Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and
    co. at Google. https://lwn.net/Articles/701165/

 2) Do TCP Small Queues for retransmits, from Eric Dumazet.

 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei
    Starovoitov.

 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai.

 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn.

 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker.

 7) Support ndo_poll_controller in mlx5, from Calvin Owens.

 8) Move VRF processing to an output hook and allow l3mdev to be
    loopback, from David Ahern.

 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern.

10) Congestion control in RXRPC, from David Howells.

11) Support geneve RX offload in ixgbe, from Emil Tantilov.

12) When hitting pressure for new incoming TCP data SKBs, perform a
    partial rathern than a full purge of the OFO queue (which could be
    huge). From Eric Dumazet.

13) Convert XFRM state and policy lookups to RCU, from Florian Westphal.

14) Support RX network flow classification to igb, from Gangfeng Huang.

15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski.

16) New skbmod packet action, from Jamal Hadi Salim.

17) Remove some inefficiencies in snmp proc output, from Jia He.

18) Add FIB notifications to properly propagate route changes to
    hardware which is doing forwarding offloading. From Jiri Pirko.

19) New dsa driver for qca8xxx chips, from John Crispin.

20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej
    Żenczykowski.

21) Add L3 mode to ipvlan, from Mahesh Bandewar.

22) Support 802.1ad in mlx4, from Moshe Shemesh.

23) Support hardware LRO in mediatek driver, from Nelson Chang.

24) Add TC offloading to mlx5, from Or Gerlitz.

25) Convert various drivers to ethtool ksettings interfaces, from
    Philippe Reynes.

26) TX max rate limiting for cxgb4, from Rahul Lakkireddy.

27) NAPI support for ath10k, from Rajkumar Manoharan.

28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed.

29) UDP replicast support in TIPC, from Richard Alpe.

30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru.

31) Support BQL in thunderx driver, from Sunil Goutham.

32) TSO support in alx driver, from Tobias Regnery.

33) Add stream parser engine and use it in kcm.

34) Support async DHCP replies in ipconfig module, from Uwe
    Kleine-König.

35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits)
  mlxsw: switchx2: Fix misuse of hard_header_len
  mlxsw: spectrum: Fix misuse of hard_header_len
  net/faraday: Stop NCSI device on shutdown
  net/ncsi: Introduce ncsi_stop_dev()
  net/ncsi: Rework the channel monitoring
  net/ncsi: Allow to extend NCSI request properties
  net/ncsi: Rework request index allocation
  net/ncsi: Don't probe on the reserved channel ID (0x1f)
  net/ncsi: Introduce NCSI_RESERVED_CHANNEL
  net/ncsi: Avoid unused-value build warning from ia64-linux-gcc
  net: Add netdev all_adj_list refcnt propagation to fix panic
  net: phy: Add Edge-rate driver for Microsemi PHYs.
  vmxnet3: Wake queue from reset work
  i40e: avoid NULL pointer dereference and recursive errors on early PCI error
  qed: Add RoCE ll2 & GSI support
  qed: Add support for memory registeration verbs
  qed: Add support for QP verbs
  qed: PD,PKEY and CQ verb support
  qed: Add support for RoCE hw init
  qede: Add qedr framework
  ...

10 files changed, 286 insertions, 71 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index f04a423ff79d..b1cef7a0f7ca 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -785,17 +785,23 @@ int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		return mlx4_cmd_reset_flow(dev, op, op_modifier, -EIO);
 
 	if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
+		int ret;
+
 		if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
 			return mlx4_internal_err_ret_value(dev, op,
 							  op_modifier);
+		down_read(&mlx4_priv(dev)->cmd.switch_sem);
 		if (mlx4_priv(dev)->cmd.use_events)
-			return mlx4_cmd_wait(dev, in_param, out_param,
-					     out_is_imm, in_modifier,
-					     op_modifier, op, timeout);
+			ret = mlx4_cmd_wait(dev, in_param, out_param,
+					    out_is_imm, in_modifier,
+					    op_modifier, op, timeout);
 		else
-			return mlx4_cmd_poll(dev, in_param, out_param,
-					     out_is_imm, in_modifier,
-					     op_modifier, op, timeout);
+			ret = mlx4_cmd_poll(dev, in_param, out_param,
+					    out_is_imm, in_modifier,
+					    op_modifier, op, timeout);
+
+		up_read(&mlx4_priv(dev)->cmd.switch_sem);
+		return ret;
 	}
 	return mlx4_slave_cmd(dev, in_param, out_param, out_is_imm,
 			      in_modifier, op_modifier, op, timeout);
@@ -1845,6 +1851,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 
 	if (vp_oper->state.default_vlan == vp_admin->default_vlan &&
 	    vp_oper->state.default_qos == vp_admin->default_qos &&
+	    vp_oper->state.vlan_proto == vp_admin->vlan_proto &&
 	    vp_oper->state.link_state == vp_admin->link_state &&
 	    vp_oper->state.qos_vport == vp_admin->qos_vport)
 		return 0;
@@ -1903,6 +1910,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 
 	vp_oper->state.default_vlan = vp_admin->default_vlan;
 	vp_oper->state.default_qos = vp_admin->default_qos;
+	vp_oper->state.vlan_proto = vp_admin->vlan_proto;
 	vp_oper->state.link_state = vp_admin->link_state;
 	vp_oper->state.qos_vport = vp_admin->qos_vport;
 
