private *tp)
 {
 	rtl8169_tx_clear_range(tp, tp->dirty_tx, NUM_TX_DESC);
-	tp->cur_tx = tp->dirty_tx = 0;
 	netdev_reset_queue(tp->dev);
 }
 
-- 
cgit v1.2.3


From bac75d8565e800f7a4494d8c873e38dce33d6079 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:57:10 +0200
Subject: r8169: move some calls to rtl8169_hw_reset

Move calls that are needed before and after calling rtl8169_hw_reset()
into this function. This requires to move the function in the code.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 75 +++++++++++++++----------------
 1 file changed, 36 insertions(+), 39 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 43652c450892..5f3c50fb0647 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2530,36 +2530,6 @@ static void rtl_enable_rxdvgate(struct rtl8169_private *tp)
 	rtl_wait_txrx_fifo_empty(tp);
 }
 
-static void rtl8169_hw_reset(struct rtl8169_private *tp)
-{
-	/* Disable interrupts */
-	rtl8169_irq_mask_and_ack(tp);
-
-	rtl_rx_close(tp);
-
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		rtl_loop_wait_low(tp, &rtl_npq_cond, 20, 2000);
-		break;
-	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
-		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
-		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
-		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_61:
-		rtl_enable_rxdvgate(tp);
-		fsleep(2000);
-		break;
-	default:
-		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
-		udelay(100);
-		break;
-	}
-
-	rtl_hw_reset(tp);
-}
-
 static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
 {
 	u32 val = TX_DMA_BURST << TxDMAShift |
@@ -3958,6 +3928,42 @@ static void rtl8169_tx_clear(struct rtl8169_private *tp)
 	netdev_reset_queue(tp->dev);
 }
 
+static void rtl8169_hw_reset(struct rtl8169_private *tp)
+{
+	/* Give a racing hard_start_xmit a few cycles to complete. */
+	synchronize_rcu();
+
+	/* Disable interrupts */
+	rtl8169_irq_mask_and_ack(tp);
+
+	rtl_rx_close(tp);
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_27:
+	case RTL_GIGA_MAC_VER_28:
+	case RTL_GIGA_MAC_VER_31:
+		rtl_loop_wait_low(tp, &rtl_npq_cond, 20, 2000);
+		break;
+	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
+		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
+		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_61:
+		rtl_enable_rxdvgate(tp);
+		fsleep(2000);
+		break;
+	default:
+		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
+		fsleep(100);
+		break;
+	}
+
+	rtl_hw_reset(tp);
+
+	rtl8169_tx_clear(tp);
+	rtl8169_init_ring_indexes(tp);
+}
+
 static void rtl_reset_work(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
@@ -3965,16 +3971,12 @@ static void rtl_reset_work(struct rtl8169_private *tp)
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
-	synchronize_rcu();
 
 	rtl8169_hw_reset(tp);
 
 	for (i = 0; i < NUM_RX_DESC; i++)
 		rtl8169_mark_to_asic(tp->RxDescArray + i);
 
-	rtl8169_tx_clear(tp);
-	rtl8169_init_ring_indexes(tp);
-
 	napi_enable(&tp->napi);
 	rtl_hw_start(tp);
 	netif_wake_queue(dev);
@@ -4636,11 +4638,6 @@ static void rtl8169_down(struct net_device *dev)
 
 	rtl8169_hw_reset(tp);
 
-	/* Give a racing hard_start_xmit a few cycles to complete. */
-	synchronize_rcu();
-
-	rtl8169_tx_clear(tp);
-
 	rtl8169_rx_clear(tp);
 
 	rtl_pll_power_down(tp);
-- 
cgit v1.2.3


From 8ac8e8c64b539a548a5f22d6b21f999eea38b0ee Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:58:35 +0200
Subject: r8169: make rtl8169_down central chip quiesce function

Functionality for quiescing the chip is spread across different
functions currently. Move it to rtl8169_down().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 33 +++++++++++--------------------
 1 file changed, 11 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5f3c50fb0647..fd93377f961f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4627,20 +4627,21 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	return 0;
 }
 
-static void rtl8169_down(struct net_device *dev)
+static void rtl8169_down(struct rtl8169_private *tp)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
+	rtl_lock_work(tp);
 
-	phy_stop(tp->phydev);
+	/* Clear all task flags */
+	bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
 
+	phy_stop(tp->phydev);
 	napi_disable(&tp->napi);
-	netif_stop_queue(dev);
 
 	rtl8169_hw_reset(tp);
 
-	rtl8169_rx_clear(tp);
-
 	rtl_pll_power_down(tp);
+
+	rtl_unlock_work(tp);
 }
 
 static int rtl8169_close(struct net_device *dev)
@@ -4653,12 +4654,9 @@ static int rtl8169_close(struct net_device *dev)
 	/* Update counters before going down */
 	rtl8169_update_counters(tp);
 
-	rtl_lock_work(tp);
-	/* Clear all task flags */
-	bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
-
-	rtl8169_down(dev);
-	rtl_unlock_work(tp);
+	netif_stop_queue(dev);
+	rtl8169_down(tp);
+	rtl8169_rx_clear(tp);
 
 	cancel_work_sync(&tp->wk.work);
 
@@ -4817,17 +4815,8 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp)
 	if (!netif_running(tp->dev))
 		return;
 
-	phy_stop(tp->phydev);
 	netif_device_detach(tp->dev);
-
-	rtl_lock_work(tp);
-	napi_disable(&tp->napi);
-	/* Clear all task flags */
-	bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
-
-	rtl_unlock_work(tp);
-
-	rtl_pll_power_down(tp);
+	rtl8169_down(tp);
 }
 
 #ifdef CONFIG_PM
-- 
cgit v1.2.3


From 67ee63ef2b15fcb0cb692010083592672d18f0a8 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 May 2020 23:59:58 +0200
Subject: r8169: improve handling power management ops

Simplify handling the power management callbacks.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index fd93377f961f..4d2ec9742cee 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4821,7 +4821,7 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp)
 
 #ifdef CONFIG_PM
 
-static int rtl8169_suspend(struct device *device)
+static int __maybe_unused rtl8169_suspend(struct device *device)
 {
 	struct rtl8169_private *tp = dev_get_drvdata(device);
 
@@ -4847,7 +4847,7 @@ static void __rtl8169_resume(struct rtl8169_private *tp)
 	rtl_unlock_work(tp);
 }
 
-static int rtl8169_resume(struct device *device)
+static int __maybe_unused rtl8169_resume(struct device *device)
 {
 	struct rtl8169_private *tp = dev_get_drvdata(device);
 
@@ -4909,24 +4909,12 @@ static int rtl8169_runtime_idle(struct device *device)
 }
 
 static const struct dev_pm_ops rtl8169_pm_ops = {
-	.suspend		= rtl8169_suspend,
-	.resume			= rtl8169_resume,
-	.freeze			= rtl8169_suspend,
-	.thaw			= rtl8169_resume,
-	.poweroff		= rtl8169_suspend,
-	.restore		= rtl8169_resume,
-	.runtime_suspend	= rtl8169_runtime_suspend,
-	.runtime_resume		= rtl8169_runtime_resume,
-	.runtime_idle		= rtl8169_runtime_idle,
+	SET_SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume)
+	SET_RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume,
+			   rtl8169_runtime_idle)
 };
 
-#define RTL8169_PM_OPS	(&rtl8169_pm_ops)
-
-#else /* !CONFIG_PM */
-
-#define RTL8169_PM_OPS	NULL
-
-#endif /* !CONFIG_PM */
+#endif /* CONFIG_PM */
 
 static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp)
 {
@@ -5458,7 +5446,9 @@ static struct pci_driver rtl8169_pci_driver = {
 	.probe		= rtl_init_one,
 	.remove		= rtl_remove_one,
 	.shutdown	= rtl_shutdown,
-	.driver.pm	= RTL8169_PM_OPS,
+#ifdef CONFIG_PM
+	.driver.pm	= &rtl8169_pm_ops,
+#endif
 };
 
 module_pci_driver(rtl8169_pci_driver);
-- 
cgit v1.2.3


From 9b23203c32ee02cd316e39ba3ec243e0f7bf56de Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 29 May 2020 14:25:40 +0200
Subject: ravb: Mask PHY mode to avoid inserting delays twice

Until recently, the Micrel KSZ9031 PHY driver ignored any PHY mode
("RGMII-*ID") settings, but used the hardware defaults, augmented by
explicit configuration of individual skew values using the "*-skew-ps"
DT properties.  The lack of PHY mode support was compensated by the
EtherAVB MAC driver, which configures TX and/or RX internal delay
itself, based on the PHY mode.

However, now the KSZ9031 driver has gained PHY mode support, delays may
be configured twice, causing regressions.  E.g. on the Renesas
Salvator-X board with R-Car M3-W ES1.0, TX performance dropped from ca.
400 Mbps to 0.1-0.3 Mbps, as measured by nuttcp.

As internal delay configuration supported by the KSZ9031 PHY is too
limited for some use cases, the ability to configure MAC internal delay
is deemed useful and necessary.  Hence a proper fix would involve
splitting internal delay configuration in two parts, one for the PHY,
and one for the MAC.  However, this would require adding new DT
properties, thus breaking DTB backwards-compatibility.

Hence fix the regression in a backwards-compatibility way, by letting
the EtherAVB driver mask the PHY mode when it has inserted a delay, to
avoid the PHY driver adding a second delay.  This also fixes messages
like:

    Micrel KSZ9031 Gigabit PHY e6800000.ethernet-ffffffff:00: *-skew-ps values should be used only with phy-mode = "rgmii"

as the PHY no longer sees the original RGMII-*ID mode.

Solving the issue by splitting configuration in two parts can be handled
in future patches, and would require retaining a backwards-compatibility
mode anyway.

Fixes: bcf3440c6dd78bfe ("net: phy: micrel: add phy-mode support for the KSZ9031 PHY")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 067ad25553b9..a442bcf64b9c 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1014,6 +1014,7 @@ static int ravb_phy_init(struct net_device *ndev)
 	struct ravb_private *priv = netdev_priv(ndev);
 	struct phy_device *phydev;
 	struct device_node *pn;
+	phy_interface_t iface;
 	int err;
 
 	priv->link = 0;
@@ -1032,8 +1033,13 @@ static int ravb_phy_init(struct net_device *ndev)
 		}
 		pn = of_node_get(np);
 	}
-	phydev = of_phy_connect(ndev, pn, ravb_adjust_link, 0,
-				priv->phy_interface);
+
+	iface = priv->phy_interface;
+	if (priv->chip_id != RCAR_GEN2 && phy_interface_mode_is_rgmii(iface)) {
+		/* ravb_set_delay_mode() takes care of internal delay mode */
+		iface = PHY_INTERFACE_MODE_RGMII;
+	}
+	phydev = of_phy_connect(ndev, pn, ravb_adjust_link, 0, iface);
 	of_node_put(pn);
 	if (!phydev) {
 		netdev_err(ndev, "failed to connect PHY\n");
-- 
cgit v1.2.3


From f109603a4be0578a8145c8ae7d6e10b0b5ab6df4 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:17 -0700
Subject: ice: allow host to clear administratively set VF MAC

Currently a user is not allowed to clear a VF's administratively set MAC
on the PF. Fix this by allowing an all zero MAC address via "ip link set
${pf_eth} vf ${vf_id} mac 00:00:00:00:00:00".

An example use case for this would be issuing a "virsh shutdown"
command on a VM. The call to iproute mentioned above is part of this flow.
Without this change the driver incorrectly rejects clearing the VF's
administratively set MAC and prints unhelpful log messages.

Also, improve the comments surrounding this change.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index a126e7c7663d..9550501f9279 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -3904,7 +3904,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	if (ice_validate_vf_id(pf, vf_id))
 		return -EINVAL;
 
-	if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) {
+	if (is_multicast_ether_addr(mac)) {
 		netdev_err(netdev, "%pM not a valid unicast address\n", mac);
 		return -EINVAL;
 	}
@@ -3924,15 +3924,21 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		return -EINVAL;
 	}
 
-	/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
-	 * flow will use the updated dflt_lan_addr and add a MAC filter
-	 * using ice_add_mac. Also set pf_set_mac to indicate that the PF has
-	 * set the MAC address for this VF.
+	/* VF is notified of its new MAC via the PF's response to the
+	 * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset
 	 */
 	ether_addr_copy(vf->dflt_lan_addr.addr, mac);
-	vf->pf_set_mac = true;
-	netdev_info(netdev, "MAC on VF %d set to %pM. VF driver will be reinitialized\n",
-		    vf_id, mac);
+	if (is_zero_ether_addr(mac)) {
+		/* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */
+		vf->pf_set_mac = false;
+		netdev_info(netdev, "Removing MAC on VF %d. VF driver will be reinitialized\n",
+			    vf->vf_id);
+	} else {
+		/* PF will add MAC rule for the VF */
+		vf->pf_set_mac = true;
+		netdev_info(netdev, "Setting MAC %pM on VF %d. VF driver will be reinitialized\n",
+			    mac, vf_id);
+	}
 
 	ice_vc_reset_vf(vf);
 	return 0;
-- 
cgit v1.2.3


From c1636a6e8a5e10190bd31ae085f9e8f8c5bc50a0 Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Fri, 15 May 2020 17:51:18 -0700
Subject: ice: support adding 16 unicast/multicast filter on untrusted VF

Allow untrusted VF to add 16 unicast/multicast filters. VF uses 1 filter
for the default/perm_addr/LAA MAC, 1 for broadcast, and 16 additional
unicast/multicast filters.

Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 0adff89a6749..67aa9110fdd1 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -7,7 +7,10 @@
 
 /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */
 #define ICE_MAX_VLAN_PER_VF		8
-#define ICE_MAX_MACADDR_PER_VF		12
+/* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for
+ * broadcast, and 16 for additional unicast/multicast filters
+ */
+#define ICE_MAX_MACADDR_PER_VF		18
 
 /* Malicious Driver Detection */
 #define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED		10
-- 
cgit v1.2.3


From 2bb19d6e077190bafbfd50f3793333af3f07a7b1 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:51:19 -0700
Subject: ice: Fix transmit for all software offloaded VLANs

Currently the driver does not recognize when there is an 802.1AD VLAN
tag right after the dmac/smac (outermost VLAN tag). If any DCB map is
applied and/or DCB is enabled this is causing the hardware to insert a
VLAN 0 tag after the 802.1AD VLAN tag that is already in the packet.
Fix this by preventing VLAN tag 0 from being added when any VLAN is
already present after dmac/smac (software offloaded) or skb (hardware
offloaded).

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 28 +++++++----------
 drivers/net/ethernet/intel/ice/ice_dcb_lib.h |  2 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c    | 45 +++++++---------------------
 3 files changed, 21 insertions(+), 54 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 3c7f604c0c49..979af197f8a3 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -791,39 +791,31 @@ void ice_update_dcb_stats(struct ice_pf *pf)
  * ice_tx_prepare_vlan_flags_dcb - prepare VLAN tagging for DCB
  * @tx_ring: ring to send buffer on
  * @first: pointer to struct ice_tx_buf
+ *
+ * This should not be called if the outer VLAN is software offloaded as the VLAN
+ * tag will already be configured with the correct ID and priority bits
  */
-int
+void
 ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
 			      struct ice_tx_buf *first)
 {
 	struct sk_buff *skb = first->skb;
 
 	if (!test_bit(ICE_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
-		return 0;
+		return;
 
 	/* Insert 802.1p priority into VLAN header */
-	if ((first->tx_flags & (ICE_TX_FLAGS_HW_VLAN | ICE_TX_FLAGS_SW_VLAN)) ||
+	if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN) ||
 	    skb->priority != TC_PRIO_CONTROL) {
 		first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M;
 		/* Mask the lower 3 bits to set the 802.1p priority */
 		first->tx_flags |= (skb->priority & 0x7) <<
 				   ICE_TX_FLAGS_VLAN_PR_S;
-		if (first->tx_flags & ICE_TX_FLAGS_SW_VLAN) {
-			struct vlan_ethhdr *vhdr;
-			int rc;
-
-			rc = skb_cow_head(skb, 0);
-			if (rc < 0)
-				return rc;
-			vhdr = (struct vlan_ethhdr *)skb->data;
-			vhdr->h_vlan_TCI = htons(first->tx_flags >>
-						 ICE_TX_FLAGS_VLAN_S);
-		} else {
-			first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
-		}
+		/* if this is not already set it means a VLAN 0 + priority needs
+		 * to be offloaded
+		 */
+		first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
 	}
-
-	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
index 7c42324494d2..323238669572 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -27,7 +27,7 @@ void ice_pf_dcb_recfg(struct ice_pf *pf);
 void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi);
 int ice_init_pf_dcb(struct ice_pf *pf, bool locked);
 void ice_update_dcb_stats(struct ice_pf *pf);
-int
+void
 ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
 			      struct ice_tx_buf *first);
 void
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index cda7e05bd8ae..abdb137c8bb7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2053,49 +2053,25 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
  *
  * Checks the skb and set up correspondingly several generic transmit flags
  * related to VLAN tagging for the HW, such as VLAN, DCB, etc.
- *
- * Returns error code indicate the frame should be dropped upon error and the
- * otherwise returns 0 to indicate the flags has been set properly.
  */
-static int
+static void
 ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first)
 {
 	struct sk_buff *skb = first->skb;
-	__be16 protocol = skb->protocol;
-
-	if (protocol == htons(ETH_P_8021Q) &&
-	    !(tx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
-		/* when HW VLAN acceleration is turned off by the user the
-		 * stack sets the protocol to 8021q so that the driver
-		 * can take any steps required to support the SW only
-		 * VLAN handling. In our case the driver doesn't need
-		 * to take any further steps so just set the protocol
-		 * to the encapsulated ethertype.
-		 */
-		skb->protocol = vlan_get_protocol(skb);
-		return 0;
-	}
 
-	/* if we have a HW VLAN tag being added, default to the HW one */
+	/* nothing left to do, software offloaded VLAN */
+	if (!skb_vlan_tag_present(skb) && eth_type_vlan(skb->protocol))
+		return;
+
+	/* currently, we always assume 802.1Q for VLAN insertion as VLAN
+	 * insertion for 802.1AD is not supported
+	 */
 	if (skb_vlan_tag_present(skb)) {
 		first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S;
 		first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
-	} else if (protocol == htons(ETH_P_8021Q)) {
-		struct vlan_hdr *vhdr, _vhdr;
-
-		/* for SW VLAN, check the next protocol and store the tag */
-		vhdr = (struct vlan_hdr *)skb_header_pointer(skb, ETH_HLEN,
-							     sizeof(_vhdr),
-							     &_vhdr);
-		if (!vhdr)
-			return -EINVAL;
-
-		first->tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
-				   ICE_TX_FLAGS_VLAN_S;
-		first->tx_flags |= ICE_TX_FLAGS_SW_VLAN;
 	}
 
-	return ice_tx_prepare_vlan_flags_dcb(tx_ring, first);
+	ice_tx_prepare_vlan_flags_dcb(tx_ring, first);
 }
 
 /**
@@ -2403,8 +2379,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	first->tx_flags = 0;
 
 	/* prepare the VLAN tagging flags for Tx */
-	if (ice_tx_prepare_vlan_flags(tx_ring, first))
-		goto out_drop;
+	ice_tx_prepare_vlan_flags(tx_ring, first);
 
 	/* set up TSO offload */
 	tso = ice_tso(first, &offload);
-- 
cgit v1.2.3


From c9a12d6d2091175fe2dc1707dd40d6ad781414fe Mon Sep 17 00:00:00 2001
From: Dan Nowlin <dan.nowlin@intel.com>
Date: Fri, 15 May 2020 17:51:20 -0700
Subject: ice: Increase timeout after PFR

To allow for resets during package download, increase the timeout period
after performing a PFR. The time waited is the global config lock
timeout plus the normal PFSWR timeout.

Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 8c73e161829d..d4a31c734326 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -964,7 +964,12 @@ static enum ice_status ice_pf_reset(struct ice_hw *hw)
 
 	wr32(hw, PFGEN_CTRL, (reg | PFGEN_CTRL_PFSWR_M));
 
-	for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) {
+	/* Wait for the PFR to complete. The wait time is the global config lock
+	 * timeout plus the PFR timeout which will account for a possible reset
+	 * that is occurring during a download package operation.
+	 */
+	for (cnt = 0; cnt < ICE_GLOBAL_CFG_LOCK_TIMEOUT +
+	     ICE_PF_RESET_WAIT_COUNT; cnt++) {
 		reg = rd32(hw, PFGEN_CTRL);
 		if (!(reg & PFGEN_CTRL_PFSWR_M))
 			break;
-- 
cgit v1.2.3


From bff185e2406e10d2608857171537645714bea1f4 Mon Sep 17 00:00:00 2001
From: Chinh T Cao <chinh.t.cao@intel.com>
Date: Fri, 15 May 2020 17:51:21 -0700
Subject: ice: Update ICE_PHY_TYPE_HIGH_MAX_INDEX value

As currently, we are supporting only 5 PHY_SPEEDs for phy_type_high.
Thus, we should adjust the value of ICE_PHY_TYPE_HIGH_MAX_INDEX to 5.

Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index f04c338fb6e0..50040c5c55ec 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -974,7 +974,7 @@ struct ice_aqc_get_phy_caps {
 #define ICE_PHY_TYPE_HIGH_100G_CAUI2		BIT_ULL(2)
 #define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC	BIT_ULL(3)
 #define ICE_PHY_TYPE_HIGH_100G_AUI2		BIT_ULL(4)
-#define ICE_PHY_TYPE_HIGH_MAX_INDEX		19
+#define ICE_PHY_TYPE_HIGH_MAX_INDEX		5
 
 struct ice_aqc_get_phy_caps_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-- 
cgit v1.2.3


From cf0bf41dd6cb1d5461c71d2159c7c062fff3c8fd Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:54:58 -0700
Subject: ice: Reset VF for all port VLAN changes from host

Currently the PF is modifying the VF's port VLAN on the fly when
configured via iproute. This is okay for most cases, but if the VF
already has guest VLANs configured the PF has to remove all of those
filters so only VLAN tagged traffic that matches the port VLAN will
pass. Instead of adding functionality to track which guest VLANs have
been added, just reset the VF each time port VLAN parameters are
modified.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 42 +++---------------------
 1 file changed, 5 insertions(+), 37 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 9550501f9279..2916cfb9d032 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -3295,7 +3295,6 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 		     __be16 vlan_proto)
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
-	struct ice_vsi *vsi;
 	struct device *dev;
 	struct ice_vf *vf;
 	u16 vlanprio;
@@ -3317,8 +3316,6 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 	}
 
 	vf = &pf->vf[vf_id];
-	vsi = pf->vsi[vf->lan_vsi_idx];
-
 	ret = ice_check_vf_ready_for_cfg(vf);
 	if (ret)
 		return ret;
@@ -3331,44 +3328,15 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 		return 0;
 	}
 
-	if (vlan_id || qos) {
-		/* remove VLAN 0 filter set by default when transitioning from
-		 * no port VLAN to a port VLAN. No change to old port VLAN on
-		 * failure.
-		 */
-		ret = ice_vsi_kill_vlan(vsi, 0);
-		if (ret)
-			return ret;
-		ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
-		if (ret)
-			return ret;
-	} else {
-		/* add VLAN 0 filter back when transitioning from port VLAN to
-		 * no port VLAN. No change to old port VLAN on failure.
-		 */
-		ret = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI);
-		if (ret)
-			return ret;
-		ret = ice_vsi_manage_pvid(vsi, 0, false);
-		if (ret)
-			return ret;
-	}
+	vf->port_vlan_info = vlanprio;
 
-	if (vlan_id) {
+	if (vf->port_vlan_info)
 		dev_info(dev, "Setting VLAN %d, QoS 0x%x on VF %d\n",
 			 vlan_id, qos, vf_id);
+	else
+		dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id);
 
-		/* add VLAN filter for the port VLAN */
-		ret = ice_vsi_add_vlan(vsi, vlan_id, ICE_FWD_TO_VSI);
-		if (ret)
-			return ret;
-	}
-	/* remove old port VLAN filter with valid VLAN ID or QoS fields */
-	if (vf->port_vlan_info)
-		ice_vsi_kill_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK);
-
-	/* keep port VLAN information persistent on resets */
-	vf->port_vlan_info = le16_to_cpu(vsi->info.pvid);
+	ice_vc_reset_vf(vf);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 401ce33b32812a8fde6789588416d8c5b232138f Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:54:59 -0700
Subject: ice: Always clear QRXFLXP_CNTXT before writing new value

Always clear the previous value in QRXFLXP_CNTXT before writing a new
value. This will make it so re-used queues will not accidentally take the
previously configured settings.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 33 +++++++++++--------------------
 drivers/net/ethernet/intel/ice/ice_lib.c  | 26 ++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.h  |  3 +++
 3 files changed, 40 insertions(+), 22 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index a174911d8994..d620d26d42ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -3,6 +3,7 @@
 
 #include <net/xdp_sock_drv.h>
 #include "ice_base.h"
+#include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
 /**
@@ -288,7 +289,6 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
 	struct ice_hw *hw;
-	u32 regval;
 	u16 pf_q;
 	int err;
 
@@ -385,27 +385,16 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* Rx queue threshold in units of 64 */
 	rlan_ctx.lrxqthresh = 1;
 
-	 /* Enable Flexible Descriptors in the queue context which
-	  * allows this driver to select a specific receive descriptor format
-	  */
-	regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
-	if (vsi->type != ICE_VSI_VF) {
-		regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
-			QRXFLXP_CNTXT_RXDID_IDX_M;
-
-		/* increasing context priority to pick up profile ID;
-		 * default is 0x01; setting to 0x03 to ensure profile
-		 * is programming if prev context is of same priority
-		 */
-		regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) &
-			QRXFLXP_CNTXT_RXDID_PRIO_M;
-
-	} else {
-		regval &= ~(QRXFLXP_CNTXT_RXDID_IDX_M |
-			    QRXFLXP_CNTXT_RXDID_PRIO_M |
-			    QRXFLXP_CNTXT_TS_M);
-	}
-	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
+	/* Enable Flexible Descriptors in the queue context which
+	 * allows this driver to select a specific receive descriptor format
+	 * increasing context priority to pick up profile ID; default is 0x01;
+	 * setting to 0x03 to ensure profile is programming if prev context is
+	 * of same priority
+	 */
+	if (vsi->type != ICE_VSI_VF)
+		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3);
+	else
+		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 89e8e4f7f56f..ecc04a696e50 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1595,6 +1595,32 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
 	}
 }
 
+/**
+ * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register
+ * @hw: HW pointer
+ * @pf_q: index of the Rx queue in the PF's queue space
+ * @rxdid: flexible descriptor RXDID
+ * @prio: priority for the RXDID for this queue
+ */
+void
+ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
+{
+	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
+
+	/* clear any previous values */
+	regval &= ~(QRXFLXP_CNTXT_RXDID_IDX_M |
+		    QRXFLXP_CNTXT_RXDID_PRIO_M |
+		    QRXFLXP_CNTXT_TS_M);
+
+	regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
+		QRXFLXP_CNTXT_RXDID_IDX_M;
+
+	regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) &
+		QRXFLXP_CNTXT_RXDID_PRIO_M;
+
+	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
+}
+
 /**
  * ice_vsi_cfg_rxqs - Configure the VSI for Rx
  * @vsi: the VSI being configured
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 076e635e0c9f..d80e6afa4511 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -74,6 +74,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
 
+void
+ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio);
+
 void ice_vsi_put_qs(struct ice_vsi *vsi);
 
 void ice_vsi_dis_irq(struct ice_vsi *vsi);
-- 
cgit v1.2.3


From 765dd7a1827c687b782e6ab3dd6daf4d13a4780f Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Fri, 15 May 2020 17:55:00 -0700
Subject: ice: Fix inability to set channels when down

Currently the driver prevents a user from doing
modprobe ice
ethtool -L eth0 combined 5
ip link set eth0 up

The ethtool command fails, because the driver is checking to see if the
interface is down before allowing the get_channels to proceed (even for
a set_channels).

Remove this check and allow the user to configure the interface
before bringing it up, which is a much better usability case.

Fixes: 87324e747fde ("ice: Implement ethtool ops for channels")
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index fd1849155d85..68c38004a088 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3189,10 +3189,6 @@ ice_get_channels(struct net_device *dev, struct ethtool_channels *ch)
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 
-	/* check to see if VSI is active */
-	if (test_bit(__ICE_DOWN, vsi->state))
-		return;
-
 	/* report maximum channels */
 	ch->max_rx = ice_get_max_rxq(pf);
 	ch->max_tx = ice_get_max_txq(pf);
-- 
cgit v1.2.3


From 7dcc0fb8f64913c783c7c1f06065c47e39b19794 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:55:01 -0700
Subject: ice: Allow VF to request reset as soon as it's initialized

A VF driver has the ability to request reset via VIRTCHNL_OP_RESET_VF.
This is a required step in VF driver load. Currently, the PF is only
allowing a VF to request reset using this method after the VF has
already communicated resources via VIRTCHNL_OP_GET_VF_RESOURCES.
However, this is incorrect because the VF can request reset before
requesting resources. Fix this by allowing the VF to request a reset
once it has been initialized.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 2916cfb9d032..16a2f2526ccc 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -2014,7 +2014,7 @@ err:
  */
 static void ice_vc_reset_vf_msg(struct ice_vf *vf)
 {
-	if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+	if (test_bit(ICE_VF_STATE_INIT, vf->vf_states))
 		ice_reset_vf(vf, false);
 }
 
-- 
cgit v1.2.3


From ebb462dc21eae79bed5b050afb225534992bd1f0 Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Fri, 15 May 2020 17:55:02 -0700
Subject: ice: fix function signature style format

Where possible, cuddle multiple lines of function signatures to be
consistent throughout the code.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c |  3 +--
 drivers/net/ethernet/intel/ice/ice_sched.c    | 12 ++++--------
 drivers/net/ethernet/intel/ice/ice_switch.c   |  9 +++------
 3 files changed, 8 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 479a74efc536..1e18021aa073 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -769,8 +769,7 @@ enum ice_status ice_create_all_ctrlq(struct ice_hw *hw)
  *
  * Destroys the send and receive queue locks for a given control queue.
  */
-static void
-ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq)
+static void ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq)
 {
 	mutex_destroy(&cq->sq_lock);
 	mutex_destroy(&cq->rq_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index d63acd2fcf79..0475134295e4 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1714,8 +1714,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
  * This function removes single aggregator VSI info entry from
  * aggregator list.
  */
-static void
-ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
+static void ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
 {
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
@@ -1947,8 +1946,7 @@ ice_sched_cfg_node_bw_alloc(struct ice_hw *hw, struct ice_sched_node *node,
  *
  * Save or clear CIR bandwidth (BW) in the passed param bw_t_info.
  */
-static void
-ice_set_clear_cir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
+static void ice_set_clear_cir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
 {
 	if (bw == ICE_SCHED_DFLT_BW) {
 		clear_bit(ICE_BW_TYPE_CIR, bw_t_info->bw_t_bitmap);
@@ -1967,8 +1965,7 @@ ice_set_clear_cir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
  *
  * Save or clear EIR bandwidth (BW) in the passed param bw_t_info.
  */
-static void
-ice_set_clear_eir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
+static void ice_set_clear_eir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
 {
 	if (bw == ICE_SCHED_DFLT_BW) {
 		clear_bit(ICE_BW_TYPE_EIR, bw_t_info->bw_t_bitmap);
@@ -1993,8 +1990,7 @@ ice_set_clear_eir_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
  *
  * Save or clear shared bandwidth (BW) in the passed param bw_t_info.
  */
-static void
-ice_set_clear_shared_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
+static void ice_set_clear_shared_bw(struct ice_bw_type_info *bw_t_info, u32 bw)
 {
 	if (bw == ICE_SCHED_DFLT_BW) {
 		clear_bit(ICE_BW_TYPE_SHARED, bw_t_info->bw_t_bitmap);
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 0156b73df1b1..ff7d16ac693e 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1612,8 +1612,7 @@ exit:
  * check for duplicates in this case, removing duplicates from a given
  * list should be taken care of in the caller of this function.
  */
-enum ice_status
-ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
+enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
 {
 	struct ice_aqc_sw_rules_elem *s_rule, *r_iter;
 	struct ice_fltr_list_entry *m_list_itr;
@@ -1914,8 +1913,7 @@ exit:
  * @hw: pointer to the hardware structure
  * @v_list: list of VLAN entries and forwarding information
  */
-enum ice_status
-ice_add_vlan(struct ice_hw *hw, struct list_head *v_list)
+enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *v_list)
 {
 	struct ice_fltr_list_entry *v_list_itr;
 
@@ -2145,8 +2143,7 @@ ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id,
  * the entries passed into m_list were added previously. It will not attempt to
  * do a partial remove of entries that were found.
  */
-enum ice_status
-ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
+enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list)
 {
 	struct ice_fltr_list_entry *list_itr, *tmp;
 	struct mutex *rule_lock; /* Lock to protect filter rule list */
-- 
cgit v1.2.3


From 1a9c561aa35534a03c0aa51c7fb1485731202a7c Mon Sep 17 00:00:00 2001
From: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Date: Fri, 15 May 2020 17:55:03 -0700
Subject: ice: fix PCI device serial number to be lowercase values

Commit ceb2f00707f9 ("ice: Use pci_get_dsn()") changed the code to
use a new function to get the Device Serial Number. It also changed
the case of the filename for loading a package on a specific NIC
from lowercase to uppercase. Change the filename back to
lowercase since that is what we specified.

Fixes: ceb2f00707f9 ("ice: Use pci_get_dsn()")
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index bbf92d2f1ac1..cb72ff32a29b 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3248,7 +3248,7 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf)
 	if (!opt_fw_filename)
 		return NULL;
 
-	snprintf(opt_fw_filename, NAME_MAX, "%sice-%016llX.pkg",
+	snprintf(opt_fw_filename, NAME_MAX, "%sice-%016llx.pkg",
 		 ICE_DDP_PKG_PATH, dsn);
 
 	return opt_fw_filename;
-- 
cgit v1.2.3


From a039f6fcba452fba5973798f4c641eee1ef770a1 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@intel.com>
Date: Fri, 15 May 2020 17:55:04 -0700
Subject: ice: Use coalesce values from q_vector 0 when increasing q_vectors

Currently when a VSI is built (i.e. reset, set channels, etc.)
the coalesce settings will be preserved in most cases. However, when the
number of q_vectors are increased the settings for the new q_vectors
will be set to the driver defaults of AIM on, Rx/Tx ITR 50, and INTRL 0.
This is causing issues with how the ethtool layer gets the current
coalesce settings since it only uses q_vector 0. So, assume that the user
set the coalesce settings globally (i.e. ethtool -C eth0) and use q_vector
0's settings for all of the new q_vectors.

Signed-off-by: Brett Creeley <brett.creeley@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index ecc04a696e50..28b46cc9f5cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2707,15 +2707,13 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi,
 		ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i],
 						&coalesce[i]);
 
-	for (; i < vsi->num_q_vectors; i++) {
-		struct ice_coalesce_stored coalesce_dflt = {
-			.itr_tx = ICE_DFLT_TX_ITR,
-			.itr_rx = ICE_DFLT_RX_ITR,
-			.intrl = 0
-		};
+	/* number of q_vectors increased, so assume coalesce settings were
+	 * changed globally (i.e. ethtool -C eth0 instead of per-queue) and use
+	 * the previous settings from q_vector 0 for all of the new q_vectors
+	 */
+	for (; i < vsi->num_q_vectors; i++)
 		ice_vsi_rebuild_update_coalesce(vsi->q_vectors[i],
-						&coalesce_dflt);
-	}
+						&coalesce[0]);
 }
 
 /**
-- 
cgit v1.2.3


From d5329be9907723a646f8874388cdaaccba988b4d Mon Sep 17 00:00:00 2001
From: Henry Tieman <henry.w.tieman@intel.com>
Date: Fri, 15 May 2020 17:55:05 -0700
Subject: ice: fix aRFS after flow director delete

The logic was missing for adding back perfect flows after flow director
filter delete. The code now adds perfect flows into the HW tables after
filter delete.

Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 27 ++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 42803fc0ed18..d7430ce6af26 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1363,6 +1363,31 @@ release_lock:
 	mutex_unlock(&hw->fdir_fltr_lock);
 }
 
+/**
+ * ice_fdir_do_rem_flow - delete flow and possibly add perfect flow
+ * @pf: PF structure
+ * @flow_type: FDir flow type to release
+ */
+static void
+ice_fdir_do_rem_flow(struct ice_pf *pf, enum ice_fltr_ptype flow_type)
+{
+	struct ice_hw *hw = &pf->hw;
+	bool need_perfect = false;
+
+	if (flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+	    flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP ||
+	    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_TCP ||
+	    flow_type == ICE_FLTR_PTYPE_NONF_IPV6_UDP)
+		need_perfect = true;
+
+	if (need_perfect && test_bit(flow_type, hw->fdir_perfect_fltr))
+		return;
+
+	ice_fdir_rem_flow(hw, ICE_BLK_FD, flow_type);
+	if (need_perfect)
+		ice_create_init_fdir_rule(pf, flow_type);
+}
+
 /**
  * ice_fdir_update_list_entry - add or delete a filter from the filter list
  * @pf: PF structure
@@ -1393,7 +1418,7 @@ ice_fdir_update_list_entry(struct ice_pf *pf, struct ice_fdir_fltr *input,
 			/* we just deleted the last filter of flow_type so we
 			 * should also delete the HW filter info.
 			 */
-			ice_fdir_rem_flow(hw, ICE_BLK_FD, old_fltr->flow_type);
+			ice_fdir_do_rem_flow(pf, old_fltr->flow_type);
 		list_del(&old_fltr->fltr_node);
 		devm_kfree(ice_hw_to_dev(hw), old_fltr);
 	}
-- 
cgit v1.2.3


From b5e19a642b7ed3d9e6de746957226a7ae726d226 Mon Sep 17 00:00:00 2001
From: Chinh T Cao <chinh.t.cao@intel.com>
Date: Fri, 15 May 2020 17:55:06 -0700
Subject: ice: Ignore EMODE when setting PHY config

When setting the PHY cfg (CQ cmd 0x0601), if the firmware responds
with an EMODE error, software will ignore the error as it simply
means that manageability (ex: BMC) is in control of the link and that
the new setting may not be applied.

Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 1 +
 drivers/net/ethernet/intel/ice/ice_common.c     | 7 ++++++-
 drivers/net/ethernet/intel/ice/ice_main.c       | 2 ++
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 50040c5c55ec..92f82f2a8af4 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1826,6 +1826,7 @@ enum ice_aq_err {
 	ICE_AQ_RC_EINVAL	= 14, /* Invalid argument */
 	ICE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
 	ICE_AQ_RC_ENOSYS	= 17, /* Function not implemented */
+	ICE_AQ_RC_EMODE		= 21, /* Op not allowed in current dev mode */
 	ICE_AQ_RC_ENOSEC	= 24, /* Missing security manifest */
 	ICE_AQ_RC_EBADSIG	= 25, /* Bad RSA signature */
 	ICE_AQ_RC_ESVN		= 26, /* SVN number prohibits this package */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index d4a31c734326..bce0e1281168 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2232,6 +2232,7 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
 		   struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd)
 {
 	struct ice_aq_desc desc;
+	enum ice_status status;
 
 	if (!cfg)
 		return ICE_ERR_PARAM;
@@ -2260,7 +2261,11 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
 	ice_debug(hw, ICE_DBG_LINK, "eeer_value = 0x%x\n", cfg->eeer_value);
 	ice_debug(hw, ICE_DBG_LINK, "link_fec_opt = 0x%x\n", cfg->link_fec_opt);
 
-	return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
+	status = ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
+	if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE)
+		status = 0;
+
+	return status;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index cb72ff32a29b..082825e3cb39 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5159,6 +5159,8 @@ const char *ice_aq_str(enum ice_aq_err aq_err)
 		return "ICE_AQ_RC_ENOSPC";
 	case ICE_AQ_RC_ENOSYS:
 		return "ICE_AQ_RC_ENOSYS";
+	case ICE_AQ_RC_EMODE:
+		return "ICE_AQ_RC_EMODE";
 	case ICE_AQ_RC_ENOSEC:
 		return "ICE_AQ_RC_ENOSEC";
 	case ICE_AQ_RC_EBADSIG:
-- 
cgit v1.2.3


From bda6752f3de99e9d765638b89aacfb11c07cee06 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 28 May 2020 15:49:57 +0300
Subject: cxgb4: cleanup error code in setup_sge_queues_uld()

The caller doesn't care about the error codes, they only check for zero
vs non-zero.  Still, it's better to preserve the negative error codes
from alloc_uld_rxqs() instead of changing it to 1.  We can also return
directly if there is a failure.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 6b1d3df4b9ba..9e3c6b36cde8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -174,13 +174,14 @@ static int
 setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 {
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
-	int i, ret = 0;
+	int i, ret;
 
-	ret = !(!alloc_uld_rxqs(adap, rxq_info, lro));
+	ret = alloc_uld_rxqs(adap, rxq_info, lro);
+	if (ret)
+		return ret;
 
 	/* Tell uP to route control queue completions to rdma rspq */
-	if (adap->flags & CXGB4_FULL_INIT_DONE &&
-	    !ret && uld_type == CXGB4_ULD_RDMA) {
+	if (adap->flags & CXGB4_FULL_INIT_DONE && uld_type == CXGB4_ULD_RDMA) {
 		struct sge *s = &adap->sge;
 		unsigned int cmplqid;
 		u32 param, cmdop;
-- 
cgit v1.2.3


From 240f1ae40c659713a53f8fa5e4899e7b7350bfed Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Thu, 28 May 2020 17:45:03 +0200
Subject: net: ethernet: mtk-star-emac: use regmap bitops

Shrink the code visually by replacing regmap_update_bits() with
appropriate regmap bit operations where applicable.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 80 ++++++++++++---------------
 1 file changed, 35 insertions(+), 45 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 7df35872c107..f1ace4fec19f 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -413,8 +413,8 @@ static void mtk_star_dma_unmap_tx(struct mtk_star_priv *priv,
 
 static void mtk_star_nic_disable_pd(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
-			   MTK_STAR_BIT_MAC_CFG_NIC_PD, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
+			  MTK_STAR_BIT_MAC_CFG_NIC_PD);
 }
 
 /* Unmask the three interrupts we care about, mask all others. */
@@ -434,41 +434,38 @@ static void mtk_star_intr_disable(struct mtk_star_priv *priv)
 
 static void mtk_star_intr_enable_tx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_BIT_INT_STS_TNTC, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			  MTK_STAR_BIT_INT_STS_TNTC);
 }
 
 static void mtk_star_intr_enable_rx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_BIT_INT_STS_FNRC, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			  MTK_STAR_BIT_INT_STS_FNRC);
 }
 
 static void mtk_star_intr_enable_stats(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_REG_INT_STS_MIB_CNT_TH, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			  MTK_STAR_REG_INT_STS_MIB_CNT_TH);
 }
 
 static void mtk_star_intr_disable_tx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_BIT_INT_STS_TNTC,
-			   MTK_STAR_BIT_INT_STS_TNTC);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			MTK_STAR_BIT_INT_STS_TNTC);
 }
 
 static void mtk_star_intr_disable_rx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_BIT_INT_STS_FNRC,
-			   MTK_STAR_BIT_INT_STS_FNRC);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			MTK_STAR_BIT_INT_STS_FNRC);
 }
 
 static void mtk_star_intr_disable_stats(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_INT_MASK,
-			   MTK_STAR_REG_INT_STS_MIB_CNT_TH,
-			   MTK_STAR_REG_INT_STS_MIB_CNT_TH);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
+			MTK_STAR_REG_INT_STS_MIB_CNT_TH);
 }
 
 static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv)
@@ -524,12 +521,10 @@ static void mtk_star_dma_init(struct mtk_star_priv *priv)
 
 static void mtk_star_dma_start(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
-			   MTK_STAR_BIT_TX_DMA_CTRL_START,
-			   MTK_STAR_BIT_TX_DMA_CTRL_START);
-	regmap_update_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
-			   MTK_STAR_BIT_RX_DMA_CTRL_START,
-			   MTK_STAR_BIT_RX_DMA_CTRL_START);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
+			MTK_STAR_BIT_TX_DMA_CTRL_START);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
+			MTK_STAR_BIT_RX_DMA_CTRL_START);
 }
 
 static void mtk_star_dma_stop(struct mtk_star_priv *priv)
@@ -553,16 +548,14 @@ static void mtk_star_dma_disable(struct mtk_star_priv *priv)
 
 static void mtk_star_dma_resume_rx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
-			   MTK_STAR_BIT_RX_DMA_CTRL_RESUME,
-			   MTK_STAR_BIT_RX_DMA_CTRL_RESUME);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_RX_DMA_CTRL,
+			MTK_STAR_BIT_RX_DMA_CTRL_RESUME);
 }
 
 static void mtk_star_dma_resume_tx(struct mtk_star_priv *priv)
 {
-	regmap_update_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
-			   MTK_STAR_BIT_TX_DMA_CTRL_RESUME,
-			   MTK_STAR_BIT_TX_DMA_CTRL_RESUME);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_TX_DMA_CTRL,
+			MTK_STAR_BIT_TX_DMA_CTRL_RESUME);
 }
 
 static void mtk_star_set_mac_addr(struct net_device *ndev)
@@ -842,8 +835,8 @@ static int mtk_star_hash_wait_ok(struct mtk_star_priv *priv)
 		return ret;
 
 	/* Check the BIST_OK bit. */
-	regmap_read(priv->regs, MTK_STAR_REG_HASH_CTRL, &val);
-	if (!(val & MTK_STAR_BIT_HASH_CTRL_BIST_OK))
+	if (!regmap_test_bits(priv->regs, MTK_STAR_REG_HASH_CTRL,
+			      MTK_STAR_BIT_HASH_CTRL_BIST_OK))
 		return -EIO;
 
 	return 0;
@@ -877,12 +870,10 @@ static int mtk_star_reset_hash_table(struct mtk_star_priv *priv)
 	if (ret)
 		return ret;
 
-	regmap_update_bits(priv->regs, MTK_STAR_REG_HASH_CTRL,
-			   MTK_STAR_BIT_HASH_CTRL_BIST_EN,
-			   MTK_STAR_BIT_HASH_CTRL_BIST_EN);
-	regmap_update_bits(priv->regs, MTK_STAR_REG_TEST1,
-			   MTK_STAR_BIT_TEST1_RST_HASH_MBIST,
-			   MTK_STAR_BIT_TEST1_RST_HASH_MBIST);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_HASH_CTRL,
+			MTK_STAR_BIT_HASH_CTRL_BIST_EN);
+	regmap_set_bits(priv->regs, MTK_STAR_REG_TEST1,
+			MTK_STAR_BIT_TEST1_RST_HASH_MBIST);
 
 	return mtk_star_hash_wait_ok(priv);
 }
@@ -1013,13 +1004,13 @@ static int mtk_star_enable(struct net_device *ndev)
 		return ret;
 
 	/* Setup the hashing algorithm */
-	regmap_update_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
-			   MTK_STAR_BIT_ARL_CFG_HASH_ALG |
-			   MTK_STAR_BIT_ARL_CFG_MISC_MODE, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
+			  MTK_STAR_BIT_ARL_CFG_HASH_ALG |
+			  MTK_STAR_BIT_ARL_CFG_MISC_MODE);
 
 	/* Don't strip VLAN tags */
-	regmap_update_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
-			   MTK_STAR_BIT_MAC_CFG_VLAN_STRIP, 0);
+	regmap_clear_bits(priv->regs, MTK_STAR_REG_MAC_CFG,
+			  MTK_STAR_BIT_MAC_CFG_VLAN_STRIP);
 
 	/* Setup DMA */
 	mtk_star_dma_init(priv);
@@ -1201,9 +1192,8 @@ static void mtk_star_set_rx_mode(struct net_device *ndev)
 	int ret;
 
 	if (ndev->flags & IFF_PROMISC) {
-		regmap_update_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
-				   MTK_STAR_BIT_ARL_CFG_MISC_MODE,
-				   MTK_STAR_BIT_ARL_CFG_MISC_MODE);
+		regmap_set_bits(priv->regs, MTK_STAR_REG_ARL_CFG,
+				MTK_STAR_BIT_ARL_CFG_MISC_MODE);
 	} else if (netdev_mc_count(ndev) > MTK_STAR_HASHTABLE_MC_LIMIT ||
 		   ndev->flags & IFF_ALLMULTI) {
 		for (i = 0; i < MTK_STAR_HASHTABLE_SIZE_MAX; i++) {
-- 
cgit v1.2.3


From 9eabd188716b2c53d8b9d23e969c6c17049f0fcc Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 29 May 2020 02:25:38 +0200
Subject: mlx5: update indirect block support

Register ndo callback via flow_indr_dev_register() and
flow_indr_dev_unregister().

