From 1dc0eb75a8f88e37c2aee75fca0313cd6e30a1e1 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Thu, 10 Nov 2016 16:01:33 -0800
Subject: ixgbe: Support 2.5Gb and 5Gb speed

Though not advertised through ethtool, if the link partner advertises a
2.5Gb or 5Gb connection, and the adapter supports it, allow the speed to be
used.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c |  3 +++
 drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c     | 10 +++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index ee28e54a4f75..04f15092ae31 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -340,6 +340,9 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		case IXGBE_LINK_SPEED_10GB_FULL:
 			ethtool_cmd_speed_set(ecmd, SPEED_10000);
 			break;
+		case IXGBE_LINK_SPEED_5GB_FULL:
+			ethtool_cmd_speed_set(ecmd, SPEED_5000);
+			break;
 		case IXGBE_LINK_SPEED_2_5GB_FULL:
 			ethtool_cmd_speed_set(ecmd, SPEED_2500);
 			break;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 2fcde8777a29..e55b2602f371 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -768,9 +768,7 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
 				       ixgbe_link_speed speed,
 				       bool autoneg_wait_to_complete)
 {
-
-	/*
-	 * Clear autoneg_advertised and set new values based on input link
+	/* Clear autoneg_advertised and set new values based on input link
 	 * speed.
 	 */
 	hw->phy.autoneg_advertised = 0;
@@ -778,6 +776,12 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
 	if (speed & IXGBE_LINK_SPEED_10GB_FULL)
 		hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL;
 
+	if (speed & IXGBE_LINK_SPEED_5GB_FULL)
+		hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_5GB_FULL;
+
+	if (speed & IXGBE_LINK_SPEED_2_5GB_FULL)
+		hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_2_5GB_FULL;
+
 	if (speed & IXGBE_LINK_SPEED_1GB_FULL)
 		hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL;
 
-- 
cgit v1.2.3


From 3f40c74ccef0a0bc8cdc52105e1ac712e8e32868 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Mon, 21 Nov 2016 09:52:40 -0800
Subject: ixgbe: prefix Data Center Bridge ops struct

Since dcbnl_ops is global, it should be prefixed by ixgbe_

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.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.h        | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index e83444c34cf9..6530eff01a0b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -751,7 +751,7 @@ extern const struct ixgbe_info ixgbe_X550EM_x_info;
 extern const struct ixgbe_info ixgbe_x550em_a_info;
 extern const struct ixgbe_info ixgbe_x550em_a_fw_info;
 #ifdef CONFIG_IXGBE_DCB
-extern const struct dcbnl_rtnl_ops dcbnl_ops;
+extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops;
 #endif
 
 extern char ixgbe_driver_name[];
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index b8fc3cfec831..78c52375acc6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -777,7 +777,7 @@ static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 	return err ? 1 : 0;
 }
 
-const struct dcbnl_rtnl_ops dcbnl_ops = {
+const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops = {
 	.ieee_getets	= ixgbe_dcbnl_ieee_getets,
 	.ieee_setets	= ixgbe_dcbnl_ieee_setets,
 	.ieee_getpfc	= ixgbe_dcbnl_ieee_getpfc,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 86135c00d4b1..0b73a3607fdd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9687,7 +9687,7 @@ skip_sriov:
 
 #ifdef CONFIG_IXGBE_DCB
 	if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE)
-		netdev->dcbnl_ops = &dcbnl_ops;
+		netdev->dcbnl_ops = &ixgbe_dcbnl_ops;
 #endif
 
 #ifdef IXGBE_FCOE
-- 
cgit v1.2.3


From 1733284d02e21ec256f10794109d8c39c3c1b0f8 Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Mon, 12 Dec 2016 15:08:13 -0800
Subject: ixgbe: Update version to reflect added functionality

Update the driver version to reflect the new devices that it
supports.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0b73a3607fdd..c1e14a2608ef 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -72,7 +72,7 @@ char ixgbe_default_device_descr[] =
 static char ixgbe_default_device_descr[] =
 			      "Intel(R) 10 Gigabit Network Connection";
 #endif
-#define DRV_VERSION "4.4.0-k"
+#define DRV_VERSION "5.0.0-k"
 const char ixgbe_driver_version[] = DRV_VERSION;
 static const char ixgbe_copyright[] =
 				"Copyright (c) 1999-2016 Intel Corporation.";
-- 
cgit v1.2.3


From af43da0dba0b1bc7af259cd7d6d76054f3acfab0 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:35:34 -0800
Subject: ixgbe: Add function for checking to see if we can reuse page

This patch consolidates the code for the ixgbe driver so that it is more
inline with what is already in igb.  The general idea is to just
consolidate functions that represent logical steps in the Rx process so we
can later update them more easily.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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 | 71 ++++++++++++++++-----------
 1 file changed, 42 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c1e14a2608ef..a19dda5711ae 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1930,6 +1930,42 @@ static inline bool ixgbe_page_is_reserved(struct page *page)
 	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
+static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
+				    struct ixgbe_rx_buffer *rx_buffer,
+				    struct page *page,
+				    const unsigned int truesize)
+{
+#if (PAGE_SIZE >= 8192)
+	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
+				   ixgbe_rx_bufsz(rx_ring);
+#endif
+	/* avoid re-using remote pages */
+	if (unlikely(ixgbe_page_is_reserved(page)))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* flip page offset to other buffer */
+	rx_buffer->page_offset ^= truesize;
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > last_offset)
+		return false;
+#endif
+
+	/* Even if we own the page, we are not allowed to use atomic_set()
+	 * This would break get_page_unless_zero() users.
+	 */
+	page_ref_inc(page);
+
+	return true;
+}
+
 /**
  * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
@@ -1951,18 +1987,18 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 			      struct sk_buff *skb)
 {
 	struct page *page = rx_buffer->page;
+	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
 #else
 	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
-	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
-				   ixgbe_rx_bufsz(rx_ring);
 #endif
 
-	if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
-		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+	if (unlikely(skb_is_nonlinear(skb)))
+		goto add_tail_frag;
 