@@ -1916,6 +1924,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 	work->qos_vport = vp_oper->state.qos_vport;
 	work->vlan_id = vp_oper->state.default_vlan;
 	work->vlan_ix = vp_oper->vlan_idx;
+	work->vlan_proto = vp_oper->state.vlan_proto;
 	work->priv = priv;
 	INIT_WORK(&work->work, mlx4_vf_immed_vlan_work_handler);
 	queue_work(priv->mfunc.master.comm_wq, &work->work);
@@ -1986,6 +1995,8 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 	int port, err;
 	struct mlx4_vport_state *vp_admin;
 	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_slave_state *slave_state =
+		&priv->mfunc.master.slave_state[slave];
 	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
 			&priv->dev, slave);
 	int min_port = find_first_bit(actv_ports.ports,
@@ -2000,12 +2011,26 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 			priv->mfunc.master.vf_admin[slave].enable_smi[port];
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
-		vp_oper->state = *vp_admin;
+		if (vp_admin->vlan_proto != htons(ETH_P_8021AD) ||
+		    slave_state->vst_qinq_supported) {
+			vp_oper->state.vlan_proto   = vp_admin->vlan_proto;
+			vp_oper->state.default_vlan = vp_admin->default_vlan;
+			vp_oper->state.default_qos  = vp_admin->default_qos;
+		}
+		vp_oper->state.link_state = vp_admin->link_state;
+		vp_oper->state.mac        = vp_admin->mac;
+		vp_oper->state.spoofchk   = vp_admin->spoofchk;
+		vp_oper->state.tx_rate    = vp_admin->tx_rate;
+		vp_oper->state.qos_vport  = vp_admin->qos_vport;
+		vp_oper->state.guid       = vp_admin->guid;
+
 		if (MLX4_VGT != vp_admin->default_vlan) {
 			err = __mlx4_register_vlan(&priv->dev, port,
 						   vp_admin->default_vlan, &(vp_oper->vlan_idx));
 			if (err) {
 				vp_oper->vlan_idx = NO_INDX;
+				vp_oper->state.default_vlan = MLX4_VGT;
+				vp_oper->state.vlan_proto = htons(ETH_P_8021Q);
 				mlx4_warn(&priv->dev,
 					  "No vlan resources slave %d, port %d\n",
 					  slave, port);
@@ -2086,6 +2111,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 		mlx4_warn(dev, "Received reset from slave:%d\n", slave);
 		slave_state[slave].active = false;
 		slave_state[slave].old_vlan_api = false;
+		slave_state[slave].vst_qinq_supported = false;
 		mlx4_master_deactivate_admin_state(priv, slave);
 		for (i = 0; i < MLX4_EVENT_TYPES_NUM; ++i) {
 				slave_state[slave].event_eq[i].eqn = -1;
@@ -2353,6 +2379,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			vf_oper = &priv->mfunc.master.vf_oper[i];
 			s_state = &priv->mfunc.master.slave_state[i];
 			s_state->last_cmd = MLX4_COMM_CMD_RESET;
+			s_state->vst_qinq_supported = false;
 			mutex_init(&priv->mfunc.master.gen_eqe_mutex[i]);
 			for (j = 0; j < MLX4_EVENT_TYPES_NUM; ++j)
 				s_state->event_eq[j].eqn = -1;
@@ -2382,6 +2409,8 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				admin_vport->qos_vport =
 						MLX4_VPP_DEFAULT_VPORT;
 				oper_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT;
+				admin_vport->vlan_proto = htons(ETH_P_8021Q);
+				oper_vport->vlan_proto = htons(ETH_P_8021Q);
 				vf_oper->vport[port].vlan_idx = NO_INDX;
 				vf_oper->vport[port].mac_idx = NO_INDX;
 				mlx4_set_random_admin_guid(dev, i, port);
@@ -2454,6 +2483,7 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	int flags = 0;
 