No need for mlx5e_rep_indr_clean_block_privs() since flow_block_cb_free()
already releases the internal mapping via ->release callback, which in
this case is mlx5e_rep_indr_tc_block_unbind().

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c    | 81 +++-------------------
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.h    |  4 --
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |  5 --
 4 files changed, 8 insertions(+), 83 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index c609a5e50ebc..80713123de5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -306,20 +306,6 @@ mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
 	return NULL;
 }
 
-static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
-					    struct net_device *netdev);
-
-void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
-{
-	struct mlx5e_rep_indr_block_priv *cb_priv, *temp;
-	struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list;
-
-	list_for_each_entry_safe(cb_priv, temp, head, list) {
-		mlx5e_rep_indr_unregister_block(rpriv, cb_priv->netdev);
-		kfree(cb_priv);
-	}
-}
-
 static int
 mlx5e_rep_indr_offload(struct net_device *netdev,
 		       struct flow_cls_offload *flower,
@@ -423,9 +409,14 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 			   struct flow_block_offload *f,
 			   flow_setup_cb_t *setup_cb)
 {
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 	struct mlx5e_rep_indr_block_priv *indr_priv;
 	struct flow_block_cb *block_cb;
 
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
+	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev))
+		return -EOPNOTSUPP;
+
 	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
@@ -492,76 +483,20 @@ int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv,
 	}
 }
 
-static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
-					 struct net_device *netdev)
-{
-	int err;
-
-	err = __flow_indr_block_cb_register(netdev, rpriv,
-					    mlx5e_rep_indr_setup_cb,
-					    rpriv);
-	if (err) {
-		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-
-		mlx5_core_err(priv->mdev, "Failed to register remote block notifier for %s err=%d\n",
-			      netdev_name(netdev), err);
-	}
-	return err;
-}
-
-static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
-					    struct net_device *netdev)
-{
-	__flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_cb,
-					rpriv);
-}
-
-static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
-					 unsigned long event, void *ptr)
-{
-	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
-						     uplink_priv.netdevice_nb);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
-
-	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
-	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev))
-		return NOTIFY_OK;
-
-	switch (event) {
-	case NETDEV_REGISTER:
-		mlx5e_rep_indr_register_block(rpriv, netdev);
-		break;
-	case NETDEV_UNREGISTER:
-		mlx5e_rep_indr_unregister_block(rpriv, netdev);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 int mlx5e_rep_tc_netdevice_event_register(struct mlx5e_rep_priv *rpriv)
 {
 	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-	int err;
 
 	/* init indirect block notifications */
 	INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
 
-	uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
-	err = register_netdevice_notifier_dev_net(rpriv->netdev,
-						  &uplink_priv->netdevice_nb,
-						  &uplink_priv->netdevice_nn);
-	return err;
+	return flow_indr_dev_register(mlx5e_rep_indr_setup_cb, rpriv);
 }
 
 void mlx5e_rep_tc_netdevice_event_unregister(struct mlx5e_rep_priv *rpriv)
 {
-	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
-
-	/* clean indirect TC block notifications */
-	unregister_netdevice_notifier_dev_net(rpriv->netdev,
-					      &uplink_priv->netdevice_nb,
-					      &uplink_priv->netdevice_nn);
+	flow_indr_dev_unregister(mlx5e_rep_indr_setup_cb, rpriv,
+				 mlx5e_rep_indr_setup_tc_cb);
 }
 
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
index 86f92abf2fdd..fdf9702c2d7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -33,7 +33,6 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		       void *type_data);
-void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv);
 
 bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 			     struct sk_buff *skb,
@@ -65,9 +64,6 @@ static inline int
 mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		   void *type_data) { return -EOPNOTSUPP; }
 
-static inline void
-mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv) {}
-
 struct mlx5e_tc_update_priv;
 static inline bool
 mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index af89a4803c7d..006807e04eda 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1018,7 +1018,6 @@ destroy_tises:
 static void mlx5e_cleanup_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
 {
 	mlx5e_rep_tc_netdevice_event_unregister(rpriv);
-	mlx5e_rep_indr_clean_block_privs(rpriv);
 	mlx5e_rep_bond_cleanup(rpriv);
 	mlx5e_rep_tc_cleanup(rpriv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index da9f1686d525..1d5669801484 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -69,13 +69,8 @@ struct mlx5_rep_uplink_priv {
 	 * tc_indr_block_cb_priv_list is used to lookup indirect callback
 	 * private data
 	 *
-	 * netdevice_nb is the netdev events notifier - used to register
-	 * tunnel devices for block events
-	 *
 	 */
 	struct list_head	    tc_indr_block_priv_list;
-	struct notifier_block	    netdevice_nb;
-	struct netdev_net_notifier  netdevice_nn;
 
 	struct mlx5_tun_entropy tun_entropy;
 
-- 
cgit v1.2.3


From 50c1b1c9385fbb35c25b27608e00bcf89368e8ba Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 29 May 2020 02:25:39 +0200
Subject: nfp: update indirect block support

Register ndo callback via flow_indr_dev_register() and
flow_indr_dev_unregister().

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c   | 11 ++++---
 drivers/net/ethernet/netronome/nfp/flower/main.h   |  7 +++--
 .../net/ethernet/netronome/nfp/flower/offload.c    | 35 ++++------------------
 3 files changed, 17 insertions(+), 36 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index ca7032d22196..c39327677a7d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -830,6 +830,10 @@ static int nfp_flower_init(struct nfp_app *app)
 	if (err)
 		goto err_cleanup;
 
+	err = flow_indr_dev_register(nfp_flower_indr_setup_tc_cb, app);
+	if (err)
+		goto err_cleanup;
+
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
 		nfp_flower_qos_init(app);
 
@@ -856,6 +860,9 @@ static void nfp_flower_clean(struct nfp_app *app)
 	skb_queue_purge(&app_priv->cmsg_skbs_low);
 	flush_work(&app_priv->cmsg_work);
 
+	flow_indr_dev_unregister(nfp_flower_indr_setup_tc_cb, app,
+				 nfp_flower_setup_indr_block_cb);
+
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
 		nfp_flower_qos_cleanup(app);
 
@@ -959,10 +966,6 @@ nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
 			return ret;
 	}
 
-	ret = nfp_flower_reg_indir_block_handler(app, netdev, event);
-	if (ret & NOTIFY_STOP_MASK)
-		return ret;
-
 	ret = nfp_flower_internal_port_event_handler(app, netdev, event);
 	if (ret & NOTIFY_STOP_MASK)
 		return ret;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 59abea2a39ad..6c3dc3baf387 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -458,9 +458,10 @@ void nfp_flower_qos_cleanup(struct nfp_app *app);
 int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev,
 				 struct tc_cls_matchall_offload *flow);
 void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb);
-int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
-				       struct net_device *netdev,
-				       unsigned long event);
+int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+				enum tc_setup_type type, void *type_data);
+int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, void *type_data,
+				   void *cb_priv);
 
 void
 __nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 6b60771ccb19..695d24b9dd92 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1619,8 +1619,8 @@ nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app,
 	return NULL;
 }
 
-static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
-					  void *type_data, void *cb_priv)
+int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
+				   void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
 	struct flow_cls_offload *flower = type_data;
@@ -1708,10 +1708,13 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 	return 0;
 }
 
-static int
+int
 nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
 			    enum tc_setup_type type, void *type_data)
 {
+	if (!nfp_fl_is_netdev_to_offload(netdev))
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return nfp_flower_setup_indr_tc_block(netdev, cb_priv,
@@ -1720,29 +1723,3 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
 		return -EOPNOTSUPP;
 	}
 }
-
-int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
-				       struct net_device *netdev,
-				       unsigned long event)
-{
-	int err;
-
-	if (!nfp_fl_is_netdev_to_offload(netdev))
-		return NOTIFY_OK;
-
-	if (event == NETDEV_REGISTER) {
-		err = __flow_indr_block_cb_register(netdev, app,
-						    nfp_flower_indr_setup_tc_cb,
-						    app);
-		if (err)
-			nfp_flower_cmsg_warn(app,
-					     "Indirect block reg failed - %s\n",
-					     netdev->name);
-	} else if (event == NETDEV_UNREGISTER) {
-		__flow_indr_block_cb_unregister(netdev,
-						nfp_flower_indr_setup_tc_cb,
-						app);
-	}
-
-	return NOTIFY_OK;
-}
-- 
cgit v1.2.3


From e445e30cf7e6d68566db775ce186cbe63ef286e9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 29 May 2020 02:25:40 +0200
Subject: bnxt_tc: update indirect block support

Register ndo callback via flow_indr_dev_register() and
flow_indr_dev_unregister().

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h    |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 51 +++++++---------------------
 2 files changed, 12 insertions(+), 40 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5c562e0aac67..9e173d74b72a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1870,7 +1870,6 @@ struct bnxt {
 	u8			dsn[8];
 	struct bnxt_tc_info	*tc_info;
 	struct list_head	tc_indr_block_list;
-	struct notifier_block	tc_netdev_nb;
 	struct dentry		*debugfs_pdev;
 	struct device		*hwmon_dev;
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 782ea0771221..0eef4f5e4a46 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1939,53 +1939,25 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
 	return 0;
 }
 
-static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv,
-				 enum tc_setup_type type, void *type_data)
-{
-	switch (type) {
-	case TC_SETUP_BLOCK:
-		return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static bool bnxt_is_netdev_indr_offload(struct net_device *netdev)
 {
 	return netif_is_vxlan(netdev);
 }
 
-static int bnxt_tc_indr_block_event(struct notifier_block *nb,
-				    unsigned long event, void *ptr)
+static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv,
+				 enum tc_setup_type type, void *type_data)
 {
-	struct net_device *netdev;
-	struct bnxt *bp;
-	int rc;
-
-	netdev = netdev_notifier_info_to_dev(ptr);
 	if (!bnxt_is_netdev_indr_offload(netdev))
-		return NOTIFY_OK;
-
-	bp = container_of(nb, struct bnxt, tc_netdev_nb);
+		return -EOPNOTSUPP;
 
-	switch (event) {
-	case NETDEV_REGISTER:
-		rc = __flow_indr_block_cb_register(netdev, bp,
-						   bnxt_tc_setup_indr_cb,
-						   bp);
-		if (rc)
-			netdev_info(bp->dev,
-				    "Failed to register indirect blk: dev: %s\n",
-				    netdev->name);
-		break;
-	case NETDEV_UNREGISTER:
-		__flow_indr_block_cb_unregister(netdev,
-						bnxt_tc_setup_indr_cb,
-						bp);
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data);
+	default:
 		break;
 	}
 
-	return NOTIFY_DONE;
+	return -EOPNOTSUPP;
 }
 
 static const struct rhashtable_params bnxt_tc_flow_ht_params = {
@@ -2074,8 +2046,8 @@ int bnxt_init_tc(struct bnxt *bp)
 
 	/* init indirect block notifications */
 	INIT_LIST_HEAD(&bp->tc_indr_block_list);
-	bp->tc_netdev_nb.notifier_call = bnxt_tc_indr_block_event;
-	rc = register_netdevice_notifier(&bp->tc_netdev_nb);
+
+	rc = flow_indr_dev_register(bnxt_tc_setup_indr_cb, bp);
 	if (!rc)
 		return 0;
 
@@ -2101,7 +2073,8 @@ void bnxt_shutdown_tc(struct bnxt *bp)
 	if (!bnxt_tc_flower_enabled(bp))
 		return;
 
-	unregister_netdevice_notifier(&bp->tc_netdev_nb);
+	flow_indr_dev_unregister(bnxt_tc_setup_indr_cb, bp,
+				 bnxt_tc_setup_indr_block_cb);
 	rhashtable_destroy(&tc_info->flow_table);
 	rhashtable_destroy(&tc_info->l2_table);
 	rhashtable_destroy(&tc_info->decap_l2_table);
-- 
cgit v1.2.3


From 0c34bb598c510e070160029f34efeeb217000f8d Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Fri, 29 May 2020 14:17:10 +0200
Subject: net: octeon: mgmt: Repair filling of RX ring

The removal of mips_swiotlb_ops exposed a problem in octeon_mgmt Ethernet
driver. mips_swiotlb_ops had an mb() after most of the operations and the
removal of the ops had broken the receive functionality of the driver.
My code inspection has shown no other places except
octeon_mgmt_rx_fill_ring() where an explicit barrier would be obviously
missing. The latter function however has to make sure that "ringing the
bell" doesn't happen before RX ring entry is really written.

The patch has been successfully tested on Octeon II.

Fixes: a999933db9ed ("MIPS: remove mips_swiotlb_ops")
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 9d868403d86c..cbaa1924afbe 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -234,6 +234,11 @@ static void octeon_mgmt_rx_fill_ring(struct net_device *netdev)
 
 		/* Put it in the ring.  */
 		p->rx_ring[p->rx_next_fill] = re.d64;
+		/* Make sure there is no reorder of filling the ring and ringing
+		 * the bell
+		 */
+		wmb();
+
 		dma_sync_single_for_device(p->dev, p->rx_ring_handle,
 					   ring_size_to_bytes(OCTEON_MGMT_RX_RING_SIZE),
 					   DMA_BIDIRECTIONAL);
-- 
cgit v1.2.3


From a74d19ba7c41b6c1e424ef4fb7d4600f43ff75e5 Mon Sep 17 00:00:00 2001
From: Liu Xiang <liuxiang_1999@126.com>
Date: Fri, 29 May 2020 23:24:56 +0800
Subject: net: fec: disable correct clk in the err path of fec_enet_clk_enable

When enable clk_ref failed, clk_ptp should be disabled rather than
clk_ref itself.

Signed-off-by: Liu Xiang <liuxiang_1999@126.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 4acb91dce5fc..2d0d313ee7c5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1981,8 +1981,12 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 	return 0;
 
 failed_clk_ref:
-	if (fep->clk_ref)
-		clk_disable_unprepare(fep->clk_ref);
+	if (fep->clk_ptp) {
+		mutex_lock(&fep->ptp_clk_mutex);
+		clk_disable_unprepare(fep->clk_ptp);
+		fep->ptp_clk_on = false;
+		mutex_unlock(&fep->ptp_clk_mutex);
+	}
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
-- 
cgit v1.2.3


From 1e292f5c11c1e2ef38f416b62c5d616f5768057f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 29 May 2020 21:36:37 +0300
Subject: mlxsw: spectrum_trap: Move layer 3 exceptions to exceptions trap
 group

The layer 3 exceptions are still subject to the same trap policer, so
nothing changes, but user space can choose to assign a different one.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          |  1 +
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 40 +++++++++++++---------
 2 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 38fa7304af0c..030d6f9766d2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5552,6 +5552,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_EXCEPTIONS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index f4b812276a5a..dc2217f1a07f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -212,6 +212,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS,
 		.priority = 0,
 	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(L3_EXCEPTIONS, 1),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_EXCEPTIONS,
+		.priority = 2,
+	},
 	{
 		.group = DEVLINK_TRAP_GROUP_GENERIC(TUNNEL_DROPS, 1),
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS,
@@ -332,56 +337,59 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 		},
 	},
 	{
-		.trap = MLXSW_SP_TRAP_EXCEPTION(MTU_ERROR, L3_DROPS),
+		.trap = MLXSW_SP_TRAP_EXCEPTION(MTU_ERROR, L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(MTUERROR, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(MTUERROR, L3_EXCEPTIONS,
 					       TRAP_TO_CPU),
 		},
 	},
 	{
-		.trap = MLXSW_SP_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS),
+		.trap = MLXSW_SP_TRAP_EXCEPTION(TTL_ERROR, L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(TTLERROR, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(TTLERROR, L3_EXCEPTIONS,
 					       TRAP_TO_CPU),
 		},
 	},
 	{
-		.trap = MLXSW_SP_TRAP_EXCEPTION(RPF, L3_DROPS),
+		.trap = MLXSW_SP_TRAP_EXCEPTION(RPF, L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(RPF, L3_DISCARDS, TRAP_TO_CPU),
+			MLXSW_SP_RXL_EXCEPTION(RPF, L3_EXCEPTIONS, TRAP_TO_CPU),
 		},
 	},
 	{
-		.trap = MLXSW_SP_TRAP_EXCEPTION(REJECT_ROUTE, L3_DROPS),
+		.trap = MLXSW_SP_TRAP_EXCEPTION(REJECT_ROUTE, L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(RTR_INGRESS1, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(RTR_INGRESS1, L3_EXCEPTIONS,
 					       TRAP_TO_CPU),
 		},
 	},
 	{
-		.trap = MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH, L3_DROPS),
+		.trap = MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH,
+						L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV4, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV4, L3_EXCEPTIONS,
 					       TRAP_TO_CPU),
-			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, L3_EXCEPTIONS,
 					       TRAP_TO_CPU),
-			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, L3_EXCEPTIONS,
 					       TRAP_EXCEPTION_TO_CPU),
 		},
 	},
 	{
 		.trap = MLXSW_SP_TRAP_EXCEPTION(IPV4_LPM_UNICAST_MISS,
-						L3_DROPS),
+						L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM4, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM4,
+					       L3_EXCEPTIONS,
 					       TRAP_EXCEPTION_TO_CPU),
 		},
 	},
 	{
 		.trap = MLXSW_SP_TRAP_EXCEPTION(IPV6_LPM_UNICAST_MISS,
-						L3_DROPS),
+						L3_EXCEPTIONS),
 		.listeners_arr = {
-			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6, L3_DISCARDS,
+			MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6,
+					       L3_EXCEPTIONS,
 					       TRAP_EXCEPTION_TO_CPU),
 		},
 	},
-- 
cgit v1.2.3


From 45b1c87313cd2ab2843edd4e6467e3d6458e0c68 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 29 May 2020 21:36:45 +0300
Subject: mlxsw: spectrum_trap: Factor out common Rx listener function

We currently have an Rx listener function for exception traps that marks
received skbs with 'offload_fwd_mark' and injects them to the kernel's
Rx path. The marking is done because all these exceptions occur during
L3 forwarding, after the packets were potentially flooded at L2.