+	if (size <= IXGBE_RX_HDR_SIZE) {
 		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
 
 		/* page is not reserved, we can reuse buffer as-is */
@@ -1974,34 +2010,11 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 		return false;
 	}
 
+add_tail_frag:
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
 			rx_buffer->page_offset, size, truesize);
 
-	/* avoid re-using remote pages */
-	if (unlikely(ixgbe_page_is_reserved(page)))
-		return false;
-
-#if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
-		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
-#else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
-	if (rx_buffer->page_offset > last_offset)
-		return false;
-#endif
-
-	/* Even if we own the page, we are not allowed to use atomic_set()
-	 * This would break get_page_unless_zero() users.
-	 */
-	page_ref_inc(page);
-
-	return true;
+	return ixgbe_can_reuse_rx_page(rx_ring, rx_buffer, page, truesize);
 }
 
 static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
-- 
cgit v1.2.3


From f215af8cae4c283d8a522ea166d94f763dc4aebf Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:35:44 -0800
Subject: ixgbe: Only DMA sync frame length

On some platforms, syncing a buffer for DMA is expensive. Rather than
sync the whole 2K receive buffer, only synchronise the length of the
frame, which will typically be the MTU, or a much smaller TCP ACK.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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 | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a19dda5711ae..dde2c852e01d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1841,7 +1841,7 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      IXGBE_CB(skb)->dma,
 					      frag->page_offset,
-					      ixgbe_rx_bufsz(rx_ring),
+					      skb_frag_size(frag),
 					      DMA_FROM_DEVICE);
 	}
 	IXGBE_CB(skb)->dma = 0;
@@ -1983,12 +1983,11 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
  **/
 static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 			      struct ixgbe_rx_buffer *rx_buffer,
-			      union ixgbe_adv_rx_desc *rx_desc,
+			      unsigned int size,
 			      struct sk_buff *skb)
 {
 	struct page *page = rx_buffer->page;
 	unsigned char *va = page_address(page) + rx_buffer->page_offset;
-	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
 #else
@@ -2020,6 +2019,7 @@ add_tail_frag:
 static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
 					     union ixgbe_adv_rx_desc *rx_desc)
 {
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 	struct ixgbe_rx_buffer *rx_buffer;
 	struct sk_buff *skb;
 	struct page *page;
@@ -2074,14 +2074,14 @@ dma_sync:
 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      rx_buffer->dma,
 					      rx_buffer->page_offset,
-					      ixgbe_rx_bufsz(rx_ring),
+					      size,
 					      DMA_FROM_DEVICE);
 
 		rx_buffer->skb = NULL;
 	}
 
 	/* pull page into skb */
-	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
+	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
-- 
cgit v1.2.3


From f3213d9321735aa8e252d87796d5db43d4b830ec Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:35:54 -0800
Subject: ixgbe: Update driver to make use of DMA attributes in Rx path

This patch adds support for DMA_ATTR_SKIP_CPU_SYNC and
DMA_ATTR_WEAK_ORDERING.  By enabling both of these for the Rx path we are
able to see performance improvements on architectures that implement either
one due to the fact that page mapping and unmapping only has to sync what
is actually being used instead of the entire buffer.  In addition by
enabling the weak ordering attribute enables a performance improvement for
architectures that can associate a memory ordering with a DMA buffer such
as Sparc.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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.h      |  3 ++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 56 ++++++++++++++++++---------
 2 files changed, 40 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 6530eff01a0b..8167e77b924f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -104,6 +104,9 @@
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IXGBE_RX_BUFFER_WRITE	16	/* Must be power of 2 */
 
+#define IXGBE_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 enum ixgbe_tx_flags {
 	/* cmd_type flags */
 	IXGBE_TX_FLAGS_HW_VLAN	= 0x01,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index dde2c852e01d..ddde6759f094 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1570,8 +1570,10 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0,
-			   ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 ixgbe_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 IXGBE_RX_DMA_ATTR);
 
 	/*
 	 * if mapping failed free memory back to system since
@@ -1614,6 +1616,12 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 		if (!ixgbe_alloc_mapped_page(rx_ring, bi))
 			break;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 ixgbe_rx_bufsz(rx_ring),
+						 DMA_FROM_DEVICE);
+
 		/*
 		 * Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
@@ -1832,8 +1840,10 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
 {
 	/* if the page was released unmap it, else just sync our portion */
 	if (unlikely(IXGBE_CB(skb)->page_released)) {
-		dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma,
-			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma,
+				     ixgbe_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     IXGBE_RX_DMA_ATTR);
 		IXGBE_CB(skb)->page_released = false;
 	} else {
 		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
@@ -1917,12 +1927,6 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
 
 	/* transfer page from old buffer to new buffer */
 	*new_buff = *old_buff;
-
-	/* sync the buffer for use by the device */
-	dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma,
-					 new_buff->page_offset,
-					 ixgbe_rx_bufsz(rx_ring),
-					 DMA_FROM_DEVICE);
 }
 
 static inline bool ixgbe_page_is_reserved(struct page *page)
@@ -2089,9 +2093,10 @@ dma_sync:
 		IXGBE_CB(skb)->page_released = true;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
-			       ixgbe_rx_pg_size(rx_ring),
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     ixgbe_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     IXGBE_RX_DMA_ATTR);
 	}
 
 	/* clear contents of buffer_info */
@@ -4883,10 +4888,11 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 		if (rx_buffer->skb) {
 			struct sk_buff *skb = rx_buffer->skb;
 			if (IXGBE_CB(skb)->page_released)
-				dma_unmap_page(dev,
-					       IXGBE_CB(skb)->dma,
-					       ixgbe_rx_bufsz(rx_ring),
-					       DMA_FROM_DEVICE);
+				dma_unmap_page_attrs(dev,
+						     IXGBE_CB(skb)->dma,
+						     ixgbe_rx_pg_size(rx_ring),
+						     DMA_FROM_DEVICE,
+						     IXGBE_RX_DMA_ATTR);
 			dev_kfree_skb(skb);
 			rx_buffer->skb = NULL;
 		}
@@ -4894,8 +4900,20 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 		if (!rx_buffer->page)
 			continue;
 
