Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 53 insertions, 15 deletions

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1df2c002c9f6..3e86fbe21431 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1586,12 +1586,10 @@ DECLARE_RTL_COND(rtl_counters_cond)
 
 static void rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd)
 {
-	dma_addr_t paddr = tp->counters_phys_addr;
-	u32 cmd;
+	u32 cmd = lower_32_bits(tp->counters_phys_addr);
 
-	RTL_W32(tp, CounterAddrHigh, (u64)paddr >> 32);
+	RTL_W32(tp, CounterAddrHigh, upper_32_bits(tp->counters_phys_addr));
 	rtl_pci_commit(tp);
-	cmd = (u64)paddr & DMA_BIT_MASK(32);
 	RTL_W32(tp, CounterAddrLow, cmd);
 	RTL_W32(tp, CounterAddrLow, cmd | counter_cmd);
 
@@ -1903,6 +1901,41 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data)
 	return ret;
 }
 
+static void rtl8169_get_ringparam(struct net_device *dev,
+				  struct ethtool_ringparam *data)
+{
+	data->rx_max_pending = NUM_RX_DESC;
+	data->rx_pending = NUM_RX_DESC;
+	data->tx_max_pending = NUM_TX_DESC;
+	data->tx_pending = NUM_TX_DESC;
+}
+
+static void rtl8169_get_pauseparam(struct net_device *dev,
+				   struct ethtool_pauseparam *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	bool tx_pause, rx_pause;
+
+	phy_get_pause(tp->phydev, &tx_pause, &rx_pause);
+
+	data->autoneg = tp->phydev->autoneg;
+	data->tx_pause = tx_pause ? 1 : 0;
+	data->rx_pause = rx_pause ? 1 : 0;
+}
+
+static int rtl8169_set_pauseparam(struct net_device *dev,
+				  struct ethtool_pauseparam *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+
+	if (dev->mtu > ETH_DATA_LEN)
+		return -EOPNOTSUPP;
+
+	phy_set_asym_pause(tp->phydev, data->rx_pause, data->tx_pause);
+
+	return 0;
+}
+
 static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
@@ -1923,6 +1956,9 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.set_eee		= rtl8169_set_eee,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
+	.get_ringparam		= rtl8169_get_ringparam,
+	.get_pauseparam		= rtl8169_get_pauseparam,
+	.set_pauseparam		= rtl8169_set_pauseparam,
 };
 
 static void rtl_enable_eee(struct rtl8169_private *tp)
@@ -2352,11 +2388,13 @@ static void rtl_jumbo_config(struct rtl8169_private *tp)
 		pcie_set_readrq(tp->pci_dev, readrq);
 
 	/* Chip doesn't support pause in jumbo mode */
-	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-			 tp->phydev->advertising, !jumbo);
-	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-			 tp->phydev->advertising, !jumbo);
-	phy_start_aneg(tp->phydev);
+	if (jumbo) {
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				   tp->phydev->advertising);
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				   tp->phydev->advertising);
+		phy_start_aneg(tp->phydev);
+	}
 }
 
 DECLARE_RTL_COND(rtl_chipcmd_cond)
@@ -2735,11 +2773,6 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp)
 	__rtl_hw_start_8168cp(tp);
 }
 
-static void rtl_hw_start_8168c_3(struct rtl8169_private *tp)
-{
-	rtl_hw_start_8168c_2(tp);
-}
-
 static void rtl_hw_start_8168c_4(struct rtl8169_private *tp)
 {
 	rtl_set_def_aspm_entry_latency(tp);
@@ -3652,7 +3685,7 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_18] = rtl_hw_start_8168cp_1,
 		[RTL_GIGA_MAC_VER_19] = rtl_hw_start_8168c_1,
 		[RTL_GIGA_MAC_VER_20] = rtl_hw_start_8168c_2,
-		[RTL_GIGA_MAC_VER_21] = rtl_hw_start_8168c_3,
+		[RTL_GIGA_MAC_VER_21] = rtl_hw_start_8168c_2,
 		[RTL_GIGA_MAC_VER_22] = rtl_hw_start_8168c_4,
 		[RTL_GIGA_MAC_VER_23] = rtl_hw_start_8168cp_2,
 		[RTL_GIGA_MAC_VER_24] = rtl_hw_start_8168cp_3,
@@ -4662,6 +4695,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
 static void rtl8169_up(struct rtl8169_private *tp)
 {
 	pci_set_master(tp->pci_dev);
+	phy_init_hw(tp->phydev);
 	phy_resume(tp->phydev);
 	rtl8169_init_phy(tp);
 	napi_enable(&tp->napi);
@@ -5087,6 +5121,10 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 		return -EUNATCH;
 	}
 
+	tp->phydev->mac_managed_pm = 1;
+
+	phy_support_asym_pause(tp->phydev);
+
 	/* PHY will be woken up in rtl_open() */
 	phy_suspend(tp->phydev);