A subsequent patch will add support for control traps. Packets received
via some of these control traps need different handling:

1. Packets might not need to be marked with 'offload_fwd_mark'. For
   example, if packet was trapped before L2 forwarding

2. Packets might not need to be injected to the kernel's Rx path. For
   example, sampled packets are reported to user space via the psample
   module

Factor out a common Rx listener function that only reports trapped
packets to devlink. Call it from mlxsw_sp_rx_no_mark_listener() and
mlxsw_sp_rx_mark_listener() that will inject the packets to the kernel's
Rx path, without and with the marking, respectively.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 29 ++++++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index dc2217f1a07f..206751963a4f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -125,8 +125,8 @@ static void mlxsw_sp_rx_acl_drop_listener(struct sk_buff *skb, u8 local_port,
 	consume_skb(skb);
 }
 
-static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
-					   void *trap_ctx)
+static int __mlxsw_sp_rx_no_mark_listener(struct sk_buff *skb, u8 local_port,
+					  void *trap_ctx)
 {
 	struct devlink_port *in_devlink_port;
 	struct mlxsw_sp_port *mlxsw_sp_port;
@@ -139,7 +139,7 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
 
 	err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port);
 	if (err)
-		return;
+		return err;
 
 	devlink = priv_to_devlink(mlxsw_sp->core);
 	in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core,
@@ -147,10 +147,29 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
 	skb_push(skb, ETH_HLEN);
 	devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, NULL);
 	skb_pull(skb, ETH_HLEN);
-	skb->offload_fwd_mark = 1;
+
+	return 0;
+}
+
+static void mlxsw_sp_rx_no_mark_listener(struct sk_buff *skb, u8 local_port,
+					 void *trap_ctx)
+{
+	int err;
+
+	err = __mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
+	if (err)
+		return;
+
 	netif_receive_skb(skb);
 }
 
+static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u8 local_port,
+				      void *trap_ctx)
+{
+	skb->offload_fwd_mark = 1;
+	mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
+}
+
 #define MLXSW_SP_TRAP_DROP(_id, _group_id)				      \
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				      \
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
@@ -183,7 +202,7 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port,
 		      SET_FW_DEFAULT, SP_##_dis_group_id)
 
 #define MLXSW_SP_RXL_EXCEPTION(_id, _group_id, _action)			      \
-	MLXSW_RXL(mlxsw_sp_rx_exception_listener, _id,			      \
+	MLXSW_RXL(mlxsw_sp_rx_mark_listener, _id,			      \
 		   _action, false, SP_##_group_id, SET_FW_DEFAULT)
 
 #define MLXSW_SP_TRAP_POLICER(_id, _rate, _burst)			      \
-- 
cgit v1.2.3


From 39c10350cfc8ce23faae651877171e354b9006d4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 29 May 2020 21:36:46 +0300
Subject: mlxsw: spectrum_trap: Register layer 2 control traps

In a similar fashion to other traps, register layer 2 control traps with
devlink.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  37 +----
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   2 +
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 151 +++++++++++++++++++++
 3 files changed, 159 insertions(+), 31 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c598ae9ed106..74925826a2cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4022,6 +4022,12 @@ static void mlxsw_sp_rx_listener_ptp(struct sk_buff *skb, u8 local_port,
 	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
 }
 
+void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			  u8 local_port)
+{
+	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
+}
+
 #define MLXSW_SP_RXL_NO_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
 	MLXSW_RXL(mlxsw_sp_rx_listener_no_mark_func, _trap_id, _action,	\
 		  _is_ctrl, SP_##_trap_group, DISCARD)
@@ -4041,26 +4047,9 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* Events */
 	MLXSW_SP_EVENTL(mlxsw_sp_pude_event_func, PUDE),
 	/* L2 traps */
-	MLXSW_SP_RXL_NO_MARK(STP, TRAP_TO_CPU, STP, true),
-	MLXSW_SP_RXL_NO_MARK(LACP, TRAP_TO_CPU, LACP, true),
-	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, LLDP, TRAP_TO_CPU,
-		  false, SP_LLDP, DISCARD),
-	MLXSW_SP_RXL_MARK(IGMP_QUERY, MIRROR_TO_CPU, MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V2_LEAVE, TRAP_TO_CPU, MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, TRAP_TO_CPU, MC_SNOOPING, false),
 	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, FID_MISS, false),
-	MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU,
-			  MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT, TRAP_TO_CPU,
-			     MC_SNOOPING, false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_DONE, TRAP_TO_CPU, MC_SNOOPING,
-			     false),
-	MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT, TRAP_TO_CPU,
-			     MC_SNOOPING, false),
 	/* L3 traps */
 	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),
 	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
@@ -4149,9 +4138,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 	for (i = 0; i < max_cpu_policers; i++) {
 		is_bytes = false;
 		switch (i) {
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_STP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
@@ -4159,10 +4145,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			rate = 128;
 			burst_size = 7;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
-			rate = 16 * 1024;
-			burst_size = 10;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
@@ -4225,9 +4207,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	for (i = 0; i < max_trap_groups; i++) {
 		policer_id = i;
 		switch (i) {
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_STP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
@@ -4241,10 +4220,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			priority = 4;
 			tc = 4;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING:
-			priority = 3;
-			tc = 3;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 147a5634244b..9d4dfb22cb7a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -451,6 +451,8 @@ extern struct notifier_block mlxsw_sp_switchdev_notifier;
 /* spectrum.c */
 void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
 				       u8 local_port, void *priv);
+void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			  u8 local_port);
 int mlxsw_sp_port_speed_get(struct mlxsw_sp_port *mlxsw_sp_port, u32 *speed);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 206751963a4f..32b77d5a917d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -170,6 +170,23 @@ static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u8 local_port,
 	mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
 }
 
+static void mlxsw_sp_rx_ptp_listener(struct sk_buff *skb, u8 local_port,
+				     void *trap_ctx)
+{
+	struct mlxsw_sp *mlxsw_sp = devlink_trap_ctx_priv(trap_ctx);
+	int err;
+
+	err = __mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
+	if (err)
+		return;
+
+	/* The PTP handler expects skb->data to point to the start of the
+	 * Ethernet header.
+	 */
+	skb_push(skb, ETH_HLEN);
+	mlxsw_sp_ptp_receive(mlxsw_sp, skb, local_port);
+}
+
 #define MLXSW_SP_TRAP_DROP(_id, _group_id)				      \
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				      \
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
@@ -191,6 +208,11 @@ static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u8 local_port,
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
 			     MLXSW_SP_TRAP_METADATA)
 
+#define MLXSW_SP_TRAP_CONTROL(_id, _group_id, _action)			      \
+	DEVLINK_TRAP_GENERIC(CONTROL, _action, _id,			      \
+			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
+			     MLXSW_SP_TRAP_METADATA)
+
 #define MLXSW_SP_RXL_DISCARD(_id, _group_id)				      \
 	MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, DISCARD_##_id,		      \
 		      TRAP_EXCEPTION_TO_CPU, false, SP_##_group_id,	      \
@@ -205,6 +227,14 @@ static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u8 local_port,
 	MLXSW_RXL(mlxsw_sp_rx_mark_listener, _id,			      \
 		   _action, false, SP_##_group_id, SET_FW_DEFAULT)
 
+#define MLXSW_SP_RXL_NO_MARK(_id, _group_id, _action, _is_ctrl)		      \
+	MLXSW_RXL(mlxsw_sp_rx_no_mark_listener, _id, _action,		      \
+		  _is_ctrl, SP_##_group_id, DISCARD)
+
+#define MLXSW_SP_RXL_MARK(_id, _group_id, _action, _is_ctrl)		      \
+	MLXSW_RXL(mlxsw_sp_rx_mark_listener, _id, _action, _is_ctrl,	      \
+		  SP_##_group_id, DISCARD)
+
 #define MLXSW_SP_TRAP_POLICER(_id, _rate, _burst)			      \
 	DEVLINK_TRAP_POLICER(_id, _rate, _burst,			      \
 			     MLXSW_REG_QPCR_HIGHEST_CIR,		      \
@@ -218,6 +248,18 @@ mlxsw_sp_trap_policer_items_arr[] = {
 	{
 		.policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 128),
 	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(2, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(3, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(4, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 128),
+	},
 };
 
 static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
@@ -246,6 +288,26 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS,
 		.priority = 0,
 	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(STP, 2),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(LACP, 3),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(LLDP, 4),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(MC_SNOOPING, 5),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING,
+		.priority = 3,
+	},
 };
 
 static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
@@ -466,6 +528,95 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 						 DUMMY),
 		},
 	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(STP, STP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(STP, STP, TRAP_TO_CPU, true),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(LACP, LACP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(LACP, LACP, TRAP_TO_CPU, true),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(LLDP, LLDP, TRAP),
+		.listeners_arr = {
+			MLXSW_RXL(mlxsw_sp_rx_ptp_listener, LLDP, TRAP_TO_CPU,
+				  false, SP_LLDP, DISCARD),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IGMP_QUERY, MC_SNOOPING, MIRROR),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IGMP_QUERY, MC_SNOOPING,
+					  MIRROR_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IGMP_V1_REPORT, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, MC_SNOOPING,
+					     TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IGMP_V2_REPORT, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IGMP_V2_REPORT, MC_SNOOPING,
+					     TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IGMP_V3_REPORT, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IGMP_V3_REPORT, MC_SNOOPING,
+					     TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IGMP_V2_LEAVE, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IGMP_V2_LEAVE, MC_SNOOPING,
+					     TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(MLD_QUERY, MC_SNOOPING, MIRROR),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY,
+					  MC_SNOOPING, MIRROR_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(MLD_V1_REPORT, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT,
+					     MC_SNOOPING, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(MLD_V2_REPORT, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT,
+					     MC_SNOOPING, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(MLD_V1_DONE, MC_SNOOPING,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_DONE,
+					     MC_SNOOPING, TRAP_TO_CPU, false),
+		},
+	},
 };
 
 static struct mlxsw_sp_trap_policer_item *
-- 
cgit v1.2.3


From 8110668ecd9a9e704b9b412302e76a9c6e1f4ce2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 29 May 2020 21:36:47 +0300
Subject: mlxsw: spectrum_trap: Register layer 3 control traps

In a similar fashion to layer 2 control traps, register layer 3 control
traps with devlink.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          |   1 -
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  93 ------
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 318 +++++++++++++++++++++
 3 files changed, 318 insertions(+), 94 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 030d6f9766d2..fcb88d4271bf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5536,7 +5536,6 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP,
-	MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 74925826a2cb..8daeae1384da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4014,14 +4014,6 @@ out:
 	consume_skb(skb);
 }
 
-static void mlxsw_sp_rx_listener_ptp(struct sk_buff *skb, u8 local_port,
-				     void *priv)
-{
-	struct mlxsw_sp *mlxsw_sp = priv;
-
-	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
-}
-
 void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
 			  u8 local_port)
 {
@@ -4047,43 +4039,13 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* Events */
 	MLXSW_SP_EVENTL(mlxsw_sp_pude_event_func, PUDE),
 	/* L2 traps */
-	MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, NEIGH_DISCOVERY, false),
 	MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, FID_MISS, false),
 	/* L3 traps */
-	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),
-	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
-	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, IPV6, false),
-	MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, IPV6,
-			  false),
-	MLXSW_SP_RXL_MARK(IPV4_OSPF, TRAP_TO_CPU, OSPF, false),
-	MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false),
-	MLXSW_SP_RXL_MARK(IPV4_DHCP, TRAP_TO_CPU, DHCP, false),
-	MLXSW_SP_RXL_MARK(IPV6_DHCP, TRAP_TO_CPU, DHCP, false),
-	MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false),
-	MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false),
-	MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6,
-			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISEMENT, TRAP_TO_CPU, IPV6,
-			  false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU,
-			  NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISEMENT, TRAP_TO_CPU,
-			  NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6, false),
 	MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
-	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, IP2ME, false),
-	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, IP2ME, false),
-	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
-	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
-	MLXSW_SP_RXL_MARK(IPV4_BFD, TRAP_TO_CPU, BFD, false),
-	MLXSW_SP_RXL_MARK(IPV6_BFD, TRAP_TO_CPU, BFD, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_CLASS_E, FORWARD,
 			     ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_MC_DMAC, FORWARD,
@@ -4098,18 +4060,10 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* ACL trap */
 	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, FLOW_LOGGING, false),
 	/* Multicast Router Traps */
-	MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false),
-	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
 	/* NVE traps */
 	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY, false),
-	MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY,
-			     false),
-	/* PTP traps */
-	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, PTP0, TRAP_TO_CPU,
-		  false, SP_PTP0, DISCARD),
-	MLXSW_SP_RXL_NO_MARK(PTP1, TRAP_TO_CPU, PTP1, false),
 };
 
 static const struct mlxsw_listener mlxsw_sp1_listener[] = {
@@ -4138,41 +4092,13 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 	for (i = 0; i < max_cpu_policers; i++) {
 		is_bytes = false;
 		switch (i) {
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
-			rate = 128;
-			burst_size = 7;
-			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			rate = 1024;
 			burst_size = 7;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
-			rate = 24 * 1024;
-			burst_size = 12;
-			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
-			rate = 19 * 1024;
-			burst_size = 12;
-			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
-			rate = 360;
-			burst_size = 7;
-			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD:
-			rate = 20 * 1024;
-			burst_size = 10;
-			break;
 		default:
 			continue;
 		}
@@ -4207,36 +4133,17 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	for (i = 0; i < max_trap_groups; i++) {
 		policer_id = i;
 		switch (i) {
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD:
-			priority = 5;
-			tc = 5;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP:
 			priority = 4;
 			tc = 4;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP:
-			priority = 2;
-			tc = 2;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			priority = 1;
 			tc = 1;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			priority = 0;
 			tc = 0;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 32b77d5a917d..148a35b7f4f8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -170,6 +170,14 @@ static void mlxsw_sp_rx_mark_listener(struct sk_buff *skb, u8 local_port,
 	mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
 }
 
+static void mlxsw_sp_rx_l3_mark_listener(struct sk_buff *skb, u8 local_port,
+					 void *trap_ctx)
+{
+	skb->offload_l3_fwd_mark = 1;
+	skb->offload_fwd_mark = 1;
+	mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
+}
+
 static void mlxsw_sp_rx_ptp_listener(struct sk_buff *skb, u8 local_port,
 				     void *trap_ctx)
 {
@@ -235,6 +243,10 @@ static void mlxsw_sp_rx_ptp_listener(struct sk_buff *skb, u8 local_port,
 	MLXSW_RXL(mlxsw_sp_rx_mark_listener, _id, _action, _is_ctrl,	      \
 		  SP_##_group_id, DISCARD)
 
+#define MLXSW_SP_RXL_L3_MARK(_id, _group_id, _action, _is_ctrl)		      \
+	MLXSW_RXL(mlxsw_sp_rx_l3_mark_listener, _id, _action, _is_ctrl,	      \
+		  SP_##_group_id, DISCARD)
+
 #define MLXSW_SP_TRAP_POLICER(_id, _rate, _burst)			      \
 	DEVLINK_TRAP_POLICER(_id, _rate, _burst,			      \
 			     MLXSW_REG_QPCR_HIGHEST_CIR,		      \
@@ -260,6 +272,42 @@ mlxsw_sp_trap_policer_items_arr[] = {
 	{
 		.policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 128),
 	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(6, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(7, 1024, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(8, 20 * 1024, 1024),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(9, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(10, 1024, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(11, 360, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(12, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(13, 128, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(14, 1024, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(15, 1024, 128),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(16, 24 * 1024, 4096),
+	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 4096),
+	},
 };
 
 static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
@@ -308,6 +356,66 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_MC_SNOOPING,
 		.priority = 3,
 	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(DHCP, 6),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP,
+		.priority = 2,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(NEIGH_DISCOVERY, 7),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY,
+		.priority = 2,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(BFD, 8),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_BFD,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(OSPF, 9),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(BGP, 10),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP,
+		.priority = 4,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(VRRP, 11),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(PIM, 12),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(UC_LB, 13),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
+		.priority = 0,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(LOCAL_DELIVERY, 14),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME,
+		.priority = 2,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(IPV6, 15),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6,
+		.priority = 2,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(PTP_EVENT, 16),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
+		.priority = 5,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(PTP_GENERAL, 17),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
+		.priority = 2,
+	},
 };
 
 static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
@@ -617,6 +725,216 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 					     MC_SNOOPING, TRAP_TO_CPU, false),
 		},
 	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_DHCP, DHCP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_DHCP, DHCP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_DHCP, DHCP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_DHCP, DHCP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(ARP_REQUEST, NEIGH_DISCOVERY,
+					      MIRROR),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(ARPBC, NEIGH_DISCOVERY, MIRROR_TO_CPU,
+					  false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY,
+					      MIRROR),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(ARPUC, NEIGH_DISCOVERY, MIRROR_TO_CPU,
+					  false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(ARP_OVERLAY, NEIGH_DISCOVERY,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_NEIGH_SOLICIT,
+					      NEIGH_DISCOVERY, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION,
+					  NEIGH_DISCOVERY, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_NEIGH_ADVERT,
+					      NEIGH_DISCOVERY, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISEMENT,
+					  NEIGH_DISCOVERY, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_BFD, BFD, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_BFD, BFD, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_BFD, BFD, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_BFD, BFD, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_OSPF, OSPF, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_OSPF, OSPF, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_OSPF, OSPF, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_OSPF, OSPF, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_BGP, BGP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_BGP, BGP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_BGP, BGP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_BGP, BGP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_VRRP, VRRP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_VRRP, VRRP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_VRRP, VRRP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_VRRP, VRRP, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_PIM, PIM, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV4_PIM, PIM, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_PIM, PIM, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_PIM, PIM, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(UC_LB, UC_LB, MIRROR),
+		.listeners_arr = {
+			MLXSW_SP_RXL_L3_MARK(LBERROR, LBERROR, MIRROR_TO_CPU,
+					     false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(LOCAL_ROUTE, LOCAL_DELIVERY,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IP2ME, IP2ME, TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, LOCAL_DELIVERY,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(RTR_INGRESS0, IP2ME, TRAP_TO_CPU,
+					  false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_UC_DIP_LINK_LOCAL_SCOPE,
+					      LOCAL_DELIVERY, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, IP2ME,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV4_ROUTER_ALERT, LOCAL_DELIVERY,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, IP2ME, TRAP_TO_CPU,
+					  false),
+		},
+	},
+	{
+		/* IPV6_ROUTER_ALERT is defined in uAPI as 22, but it is not
+		 * used in this file, so undefine it.
+		 */
+		#undef IPV6_ROUTER_ALERT
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_ROUTER_ALERT, LOCAL_DELIVERY,
+					      TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, IP2ME, TRAP_TO_CPU,
+					  false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_DIP_ALL_NODES, IPV6, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, IPV6,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_DIP_ALL_ROUTERS, IPV6, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, IPV6,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_ROUTER_SOLICIT, IPV6, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, IPV6,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_ROUTER_ADVERT, IPV6, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISEMENT, IPV6,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(IPV6_REDIRECT, IPV6, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, IPV6,
+					  TRAP_TO_CPU, false),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(PTP_EVENT, PTP_EVENT, TRAP),
+		.listeners_arr = {
+			MLXSW_RXL(mlxsw_sp_rx_ptp_listener, PTP0, TRAP_TO_CPU,
+				  false, SP_PTP0, DISCARD),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(PTP_GENERAL, PTP_GENERAL, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(PTP1, PTP1, TRAP_TO_CPU, false),
+		},
+	},
 };
 
 static struct mlxsw_sp_trap_policer_item *
-- 
cgit v1.2.3


From 88e2774961d7854628fa9c403166c4162cebc12e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 29 May 2020 21:36:48 +0300
Subject: mlxsw: spectrum_trap: Register ACL control traps

In a similar fashion to other control traps, register ACL control traps
with devlink.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 31 ++++-----------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  2 +
 .../net/ethernet/mellanox/mlxsw/spectrum_trap.c    | 45 ++++++++++++++++++++++
 3 files changed, 55 insertions(+), 23 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 8daeae1384da..5ffa32b75e5f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3987,10 +3987,15 @@ static void mlxsw_sp_rx_listener_l3_mark_func(struct sk_buff *skb,
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
 
-static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port,
-					     void *priv)
+void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			  u8 local_port)
+{
+	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
+}
+
+void mlxsw_sp_sample_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			     u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	struct mlxsw_sp_port_sample *sample;
 	u32 size;
@@ -4014,12 +4019,6 @@ out:
 	consume_skb(skb);
 }
 
-void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
-			  u8 local_port)
-{
-	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
-}
-
 #define MLXSW_SP_RXL_NO_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
 	MLXSW_RXL(mlxsw_sp_rx_listener_no_mark_func, _trap_id, _action,	\
 		  _is_ctrl, SP_##_trap_group, DISCARD)
@@ -4054,11 +4053,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			     ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD,
 			     ROUTER_EXP, false),
-	/* PKT Sample trap */
-	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
-		  false, SP_PKT_SAMPLE, DISCARD),
-	/* ACL trap */
-	MLXSW_SP_RXL_NO_MARK(ACL0, TRAP_TO_CPU, FLOW_LOGGING, false),
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
@@ -4094,7 +4088,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		switch (i) {
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			rate = 1024;
 			burst_size = 7;
@@ -4133,20 +4126,12 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	for (i = 0; i < max_trap_groups; i++) {
 		policer_id = i;
 		switch (i) {
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING:
-			priority = 4;
-			tc = 4;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_FID_MISS:
 			priority = 1;
 			tc = 1;
 			break;
-		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE:
-			priority = 0;
-			tc = 0;
-			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT:
 			priority = MLXSW_REG_HTGT_DEFAULT_PRIORITY;
 			tc = MLXSW_REG_HTGT_DEFAULT_TC;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 9d4dfb22cb7a..6f96ca50c9ba 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -453,6 +453,8 @@ void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
 				       u8 local_port, void *priv);
 void mlxsw_sp_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
 			  u8 local_port);
+void mlxsw_sp_sample_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			     u8 local_port);
 int mlxsw_sp_port_speed_get(struct mlxsw_sp_port *mlxsw_sp_port, u32 *speed);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 148a35b7f4f8..157a42c63066 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -195,6 +195,23 @@ static void mlxsw_sp_rx_ptp_listener(struct sk_buff *skb, u8 local_port,
 	mlxsw_sp_ptp_receive(mlxsw_sp, skb, local_port);
 }
 
+static void mlxsw_sp_rx_sample_listener(struct sk_buff *skb, u8 local_port,
+					void *trap_ctx)
+{
+	struct mlxsw_sp *mlxsw_sp = devlink_trap_ctx_priv(trap_ctx);
+	int err;
+
+	err = __mlxsw_sp_rx_no_mark_listener(skb, local_port, trap_ctx);
+	if (err)
+		return;
+
+	/* The sample handler expects skb->data to point to the start of the
+	 * Ethernet header.
+	 */
+	skb_push(skb, ETH_HLEN);
+	mlxsw_sp_sample_receive(mlxsw_sp, skb, local_port);
+}
+
 #define MLXSW_SP_TRAP_DROP(_id, _group_id)				      \
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				      \
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id,	      \
@@ -308,6 +325,9 @@ mlxsw_sp_trap_policer_items_arr[] = {
 	{
 		.policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 4096),
 	},
+	{
+		.policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128),
+	},
 };
 
 static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
@@ -416,6 +436,16 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = {
 		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
 		.priority = 2,
 	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(ACL_SAMPLE, 0),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_PKT_SAMPLE,
+		.priority = 0,
+	},
+	{
+		.group = DEVLINK_TRAP_GROUP_GENERIC(ACL_TRAP, 18),
+		.hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING,
+		.priority = 4,
+	},
 };
 
 static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
@@ -935,6 +965,21 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 			MLXSW_SP_RXL_NO_MARK(PTP1, PTP1, TRAP_TO_CPU, false),
 		},
 	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(FLOW_ACTION_SAMPLE, ACL_SAMPLE,
+					      MIRROR),
+		.listeners_arr = {
+			MLXSW_RXL(mlxsw_sp_rx_sample_listener, PKT_SAMPLE,
+				  MIRROR_TO_CPU, false, SP_PKT_SAMPLE, DISCARD),
+		},
+	},
+	{
+		.trap = MLXSW_SP_TRAP_CONTROL(FLOW_ACTION_TRAP, ACL_TRAP, TRAP),
+		.listeners_arr = {
+			MLXSW_SP_RXL_NO_MARK(ACL0, FLOW_LOGGING, TRAP_TO_CPU,
+					     false),
+		},
+	},
 };
 
 static struct mlxsw_sp_trap_policer_item *
-- 
cgit v1.2.3


From 6f197fb63850b26ef8f70f1bfe5900e377910a5a Mon Sep 17 00:00:00 2001
From: Roelof Berg <rberg@berg-solutions.de>
Date: Fri, 29 May 2020 21:30:02 +0200
Subject: lan743x: Added fixed link and RGMII support

Microchip lan7431 is frequently connected to a phy. However, it
can also be directly connected to a MII remote peer without
any phy in between. For supporting such a phyless hardware setup
in Linux we utilized phylib, which supports a fixed-link
configuration via the device tree. And we added support for
defining the connection type R/GMII in the device tree.

New behavior:
-------------
. The automatic speed and duplex detection of the lan743x silicon
  between mac and phy is disabled. Instead phylib is used like in
  other typical Linux drivers. The usage of phylib allows to
  specify fixed-link parameters in the device tree.

. The device tree entry phy-connection-type is supported now with
  the modes RGMII or (G)MII (default).

Development state:
------------------
. Tested with fixed-phy configurations. Not yet tested in normal
  configurations with phy. Microchip kindly offered testing
  as soon as the Corona measures allow this.