-		dma_unmap_page(dev, rx_buffer->dma,
-			       ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_buffer->dma,
+					      rx_buffer->page_offset,
+					      ixgbe_rx_bufsz(rx_ring),
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(dev, rx_buffer->dma,
+				     ixgbe_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     IXGBE_RX_DMA_ATTR);
 		__free_pages(rx_buffer->page, ixgbe_rx_pg_order(rx_ring));
 
 		rx_buffer->page = NULL;
-- 
cgit v1.2.3


From 1b56cf49f5b0bab9ad4eab18f9b0aee1929afd89 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:36:03 -0800
Subject: ixgbe: Update code to better handle incrementing page count

Batch the page count updates instead of doing them one at a time.  By doing
this we can improve the overall performance as the atomic increment
operations can be expensive due to the fact that on x86 they are locked
operations which can cause stalls.  By doing bulk updates we can
consolidate the stall which should help to improve the overall receive
performance.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h      |  7 ++++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 39 +++++++++++++++++----------
 2 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 8167e77b924f..d765db6bd8b2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -195,7 +195,12 @@ struct ixgbe_rx_buffer {
 	struct sk_buff *skb;
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct ixgbe_queue_stats {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ddde6759f094..e4487109292a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1589,6 +1589,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
+	bi->pagecnt_bias = 1;
 
 	return true;
 }
@@ -1943,13 +1944,15 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
 	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
 				   ixgbe_rx_bufsz(rx_ring);
 #endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+
 	/* avoid re-using remote pages */
 	if (unlikely(ixgbe_page_is_reserved(page)))
 		return false;
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_count(page) != pagecnt_bias))
 		return false;
 
 	/* flip page offset to other buffer */
@@ -1962,10 +1965,14 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
 		return false;
 #endif
 
-	/* Even if we own the page, we are not allowed to use atomic_set()
-	 * This would break get_page_unless_zero() users.
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
 	 */
-	page_ref_inc(page);
+	if (unlikely(pagecnt_bias == 1)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -2009,7 +2016,6 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 			return true;
 
 		/* this page cannot be reused so discard it */
-		__free_pages(page, ixgbe_rx_pg_order(rx_ring));
 		return false;
 	}
 
@@ -2088,15 +2094,19 @@ dma_sync:
 	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
-	} else if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
-		/* the page has been released from the ring */
-		IXGBE_CB(skb)->page_released = true;
 	} else {
-		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
-				     ixgbe_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE,
-				     IXGBE_RX_DMA_ATTR);
+		if (IXGBE_CB(skb)->dma == rx_buffer->dma) {
+			/* the page has been released from the ring */
+			IXGBE_CB(skb)->page_released = true;
+		} else {
+			/* we are not reusing the buffer so unmap it */
+			dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+					     ixgbe_rx_pg_size(rx_ring),
+					     DMA_FROM_DEVICE,
+					     IXGBE_RX_DMA_ATTR);
+		}
+		__page_frag_cache_drain(page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
@@ -4914,7 +4924,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 				     ixgbe_rx_pg_size(rx_ring),
 				     DMA_FROM_DEVICE,
 				     IXGBE_RX_DMA_ATTR);
-		__free_pages(rx_buffer->page, ixgbe_rx_pg_order(rx_ring));
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 
 		rx_buffer->page = NULL;
 	}
-- 
cgit v1.2.3


From 4f4542bfb3b539bef118578ffafcc98e4ce91979 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:36:14 -0800
Subject: ixgbe: Make use of order 1 pages and 3K buffers independent of FCoE

In order to support build_skb with jumbo frames it will be necessary to use
3K buffers for the Rx path with 8K pages backing them.  This is needed on
architectures that implement 4K pages because we can't support 2K buffers
plus padding in a 4K page.

In the case of systems that support page sizes larger than 4K the 3K
attribute will only be applied to FCoE as we can fall back to using just 2K
buffers and adding the padding.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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.h      | 20 +++++++++-----------
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 19 +++++++++++++------
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index d765db6bd8b2..f3515ce8894d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -226,13 +226,14 @@ struct ixgbe_rx_queue_stats {
 #define IXGBE_TS_HDR_LEN 8
 
 enum ixgbe_ring_state_t {
+	__IXGBE_RX_3K_BUFFER,
+	__IXGBE_RX_RSC_ENABLED,
+	__IXGBE_RX_CSUM_UDP_ZERO_ERR,
+	__IXGBE_RX_FCOE,
 	__IXGBE_TX_FDIR_INIT_DONE,
 	__IXGBE_TX_XPS_INIT_DONE,
 	__IXGBE_TX_DETECT_HANG,
 	__IXGBE_HANG_CHECK_ARMED,
-	__IXGBE_RX_RSC_ENABLED,
-	__IXGBE_RX_CSUM_UDP_ZERO_ERR,
-	__IXGBE_RX_FCOE,
 };
 
 struct ixgbe_fwd_adapter {
@@ -344,19 +345,16 @@ struct ixgbe_ring_feature {
  */
 static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring)
 {
-#ifdef IXGBE_FCOE
-	if (test_bit(__IXGBE_RX_FCOE, &ring->state))
-		return (PAGE_SIZE < 8192) ? IXGBE_RXBUFFER_4K :
-					    IXGBE_RXBUFFER_3K;
-#endif
+	if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
+		return IXGBE_RXBUFFER_3K;
 	return IXGBE_RXBUFFER_2K;
 }
 
 static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring)
 {
-#ifdef IXGBE_FCOE
-	if (test_bit(__IXGBE_RX_FCOE, &ring->state))
-		return (PAGE_SIZE < 8192) ? 1 : 0;
+#if (PAGE_SIZE < 8192)
+	if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
+		return 1;
 #endif
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e4487109292a..415e5ad1485a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1604,6 +1604,7 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 	union ixgbe_adv_rx_desc *rx_desc;
 	struct ixgbe_rx_buffer *bi;
 	u16 i = rx_ring->next_to_use;
+	u16 bufsz;
 