 	if (!priv->cmd.initialized) {
+		init_rwsem(&priv->cmd.switch_sem);
 		mutex_init(&priv->cmd.slave_cmd_mutex);
 		sema_init(&priv->cmd.poll_sem, 1);
 		priv->cmd.use_events = 0;
@@ -2583,6 +2613,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	if (!priv->cmd.context)
 		return -ENOMEM;
 
+	down_write(&priv->cmd.switch_sem);
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
 		priv->cmd.context[i].next  = i + 1;
@@ -2606,6 +2637,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 
 	down(&priv->cmd.poll_sem);
 	priv->cmd.use_events = 1;
+	up_write(&priv->cmd.switch_sem);
 
 	return err;
 }
@@ -2618,6 +2650,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
+	down_write(&priv->cmd.switch_sem);
 	priv->cmd.use_events = 0;
 
 	for (i = 0; i < priv->cmd.max_cmds; ++i)
@@ -2626,6 +2659,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	kfree(priv->cmd.context);
 
 	up(&priv->cmd.poll_sem);
+	up_write(&priv->cmd.switch_sem);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
@@ -2937,10 +2971,13 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac)
 EXPORT_SYMBOL_GPL(mlx4_set_vf_mac);
 
 
-int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
+int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos,
+		     __be16 proto)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_vport_state *vf_admin;
+	struct mlx4_slave_state *slave_state;
+	struct mlx4_vport_oper_state *vf_oper;
 	int slave;
 
 	if ((!mlx4_is_master(dev)) ||
@@ -2950,12 +2987,31 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 	if ((vlan > 4095) || (qos > 7))
 		return -EINVAL;
 
+	if (proto == htons(ETH_P_8021AD) &&
+	    !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP))
+		return -EPROTONOSUPPORT;
+
+	if (proto != htons(ETH_P_8021Q) &&
+	    proto != htons(ETH_P_8021AD))
+		return -EINVAL;
+
+	if ((proto == htons(ETH_P_8021AD)) &&
+	    ((vlan == 0) || (vlan == MLX4_VGT)))
+		return -EINVAL;
+
 	slave = mlx4_get_slave_indx(dev, vf);
 	if (slave < 0)
 		return -EINVAL;
 
+	slave_state = &priv->mfunc.master.slave_state[slave];
+	if ((proto == htons(ETH_P_8021AD)) && (slave_state->active) &&
+	    (!slave_state->vst_qinq_supported)) {
+		mlx4_err(dev, "vf %d does not support VST QinQ mode\n", vf);
+		return -EPROTONOSUPPORT;
+	}
 	port = mlx4_slaves_closest_port(dev, slave, port);
 	vf_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
+	vf_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 
 	if (!mlx4_valid_vf_state_change(dev, port, vf_admin, vlan, qos))
 		return -EPERM;
@@ -2965,6 +3021,7 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 	else
 		vf_admin->default_vlan = vlan;
 	vf_admin->default_qos = qos;
+	vf_admin->vlan_proto = proto;
 
 	/* If rate was configured prior to VST, we saved the configured rate
 	 * in vf_admin->rate and now, if priority supported we enforce the QoS
@@ -2973,7 +3030,12 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 	    vf_admin->tx_rate)
 		vf_admin->qos_vport = slave;
 
-	if (mlx4_master_immediate_activate_vlan_qos(priv, slave, port))
+	/* Try to activate new vf state without restart,
+	 * this option is not supported while moving to VST QinQ mode.
+	 */
+	if ((proto == htons(ETH_P_8021AD) &&
+	     vf_oper->state.vlan_proto != proto) ||
+	    mlx4_master_immediate_activate_vlan_qos(priv, slave, port))
 		mlx4_info(dev,
 			  "updating vf %d port %d config will take effect on next VF restart\n",
 			  vf, port);
@@ -3117,6 +3179,7 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in
 
 	ivf->vlan		= s_info->default_vlan;
 	ivf->qos		= s_info->default_qos;
+	ivf->vlan_proto		= s_info->vlan_proto;
 
 	if (mlx4_is_vf_vst_and_prio_qos(dev, port, s_info))
 		ivf->max_tx_rate = s_info->tx_rate;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 1494997c4f7e..08fc5fc56d43 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -298,7 +298,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	if (IS_ERR(mdev->ptp_clock)) {
 		mdev->ptp_clock = NULL;
 		mlx4_err(mdev, "ptp_clock_register failed\n");
-	} else {
+	} else if (mdev->ptp_clock) {
 		mlx4_info(mdev, "registered PHC clock\n");
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fedb829276f4..7e703bed7b82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2400,12 +2400,14 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
 }
 