. All review findings of Andrew Lunn are included

Example:
--------
&pcie {
	status = "okay";

	host@0 {
		reg = <0 0 0 0 0>;

		#address-cells = <3>;
		#size-cells = <2>;

		ethernet@0 {
			compatible = "weyland-yutani,noscom1", "microchip,lan743x";
			status = "okay";
			reg = <0 0 0 0 0>;
			phy-connection-type = "rgmii";

			fixed-link {
				speed = <100>;
				full-duplex;
			};
		};
	};
};

Signed-off-by: Roelof Berg <rberg@berg-solutions.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c |  4 +-
 drivers/net/ethernet/microchip/lan743x_main.c    | 81 +++++++++++++++++++++---
 drivers/net/ethernet/microchip/lan743x_main.h    |  6 ++
 drivers/net/ethernet/microchip/lan743x_ptp.c     |  2 +-
 4 files changed, 80 insertions(+), 13 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 3a0b289d9771..c533d06fbe3a 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -2,11 +2,11 @@
 /* Copyright (C) 2018 Microchip Technology Inc. */
 
 #include <linux/netdevice.h>
-#include "lan743x_main.h"
-#include "lan743x_ethtool.h"
 #include <linux/net_tstamp.h>
 #include <linux/pci.h>
 #include <linux/phy.h>
+#include "lan743x_main.h"
+#include "lan743x_ethtool.h"
 
 /* eeprom */
 #define LAN743X_EEPROM_MAGIC		    (0x74A5)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a43140f7b5eb..36624e3c633b 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -8,7 +8,10 @@
 #include <linux/crc32.h>
 #include <linux/microchipphy.h>
 #include <linux/net_tstamp.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/rtnetlink.h>
 #include <linux/iopoll.h>
 #include <linux/crc16.h>
@@ -798,9 +801,9 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter)
 
 	netdev = adapter->netdev;
 
-	/* setup auto duplex, and speed detection */
+	/* disable auto duplex, and speed detection. Phylib does that */
 	data = lan743x_csr_read(adapter, MAC_CR);
-	data |= MAC_CR_ADD_ | MAC_CR_ASD_;
+	data &= ~(MAC_CR_ADD_ | MAC_CR_ASD_);
 	data |= MAC_CR_CNTR_RST_;
 	lan743x_csr_write(adapter, MAC_CR, data);
 
@@ -946,6 +949,7 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 	struct phy_device *phydev = netdev->phydev;
+	u32 data;
 
 	phy_print_status(phydev);
 	if (phydev->state == PHY_RUNNING) {
@@ -953,6 +957,39 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 		int remote_advertisement = 0;
 		int local_advertisement = 0;
 
+		data = lan743x_csr_read(adapter, MAC_CR);
+
+		/* set interface mode */
+		if (phy_interface_mode_is_rgmii(adapter->phy_mode))
+			/* RGMII */
+			data &= ~MAC_CR_MII_EN_;
+		else
+			/* GMII */
+			data |= MAC_CR_MII_EN_;
+
+		/* set duplex mode */
+		if (phydev->duplex)
+			data |= MAC_CR_DPX_;
+		else
+			data &= ~MAC_CR_DPX_;
+
+		/* set bus speed */
+		switch (phydev->speed) {
+		case SPEED_10:
+			data &= ~MAC_CR_CFG_H_;
+			data &= ~MAC_CR_CFG_L_;
+		break;
+		case SPEED_100:
+			data &= ~MAC_CR_CFG_H_;
+			data |= MAC_CR_CFG_L_;
+		break;
+		case SPEED_1000:
+			data |= MAC_CR_CFG_H_;
+			data |= MAC_CR_CFG_L_;
+		break;
+		}
+		lan743x_csr_write(adapter, MAC_CR, data);
+
 		memset(&ksettings, 0, sizeof(ksettings));
 		phy_ethtool_get_link_ksettings(netdev, &ksettings);
 		local_advertisement =
@@ -980,20 +1017,44 @@ static void lan743x_phy_close(struct lan743x_adapter *adapter)
 static int lan743x_phy_open(struct lan743x_adapter *adapter)
 {
 	struct lan743x_phy *phy = &adapter->phy;
+	struct device_node *phynode;
 	struct phy_device *phydev;
 	struct net_device *netdev;
 	int ret = -EIO;
 
 	netdev = adapter->netdev;
-	phydev = phy_find_first(adapter->mdiobus);
-	if (!phydev)
-		goto return_error;
+	phynode = of_node_get(adapter->pdev->dev.of_node);
+	adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
+
+	if (phynode) {
+		of_get_phy_mode(phynode, &adapter->phy_mode);
+
+		if (of_phy_is_fixed_link(phynode)) {
+			ret = of_phy_register_fixed_link(phynode);
+			if (ret) {
+				netdev_err(netdev,
+					   "cannot register fixed PHY\n");
+				of_node_put(phynode);
+				goto return_error;
+			}
+		}
+		phydev = of_phy_connect(netdev, phynode,
+					lan743x_phy_link_status_change, 0,
+					adapter->phy_mode);
+		of_node_put(phynode);
+		if (!phydev)
+			goto return_error;
+	} else {
+		phydev = phy_find_first(adapter->mdiobus);
+		if (!phydev)
+			goto return_error;
 
-	ret = phy_connect_direct(netdev, phydev,
-				 lan743x_phy_link_status_change,
-				 PHY_INTERFACE_MODE_GMII);
-	if (ret)
-		goto return_error;
+		ret = phy_connect_direct(netdev, phydev,
+					 lan743x_phy_link_status_change,
+					 adapter->phy_mode);
+		if (ret)
+			goto return_error;
+	}
 
 	/* MAC doesn't support 1000T Half */
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 3b02eeae5f45..c61a40411317 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -4,6 +4,7 @@
 #ifndef _LAN743X_H
 #define _LAN743X_H
 
+#include <linux/phy.h>
 #include "lan743x_ptp.h"
 
 #define DRIVER_AUTHOR   "Bryan Whitehead <Bryan.Whitehead@microchip.com>"
@@ -104,10 +105,14 @@
 	((value << 0) & FCT_FLOW_CTL_ON_THRESHOLD_)
 
 #define MAC_CR				(0x100)
+#define MAC_CR_MII_EN_			BIT(19)
 #define MAC_CR_EEE_EN_			BIT(17)
 #define MAC_CR_ADD_			BIT(12)
 #define MAC_CR_ASD_			BIT(11)
 #define MAC_CR_CNTR_RST_		BIT(5)
+#define MAC_CR_DPX_			BIT(3)
+#define MAC_CR_CFG_H_			BIT(2)
+#define MAC_CR_CFG_L_			BIT(1)
 #define MAC_CR_RST_			BIT(0)
 
 #define MAC_RX				(0x104)
@@ -698,6 +703,7 @@ struct lan743x_rx {
 struct lan743x_adapter {
 	struct net_device       *netdev;
 	struct mii_bus		*mdiobus;
+	phy_interface_t		phy_mode;
 	int                     msg_enable;
 #ifdef CONFIG_PM
 	u32			wolopts;
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 9399f6a98748..ab6d719d40f0 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -2,12 +2,12 @@
 /* Copyright (C) 2018 Microchip Technology Inc. */
 
 #include <linux/netdevice.h>
-#include "lan743x_main.h"
 
 #include <linux/ptp_clock_kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/net_tstamp.h>
+#include "lan743x_main.h"
 
 #include "lan743x_ptp.h"
 
-- 
cgit v1.2.3


From 685e39eaf4b5bf68167c799fe683e26cdc43a5ea Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Sun, 31 May 2020 00:08:08 +0300
Subject: dpaa2-eth: Add support for Rx traffic classes

The firmware reserves for each DPNI a number of RX frame queues
equal to the number of configured flows x number of configured
traffic classes.

Current driver configuration directs all incoming traffic to
FQs corresponding to TC0, leaving all other priority levels unused.

Start adding support for multiple ingress traffic classes, by
configuring the FQs associated with all priority levels, not just
TC0. All settings that are per-TC, such as those related to
hashing and flow steering, are also updated.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c   |  7 ++-
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c   | 70 +++++++++++++++-------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h   |  4 +-
 .../net/ethernet/freescale/dpaa2/dpaa2-ethtool.c   | 19 ++++--
 4 files changed, 68 insertions(+), 32 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
index 0a31e4268dfb..c453a23045c1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -81,8 +81,8 @@ static int dpaa2_dbg_fqs_show(struct seq_file *file, void *offset)
 	int i, err;
 
 	seq_printf(file, "FQ stats for %s:\n", priv->net_dev->name);
-	seq_printf(file, "%s%16s%16s%16s%16s\n",
-		   "VFQID", "CPU", "Type", "Frames", "Pending frames");
+	seq_printf(file, "%s%16s%16s%16s%16s%16s\n",
+		   "VFQID", "CPU", "TC", "Type", "Frames", "Pending frames");
 
 	for (i = 0; i <  priv->num_fqs; i++) {
 		fq = &priv->fq[i];
@@ -90,9 +90,10 @@ static int dpaa2_dbg_fqs_show(struct seq_file *file, void *offset)
 		if (err)
 			fcnt = 0;
 
-		seq_printf(file, "%5d%16d%16s%16llu%16u\n",
+		seq_printf(file, "%5d%16d%16d%16s%16llu%16u\n",
 			   fq->fqid,
 			   fq->target_cpu,
+			   fq->tc,
 			   fq_type_to_str(fq),
 			   fq->stats.frames,
 			   fcnt);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index fe3806d54630..01263e247d39 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1290,6 +1290,7 @@ static void disable_ch_napi(struct dpaa2_eth_priv *priv)
 static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
 {
 	struct dpni_taildrop td = {0};
+	struct dpaa2_eth_fq *fq;
 	int i, err;
 
 	if (priv->rx_td_enabled == enable)
@@ -1299,11 +1300,12 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
 	td.threshold = DPAA2_ETH_TAILDROP_THRESH;
 
 	for (i = 0; i < priv->num_fqs; i++) {
-		if (priv->fq[i].type != DPAA2_RX_FQ)
+		fq = &priv->fq[i];
+		if (fq->type != DPAA2_RX_FQ)
 			continue;
 		err = dpni_set_taildrop(priv->mc_io, 0, priv->mc_token,
-					DPNI_CP_QUEUE, DPNI_QUEUE_RX, 0,
-					priv->fq[i].flowid, &td);
+					DPNI_CP_QUEUE, DPNI_QUEUE_RX,
+					fq->tc, fq->flowid, &td);
 		if (err) {
 			netdev_err(priv->net_dev,
 				   "dpni_set_taildrop() failed\n");
@@ -2407,7 +2409,7 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 
 static void setup_fqs(struct dpaa2_eth_priv *priv)
 {
-	int i;
+	int i, j;
 
 	/* We have one TxConf FQ per Tx flow.
 	 * The number of Tx and Rx queues is the same.
@@ -2419,10 +2421,13 @@ static void setup_fqs(struct dpaa2_eth_priv *priv)
 		priv->fq[priv->num_fqs++].flowid = (u16)i;
 	}
 
-	for (i = 0; i < dpaa2_eth_queue_count(priv); i++) {
-		priv->fq[priv->num_fqs].type = DPAA2_RX_FQ;
-		priv->fq[priv->num_fqs].consume = dpaa2_eth_rx;
-		priv->fq[priv->num_fqs++].flowid = (u16)i;
+	for (j = 0; j < dpaa2_eth_tc_count(priv); j++) {
+		for (i = 0; i < dpaa2_eth_queue_count(priv); i++) {
+			priv->fq[priv->num_fqs].type = DPAA2_RX_FQ;
+			priv->fq[priv->num_fqs].consume = dpaa2_eth_rx;
+			priv->fq[priv->num_fqs].tc = (u8)j;
+			priv->fq[priv->num_fqs++].flowid = (u16)i;
+		}
 	}
 
 	/* For each FQ, decide on which core to process incoming frames */
@@ -2789,7 +2794,7 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 	int err;
 
 	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
-			     DPNI_QUEUE_RX, 0, fq->flowid, &queue, &qid);
+			     DPNI_QUEUE_RX, fq->tc, fq->flowid, &queue, &qid);
 	if (err) {
 		dev_err(dev, "dpni_get_queue(RX) failed\n");
 		return err;
@@ -2802,7 +2807,7 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 	queue.destination.priority = 1;
 	queue.user_context = (u64)(uintptr_t)fq;
 	err = dpni_set_queue(priv->mc_io, 0, priv->mc_token,
-			     DPNI_QUEUE_RX, 0, fq->flowid,
+			     DPNI_QUEUE_RX, fq->tc, fq->flowid,
 			     DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST,
 			     &queue);
 	if (err) {
@@ -2811,6 +2816,10 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 	}
 
 	/* xdp_rxq setup */
+	/* only once for each channel */
+	if (fq->tc > 0)
+		return 0;
+
 	err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev,
 			       fq->flowid);
 	if (err) {
@@ -2948,7 +2957,7 @@ static int config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_rx_tc_dist_cfg dist_cfg;
-	int err;
+	int i, err = 0;
 
 	memset(&dist_cfg, 0, sizeof(dist_cfg));
 
@@ -2956,9 +2965,14 @@ static int config_legacy_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 	dist_cfg.dist_size = dpaa2_eth_queue_count(priv);
 	dist_cfg.dist_mode = DPNI_DIST_MODE_HASH;
 
-	err = dpni_set_rx_tc_dist(priv->mc_io, 0, priv->mc_token, 0, &dist_cfg);
-	if (err)
-		dev_err(dev, "dpni_set_rx_tc_dist failed\n");
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		err = dpni_set_rx_tc_dist(priv->mc_io, 0, priv->mc_token,
+					  i, &dist_cfg);
+		if (err) {
+			dev_err(dev, "dpni_set_rx_tc_dist failed\n");
+			break;
+		}
+	}
 
 	return err;
 }
@@ -2968,7 +2982,7 @@ static int config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_rx_dist_cfg dist_cfg;
-	int err;
+	int i, err = 0;
 
 	memset(&dist_cfg, 0, sizeof(dist_cfg));
 
@@ -2976,9 +2990,15 @@ static int config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 	dist_cfg.dist_size = dpaa2_eth_queue_count(priv);
 	dist_cfg.enable = 1;
 
-	err = dpni_set_rx_hash_dist(priv->mc_io, 0, priv->mc_token, &dist_cfg);
-	if (err)
-		dev_err(dev, "dpni_set_rx_hash_dist failed\n");
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		dist_cfg.tc = i;
+		err = dpni_set_rx_hash_dist(priv->mc_io, 0, priv->mc_token,
+					    &dist_cfg);
+		if (err) {
+			dev_err(dev, "dpni_set_rx_hash_dist failed\n");
+			break;
+		}
+	}
 
 	return err;
 }
@@ -2988,7 +3008,7 @@ static int config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_rx_dist_cfg dist_cfg;
-	int err;
+	int i, err = 0;
 
 	memset(&dist_cfg, 0, sizeof(dist_cfg));
 
@@ -2996,9 +3016,15 @@ static int config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 	dist_cfg.dist_size = dpaa2_eth_queue_count(priv);
 	dist_cfg.enable = 1;
 
-	err = dpni_set_rx_fs_dist(priv->mc_io, 0, priv->mc_token, &dist_cfg);
-	if (err)
-		dev_err(dev, "dpni_set_rx_fs_dist failed\n");
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		dist_cfg.tc = i;
+		err = dpni_set_rx_fs_dist(priv->mc_io, 0, priv->mc_token,
+					  &dist_cfg);
+		if (err) {
+			dev_err(dev, "dpni_set_rx_fs_dist failed\n");
+			break;
+		}
+	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 0581fbf1f98c..580ad5fd7bd8 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -294,7 +294,9 @@ struct dpaa2_eth_ch_stats {
 
 /* Maximum number of queues associated with a DPNI */
 #define DPAA2_ETH_MAX_TCS		8
-#define DPAA2_ETH_MAX_RX_QUEUES		16
+#define DPAA2_ETH_MAX_RX_QUEUES_PER_TC	16
+#define DPAA2_ETH_MAX_RX_QUEUES		\
+	(DPAA2_ETH_MAX_RX_QUEUES_PER_TC * DPAA2_ETH_MAX_TCS)
 #define DPAA2_ETH_MAX_TX_QUEUES		16
 #define DPAA2_ETH_MAX_QUEUES		(DPAA2_ETH_MAX_RX_QUEUES + \
 					DPAA2_ETH_MAX_TX_QUEUES)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 049afd1d6252..8bf169783bea 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -547,7 +547,7 @@ static int do_cls_rule(struct net_device *net_dev,
 	dma_addr_t key_iova;
 	u64 fields = 0;
 	void *key_buf;
-	int err;
+	int i, err;
 
 	if (fs->ring_cookie != RX_CLS_FLOW_DISC &&
 	    fs->ring_cookie >= dpaa2_eth_queue_count(priv))
@@ -607,11 +607,18 @@ static int do_cls_rule(struct net_device *net_dev,
 			fs_act.options |= DPNI_FS_OPT_DISCARD;
 		else
 			fs_act.flow_id = fs->ring_cookie;
-		err = dpni_add_fs_entry(priv->mc_io, 0, priv->mc_token, 0,
-					fs->location, &rule_cfg, &fs_act);
-	} else {
-		err = dpni_remove_fs_entry(priv->mc_io, 0, priv->mc_token, 0,
-					   &rule_cfg);
+	}
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		if (add)
+			err = dpni_add_fs_entry(priv->mc_io, 0, priv->mc_token,
+						i, fs->location, &rule_cfg,
+						&fs_act);
+		else
+			err = dpni_remove_fs_entry(priv->mc_io, 0,
+						   priv->mc_token, i,
+						   &rule_cfg);
+		if (err)
+			break;
 	}
 
 	dma_unmap_single(dev, key_iova, rule_cfg.key_size * 2, DMA_TO_DEVICE);
-- 
cgit v1.2.3


From 6aa90fe2d96745b63d4ccc74c0c37b90d31b699e Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Sun, 31 May 2020 00:08:09 +0300
Subject: dpaa2-eth: Distribute ingress frames based on VLAN prio

Configure static ingress classification based on VLAN PCP field.
If the DPNI doesn't have enough traffic classes to accommodate all
priority levels, the lowest ones end up on TC 0 (default on miss).

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 116 ++++++++++++++++++++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h |   1 +
 drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h  |  34 ++++++
 drivers/net/ethernet/freescale/dpaa2/dpni.c      | 131 +++++++++++++++++++++++
 drivers/net/ethernet/freescale/dpaa2/dpni.h      |  36 +++++++
 5 files changed, 318 insertions(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 01263e247d39..3bf5df92ecfa 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2696,6 +2696,118 @@ out_err:
 	priv->enqueue = dpaa2_eth_enqueue_qd;
 }
 
+/* Configure ingress classification based on VLAN PCP */
+static int set_vlan_qos(struct dpaa2_eth_priv *priv)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	struct dpkg_profile_cfg kg_cfg = {0};
+	struct dpni_qos_tbl_cfg qos_cfg = {0};
+	struct dpni_rule_cfg key_params;
+	void *dma_mem, *key, *mask;
+	u8 key_size = 2;	/* VLAN TCI field */
+	int i, pcp, err;
+
+	/* VLAN-based classification only makes sense if we have multiple
+	 * traffic classes.
+	 * Also, we need to extract just the 3-bit PCP field from the VLAN
+	 * header and we can only do that by using a mask
+	 */
+	if (dpaa2_eth_tc_count(priv) == 1 || !dpaa2_eth_fs_mask_enabled(priv)) {
+		dev_dbg(dev, "VLAN-based QoS classification not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	dma_mem = kzalloc(DPAA2_CLASSIFIER_DMA_SIZE, GFP_KERNEL);
+	if (!dma_mem)
+		return -ENOMEM;
+
+	kg_cfg.num_extracts = 1;
+	kg_cfg.extracts[0].type = DPKG_EXTRACT_FROM_HDR;
+	kg_cfg.extracts[0].extract.from_hdr.prot = NET_PROT_VLAN;
+	kg_cfg.extracts[0].extract.from_hdr.type = DPKG_FULL_FIELD;
+	kg_cfg.extracts[0].extract.from_hdr.field = NH_FLD_VLAN_TCI;
+
+	err = dpni_prepare_key_cfg(&kg_cfg, dma_mem);
+	if (err) {
+		dev_err(dev, "dpni_prepare_key_cfg failed\n");
+		goto out_free_tbl;
+	}
+
+	/* set QoS table */
+	qos_cfg.default_tc = 0;
+	qos_cfg.discard_on_miss = 0;
+	qos_cfg.key_cfg_iova = dma_map_single(dev, dma_mem,
+					      DPAA2_CLASSIFIER_DMA_SIZE,
+					      DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, qos_cfg.key_cfg_iova)) {
+		dev_err(dev, "QoS table DMA mapping failed\n");
+		err = -ENOMEM;
+		goto out_free_tbl;
+	}
+
+	err = dpni_set_qos_table(priv->mc_io, 0, priv->mc_token, &qos_cfg);
+	if (err) {
+		dev_err(dev, "dpni_set_qos_table failed\n");
+		goto out_unmap_tbl;
+	}
+
+	/* Add QoS table entries */
+	key = kzalloc(key_size * 2, GFP_KERNEL);
+	if (!key) {
+		err = -ENOMEM;
+		goto out_unmap_tbl;
+	}
+	mask = key + key_size;
+	*(__be16 *)mask = cpu_to_be16(VLAN_PRIO_MASK);
+
+	key_params.key_iova = dma_map_single(dev, key, key_size * 2,
+					     DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, key_params.key_iova)) {
+		dev_err(dev, "Qos table entry DMA mapping failed\n");
+		err = -ENOMEM;
+		goto out_free_key;
+	}
+
+	key_params.mask_iova = key_params.key_iova + key_size;
+	key_params.key_size = key_size;
+
+	/* We add rules for PCP-based distribution starting with highest
+	 * priority (VLAN PCP = 7). If this DPNI doesn't have enough traffic
+	 * classes to accommodate all priority levels, the lowest ones end up
+	 * on TC 0 which was configured as default
+	 */
+	for (i = dpaa2_eth_tc_count(priv) - 1, pcp = 7; i >= 0; i--, pcp--) {
+		*(__be16 *)key = cpu_to_be16(pcp << VLAN_PRIO_SHIFT);
+		dma_sync_single_for_device(dev, key_params.key_iova,
+					   key_size * 2, DMA_TO_DEVICE);
+
+		err = dpni_add_qos_entry(priv->mc_io, 0, priv->mc_token,
+					 &key_params, i, i);
+		if (err) {
+			dev_err(dev, "dpni_add_qos_entry failed\n");
+			dpni_clear_qos_table(priv->mc_io, 0, priv->mc_token);
+			goto out_unmap_key;
+		}
+	}
+
+	priv->vlan_cls_enabled = true;
+
+	/* Table and key memory is not persistent, clean everything up after
+	 * configuration is finished
+	 */
+out_unmap_key:
+	dma_unmap_single(dev, key_params.key_iova, key_size * 2, DMA_TO_DEVICE);
+out_free_key:
+	kfree(key);
+out_unmap_tbl:
+	dma_unmap_single(dev, qos_cfg.key_cfg_iova, DPAA2_CLASSIFIER_DMA_SIZE,
+			 DMA_TO_DEVICE);
+out_free_tbl:
+	kfree(dma_mem);
+
+	return err;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
@@ -2758,6 +2870,10 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 			goto close;
 	}
 
+	err = set_vlan_qos(priv);
+	if (err && err != -EOPNOTSUPP)
+		goto close;
+
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
 	if (!priv->cls_rules) {
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 580ad5fd7bd8..7856f69bcf36 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -427,6 +427,7 @@ struct dpaa2_eth_priv {
 	u64 rx_cls_fields;
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
+	u8 vlan_cls_enabled;
 	struct bpf_prog *xdp_prog;
 #ifdef CONFIG_DEBUG_FS
 	struct dpaa2_debugfs dbg;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
index d9b6918807af..0048e856f85e 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
@@ -59,6 +59,10 @@
 
 #define DPNI_CMDID_SET_RX_TC_DIST			DPNI_CMD(0x235)
 