 	/* nothing to do */
 	if (!cleaned_count)
@@ -1613,14 +1614,15 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 	bi = &rx_ring->rx_buffer_info[i];
 	i -= rx_ring->count;
 
+	bufsz = ixgbe_rx_bufsz(rx_ring);
+
 	do {
 		if (!ixgbe_alloc_mapped_page(rx_ring, bi))
 			break;
 
 		/* sync the buffer for use by the device */
 		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 ixgbe_rx_bufsz(rx_ring),
+						 bi->page_offset, bufsz,
 						 DMA_FROM_DEVICE);
 
 		/*
@@ -2000,9 +2002,9 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 	struct page *page = rx_buffer->page;
 	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = ixgbe_rx_bufsz(rx_ring);
+	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
 
 	if (unlikely(skb_is_nonlinear(skb)))
@@ -3866,10 +3868,15 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 	 */
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		rx_ring = adapter->rx_ring[i];
+
+		clear_ring_rsc_enabled(rx_ring);
+		clear_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+
 		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 			set_ring_rsc_enabled(rx_ring);
-		else
-			clear_ring_rsc_enabled(rx_ring);
+
+		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
+			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 	}
 }
 
-- 
cgit v1.2.3


From c3630cc40b4f0fe004e21f19bfb5cd2231c105f8 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:36:28 -0800
Subject: ixgbe: Use length to determine if descriptor is done

This change makes it so that we use the length of the packet instead of the
DD status bit to determine if a new descriptor is ready to be processed.
The obvious advantage is that it cuts down on reads as we don't really even
need the DD bit if going from a 0 to a non-zero value on size is enough to
inform us that the packet has been completed.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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_ethtool.c |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c    | 14 ++++++++------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 04f15092ae31..51a1695a75ee 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1868,7 +1868,7 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 	tx_ntc = tx_ring->next_to_clean;
 	rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc);
 
-	while (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) {
+	while (rx_desc->wb.upper.length) {
 		/* check Rx buffer */
 		rx_buffer = &rx_ring->rx_buffer_info[rx_ntc];
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 415e5ad1485a..6fc26cdacba2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1640,8 +1640,8 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 			i -= rx_ring->count;
 		}
 
-		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.upper.status_error = 0;
+		/* clear the length for the next_to_use descriptor */
+		rx_desc->wb.upper.length = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -2154,7 +2154,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 
 		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		if (!rx_desc->wb.upper.status_error)
+		if (!rx_desc->wb.upper.length)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -3698,6 +3698,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 			     struct ixgbe_ring *ring)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
+	union ixgbe_adv_rx_desc *rx_desc;
 	u64 rdba = ring->dma;
 	u32 rxdctl;
 	u8 reg_idx = ring->reg_idx;
@@ -3732,6 +3733,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 		rxdctl |=  0x080420;
 	}
 
+	/* initialize Rx descriptor 0 */
+	rx_desc = IXGBE_RX_DESC(ring, 0);
+	rx_desc->wb.upper.length = 0;
+
 	/* enable receive descriptor ring */
 	rxdctl |= IXGBE_RXDCTL_ENABLE;
 	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
@@ -4940,9 +4945,6 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
 	memset(rx_ring->rx_buffer_info, 0, size);
 
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
-- 
cgit v1.2.3


From 3fd218767fa49857e812e53a27fcbf5d24d040d6 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:36:45 -0800
Subject: ixgbe: Break out Rx buffer page management

We are going to be expanding the number of Rx paths in the driver.  Instead
of duplicating all that code I am pulling it apart into separate functions
so that we don't have so much code duplication.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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 | 231 ++++++++++++++------------
 1 file changed, 122 insertions(+), 109 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6fc26cdacba2..1e5575305f2a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1847,7 +1847,6 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
 				     ixgbe_rx_pg_size(rx_ring),
 				     DMA_FROM_DEVICE,
 				     IXGBE_RX_DMA_ATTR);
-		IXGBE_CB(skb)->page_released = false;
 	} else {
 		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
 
@@ -1857,7 +1856,6 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
 					      skb_frag_size(frag),
 					      DMA_FROM_DEVICE);
 	}
-	IXGBE_CB(skb)->dma = 0;
 }
 
 /**
@@ -1928,8 +1926,14 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring,
 	nta++;
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
-	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	/* Transfer page from old buffer to new buffer.
+	 * Move each member individually to avoid possible store
+	 * forwarding stalls and unnecessary copy of skb.
+	 */
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 static inline bool ixgbe_page_is_reserved(struct page *page)
@@ -1937,16 +1941,10 @@ static inline bool ixgbe_page_is_reserved(struct page *page)
 	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
-static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
-				    struct ixgbe_rx_buffer *rx_buffer,
-				    struct page *page,
-				    const unsigned int truesize)
+static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer)
 {
-#if (PAGE_SIZE >= 8192)
-	unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) -
-				   ixgbe_rx_bufsz(rx_ring);
-#endif
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* avoid re-using remote pages */
 	if (unlikely(ixgbe_page_is_reserved(page)))
@@ -1954,16 +1952,17 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != pagecnt_bias))
+	if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
-	if (rx_buffer->page_offset > last_offset)
+	/* The last offset is a bit aggressive in that we assume the
+	 * worst case of FCoE being enabled and using a 3K buffer.
+	 * However this should have minimal impact as the 1K extra is
+	 * still less than one buffer in size.
+	 */
+#define IXGBE_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBE_RXBUFFER_3K)
+	if (rx_buffer->page_offset > IXGBE_LAST_OFFSET)
 		return false;
 #endif
 
@@ -1971,7 +1970,7 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
 	 * the pagecnt_bias and page count so that we fully restock the
 	 * number of references the driver holds.
 	 */
-	if (unlikely(pagecnt_bias == 1)) {
+	if (unlikely(!pagecnt_bias)) {
 		page_ref_add(page, USHRT_MAX);
 		rx_buffer->pagecnt_bias = USHRT_MAX;
 	}
@@ -1994,106 +1993,65 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_ring *rx_ring,
  * The function will then update the page offset if necessary and return
  * true if the buffer can be reused by the adapter.
  **/
-static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
+static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 			      struct ixgbe_rx_buffer *rx_buffer,
-			      unsigned int size,
-			      struct sk_buff *skb)
+			      struct sk_buff *skb,
+			      unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
-
-	if (size <= IXGBE_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is not reserved, we can reuse buffer as-is */
-		if (likely(!ixgbe_page_is_reserved(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		return false;
-	}
-
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
 			rx_buffer->page_offset, size, truesize);
-
-	return ixgbe_can_reuse_rx_page(rx_ring, rx_buffer, page, truesize);
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 }
 
-static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring,
-					     union ixgbe_adv_rx_desc *rx_desc)
+static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring,
+						   union ixgbe_adv_rx_desc *rx_desc,
+						   struct sk_buff **skb,
+						   const unsigned int size)
 {
-	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 	struct ixgbe_rx_buffer *rx_buffer;
-	struct sk_buff *skb;
-	struct page *page;
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
-
-	skb = rx_buffer->skb;
-
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) +
-				  rx_buffer->page_offset;
+	prefetchw(rx_buffer->page);
+	*skb = rx_buffer->skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
-#endif
-
-		/* allocate a skb to store the frags */
-		skb = napi_alloc_skb(&rx_ring->q_vector->napi,
-				     IXGBE_RX_HDR_SIZE);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_rx_buff_failed++;
-			return NULL;
-		}
-
-		/*
-		 * we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-
-		/*
-		 * Delay unmapping of the first packet. It carries the
-		 * header information, HW may still access the header
-		 * after the writeback.  Only unmap it when EOP is
-		 * reached
-		 */
-		if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
-			goto dma_sync;
-
-		IXGBE_CB(skb)->dma = rx_buffer->dma;
+	/* Delay unmapping of the first packet. It carries the header
+	 * information, HW may still access the header after the writeback.
+	 * Only unmap it when EOP is reached
+	 */
+	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) {
+		if (!*skb)
+			goto skip_sync;
 	} else {
-		if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
-			ixgbe_dma_sync_frag(rx_ring, skb);
+		if (*skb)
+			ixgbe_dma_sync_frag(rx_ring, *skb);
+	}
 
-dma_sync:
-		/* we are reusing so sync this buffer for CPU use */
-		dma_sync_single_range_for_cpu(rx_ring->dev,
-					      rx_buffer->dma,
-					      rx_buffer->page_offset,
-					      size,
-					      DMA_FROM_DEVICE);
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
+skip_sync:
+	rx_buffer->pagecnt_bias--;
 
-		rx_buffer->skb = NULL;
-	}
+	return rx_buffer;
+}
 
-	/* pull page into skb */
-	if (ixgbe_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring,
+				struct ixgbe_rx_buffer *rx_buffer,
+				struct sk_buff *skb)
+{
+	if (ixgbe_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		ixgbe_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
@@ -2107,12 +2065,55 @@ dma_sync:
 					     DMA_FROM_DEVICE,
 					     IXGBE_RX_DMA_ATTR);
 		}
-		__page_frag_cache_drain(page,
+		__page_frag_cache_drain(rx_buffer->page,
 					rx_buffer->pagecnt_bias);
 	}
 
-	/* clear contents of buffer_info */
+	/* clear contents of rx_buffer */
 	rx_buffer->page = NULL;
+	rx_buffer->skb = NULL;
+}
+
+static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
+					   struct ixgbe_rx_buffer *rx_buffer,
+					   union ixgbe_adv_rx_desc *rx_desc,
+					   unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+#endif
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	if (size > IXGBE_RX_HDR_SIZE) {
+		if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
+			IXGBE_CB(skb)->dma = rx_buffer->dma;
+
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset,
+				size, truesize);
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+		rx_buffer->pagecnt_bias++;
+	}
 
 	return skb;
 }
@@ -2144,7 +2145,9 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
+		struct ixgbe_rx_buffer *rx_buffer;
 		struct sk_buff *skb;
+		unsigned int size;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
@@ -2153,8 +2156,8 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
-
-		if (!rx_desc->wb.upper.length)
+		size = le16_to_cpu(rx_desc->wb.upper.length);
+		if (!size)
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -2163,13 +2166,23 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		dma_rmb();
 
+		rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size);
+
 		/* retrieve a buffer from the ring */
-		skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc);
+		if (skb)
+			ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else
+			skb = ixgbe_construct_skb(rx_ring, rx_buffer,
+						  rx_desc, size);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb)
+		if (!skb) {
+			rx_ring->rx_stats.alloc_rx_buff_failed++;
+			rx_buffer->pagecnt_bias++;
 			break;
+		}
 
+		ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb);
 		cleaned_count++;
 
 		/* place incomplete frames back on ring for completion */
-- 
cgit v1.2.3


From 2de6aa3a666e63699978f81d0d5523e7e0778f7b Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:36:54 -0800
Subject: ixgbe: Add support for padding packet

This patch adds support for providing a buffer with headroom and tailroom
to allow for shared info, NET_SKB_PAD, and NET_IP_ALIGN.  With this
combined with the DMA changes we can start using build_skb to build frames
around an incoming Rx buffer instead of having to memcpy the headers.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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.h      | 17 +++++++++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 43 ++++++++++++++++++++++++---
 2 files changed, 56 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index f3515ce8894d..a2cc43d28888 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -91,6 +91,14 @@
 #define IXGBE_RXBUFFER_4K    4096
 #define IXGBE_MAX_RXBUFFER  16384  /* largest size for a single descriptor */
 
+#define IXGBE_SKB_PAD		(NET_SKB_PAD + NET_IP_ALIGN)
+#if (PAGE_SIZE < 8192)
+#define IXGBE_MAX_FRAME_BUILD_SKB \
+	(SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD)
+#else
+#define IGB_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K
+#endif
+
 /*
  * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
  * reserve 64 more, and skb_shared_info adds an additional 320 bytes more,
@@ -227,6 +235,7 @@ struct ixgbe_rx_queue_stats {
 
 enum ixgbe_ring_state_t {
 	__IXGBE_RX_3K_BUFFER,
+	__IXGBE_RX_BUILD_SKB_ENABLED,
 	__IXGBE_RX_RSC_ENABLED,
 	__IXGBE_RX_CSUM_UDP_ZERO_ERR,
 	__IXGBE_RX_FCOE,
@@ -236,6 +245,9 @@ enum ixgbe_ring_state_t {
 	__IXGBE_HANG_CHECK_ARMED,
 };
 