+#define DPNI_CMDID_SET_QOS_TBL				DPNI_CMD(0x240)
+#define DPNI_CMDID_ADD_QOS_ENT				DPNI_CMD(0x241)
+#define DPNI_CMDID_REMOVE_QOS_ENT			DPNI_CMD(0x242)
+#define DPNI_CMDID_CLR_QOS_TBL				DPNI_CMD(0x243)
 #define DPNI_CMDID_ADD_FS_ENT				DPNI_CMD(0x244)
 #define DPNI_CMDID_REMOVE_FS_ENT			DPNI_CMD(0x245)
 #define DPNI_CMDID_CLR_FS_ENT				DPNI_CMD(0x246)
@@ -567,4 +571,34 @@ struct dpni_cmd_remove_fs_entry {
 	__le64 mask_iova;
 };
 
+#define DPNI_DISCARD_ON_MISS_SHIFT	0
+#define DPNI_DISCARD_ON_MISS_SIZE	1
+
+struct dpni_cmd_set_qos_table {
+	__le32 pad;
+	u8 default_tc;
+	/* only the LSB */
+	u8 discard_on_miss;
+	__le16 pad1[21];
+	__le64 key_cfg_iova;
+};
+
+struct dpni_cmd_add_qos_entry {
+	__le16 pad;
+	u8 tc_id;
+	u8 key_size;
+	__le16 index;
+	__le16 pad1;
+	__le64 key_iova;
+	__le64 mask_iova;
+};
+
+struct dpni_cmd_remove_qos_entry {
+	u8 pad[3];
+	u8 key_size;
+	__le32 pad1;
+	__le64 key_iova;
+	__le64 mask_iova;
+};
+
 #endif /* _FSL_DPNI_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c
index dd54e6953aeb..78fa325407ca 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c
@@ -1786,3 +1786,134 @@ int dpni_remove_fs_entry(struct fsl_mc_io *mc_io,
 	/* send command to mc*/
 	return mc_send_command(mc_io, &cmd);
 }
+
+/**
+ * dpni_set_qos_table() - Set QoS mapping table
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPNI object
+ * @cfg:	QoS table configuration
+ *
+ * This function and all QoS-related functions require that
+ *'max_tcs > 1' was set at DPNI creation.
+ *
+ * warning: Before calling this function, call dpkg_prepare_key_cfg() to
+ *			prepare the key_cfg_iova parameter
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpni_set_qos_table(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       const struct dpni_qos_tbl_cfg *cfg)
+{
+	struct dpni_cmd_set_qos_table *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPNI_CMDID_SET_QOS_TBL,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpni_cmd_set_qos_table *)cmd.params;
+	cmd_params->default_tc = cfg->default_tc;
+	cmd_params->key_cfg_iova = cpu_to_le64(cfg->key_cfg_iova);
+	dpni_set_field(cmd_params->discard_on_miss, DISCARD_ON_MISS,
+		       cfg->discard_on_miss);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpni_add_qos_entry() - Add QoS mapping entry (to select a traffic class)
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPNI object
+ * @cfg:	QoS rule to add
+ * @tc_id:	Traffic class selection (0-7)
+ * @index:	Location in the QoS table where to insert the entry.
+ *		Only relevant if MASKING is enabled for QoS classification on
+ *		this DPNI, it is ignored for exact match.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpni_add_qos_entry(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       const struct dpni_rule_cfg *cfg,
+		       u8 tc_id,
+		       u16 index)
+{
+	struct dpni_cmd_add_qos_entry *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPNI_CMDID_ADD_QOS_ENT,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpni_cmd_add_qos_entry *)cmd.params;
+	cmd_params->tc_id = tc_id;
+	cmd_params->key_size = cfg->key_size;
+	cmd_params->index = cpu_to_le16(index);
+	cmd_params->key_iova = cpu_to_le64(cfg->key_iova);
+	cmd_params->mask_iova = cpu_to_le64(cfg->mask_iova);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpni_remove_qos_entry() - Remove QoS mapping entry
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPNI object
+ * @cfg:	QoS rule to remove
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpni_remove_qos_entry(struct fsl_mc_io *mc_io,
+			  u32 cmd_flags,
+			  u16 token,
+			  const struct dpni_rule_cfg *cfg)
+{
+	struct dpni_cmd_remove_qos_entry *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPNI_CMDID_REMOVE_QOS_ENT,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dpni_cmd_remove_qos_entry *)cmd.params;
+	cmd_params->key_size = cfg->key_size;
+	cmd_params->key_iova = cpu_to_le64(cfg->key_iova);
+	cmd_params->mask_iova = cpu_to_le64(cfg->mask_iova);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpni_clear_qos_table() - Clear all QoS mapping entries
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPNI object
+ *
+ * Following this function call, all frames are directed to
+ * the default traffic class (0)
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dpni_clear_qos_table(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token)
+{
+	struct fsl_mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(DPNI_CMDID_CLR_QOS_TBL,
+					  cmd_flags,
+					  token);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index ee0711d06b3a..8c7ac20bf1a7 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -715,6 +715,26 @@ int dpni_set_rx_hash_dist(struct fsl_mc_io *mc_io,
 			  u16 token,
 			  const struct dpni_rx_dist_cfg *cfg);
 
+/**
+ * struct dpni_qos_tbl_cfg - Structure representing QOS table configuration
+ * @key_cfg_iova: I/O virtual address of 256 bytes DMA-able memory filled with
+ *		key extractions to be used as the QoS criteria by calling
+ *		dpkg_prepare_key_cfg()
+ * @discard_on_miss: Set to '1' to discard frames in case of no match (miss);
+ *		'0' to use the 'default_tc' in such cases
+ * @default_tc: Used in case of no-match and 'discard_on_miss'= 0
+ */
+struct dpni_qos_tbl_cfg {
+	u64 key_cfg_iova;
+	int discard_on_miss;
+	u8 default_tc;
+};
+
+int dpni_set_qos_table(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       const struct dpni_qos_tbl_cfg *cfg);
+
 /**
  * enum dpni_dest - DPNI destination types
  * @DPNI_DEST_NONE: Unassigned destination; The queue is set in parked mode and
@@ -961,6 +981,22 @@ int dpni_remove_fs_entry(struct fsl_mc_io *mc_io,
 			 u8 tc_id,
 			 const struct dpni_rule_cfg *cfg);
 
+int dpni_add_qos_entry(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       const struct dpni_rule_cfg *cfg,
+		       u8 tc_id,
+		       u16 index);
+
+int dpni_remove_qos_entry(struct fsl_mc_io *mc_io,
+			  u32 cmd_flags,
+			  u16 token,
+			  const struct dpni_rule_cfg *cfg);
+
+int dpni_clear_qos_table(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token);
+
 int dpni_get_api_version(struct fsl_mc_io *mc_io,
 			 u32 cmd_flags,
 			 u16 *major_ver,
-- 
cgit v1.2.3


From ad054f265401d8279837a916e9b5a5aee2a1749d Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Sun, 31 May 2020 00:08:10 +0300
Subject: dpaa2-eth: Add helper functions

Add convenient helper functions that determines whether Rx/Tx pause
frames are enabled based on link state flags received from firmware.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c     |  3 +--
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h     | 11 +++++++++++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c |  5 ++---
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 3bf5df92ecfa..c16c8ea3a174 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1333,8 +1333,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv)
 	 * Rx FQ taildrop configuration as well. We configure taildrop
 	 * only when pause frame generation is disabled.
 	 */
-	tx_pause = !!(state.options & DPNI_LINK_OPT_PAUSE) ^
-		   !!(state.options & DPNI_LINK_OPT_ASYM_PAUSE);
+	tx_pause = dpaa2_eth_tx_pause_enabled(state.options);
 	dpaa2_eth_set_rx_taildrop(priv, !tx_pause);
 
 	/* When we manage the MAC/PHY using phylink there is no need
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 7856f69bcf36..6384f6a23349 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -510,6 +510,17 @@ enum dpaa2_eth_rx_dist {
 	(dpaa2_eth_cmp_dpni_ver((priv), DPNI_PAUSE_VER_MAJOR,	\
 				DPNI_PAUSE_VER_MINOR) >= 0)
 
+static inline bool dpaa2_eth_tx_pause_enabled(u64 link_options)
+{
+	return !!(link_options & DPNI_LINK_OPT_PAUSE) ^
+	       !!(link_options & DPNI_LINK_OPT_ASYM_PAUSE);
+}
+
+static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options)
+{
+	return !!(link_options & DPNI_LINK_OPT_PAUSE);
+}
+
 static inline
 unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
 				       struct sk_buff *skb)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 8bf169783bea..e88269fe3de7 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -130,9 +130,8 @@ static void dpaa2_eth_get_pauseparam(struct net_device *net_dev,
 		return;
 	}
 
-	pause->rx_pause = !!(link_options & DPNI_LINK_OPT_PAUSE);
-	pause->tx_pause = pause->rx_pause ^
-			  !!(link_options & DPNI_LINK_OPT_ASYM_PAUSE);
+	pause->rx_pause = dpaa2_eth_rx_pause_enabled(link_options);
+	pause->tx_pause = dpaa2_eth_tx_pause_enabled(link_options);
 	pause->autoneg = AUTONEG_DISABLE;
 }
 
-- 
cgit v1.2.3


From 2c8d1c8d7d62dfedab97927c22e9421f0d72de8e Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Sun, 31 May 2020 00:08:11 +0300
Subject: dpaa2-eth: Add congestion group taildrop

The increase in number of ingress frame queues means we now risk
depleting the buffer pool before the FQ taildrop kicks in.

Congestion group taildrop allows us to control the number of frames that
can accumulate on a group of Rx frame queues belonging to the same
traffic class.  This setting coexists with the frame queue based
taildrop: whichever limit gets hit first triggers the frame drop.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 35 ++++++++++++++++++------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 13 +++++++--
 2 files changed, 38 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index c16c8ea3a174..04eff6308c72 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1287,17 +1287,20 @@ static void disable_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
-static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
+static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
+				      bool tx_pause)
 {
 	struct dpni_taildrop td = {0};
 	struct dpaa2_eth_fq *fq;
 	int i, err;
 
-	if (priv->rx_td_enabled == enable)
+	td.enable = !tx_pause;
+	if (priv->rx_td_enabled == td.enable)
 		return;
 
-	td.enable = enable;
-	td.threshold = DPAA2_ETH_TAILDROP_THRESH;
+	/* FQ taildrop: threshold is in bytes, per frame queue */
+	td.threshold = DPAA2_ETH_FQ_TAILDROP_THRESH;
+	td.units = DPNI_CONGESTION_UNIT_BYTES;
 
 	for (i = 0; i < priv->num_fqs; i++) {
 		fq = &priv->fq[i];
@@ -1308,12 +1311,28 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
 					fq->tc, fq->flowid, &td);
 		if (err) {
 			netdev_err(priv->net_dev,
-				   "dpni_set_taildrop() failed\n");
-			break;
+				   "dpni_set_taildrop(FQ) failed\n");
+			return;
+		}
+	}
+
+	/* Congestion group taildrop: threshold is in frames, per group
+	 * of FQs belonging to the same traffic class
+	 */
+	td.threshold = DPAA2_ETH_CG_TAILDROP_THRESH(priv);
+	td.units = DPNI_CONGESTION_UNIT_FRAMES;
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		err = dpni_set_taildrop(priv->mc_io, 0, priv->mc_token,
+					DPNI_CP_GROUP, DPNI_QUEUE_RX,
+					i, 0, &td);
+		if (err) {
+			netdev_err(priv->net_dev,
+				   "dpni_set_taildrop(CG) failed\n");
+			return;
 		}
 	}
 
-	priv->rx_td_enabled = enable;
+	priv->rx_td_enabled = td.enable;
 }
 
 static int link_state_update(struct dpaa2_eth_priv *priv)
@@ -1334,7 +1353,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv)
 	 * only when pause frame generation is disabled.
 	 */
 	tx_pause = dpaa2_eth_tx_pause_enabled(state.options);
-	dpaa2_eth_set_rx_taildrop(priv, !tx_pause);
+	dpaa2_eth_set_rx_taildrop(priv, tx_pause);
 
 	/* When we manage the MAC/PHY using phylink there is no need
 	 * to manually update the netif_carrier.
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 6384f6a23349..184d5d83e497 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -40,7 +40,7 @@
  * frames in the Rx queues (length of the current frame is not
  * taken into account when making the taildrop decision)
  */
-#define DPAA2_ETH_TAILDROP_THRESH	(64 * 1024)
+#define DPAA2_ETH_FQ_TAILDROP_THRESH	(64 * 1024)
 
 /* Maximum number of Tx confirmation frames to be processed
  * in a single NAPI call
@@ -52,11 +52,20 @@
  * how many 64B frames fit inside the taildrop threshold and add a margin
  * to accommodate the buffer refill delay.
  */
-#define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_TAILDROP_THRESH / 64)
+#define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_FQ_TAILDROP_THRESH / 64)
 #define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
 #define DPAA2_ETH_REFILL_THRESH \
 	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
+/* Congestion group taildrop threshold: number of frames allowed to accumulate
+ * at any moment in a group of Rx queues belonging to the same traffic class.
+ * Choose value such that we don't risk depleting the buffer pool before the
+ * taildrop kicks in
+ */
+#define DPAA2_ETH_CG_TAILDROP_THRESH(priv)				\
+	(DPAA2_ETH_MAX_FRAMES_PER_QUEUE * dpaa2_eth_queue_count(priv) /	\
+	 dpaa2_eth_tc_count(priv))
+
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
  */
-- 
cgit v1.2.3


From 3f8b826d705fc6f0f0602fcbe6ee3b646ed3316e Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Sun, 31 May 2020 00:08:12 +0300
Subject: dpaa2-eth: Update FQ taildrop threshold and buffer pool count

Now that we have congestion group taildrop configured at all
times, we can afford to increase the frame queue taildrop
threshold; this will ensure a better response when receiving
bursts of large-sized frames.

Also decouple the buffer pool count from the Rx FQ taildrop
threshold, as above change would increase it too much. Instead,
keep the old count as a hardcoded value.

With the new limits, we try to ensure that:
* we allow enough leeway for large frame bursts (by buffering
enough of them in queues to avoid heavy dropping in case of
bursty traffic, but when overall ingress bandwidth is manageable)
* allow pending frames to be evenly spread between ingress FQs,
regardless of frame size
* avoid dropping frames due to the buffer pool being empty; this
is not a bad behaviour per se, but system overall response is
more linear and predictable when frames are dropped at frame
queue/group level.

Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 184d5d83e497..02c0eea69a23 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -36,24 +36,24 @@
 /* Convert L3 MTU to L2 MFL */
 #define DPAA2_ETH_L2_MAX_FRM(mtu)	((mtu) + VLAN_ETH_HLEN)
 
-/* Set the taildrop threshold (in bytes) to allow the enqueue of several jumbo
- * frames in the Rx queues (length of the current frame is not
- * taken into account when making the taildrop decision)
+/* Set the taildrop threshold (in bytes) to allow the enqueue of a large
+ * enough number of jumbo frames in the Rx queues (length of the current
+ * frame is not taken into account when making the taildrop decision)
  */
-#define DPAA2_ETH_FQ_TAILDROP_THRESH	(64 * 1024)
+#define DPAA2_ETH_FQ_TAILDROP_THRESH	(1024 * 1024)
 
 /* Maximum number of Tx confirmation frames to be processed
  * in a single NAPI call
  */
 #define DPAA2_ETH_TXCONF_PER_NAPI	256
 
-/* Buffer quota per queue. Must be large enough such that for minimum sized
- * frames taildrop kicks in before the bpool gets depleted, so we compute
- * how many 64B frames fit inside the taildrop threshold and add a margin
- * to accommodate the buffer refill delay.
+/* Buffer qouta per channel. We want to keep in check number of ingress frames
+ * in flight: for small sized frames, congestion group taildrop may kick in
+ * first; for large sizes, Rx FQ taildrop threshold will ensure only a
+ * reasonable number of frames will be pending at any given time.
+ * Ingress frame drop due to buffer pool depletion should be a corner case only
  */
-#define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_FQ_TAILDROP_THRESH / 64)
-#define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
+#define DPAA2_ETH_NUM_BUFS		1280
 #define DPAA2_ETH_REFILL_THRESH \
 	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
@@ -63,8 +63,7 @@
  * taildrop kicks in
  */
 #define DPAA2_ETH_CG_TAILDROP_THRESH(priv)				\
-	(DPAA2_ETH_MAX_FRAMES_PER_QUEUE * dpaa2_eth_queue_count(priv) /	\
-	 dpaa2_eth_tc_count(priv))
+	(1024 * dpaa2_eth_queue_count(priv) / dpaa2_eth_tc_count(priv))
 
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
-- 
cgit v1.2.3


From f395b69f40f580491ef56f2395a98e3189baa53c Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 31 May 2020 00:08:13 +0300
Subject: dpaa2-eth: Add PFC support through DCB ops

Add support in dpaa2-eth for PFC (Priority Flow Control)
through the DCB ops.

Instruct the hardware to respond to received PFC frames.
Current firmware doesn't allow us to selectively enable PFC
on the Rx side for some priorities only, so we will react to
all incoming PFC frames (and stop transmitting on the traffic
classes specified in the frame).

Also, configure the hardware to generate PFC frames based on Rx
congestion notifications. When a certain number of frames accumulate in
the ingress queues corresponding to a traffic class, priority flow
control frames are generated for that TC.

The number of PFC traffic classes available can be queried through
lldptool. Also, which of those traffic classes have PFC enabled is also
controlled through the same dcbnl_rtnl_ops callbacks.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/Kconfig       |  10 ++
 drivers/net/ethernet/freescale/dpaa2/Makefile      |   1 +
 .../net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c   | 146 +++++++++++++++++++++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c   |   9 ++
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h   |  18 +++
 drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h    |  25 ++++
 drivers/net/ethernet/freescale/dpaa2/dpni.c        |  46 +++++++
 drivers/net/ethernet/freescale/dpaa2/dpni.h        |  61 +++++++++
 8 files changed, 316 insertions(+)
 create mode 100644 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig
index c6fb8e4021ac..feea797cde02 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig
@@ -9,6 +9,16 @@ config FSL_DPAA2_ETH
 	  The driver manages network objects discovered on the Freescale
 	  MC bus.
 
+if FSL_DPAA2_ETH
+config FSL_DPAA2_ETH_DCB
+	bool "Data Center Bridging (DCB) Support"
+	default n
+	depends on DCB
+	help
+	  Enable Priority-Based Flow Control (PFC) support for DPAA2 Ethernet
+	  devices.
+endif
+
 config FSL_DPAA2_PTP_CLOCK
 	tristate "Freescale DPAA2 PTP Clock"
 	depends on FSL_DPAA2_ETH && PTP_1588_CLOCK_QORIQ
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index 69184ca3b7b9..6e7f33c956bf 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_FSL_DPAA2_ETH)		+= fsl-dpaa2-eth.o
 obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK)	+= fsl-dpaa2-ptp.o
 
 fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o
+fsl-dpaa2-eth-${CONFIG_FSL_DPAA2_ETH_DCB} += dpaa2-eth-dcb.o
 fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c
new file mode 100644
index 000000000000..7ee07872af4d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2020 NXP */
+
+#include "dpaa2-eth.h"
+
+static int dpaa2_eth_dcbnl_ieee_getpfc(struct net_device *net_dev,
+				       struct ieee_pfc *pfc)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	if (!(priv->link_state.options & DPNI_LINK_OPT_PFC_PAUSE))
+		return 0;
+
+	memcpy(pfc, &priv->pfc, sizeof(priv->pfc));
+	pfc->pfc_cap = dpaa2_eth_tc_count(priv);
+
+	return 0;
+}
+
+static inline bool is_prio_enabled(u8 pfc_en, u8 tc)
+{
+	return !!(pfc_en & (1 << tc));
+}
+
+static int set_pfc_cn(struct dpaa2_eth_priv *priv, u8 pfc_en)
+{
+	struct dpni_congestion_notification_cfg cfg = {0};
+	int i, err;
+
+	cfg.notification_mode = DPNI_CONG_OPT_FLOW_CONTROL;
+	cfg.units = DPNI_CONGESTION_UNIT_FRAMES;
+	cfg.message_iova = 0ULL;
+	cfg.message_ctx = 0ULL;
+
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		if (is_prio_enabled(pfc_en, i)) {
+			cfg.threshold_entry = DPAA2_ETH_CN_THRESH_ENTRY(priv);
+			cfg.threshold_exit = DPAA2_ETH_CN_THRESH_EXIT(priv);
+		} else {
+			/* For priorities not set in the pfc_en mask, we leave
+			 * the congestion thresholds at zero, which effectively
+			 * disables generation of PFC frames for them
+			 */
+			cfg.threshold_entry = 0;
+			cfg.threshold_exit = 0;
+		}
+
+		err = dpni_set_congestion_notification(priv->mc_io, 0,
+						       priv->mc_token,
+						       DPNI_QUEUE_RX, i, &cfg);
+		if (err) {
+			netdev_err(priv->net_dev,
+				   "dpni_set_congestion_notification failed\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int dpaa2_eth_dcbnl_ieee_setpfc(struct net_device *net_dev,
+				       struct ieee_pfc *pfc)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct dpni_link_cfg link_cfg = {0};
+	int err;
+
+	if (pfc->mbc || pfc->delay)
+		return -EOPNOTSUPP;
+
+	/* If same PFC enabled mask, nothing to do */
+	if (priv->pfc.pfc_en == pfc->pfc_en)
+		return 0;
+
+	/* We allow PFC configuration even if it won't have any effect until
+	 * general pause frames are enabled
+	 */
+	if (!dpaa2_eth_rx_pause_enabled(priv->link_state.options) ||
+	    !dpaa2_eth_tx_pause_enabled(priv->link_state.options))
+		netdev_warn(net_dev, "Pause support must be enabled in order for PFC to work!\n");
+
+	link_cfg.rate = priv->link_state.rate;
+	link_cfg.options = priv->link_state.options;
+	if (pfc->pfc_en)
+		link_cfg.options |= DPNI_LINK_OPT_PFC_PAUSE;
+	else
+		link_cfg.options &= ~DPNI_LINK_OPT_PFC_PAUSE;
+	err = dpni_set_link_cfg(priv->mc_io, 0, priv->mc_token, &link_cfg);
+	if (err) {
+		netdev_err(net_dev, "dpni_set_link_cfg failed\n");
+		return err;
+	}
+
+	/* Configure congestion notifications for the enabled priorities */
+	err = set_pfc_cn(priv, pfc->pfc_en);
+	if (err)
+		return err;
+
+	memcpy(&priv->pfc, pfc, sizeof(priv->pfc));
+
+	return 0;
+}
+
+static u8 dpaa2_eth_dcbnl_getdcbx(struct net_device *net_dev)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	return priv->dcbx_mode;
+}
+
+static u8 dpaa2_eth_dcbnl_setdcbx(struct net_device *net_dev, u8 mode)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	return (mode != (priv->dcbx_mode)) ? 1 : 0;
+}
+
+static u8 dpaa2_eth_dcbnl_getcap(struct net_device *net_dev, int capid, u8 *cap)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PFC:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 1 << (dpaa2_eth_tc_count(priv) - 1);
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = priv->dcbx_mode;
+		break;
+	default:
+		*cap = false;
+		break;
+	}
+
+	return 0;
+}
+
+const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops = {
+	.ieee_getpfc	= dpaa2_eth_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= dpaa2_eth_dcbnl_ieee_setpfc,
+	.getdcbx	= dpaa2_eth_dcbnl_getdcbx,
+	.setdcbx	= dpaa2_eth_dcbnl_setdcbx,
+	.getcap		= dpaa2_eth_dcbnl_getcap,
+};
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 04eff6308c72..cde9d0e2dd6d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -3844,6 +3844,15 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	if (err)
 		goto err_alloc_rings;
 