+#define ring_uses_build_skb(ring) \
+	test_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &(ring)->state)
+
 struct ixgbe_fwd_adapter {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	struct net_device *netdev;
@@ -347,6 +359,10 @@ static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring)
 {
 	if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
 		return IXGBE_RXBUFFER_3K;
+#if (PAGE_SIZE < 8192)
+	if (ring_uses_build_skb(ring))
+		return IXGBE_MAX_FRAME_BUILD_SKB;
+#endif
 	return IXGBE_RXBUFFER_2K;
 }
 
@@ -545,6 +561,7 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_VLAN_PROMISC		BIT(13)
 #define IXGBE_FLAG2_EEE_CAPABLE			BIT(14)
 #define IXGBE_FLAG2_EEE_ENABLED			BIT(15)
+#define IXGBE_FLAG2_RX_LEGACY			BIT(16)
 
 	/* Tx fast path data */
 	int num_tx_queues;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1e5575305f2a..7c696b38b405 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1552,6 +1552,11 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring,
 	}
 }
 
+static inline unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? IXGBE_SKB_PAD : 0;
+}
+
 static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 				    struct ixgbe_rx_buffer *bi)
 {
@@ -1588,7 +1593,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = ixgbe_rx_offset(rx_ring);
 	bi->pagecnt_bias = 1;
 
 	return true;
@@ -2001,7 +2006,9 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
+	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
+				SKB_DATA_ALIGN(size);
 #endif
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
 			rx_buffer->page_offset, size, truesize);
@@ -2083,7 +2090,7 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
 	struct sk_buff *skb;
 
@@ -3410,7 +3417,10 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
 
 	/* configure the packet buffer length */
-	srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state))
+		srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	else
+		srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
 
 	/* configure descriptor type */
 	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
@@ -3744,6 +3754,17 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 		 */
 		rxdctl &= ~0x3FFFFF;
 		rxdctl |=  0x080420;
+#if (PAGE_SIZE < 8192)
+	} else {
+		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
+			    IXGBE_RXDCTL_RLPML_EN);
+
+		/* Limit the maximum frame size so we don't overrun the skb */
+		if (ring_uses_build_skb(ring) &&
+		    !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state))
+			rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB |
+				  IXGBE_RXDCTL_RLPML_EN;
+#endif
 	}
 
 	/* initialize Rx descriptor 0 */
@@ -3889,12 +3910,26 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 
 		clear_ring_rsc_enabled(rx_ring);
 		clear_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+		clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
 
 		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
 			set_ring_rsc_enabled(rx_ring);
 
 		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+
+		if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
+			continue;
+
+		set_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
+
+#if (PAGE_SIZE < 8192)
+		if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
+			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+
+		if (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))
+			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
+#endif
 	}
 }
 
-- 
cgit v1.2.3


From 2ccdf26ff614dd49b14e76c0c076f5f4e9562e79 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:37:03 -0800
Subject: ixgbe: Add private flag to control buffer mode

Since there are potential drawbacks to the new Rx allocation approach I
thought it best to add a "chicken bit" so that we can turn the feature off
if in the event that a problem is found.

It also provides a means of validating the legacy Rx path in the event that
we are forced to fall back.  At some point in the future when we are
convinced we don't need it anymore we might be able to drop the legacy-rx
flag.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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_ethtool.c | 47 ++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 51a1695a75ee..68500881cbc0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -151,6 +151,13 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
 };
 #define IXGBE_TEST_LEN sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN
 
+static const char ixgbe_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IXGBE_PRIV_FLAGS_LEGACY_RX	BIT(0)
+	"legacy-rx",
+};
+
+#define IXGBE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbe_priv_flags_strings)
+
 /* currently supported speeds for 10G */
 #define ADVRTSD_MSK_10G (SUPPORTED_10000baseT_Full | \
 			 SUPPORTED_10000baseKX4_Full | \
@@ -1001,6 +1008,8 @@ static void ixgbe_get_drvinfo(struct net_device *netdev,
 
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
+
+	drvinfo->n_priv_flags = IXGBE_PRIV_FLAGS_STR_LEN;
 }
 
 static void ixgbe_get_ringparam(struct net_device *netdev,
@@ -1140,6 +1149,8 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 		return IXGBE_TEST_LEN;
 	case ETH_SS_STATS:
 		return IXGBE_STATS_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return IXGBE_PRIV_FLAGS_STR_LEN;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1264,6 +1275,9 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset,
 		}
 		/* BUG_ON(p - data != IXGBE_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, ixgbe_priv_flags_strings,
+		       IXGBE_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
 	}
 }
 
@@ -3345,6 +3359,37 @@ static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_eee *edata)
 	return 0;
 }
 
+static u32 ixgbe_get_priv_flags(struct net_device *netdev)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
+		priv_flags |= IXGBE_PRIV_FLAGS_LEGACY_RX;
+
+	return priv_flags;
+}
+
+static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags2 = adapter->flags2;
+
+	flags2 &= ~IXGBE_FLAG2_RX_LEGACY;
+	if (priv_flags & IXGBE_PRIV_FLAGS_LEGACY_RX)
+		flags2 |= IXGBE_FLAG2_RX_LEGACY;
+
+	if (flags2 != adapter->flags2) {
+		adapter->flags2 = flags2;
+
+		/* reset interface to repopulate queues */
+		if (netif_running(netdev))
+			ixgbe_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.get_settings           = ixgbe_get_settings,
 	.set_settings           = ixgbe_set_settings,
@@ -3381,6 +3426,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.set_eee		= ixgbe_set_eee,
 	.get_channels		= ixgbe_get_channels,
 	.set_channels		= ixgbe_set_channels,
+	.get_priv_flags		= ixgbe_get_priv_flags,
+	.set_priv_flags		= ixgbe_set_priv_flags,
 	.get_ts_info		= ixgbe_get_ts_info,
 	.get_module_info	= ixgbe_get_module_info,
 	.get_module_eeprom	= ixgbe_get_module_eeprom,
-- 
cgit v1.2.3


From 6f429223b31c550b835b4f066ac034d0cf0cc71e Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:37:13 -0800
Subject: ixgbe: Add support for build_skb

This patch adds build_skb support to the Rx path.  There are several
advantages to this change.

1.  It avoids the memcpy and skb->head allocation for small packets which
    improves performance by about 5% in my tests.
2.  It avoids the memcpy, skb->head allocation, and eth_get_headlen
    for larger packets improving performance by about 10% in my tests.
3.  For VXLAN packets it allows the full header to be in skb->data which
    improves the performance by as much as 30% in some of my tests.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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 | 49 ++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7c696b38b405..2a10365eae75 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1896,7 +1896,7 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 	}
 
 	/* place header in linear portion of buffer */
-	if (skb_is_nonlinear(skb))
+	if (!skb_headlen(skb))
 		ixgbe_pull_tail(rx_ring, skb);
 
 #ifdef IXGBE_FCOE
@@ -2125,6 +2125,49 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
+static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
+				       struct ixgbe_rx_buffer *rx_buffer,
+				       union ixgbe_adv_rx_desc *rx_desc,
+				       unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size);
+#endif
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* build an skb to around the page buffer */
+	skb = build_skb(va - IXGBE_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, IXGBE_SKB_PAD);
+	__skb_put(skb, size);
+
+	/* record DMA address if this is the start of a chain of buffers */
+	if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))
+		IXGBE_CB(skb)->dma = rx_buffer->dma;
+
+	/* update buffer offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+
+	return skb;
+}
+
 /**
  * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @q_vector: structure containing interrupt and ring information
@@ -2178,6 +2221,9 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		/* retrieve a buffer from the ring */
 		if (skb)
 			ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = ixgbe_build_skb(rx_ring, rx_buffer,
+					      rx_desc, size);
 		else
 			skb = ixgbe_construct_skb(rx_ring, rx_buffer,
 						  rx_desc, size);
@@ -3918,6 +3964,7 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 
+		clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
 		if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
 			continue;
 
-- 
cgit v1.2.3


From ffed21bcee7a544f99a9c9b18c23b361a0b1e476 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 17 Jan 2017 08:37:29 -0800
Subject: ixgbe: Don't bother clearing buffer memory for descriptor rings

This patch makes it so that we don't need to bother with clearing the
memory out for the descriptor rings.  The general idea is to only free
buffers associated with buffers in use which are located between the
next_to_clean and next_to_use or next_to_alloc values.  Everything outside
of those regions can be safely ignored since they should have no buffers
associated with them.

The advantage to doing things this way is that is should speed up bring-up
and tear-down of the rings.  Specifically we can avoid the 512 or more
cycles required to memset the rings in tear-down.  In the bring-up phase we
then clear the memory as a part of initialization.  The general idea is
that the clearing in initialization can act as a prefetch of sorts for the
buffer info structures so they are in the local CPU when we go to populate
them.  This should help to improve overall time needed to perform a
suspend/resume.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.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_ethtool.c |  11 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c    | 159 +++++++++++++----------
 2 files changed, 99 insertions(+), 71 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 68500881cbc0..a7574c7b12af 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1904,7 +1904,16 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 
 		/* unmap buffer on Tx side */
 		tx_buffer = &tx_ring->tx_buffer_info[tx_ntc];
-		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer);
+
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer->skb);
+
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer, len, 0);
 
 		/* increment Rx/Tx next to clean counters */
 		rx_ntc++;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2a10365eae75..060cdce8058f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -945,28 +945,6 @@ static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
 	}
 }
 
-void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring,
-				      struct ixgbe_tx_buffer *tx_buffer)
-{
-	if (tx_buffer->skb) {
-		dev_kfree_skb_any(tx_buffer->skb);
-		if (dma_unmap_len(tx_buffer, len))
-			dma_unmap_single(ring->dev,
-					 dma_unmap_addr(tx_buffer, dma),
-					 dma_unmap_len(tx_buffer, len),
-					 DMA_TO_DEVICE);
-	} else if (dma_unmap_len(tx_buffer, len)) {
-		dma_unmap_page(ring->dev,
-			       dma_unmap_addr(tx_buffer, dma),
-			       dma_unmap_len(tx_buffer, len),
-			       DMA_TO_DEVICE);
-	}
-	tx_buffer->next_to_watch = NULL;
-	tx_buffer->skb = NULL;
-	dma_unmap_len_set(tx_buffer, len, 0);
-	/* tx_buffer must be completely set up in the transmit path */
-}
-
 static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1198,7 +1176,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 				 DMA_TO_DEVICE);
 
 		/* clear tx_buffer data */
-		tx_buffer->skb = NULL;
 		dma_unmap_len_set(tx_buffer, len, 0);
 
 		/* unmap remaining buffers */
@@ -3293,6 +3270,10 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 
 	clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);
 
+	/* reinitialize tx_buffer_info */
+	memset(ring->tx_buffer_info, 0,
+	       sizeof(struct ixgbe_tx_buffer) * ring->count);
+
 	/* enable queue */
 	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);
 
@@ -3813,6 +3794,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 #endif
 	}
 
+	/* initialize rx_buffer_info */
+	memset(ring->rx_buffer_info, 0,
+	       sizeof(struct ixgbe_rx_buffer) * ring->count);
+
 	/* initialize Rx descriptor 0 */
 	rx_desc = IXGBE_RX_DESC(ring, 0);
 	rx_desc->wb.upper.length = 0;
@@ -4990,33 +4975,22 @@ static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter)
  **/
 static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
-	unsigned long size;
-	u16 i;
-
-	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_buffer_info)
-		return;
+	u16 i = rx_ring->next_to_clean;
+	struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
 