+#ifdef CONFIG_FSL_DPAA2_ETH_DCB
+	if (dpaa2_eth_has_pause_support(priv) && priv->vlan_cls_enabled) {
+		priv->dcbx_mode = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+		net_dev->dcbnl_ops = &dpaa2_eth_dcbnl_ops;
+	} else {
+		dev_dbg(dev, "PFC not supported\n");
+	}
+#endif
+
 	err = setup_irqs(dpni_dev);
 	if (err) {
 		netdev_warn(net_dev, "Failed to set link interrupt, fall back to polling\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 02c0eea69a23..31b7b9b52da0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -6,6 +6,7 @@
 #ifndef __DPAA2_ETH_H
 #define __DPAA2_ETH_H
 
+#include <linux/dcbnl.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/fsl/mc.h>
@@ -65,6 +66,17 @@
 #define DPAA2_ETH_CG_TAILDROP_THRESH(priv)				\
 	(1024 * dpaa2_eth_queue_count(priv) / dpaa2_eth_tc_count(priv))
 
+/* Congestion group notification threshold: when this many frames accumulate
+ * on the Rx queues belonging to the same TC, the MAC is instructed to send
+ * PFC frames for that TC.
+ * When number of pending frames drops below exit threshold transmission of
+ * PFC frames is stopped.
+ */
+#define DPAA2_ETH_CN_THRESH_ENTRY(priv) \
+	(DPAA2_ETH_CG_TAILDROP_THRESH(priv) / 2)
+#define DPAA2_ETH_CN_THRESH_EXIT(priv) \
+	(DPAA2_ETH_CN_THRESH_ENTRY(priv) * 3 / 4)
+
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
  */
@@ -436,6 +448,10 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
 	u8 vlan_cls_enabled;
+#ifdef CONFIG_FSL_DPAA2_ETH_DCB
+	u8 dcbx_mode;
+	struct ieee_pfc pfc;
+#endif
 	struct bpf_prog *xdp_prog;
 #ifdef CONFIG_DEBUG_FS
 	struct dpaa2_debugfs dbg;
@@ -568,4 +584,6 @@ int dpaa2_eth_cls_key_size(u64 key);
 int dpaa2_eth_cls_fld_off(int prot, int field);
 void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields);
 
+extern const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops;
+
 #endif	/* __DPAA2_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
index 0048e856f85e..fd069f67be9b 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
@@ -601,4 +601,29 @@ struct dpni_cmd_remove_qos_entry {
 	__le64 mask_iova;
 };
 
+#define DPNI_DEST_TYPE_SHIFT		0
+#define DPNI_DEST_TYPE_SIZE		4
+#define DPNI_CONG_UNITS_SHIFT		4
+#define DPNI_CONG_UNITS_SIZE		2
+
+struct dpni_cmd_set_congestion_notification {
+	/* cmd word 0 */
+	u8 qtype;
+	u8 tc;
+	u8 pad[6];
+	/* cmd word 1 */
+	__le32 dest_id;
+	__le16 notification_mode;
+	u8 dest_priority;
+	/* from LSB: dest_type: 4 units:2 */
+	u8 type_units;
+	/* cmd word 2 */
+	__le64 message_iova;
+	/* cmd word 3 */
+	__le64 message_ctx;
+	/* cmd word 4 */
+	__le32 threshold_entry;
+	__le32 threshold_exit;
+};
+
 #endif /* _FSL_DPNI_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c
index 78fa325407ca..6b479ba66465 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c
@@ -1354,6 +1354,52 @@ int dpni_set_rx_tc_dist(struct fsl_mc_io *mc_io,
 	return mc_send_command(mc_io, &cmd);
 }
 
+/**
+ * dpni_set_congestion_notification() - Set traffic class congestion
+ *					notification configuration
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPNI object
+ * @qtype:	Type of queue - Rx, Tx and Tx confirm types are supported
+ * @tc_id:	Traffic class selection (0-7)
+ * @cfg:	Congestion notification configuration
+ *
+ * Return:	'0' on Success; error code otherwise.
+ */
+int dpni_set_congestion_notification(
+			struct fsl_mc_io *mc_io,
+			u32 cmd_flags,
+			u16 token,
+			enum dpni_queue_type qtype,
+			u8 tc_id,
+			const struct dpni_congestion_notification_cfg *cfg)
+{
+	struct dpni_cmd_set_congestion_notification *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	/* prepare command */
+	cmd.header =
+		mc_encode_cmd_header(DPNI_CMDID_SET_CONGESTION_NOTIFICATION,
+				     cmd_flags,
+				     token);
+	cmd_params = (struct dpni_cmd_set_congestion_notification *)cmd.params;
+	cmd_params->qtype = qtype;
+	cmd_params->tc = tc_id;
+	cmd_params->dest_id = cpu_to_le32(cfg->dest_cfg.dest_id);
+	cmd_params->notification_mode = cpu_to_le16(cfg->notification_mode);
+	cmd_params->dest_priority = cfg->dest_cfg.priority;
+	dpni_set_field(cmd_params->type_units, DEST_TYPE,
+		       cfg->dest_cfg.dest_type);
+	dpni_set_field(cmd_params->type_units, CONG_UNITS, cfg->units);
+	cmd_params->message_iova = cpu_to_le64(cfg->message_iova);
+	cmd_params->message_ctx = cpu_to_le64(cfg->message_ctx);
+	cmd_params->threshold_entry = cpu_to_le32(cfg->threshold_entry);
+	cmd_params->threshold_exit = cpu_to_le32(cfg->threshold_exit);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+
 /**
  * dpni_set_queue() - Set queue parameters
  * @mc_io:	Pointer to MC portal's I/O object
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index 8c7ac20bf1a7..e874d8084142 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -513,6 +513,11 @@ int dpni_get_statistics(struct fsl_mc_io	*mc_io,
  */
 #define DPNI_LINK_OPT_ASYM_PAUSE	0x0000000000000008ULL
 
+/**
+ * Enable priority flow control pause frames
+ */
+#define DPNI_LINK_OPT_PFC_PAUSE		0x0000000000000010ULL
+
 /**
  * struct - Structure representing DPNI link configuration
  * @rate: Rate
@@ -877,6 +882,62 @@ enum dpni_congestion_point {
 	DPNI_CP_GROUP,
 };
 
+/**
+ * struct dpni_dest_cfg - Structure representing DPNI destination parameters
+ * @dest_type:	Destination type
+ * @dest_id:	Either DPIO ID or DPCON ID, depending on the destination type
+ * @priority:	Priority selection within the DPIO or DPCON channel; valid
+ *		values are 0-1 or 0-7, depending on the number of priorities
+ *		in that channel; not relevant for 'DPNI_DEST_NONE' option
+ */
+struct dpni_dest_cfg {
+	enum dpni_dest dest_type;
+	int dest_id;
+	u8 priority;
+};
+
+/* DPNI congestion options */
+
+/**
+ * This congestion will trigger flow control or priority flow control.
+ * This will have effect only if flow control is enabled with
+ * dpni_set_link_cfg().
+ */
+#define DPNI_CONG_OPT_FLOW_CONTROL		0x00000040
+
+/**
+ * struct dpni_congestion_notification_cfg - congestion notification
+ *					configuration
+ * @units: Units type
+ * @threshold_entry: Above this threshold we enter a congestion state.
+ *		set it to '0' to disable it
+ * @threshold_exit: Below this threshold we exit the congestion state.
+ * @message_ctx: The context that will be part of the CSCN message
+ * @message_iova: I/O virtual address (must be in DMA-able memory),
+ *		must be 16B aligned; valid only if 'DPNI_CONG_OPT_WRITE_MEM_<X>'
+ *		is contained in 'options'
+ * @dest_cfg: CSCN can be send to either DPIO or DPCON WQ channel
+ * @notification_mode: Mask of available options; use 'DPNI_CONG_OPT_<X>' values
+ */
+
+struct dpni_congestion_notification_cfg {
+	enum dpni_congestion_unit units;
+	u32 threshold_entry;
+	u32 threshold_exit;
+	u64 message_ctx;
+	u64 message_iova;
+	struct dpni_dest_cfg dest_cfg;
+	u16 notification_mode;
+};
+
+int dpni_set_congestion_notification(
+			struct fsl_mc_io *mc_io,
+			u32 cmd_flags,
+			u16 token,
+			enum dpni_queue_type qtype,
+			u8 tc_id,
+			const struct dpni_congestion_notification_cfg *cfg);
+
 /**
  * struct dpni_taildrop - Structure representing the taildrop
  * @enable:	Indicates whether the taildrop is active or not.
-- 
cgit v1.2.3


From 07beb1651adcd324f4d91584d5cab75d5882a9c2 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 31 May 2020 00:08:14 +0300
Subject: dpaa2-eth: Keep congestion group taildrop enabled when PFC on

Leave congestion group taildrop enabled for all traffic classes
when PFC is enabled. Notification threshold is low enough such
that it will be hit first and this also ensures that FQs on
traffic classes which are not PFC enabled won't drain the buffer
pool.

FQ taildrop threshold is kept disabled as long as any form of
flow control is on. Since FQ taildrop works with bytes, not number
of frames, we can't guarantee it will not interfere with the
congestion notification mechanism for all frame sizes.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c   |  8 ++++--
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c   | 29 ++++++++++++++++------
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h   |  7 +++++-
 3 files changed, 34 insertions(+), 10 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c
index 7ee07872af4d..83dee575c2fa 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-dcb.c
@@ -63,6 +63,7 @@ static int dpaa2_eth_dcbnl_ieee_setpfc(struct net_device *net_dev,
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpni_link_cfg link_cfg = {0};
+	bool tx_pause;
 	int err;
 
 	if (pfc->mbc || pfc->delay)
@@ -75,8 +76,8 @@ static int dpaa2_eth_dcbnl_ieee_setpfc(struct net_device *net_dev,
 	/* We allow PFC configuration even if it won't have any effect until
 	 * general pause frames are enabled
 	 */
-	if (!dpaa2_eth_rx_pause_enabled(priv->link_state.options) ||
-	    !dpaa2_eth_tx_pause_enabled(priv->link_state.options))
+	tx_pause = dpaa2_eth_tx_pause_enabled(priv->link_state.options);
+	if (!dpaa2_eth_rx_pause_enabled(priv->link_state.options) || !tx_pause)
 		netdev_warn(net_dev, "Pause support must be enabled in order for PFC to work!\n");
 
 	link_cfg.rate = priv->link_state.rate;
@@ -97,6 +98,9 @@ static int dpaa2_eth_dcbnl_ieee_setpfc(struct net_device *net_dev,
 		return err;
 
 	memcpy(&priv->pfc, pfc, sizeof(priv->pfc));
+	priv->pfc_enabled = !!pfc->pfc_en;
+
+	dpaa2_eth_set_rx_taildrop(priv, tx_pause, priv->pfc_enabled);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index cde9d0e2dd6d..8fb48de5d18c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1287,18 +1287,22 @@ static void disable_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
-static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
-				      bool tx_pause)
+void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
+			       bool tx_pause, bool pfc)
 {
 	struct dpni_taildrop td = {0};
 	struct dpaa2_eth_fq *fq;
 	int i, err;
 
+	/* FQ taildrop: threshold is in bytes, per frame queue. Enabled if
+	 * flow control is disabled (as it might interfere with either the
+	 * buffer pool depletion trigger for pause frames or with the group
+	 * congestion trigger for PFC frames)
+	 */
 	td.enable = !tx_pause;
-	if (priv->rx_td_enabled == td.enable)
-		return;
+	if (priv->rx_fqtd_enabled == td.enable)
+		goto set_cgtd;
 
-	/* FQ taildrop: threshold is in bytes, per frame queue */
 	td.threshold = DPAA2_ETH_FQ_TAILDROP_THRESH;
 	td.units = DPNI_CONGESTION_UNIT_BYTES;
 
@@ -1316,9 +1320,20 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
 		}
 	}
 
+	priv->rx_fqtd_enabled = td.enable;
+
+set_cgtd:
 	/* Congestion group taildrop: threshold is in frames, per group
 	 * of FQs belonging to the same traffic class
+	 * Enabled if general Tx pause disabled or if PFCs are enabled
+	 * (congestion group threhsold for PFC generation is lower than the
+	 * CG taildrop threshold, so it won't interfere with it; we also
+	 * want frames in non-PFC enabled traffic classes to be kept in check)
 	 */
+	td.enable = !tx_pause || (tx_pause && pfc);
+	if (priv->rx_cgtd_enabled == td.enable)
+		return;
+
 	td.threshold = DPAA2_ETH_CG_TAILDROP_THRESH(priv);
 	td.units = DPNI_CONGESTION_UNIT_FRAMES;
 	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
@@ -1332,7 +1347,7 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
 		}
 	}
 
-	priv->rx_td_enabled = td.enable;
+	priv->rx_cgtd_enabled = td.enable;
 }
 
 static int link_state_update(struct dpaa2_eth_priv *priv)
@@ -1353,7 +1368,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv)
 	 * only when pause frame generation is disabled.
 	 */
 	tx_pause = dpaa2_eth_tx_pause_enabled(state.options);
-	dpaa2_eth_set_rx_taildrop(priv, tx_pause);
+	dpaa2_eth_set_rx_taildrop(priv, tx_pause, priv->pfc_enabled);
 
 	/* When we manage the MAC/PHY using phylink there is no need
 	 * to manually update the netif_carrier.
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 31b7b9b52da0..2d7ada0f0dbd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -436,7 +436,8 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_drv_stats __percpu *percpu_extras;
 
 	u16 mc_token;
-	u8 rx_td_enabled;
+	u8 rx_fqtd_enabled;
+	u8 rx_cgtd_enabled;
 
 	struct dpni_link_state link_state;
 	bool do_link_poll;
@@ -448,6 +449,7 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
 	u8 vlan_cls_enabled;
+	u8 pfc_enabled;
 #ifdef CONFIG_FSL_DPAA2_ETH_DCB
 	u8 dcbx_mode;
 	struct ieee_pfc pfc;
@@ -584,6 +586,9 @@ int dpaa2_eth_cls_key_size(u64 key);
 int dpaa2_eth_cls_fld_off(int prot, int field);
 void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields);
 
+void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
+			       bool tx_pause, bool pfc);
+
 extern const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops;
 
 #endif	/* __DPAA2_H */
-- 
cgit v1.2.3


From 1b698fa5d8ef958007c455e316aa44c37ab3c5fb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 28 May 2020 22:47:29 +0200
Subject: xdp: Rename convert_to_xdp_frame in xdp_convert_buff_to_frame

In order to use standard 'xdp' prefix, rename convert_to_xdp_frame
utility routine in xdp_convert_buff_to_frame and replace all the
occurrences

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/6344f739be0d1a08ab2b9607584c4d5478c8c083.1590698295.git.lorenzo@kernel.org
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c     |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c      |  2 +-
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c    |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c    |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c     |  2 +-
 drivers/net/ethernet/marvell/mvneta.c            |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 10 +++++-----
 drivers/net/ethernet/sfc/rx.c                    |  2 +-
 drivers/net/ethernet/socionext/netsec.c          |  2 +-
 drivers/net/ethernet/ti/cpsw_priv.c              |  2 +-
 drivers/net/tun.c                                |  2 +-
 drivers/net/veth.c                               |  2 +-
 drivers/net/virtio_net.c                         |  4 ++--
 include/net/xdp.h                                |  2 +-
 kernel/bpf/cpumap.c                              |  2 +-
 kernel/bpf/devmap.c                              |  2 +-
 16 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 46865d5bd7e7..a0af74c93971 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -263,7 +263,7 @@ static int ena_xdp_tx_map_buff(struct ena_ring *xdp_ring,
 	dma_addr_t dma = 0;
 	u32 size;
 
-	tx_info->xdpf = convert_to_xdp_frame(xdp);
+	tx_info->xdpf = xdp_convert_buff_to_frame(xdp);
 	size = tx_info->xdpf->len;
 	ena_buf = tx_info->bufs;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f613782f2f56..f9555c847f73 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2167,7 +2167,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 
 int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring)
 {
-	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 
 	if (unlikely(!xdpf))
 		return I40E_XDP_CONSUMED;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index ab2031b1c635..02b12736ea80 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -254,7 +254,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring)
  */
 int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring)
 {
-	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 
 	if (unlikely(!xdpf))
 		return ICE_XDP_CONSUMED;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a59c166f794f..f162b8b8f345 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2215,7 +2215,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		xdpf = convert_to_xdp_frame(xdp);
+		xdpf = xdp_convert_buff_to_frame(xdp);
 		if (unlikely(!xdpf)) {
 			result = IXGBE_XDP_CONSUMED;
 			break;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 86add9fbd36c..be9d2a8da515 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -107,7 +107,7 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		xdpf = convert_to_xdp_frame(xdp);
+		xdpf = xdp_convert_buff_to_frame(xdp);
 		if (unlikely(!xdpf)) {
 			result = IXGBE_XDP_CONSUMED;
 			break;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 15e42a7f8a86..011cd26953d9 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2073,7 +2073,7 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp)
 	int cpu;
 	u32 ret;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return MVNETA_XDP_DROPPED;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3bea1d4be53b..c9d308e91965 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -64,7 +64,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	struct xdp_frame *xdpf;
 	dma_addr_t dma_addr;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return false;
 
@@ -97,10 +97,10 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 		xdpi.frame.xdpf     = xdpf;
 		xdpi.frame.dma_addr = dma_addr;
 	} else {
-		/* Driver assumes that convert_to_xdp_frame returns an xdp_frame
-		 * that points to the same memory region as the original
-		 * xdp_buff. It allows to map the memory only once and to use
-		 * the DMA_BIDIRECTIONAL mode.
+		/* Driver assumes that xdp_convert_buff_to_frame returns
+		 * an xdp_frame that points to the same memory region as
+		 * the original xdp_buff. It allows to map the memory only
+		 * once and to use the DMA_BIDIRECTIONAL mode.
 		 */
 
 		xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 68c47a8c71df..c01916cff507 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -329,7 +329,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 
 	case XDP_TX:
 		/* Buffer ownership passes to tx on success. */
-		xdpf = convert_to_xdp_frame(&xdp);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
 		err = efx_xdp_tx_buffers(efx, 1, &xdpf, true);
 		if (unlikely(err != 1)) {
 			efx_free_rx_buffers(rx_queue, rx_buf, 1);
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index e1f4be4b3d69..328bc38848bb 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -867,7 +867,7 @@ static u32 netsec_xdp_queue_one(struct netsec_priv *priv,
 static u32 netsec_xdp_xmit_back(struct netsec_priv *priv, struct xdp_buff *xdp)
 {
 	struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
-	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	u32 ret;
 
 	if (unlikely(!xdpf))
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index d940628bff8d..a399f3659346 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1355,7 +1355,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
 		ret = CPSW_XDP_PASS;
 		break;
 	case XDP_TX:
-		xdpf = convert_to_xdp_frame(xdp);
+		xdpf = xdp_convert_buff_to_frame(xdp);
 		if (unlikely(!xdpf))
 			goto drop;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b0ab882c021e..858b012074bd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1295,7 +1295,7 @@ resample:
 
 static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
 {
-	struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+	struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp);
 
 	if (unlikely(!frame))
 		return -EOVERFLOW;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index fb5c17361f64..b594f03eeddb 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -541,7 +541,7 @@ out:
 static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp,
 		       struct veth_xdp_tx_bq *bq)
 {
-	struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+	struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp);
 
 	if (unlikely(!frame))
 		return -EOVERFLOW;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b6951aa76295..ba38765dc490 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -703,7 +703,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			break;
 		case XDP_TX:
 			stats->xdp_tx++;
-			xdpf = convert_to_xdp_frame(&xdp);
+			xdpf = xdp_convert_buff_to_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
 			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
@@ -892,7 +892,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			break;
 		case XDP_TX:
 			stats->xdp_tx++;
-			xdpf = convert_to_xdp_frame(&xdp);
+			xdpf = xdp_convert_buff_to_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
 			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
diff --git a/include/net/xdp.h b/include/net/xdp.h
index db5c2c687f48..609f819ed08b 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -123,7 +123,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 
 /* Convert xdp_buff to xdp_frame */
 static inline
-struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
+struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
 {
 	struct xdp_frame *xdp_frame;
 	int metasize;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8b85bfddfac7..27595fc6da56 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -621,7 +621,7 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 {
 	struct xdp_frame *xdpf;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index c04fb1c72f5e..854b09beb16b 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -465,7 +465,7 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 	if (unlikely(err))
 		return err;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
-- 
cgit v1.2.3


From a3ac249a1ab57552cb2a63e70556ee87610a591d Mon Sep 17 00:00:00 2001
From: Rohit Maheshwari <rohitm@chelsio.com>
Date: Mon, 1 Jun 2020 13:08:29 +0530
Subject: cxgb4/chcr: Enable ktls settings at run time

Current design enables ktls setting from start, which is not
efficient. Now the feature will be enabled when user demands
TLS offload on any interface.

v1->v2:
- taking ULD module refcount till any single connection exists.
- taking rtnl_lock() before clearing tls_devops.

v2->v3:
- cxgb4 is now registering to tlsdev_ops.
- module refcount inc/dec in chcr.
- refcount is only for connections.
- removed new code from cxgb_set_feature().

v3->v4:
- fixed warning message.

Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/chelsio/chcr_core.c                 | 23 +++---
 drivers/crypto/chelsio/chcr_core.h                 | 10 ++-
 drivers/crypto/chelsio/chcr_ktls.c                 | 59 ++++-----------
 drivers/crypto/chelsio/chcr_ktls.h                 |  9 ++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h         |  4 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c |  2 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    | 85 +++++++++++++++++++++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c     | 71 ++++++++++++------
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h     |  7 ++
 drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h      | 10 ++-
 10 files changed, 195 insertions(+), 85 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index ffd4ec0c7374..bd8dac806e7a 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -33,6 +33,13 @@ static int cpl_fw6_pld_handler(struct adapter *adap, unsigned char *input);
 static void *chcr_uld_add(const struct cxgb4_lld_info *lld);
 static int chcr_uld_state_change(void *handle, enum cxgb4_state state);
 
+#if defined(CONFIG_CHELSIO_TLS_DEVICE)
+static const struct tlsdev_ops chcr_ktls_ops = {
+	.tls_dev_add = chcr_ktls_dev_add,
+	.tls_dev_del = chcr_ktls_dev_del,
+};
+#endif
+
 #ifdef CONFIG_CHELSIO_IPSEC_INLINE
 static void update_netdev_features(void);
 #endif /* CONFIG_CHELSIO_IPSEC_INLINE */
@@ -56,6 +63,9 @@ static struct cxgb4_uld_info chcr_uld_info = {
 #if defined(CONFIG_CHELSIO_IPSEC_INLINE) || defined(CONFIG_CHELSIO_TLS_DEVICE)
 	.tx_handler = chcr_uld_tx_handler,
 #endif /* CONFIG_CHELSIO_IPSEC_INLINE || CONFIG_CHELSIO_TLS_DEVICE */
+#if defined(CONFIG_CHELSIO_TLS_DEVICE)
+	.tlsdev_ops = &chcr_ktls_ops,
+#endif
 };
 
 static void detach_work_fn(struct work_struct *work)
@@ -207,11 +217,6 @@ static void *chcr_uld_add(const struct cxgb4_lld_info *lld)
 	}
 	u_ctx->lldi = *lld;
 	chcr_dev_init(u_ctx);
-
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-	if (lld->ulp_crypto & ULP_CRYPTO_KTLS_INLINE)
-		chcr_enable_ktls(padap(&u_ctx->dev));
-#endif
 out:
 	return u_ctx;
 }
@@ -348,20 +353,12 @@ static void __exit chcr_crypto_exit(void)
 	list_for_each_entry_safe(u_ctx, tmp, &drv_data.act_dev, entry) {
 		adap = padap(&u_ctx->dev);
 		memset(&adap->chcr_stats, 0, sizeof(adap->chcr_stats));
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-		if (u_ctx->lldi.ulp_crypto & ULP_CRYPTO_KTLS_INLINE)
-			chcr_disable_ktls(adap);
-#endif
 		list_del(&u_ctx->entry);
 		kfree(u_ctx);
 	}
 	list_for_each_entry_safe(u_ctx, tmp, &drv_data.inact_dev, entry) {
 		adap = padap(&u_ctx->dev);
 		memset(&adap->chcr_stats, 0, sizeof(adap->chcr_stats));
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-		if (u_ctx->lldi.ulp_crypto & ULP_CRYPTO_KTLS_INLINE)
-			chcr_disable_ktls(adap);
-#endif
 		list_del(&u_ctx->entry);
 		kfree(u_ctx);
 	}
diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h
index 2c09672e00a4..67d77abd6775 100644
--- a/drivers/crypto/chelsio/chcr_core.h
+++ b/drivers/crypto/chelsio/chcr_core.h
@@ -37,6 +37,7 @@
 #define __CHCR_CORE_H__
 
 #include <crypto/algapi.h>
+#include <net/tls.h>
 #include "t4_hw.h"
 #include "cxgb4.h"
 #include "t4_msg.h"
@@ -223,10 +224,15 @@ int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
 int chcr_ipsec_xmit(struct sk_buff *skb, struct net_device *dev);
 void chcr_add_xfrmops(const struct cxgb4_lld_info *lld);
 #ifdef CONFIG_CHELSIO_TLS_DEVICE
-void chcr_enable_ktls(struct adapter *adap);
-void chcr_disable_ktls(struct adapter *adap);
 int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, unsigned char *input);
 int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input);
 int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev);
+extern int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
+			     enum tls_offload_ctx_dir direction,
+			     struct tls_crypto_info *crypto_info,
+			     u32 start_offload_tcp_sn);
+extern void chcr_ktls_dev_del(struct net_device *netdev,
+			      struct tls_context *tls_ctx,
+			      enum tls_offload_ctx_dir direction);
 #endif
 #endif /* __CHCR_CORE_H__ */
diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c
index 43d9e2420110..f55b87152166 100644
--- a/drivers/crypto/chelsio/chcr_ktls.c
+++ b/drivers/crypto/chelsio/chcr_ktls.c
@@ -373,9 +373,9 @@ static int chcr_ktls_mark_tcb_close(struct chcr_ktls_info *tx_info)
  * @tls_cts - tls context.
  * @direction - TX/RX crypto direction
  */
-static void chcr_ktls_dev_del(struct net_device *netdev,
-			      struct tls_context *tls_ctx,
-			      enum tls_offload_ctx_dir direction)
+void chcr_ktls_dev_del(struct net_device *netdev,
+		       struct tls_context *tls_ctx,
+		       enum tls_offload_ctx_dir direction)
 {
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx =
 				chcr_get_ktls_tx_context(tls_ctx);
@@ -411,6 +411,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
 	atomic64_inc(&tx_info->adap->chcr_stats.ktls_tx_connection_close);
 	kvfree(tx_info);
 	tx_ctx->chcr_info = NULL;
+	/* release module refcount */
+	module_put(THIS_MODULE);
 }
 
 /*
@@ -422,10 +424,10 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
  * @direction - TX/RX crypto direction
  * return: SUCCESS/FAILURE.
  */
-static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
-			     enum tls_offload_ctx_dir direction,
-			     struct tls_crypto_info *crypto_info,
-			     u32 start_offload_tcp_sn)
+int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
+		      enum tls_offload_ctx_dir direction,
+		      struct tls_crypto_info *crypto_info,
+		      u32 start_offload_tcp_sn)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx;
@@ -528,6 +530,12 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 	if (ret)
 		goto out2;
 
+	/* Driver shouldn't be removed until any single connection exists */
+	if (!try_module_get(THIS_MODULE)) {
+		ret = -EINVAL;
+		goto out2;
+	}
+
 	atomic64_inc(&adap->chcr_stats.ktls_tx_connection_open);
 	return 0;
 out2:
@@ -537,43 +545,6 @@ out:
 	return ret;
 }
 
-static const struct tlsdev_ops chcr_ktls_ops = {
-	.tls_dev_add = chcr_ktls_dev_add,
-	.tls_dev_del = chcr_ktls_dev_del,
-};
-
-/*
- * chcr_enable_ktls:  add NETIF_F_HW_TLS_TX flag in all the ports.
- */
-void chcr_enable_ktls(struct adapter *adap)
-{
-	struct net_device *netdev;
-	int i;
-
-	for_each_port(adap, i) {
-		netdev = adap->port[i];
-		netdev->features |= NETIF_F_HW_TLS_TX;
-		netdev->hw_features |= NETIF_F_HW_TLS_TX;
-		netdev->tlsdev_ops = &chcr_ktls_ops;
-	}
-}
-
-/*
- * chcr_disable_ktls:  remove NETIF_F_HW_TLS_TX flag from all the ports.
- */
-void chcr_disable_ktls(struct adapter *adap)
-{
-	struct net_device *netdev;
-	int i;
-
-	for_each_port(adap, i) {
-		netdev = adap->port[i];
-		netdev->features &= ~NETIF_F_HW_TLS_TX;
-		netdev->hw_features &= ~NETIF_F_HW_TLS_TX;
-		netdev->tlsdev_ops = NULL;
-	}
-}
-
 /*
  * chcr_init_tcb_fields:  Initialize tcb fields to handle TCP seq number
  *			  handling.
diff --git a/drivers/crypto/chelsio/chcr_ktls.h b/drivers/crypto/chelsio/chcr_ktls.h
index 5a7ae2ca446e..5cbd84b1da05 100644
--- a/drivers/crypto/chelsio/chcr_ktls.h
+++ b/drivers/crypto/chelsio/chcr_ktls.h
@@ -89,10 +89,15 @@ static inline int chcr_get_first_rx_qid(struct adapter *adap)
 	return u_ctx->lldi.rxq_ids[0];
 }
 
-void chcr_enable_ktls(struct adapter *adap);
-void chcr_disable_ktls(struct adapter *adap);
 int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, unsigned char *input);
 int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input);
 int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev);
+int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
+		      enum tls_offload_ctx_dir direction,
+		      struct tls_crypto_info *crypto_info,
+		      u32 start_offload_tcp_sn);
+void chcr_ktls_dev_del(struct net_device *netdev,
+		       struct tls_context *tls_ctx,
+		       enum tls_offload_ctx_dir direction);
 #endif /* CONFIG_CHELSIO_TLS_DEVICE */
 #endif /* __CHCR_KTLS_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 5a41801acb6a..cf69c6edcfec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1099,6 +1099,7 @@ struct adapter {
 
 	/* TC u32 offload */
 	struct cxgb4_tc_u32_table *tc_u32;
+	struct chcr_ktls chcr_ktls;
 	struct chcr_stats_debug chcr_stats;
 
 	/* TC flower offload */
@@ -2060,4 +2061,7 @@ int cxgb_open(struct net_device *dev);
 int cxgb_close(struct net_device *dev);
 void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q);
 void cxgb4_quiesce_rx(struct sge_rspq *q);
+#ifdef CONFIG_CHELSIO_TLS_DEVICE
+int cxgb4_set_ktls_feature(struct adapter *adap, bool enable);
+#endif
 #endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index c3dd50b45c48..41315712deb8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -3491,6 +3491,8 @@ static int chcr_stats_show(struct seq_file *seq, void *v)
 		   atomic_read(&adap->chcr_stats.tls_key));
 #ifdef CONFIG_CHELSIO_TLS_DEVICE
 	seq_puts(seq, "\nChelsio KTLS Crypto Accelerator Stats\n");
+	seq_printf(seq, "Tx TLS offload refcount:          %20u\n",
+		   refcount_read(&adap->chcr_ktls.ktls_refcount));
 	seq_printf(seq, "Tx HW offload contexts added:     %20llu\n",
 		   atomic64_read(&adap->chcr_stats.ktls_tx_ctx));
 	seq_printf(seq, "Tx connection created:            %20llu\n",
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 7a0414f379be..854b1717a70d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -66,6 +66,9 @@
 #include <linux/crash_dump.h>
 #include <net/udp_tunnel.h>
 #include <net/xfrm.h>
+#if defined(CONFIG_CHELSIO_TLS_DEVICE)
+#include <net/tls.h>
+#endif
 
 #include "cxgb4.h"
 #include "cxgb4_filter.h"
@@ -6064,6 +6067,79 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs)
 }
 #endif /* CONFIG_PCI_IOV */
 
+#if defined(CONFIG_CHELSIO_TLS_DEVICE)
+
+static int cxgb4_ktls_dev_add(struct net_device *netdev, struct sock *sk,
+			      enum tls_offload_ctx_dir direction,
+			      struct tls_crypto_info *crypto_info,
+			      u32 tcp_sn)
+{
+	struct adapter *adap = netdev2adap(netdev);
+	int ret = 0;
+
+	mutex_lock(&uld_mutex);
+	if (!adap->uld[CXGB4_ULD_CRYPTO].handle) {
+		dev_err(adap->pdev_dev, "chcr driver is not loaded\n");
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
+	if (!adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops) {
+		dev_err(adap->pdev_dev,
+			"chcr driver has no registered tlsdev_ops()\n");
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
+	ret = cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_ENABLE);
+	if (ret)
+		goto out_unlock;
+
+	ret = adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops->tls_dev_add(netdev, sk,
+								  direction,
+								  crypto_info,
+								  tcp_sn);
+	/* if there is a failure, clear the refcount */
+	if (ret)
+		cxgb4_set_ktls_feature(adap,
+				       FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
+out_unlock:
+	mutex_unlock(&uld_mutex);
+	return ret;
+}
+
+static void cxgb4_ktls_dev_del(struct net_device *netdev,
+			       struct tls_context *tls_ctx,
+			       enum tls_offload_ctx_dir direction)
+{
+	struct adapter *adap = netdev2adap(netdev);
+
+	mutex_lock(&uld_mutex);
+	if (!adap->uld[CXGB4_ULD_CRYPTO].handle) {
+		dev_err(adap->pdev_dev, "chcr driver is not loaded\n");
+		goto out_unlock;
+	}
+
+	if (!adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops) {
+		dev_err(adap->pdev_dev,
+			"chcr driver has no registered tlsdev_ops\n");
+		goto out_unlock;
+	}
+
+	adap->uld[CXGB4_ULD_CRYPTO].tlsdev_ops->tls_dev_del(netdev, tls_ctx,
+							    direction);
+	cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+}
+
+static const struct tlsdev_ops cxgb4_ktls_ops = {
+	.tls_dev_add = cxgb4_ktls_dev_add,
+	.tls_dev_del = cxgb4_ktls_dev_del,
+};
+#endif /* CONFIG_CHELSIO_TLS_DEVICE */
+
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
@@ -6313,7 +6389,14 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			netdev->hw_features |= NETIF_F_HIGHDMA;
 		netdev->features |= netdev->hw_features;
 		netdev->vlan_features = netdev->features & VLAN_FEAT;
-
+#if defined(CONFIG_CHELSIO_TLS_DEVICE)
+		if (pi->adapter->params.crypto & FW_CAPS_CONFIG_TLS_HW) {
+			netdev->hw_features |= NETIF_F_HW_TLS_TX;
+			netdev->tlsdev_ops = &cxgb4_ktls_ops;
+			/* initialize the refcount */
+			refcount_set(&pi->adapter->chcr_ktls.ktls_refcount, 0);
+		}
+#endif
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 
 		/* MTU range: 81 - 9600 */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 9e3c6b36cde8..0307e9c69a47 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -663,22 +663,64 @@ static int uld_attach(struct adapter *adap, unsigned int uld)
 	return 0;
 }
 
+static bool cxgb4_uld_in_use(struct adapter *adap)
+{
+	const struct tid_info *t = &adap->tids;
+
+	return (atomic_read(&t->conns_in_use) || t->stids_in_use);
+}
+
 #ifdef CONFIG_CHELSIO_TLS_DEVICE
 /* cxgb4_set_ktls_feature: request FW to enable/disable ktls settings.
  * @adap: adapter info
  * @enable: 1 to enable / 0 to disable ktls settings.
  */
-static void cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
+int cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 {
-	u32 params = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
-		      FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_KTLS_TX_HW) |
-		      FW_PARAMS_PARAM_Y_V(enable));
 	int ret = 0;
+	u32 params =
+		FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_KTLS_HW) |
+		FW_PARAMS_PARAM_Y_V(enable) |
+		FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_KTLS_HW_USER_ENABLE);
+
+	if (enable) {
+		if (!refcount_read(&adap->chcr_ktls.ktls_refcount)) {
+			/* At this moment if ULD connection are up means, other
+			 * ULD is/are already active, return failure.
+			 */
+			if (cxgb4_uld_in_use(adap)) {
+				dev_warn(adap->pdev_dev,
+					 "ULD connections (tid/stid) active. Can't enable kTLS\n");
+				return -EINVAL;
+			}
+			ret = t4_set_params(adap, adap->mbox, adap->pf,
+					    0, 1, &params, &params);
+			if (ret)
+				return ret;
+			refcount_set(&adap->chcr_ktls.ktls_refcount, 1);
+			pr_info("kTLS has been enabled. Restrictions placed on ULD support\n");
+		} else {
+			/* ktls settings already up, just increment refcount. */
+			refcount_inc(&adap->chcr_ktls.ktls_refcount);
+		}
+	} else {
+		/* return failure if refcount is already 0. */
+		if (!refcount_read(&adap->chcr_ktls.ktls_refcount))
+			return -EINVAL;
+		/* decrement refcount and test, if 0, disable ktls feature,
+		 * else return command success.
+		 */
+		if (refcount_dec_and_test(&adap->chcr_ktls.ktls_refcount)) {
+			ret = t4_set_params(adap, adap->mbox, adap->pf,
+					    0, 1, &params, &params);
+			if (ret)
+				return ret;
+			pr_info("kTLS is disabled. Restrictions on ULD support removed\n");
+		}
+	}
 
-	ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, &params, &params);
-	/* if fw returns failure, clear the ktls flag */
-	if (ret)
-		adap->params.crypto &= ~ULP_CRYPTO_KTLS_INLINE;
+	return ret;
 }
 #endif
 
@@ -706,12 +748,6 @@ static void cxgb4_uld_alloc_resources(struct adapter *adap,
 	}
 	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		enable_rx_uld(adap, type);
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-	/* send mbox to enable ktls related settings. */
-	if (type == CXGB4_ULD_CRYPTO &&
-	    (adap->params.crypto & FW_CAPS_CONFIG_TX_TLS_HW))
-		cxgb4_set_ktls_feature(adap, 1);
-#endif
 	if (adap->uld[type].add)
 		goto free_irq;
 	ret = setup_sge_txq_uld(adap, type, p);
@@ -805,13 +841,6 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 			continue;
 
 		cxgb4_shutdown_uld_adapter(adap, type);
-
-#ifdef CONFIG_CHELSIO_TLS_DEVICE
-		/* send mbox to disable ktls related settings. */
-		if (type == CXGB4_ULD_CRYPTO &&
-		    (adap->params.crypto & FW_CAPS_CONFIG_TX_TLS_HW))
-			cxgb4_set_ktls_feature(adap, 0);
-#endif
 	}
 
 	list_for_each_entry_safe(uld_entry, tmp, &uld_list, list_node) {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 085fa1424f9a..dbce99b209d6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -268,6 +268,10 @@ struct filter_ctx {
 	u32 tid;			/* to store tid */
 };
 
+struct chcr_ktls {
+	refcount_t ktls_refcount;
+};
+
 struct ch_filter_specification;
 
 int cxgb4_get_free_ftid(struct net_device *dev, u8 family, bool hash_en,
@@ -464,6 +468,9 @@ struct cxgb4_uld_info {
 			      struct napi_struct *napi);
 	void (*lro_flush)(struct t4_lro_mgr *);
 	int (*tx_handler)(struct sk_buff *skb, struct net_device *dev);
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+	const struct tlsdev_ops *tlsdev_ops;
+#endif
 };
 
 void cxgb4_uld_enable(struct adapter *adap);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 68fe734b9b37..0a326c054707 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1205,7 +1205,7 @@ enum fw_caps_config_crypto {
 	FW_CAPS_CONFIG_CRYPTO_LOOKASIDE = 0x00000001,
 	FW_CAPS_CONFIG_TLS_INLINE = 0x00000002,
 	FW_CAPS_CONFIG_IPSEC_INLINE = 0x00000004,
-	FW_CAPS_CONFIG_TX_TLS_HW = 0x00000008,
+	FW_CAPS_CONFIG_TLS_HW = 0x00000008,
 };
 
 enum fw_caps_config_fcoe {
@@ -1329,7 +1329,7 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK = 0x2A,
 	FW_PARAMS_PARAM_DEV_NUM_TM_CLASS = 0x2B,
 	FW_PARAMS_PARAM_DEV_FILTER = 0x2E,
-	FW_PARAMS_PARAM_DEV_KTLS_TX_HW = 0x31,
+	FW_PARAMS_PARAM_DEV_KTLS_HW = 0x31,
 };
 
 /*
@@ -1412,6 +1412,12 @@ enum fw_params_param_dmaq {
 	FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20,
 };
 
+enum fw_params_param_dev_ktls_hw {
+	FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE      = 0x00,
+	FW_PARAMS_PARAM_DEV_KTLS_HW_ENABLE       = 0x01,
+	FW_PARAMS_PARAM_DEV_KTLS_HW_USER_ENABLE  = 0x01,
+};
+
 enum fw_params_param_dev_phyfw {
 	FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD = 0x00,
 	FW_PARAMS_PARAM_DEV_PHYFW_VERSION = 0x01,
-- 
cgit v1.2.3


From efd7ed0f5f2d07ccbb1853c5d46656cdfa1371fb Mon Sep 17 00:00:00 2001
From: Jules Irenge <jbi.octave@gmail.com>
Date: Mon, 1 Jun 2020 19:45:52 +0100
Subject: sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()

Sparse reports a warning at efx_ef10_try_update_nic_stats_vf()
warning: context imbalance in efx_ef10_try_update_nic_stats_vf()
	- unexpected unlock
The root cause is the missing annotation at
efx_ef10_try_update_nic_stats_vf()
Add the missing _must_hold(&efx->stats_lock) annotation

Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 964c5e842cec..4b0e3695a71a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1819,6 +1819,7 @@ static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats,
 }
 
 static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx)
+	__must_hold(&efx->stats_lock)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-- 
cgit v1.2.3


From 2eed5a8b614bc0197b29da7b21a78d2c564a7098 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Tue, 2 Jun 2020 08:40:32 +0800
Subject: hinic: add set_channels ethtool_ops support

add support to change TX/RX queue number with "ethtool -L combined".

V5 -> V6: remove check for carrier in hinic_xmit_frame
V4 -> V5: change time zone in patch header
V3 -> V4: update date in patch header
V2 -> V3: remove check for zero channels->combined_count
V1 -> V2: update commit message("ethtool -L" to "ethtool -L combined")
V0 -> V1: remove check for channels->tx_count/rx_count/other_count

Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 40 ++++++++++++++++++-----
 drivers/net/ethernet/huawei/hinic/hinic_main.c    |  2 +-
 2 files changed, 33 insertions(+), 9 deletions(-)

(limited to 'drivers/net/ethernet')

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index ace18d258049..efb02e03e7da 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -619,14 +619,37 @@ static void hinic_get_channels(struct net_device *netdev,
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 
-	channels->max_rx = hwdev->nic_cap.max_qps;
-	channels->max_tx = hwdev->nic_cap.max_qps;
-	channels->max_other = 0;
-	channels->max_combined = 0;
-	channels->rx_count = hinic_hwdev_num_qps(hwdev);
-	channels->tx_count = hinic_hwdev_num_qps(hwdev);
-	channels->other_count = 0;
-	channels->combined_count = 0;
+	channels->max_combined = nic_dev->max_qps;
+	channels->combined_count = hinic_hwdev_num_qps(hwdev);
+}
+
+static int hinic_set_channels(struct net_device *netdev,
+			      struct ethtool_channels *channels)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	unsigned int count = channels->combined_count;
+	int err;
+
+	netif_info(nic_dev, drv, netdev, "Set max combined queue number from %d to %d\n",
+		   hinic_hwdev_num_qps(nic_dev->hwdev), count);
+
+	if (netif_running(netdev)) {
+		netif_info(nic_dev, drv, netdev, "Restarting netdev\n");
+		hinic_close(netdev);
+
+		nic_dev->hwdev->nic_cap.num_qps = count;
+
+		err = hinic_open(netdev);
+		if (err) {
+			netif_err(nic_dev, drv, netdev,
+				  "Failed to open netdev\n");
+			return -EFAULT;
+		}
+	} else {
+		nic_dev->hwdev->nic_cap.num_qps = count;
+	}
+
+	return 0;
 }
 
 static int hinic_get_rss_hash_opts(struct hinic_dev *nic_dev,
@@ -1219,6 +1242,7 @@ static const struct ethtool_ops hinic_ethtool_ops = {
 	.get_ringparam = hinic_get_ringparam,
 	.set_ringparam = hinic_set_ringparam,
 	.get_channels = hinic_get_channels,
+	.set_channels = hinic_set_channels,
 	.get_rxnfc = hinic_get_rxnfc,
 	.set_rxnfc = hinic_set_rxnfc,
 	.get_rxfh_key_size = hinic_get_rxfh_key_size,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index c8ab129a7ae8..e9e6f4c9309a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -326,7 +326,6 @@ static void hinic_enable_rss(struct hinic_dev *nic_dev)
 	int i, node, err = 0;
 	u16 num_cpus = 0;
 
-	nic_dev->max_qps = hinic_hwdev_max_num_qps(hwdev);
 	if (nic_dev->max_qps <= 1) {
 		nic_dev->flags &= ~HINIC_RSS_ENABLE;
 		nic_dev->rss_limit = nic_dev->max_qps;
@@ -1031,6 +1030,7 @@ static int nic_dev_init(struct pci_dev *pdev)
 	nic_dev->rq_depth = HINIC_RQ_DEPTH;
 	nic_dev->sriov_info.hwdev = hwdev;
 	nic_dev->sriov_info.pdev = pdev;
+	nic_dev->max_qps = num_qps;
 
 	sema_init(&nic_dev->mgmt_lock, 1);
 
-- 
cgit v1.2.3