 	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
-
+	while (i != rx_ring->next_to_alloc) {
 		if (rx_buffer->skb) {
 			struct sk_buff *skb = rx_buffer->skb;
 			if (IXGBE_CB(skb)->page_released)
-				dma_unmap_page_attrs(dev,
+				dma_unmap_page_attrs(rx_ring->dev,
 						     IXGBE_CB(skb)->dma,
 						     ixgbe_rx_pg_size(rx_ring),
 						     DMA_FROM_DEVICE,
 						     IXGBE_RX_DMA_ATTR);
 			dev_kfree_skb(skb);
-			rx_buffer->skb = NULL;
 		}
 
-		if (!rx_buffer->page)
-			continue;
-
 		/* Invalidate cache lines that may have been written to by
 		 * device so that we avoid corrupting memory.
 		 */
@@ -5027,19 +5001,21 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 					      DMA_FROM_DEVICE);
 
 		/* free resources associated with mapping */
-		dma_unmap_page_attrs(dev, rx_buffer->dma,
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
 				     ixgbe_rx_pg_size(rx_ring),
 				     DMA_FROM_DEVICE,
 				     IXGBE_RX_DMA_ATTR);
 		__page_frag_cache_drain(rx_buffer->page,
 					rx_buffer->pagecnt_bias);
 
-		rx_buffer->page = NULL;
+		i++;
+		rx_buffer++;
+		if (i == rx_ring->count) {
+			i = 0;
+			rx_buffer = rx_ring->rx_buffer_info;
+		}
 	}
 
-	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_buffer_info, 0, size);
-
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
@@ -5508,28 +5484,57 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 {
-	struct ixgbe_tx_buffer *tx_buffer_info;
-	unsigned long size;
-	u16 i;
+	u16 i = tx_ring->next_to_clean;
+	struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
 
-	/* ring already cleared, nothing to do */
-	if (!tx_ring->tx_buffer_info)
-		return;
+	while (i != tx_ring->next_to_use) {
+		union ixgbe_adv_tx_desc *eop_desc, *tx_desc;
 
-	/* Free all the Tx ring sk_buffs */
-	for (i = 0; i < tx_ring->count; i++) {
-		tx_buffer_info = &tx_ring->tx_buffer_info[i];
-		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
-	}
+		/* Free all the Tx ring sk_buffs */
+		dev_kfree_skb_any(tx_buffer->skb);
 
-	netdev_tx_reset_queue(txring_txq(tx_ring));
+		/* unmap skb header data */
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
 
-	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
-	memset(tx_ring->tx_buffer_info, 0, size);
+		/* check for eop_desc to determine the end of the packet */
+		eop_desc = tx_buffer->next_to_watch;
+		tx_desc = IXGBE_TX_DESC(tx_ring, i);
+
+		/* unmap remaining buffers */
+		while (tx_desc != eop_desc) {
+			tx_buffer++;
+			tx_desc++;
+			i++;
+			if (unlikely(i == tx_ring->count)) {
+				i = 0;
+				tx_buffer = tx_ring->tx_buffer_info;
+				tx_desc = IXGBE_TX_DESC(tx_ring, 0);
+			}
+
+			/* unmap any remaining paged data */
+			if (dma_unmap_len(tx_buffer, len))
+				dma_unmap_page(tx_ring->dev,
+					       dma_unmap_addr(tx_buffer, dma),
+					       dma_unmap_len(tx_buffer, len),
+					       DMA_TO_DEVICE);
+		}
+
+		/* move us one more past the eop_desc for start of next pkt */
+		tx_buffer++;
+		i++;
+		if (unlikely(i == tx_ring->count)) {
+			i = 0;
+			tx_buffer = tx_ring->tx_buffer_info;
+		}
+	}
 
-	/* Zero out the descriptor ring */
-	memset(tx_ring->desc, 0, tx_ring->size);
+	/* reset BQL for queue */
+	netdev_tx_reset_queue(txring_txq(tx_ring));
 
+	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
 }
@@ -5975,9 +5980,9 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 	if (tx_ring->q_vector)
 		ring_node = tx_ring->q_vector->numa_node;
 
-	tx_ring->tx_buffer_info = vzalloc_node(size, ring_node);
+	tx_ring->tx_buffer_info = vmalloc_node(size, ring_node);
 	if (!tx_ring->tx_buffer_info)
-		tx_ring->tx_buffer_info = vzalloc(size);
+		tx_ring->tx_buffer_info = vmalloc(size);
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
@@ -6059,9 +6064,9 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	if (rx_ring->q_vector)
 		ring_node = rx_ring->q_vector->numa_node;
 
-	rx_ring->rx_buffer_info = vzalloc_node(size, ring_node);
+	rx_ring->rx_buffer_info = vmalloc_node(size, ring_node);
 	if (!rx_ring->rx_buffer_info)
-		rx_ring->rx_buffer_info = vzalloc(size);
+		rx_ring->rx_buffer_info = vmalloc(size);
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
@@ -7776,18 +7781,32 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 	return;
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
+	tx_buffer = &tx_ring->tx_buffer_info[i];
 
 	/* clear dma mappings for failed tx_buffer_info map */
-	for (;;) {
+	while (tx_buffer != first) {
+		if (dma_unmap_len(tx_buffer, len))
+			dma_unmap_page(tx_ring->dev,
+				       dma_unmap_addr(tx_buffer, dma),
+				       dma_unmap_len(tx_buffer, len),
+				       DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buffer, len, 0);
+
+		if (i--)
+			i += tx_ring->count;
 		tx_buffer = &tx_ring->tx_buffer_info[i];
-		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer);
-		if (tx_buffer == first)
-			break;
-		if (i == 0)
-			i = tx_ring->count;
-		i--;
 	}
 
+	if (dma_unmap_len(tx_buffer, len))
+		dma_unmap_single(tx_ring->dev,
+				 dma_unmap_addr(tx_buffer, dma),
+				 dma_unmap_len(tx_buffer, len),
+				 DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buffer, len, 0);
+
+	dev_kfree_skb_any(first->skb);
+	first->skb = NULL;
+
 	tx_ring->next_to_use = i;
 }
 
-- 
cgit v1.2.3