-static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos)
+static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos,
+			       __be16 vlan_proto)
 {
 	struct mlx4_en_priv *en_priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = en_priv->mdev;
 
-	return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos);
+	return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos,
+				vlan_proto);
 }
 
 static int mlx4_en_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
@@ -2643,12 +2645,16 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 			if (IS_ERR(prog))
 				return PTR_ERR(prog);
 		}
+		mutex_lock(&mdev->state_lock);
 		for (i = 0; i < priv->rx_ring_num; i++) {
-			/* This xchg is paired with READ_ONCE in the fastpath */
-			old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+			old_prog = rcu_dereference_protected(
+					priv->rx_ring[i]->xdp_prog,
+					lockdep_is_held(&mdev->state_lock));
+			rcu_assign_pointer(priv->rx_ring[i]->xdp_prog, prog);
 			if (old_prog)
 				bpf_prog_put(old_prog);
 		}
+		mutex_unlock(&mdev->state_lock);
 		return 0;
 	}
 
@@ -2681,7 +2687,10 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 							priv->xdp_ring_num);
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
-		old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+		old_prog = rcu_dereference_protected(
+					priv->rx_ring[i]->xdp_prog,
+					lockdep_is_held(&mdev->state_lock));
+		rcu_assign_pointer(priv->rx_ring[i]->xdp_prog, prog);
 		if (old_prog)
 			bpf_prog_put(old_prog);
 	}
@@ -3217,6 +3226,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	}
 
 	if (mlx4_is_slave(mdev->dev)) {
+		bool vlan_offload_disabled;
 		int phv;
 
 		err = get_phv_bit(mdev->dev, port, &phv);
@@ -3224,6 +3234,18 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			dev->hw_features |= NETIF_F_HW_VLAN_STAG_TX;
 			priv->pflags |= MLX4_EN_PRIV_FLAGS_PHV;
 		}
+		err = mlx4_get_is_vlan_offload_disabled(mdev->dev, port,
+							&vlan_offload_disabled);
+		if (!err && vlan_offload_disabled) {
+			dev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+					      NETIF_F_HW_VLAN_CTAG_RX |
+					      NETIF_F_HW_VLAN_STAG_TX |
+					      NETIF_F_HW_VLAN_STAG_RX);
+			dev->features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
+					   NETIF_F_HW_VLAN_CTAG_RX |
+					   NETIF_F_HW_VLAN_STAG_TX |
+					   NETIF_F_HW_VLAN_STAG_RX);
+		}
 	} else {
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN &&
 		    !(mdev->dev->caps.flags2 &
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 2040dad8611d..f2e8beddcf44 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -72,7 +72,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 	}
 	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order,
 			   frag_info->dma_dir);
-	if (dma_mapping_error(priv->ddev, dma)) {
+	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
 		put_page(page);
 		return -ENOMEM;
 	}
@@ -108,7 +108,8 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 		    ring_alloc[i].page_size)
 			continue;
 
-		if (mlx4_alloc_pages(priv, &page_alloc[i], frag_info, gfp))
+		if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i],
+					      frag_info, gfp)))
 			goto out;
 	}
 
@@ -537,7 +538,9 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_ring *ring = *pring;
 	struct bpf_prog *old_prog;
 
-	old_prog = READ_ONCE(ring->xdp_prog);
+	old_prog = rcu_dereference_protected(
+					ring->xdp_prog,
+					lockdep_is_held(&mdev->state_lock));
 	if (old_prog)
 		bpf_prog_put(old_prog);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
@@ -583,7 +586,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		frag_info = &priv->frag_info[nr];
 		if (length <= frag_info->frag_prefix_size)
 			break;
-		if (!frags[nr].page)
+		if (unlikely(!frags[nr].page))
 			goto fail;
 
 		dma = be64_to_cpu(rx_desc->data[nr].addr);
@@ -623,7 +626,7 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
 	dma_addr_t dma;
 
 	skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN);
-	if (!skb) {
+	if (unlikely(!skb)) {
 		en_dbg(RX_ERR, priv, "Failed allocating skb\n");
 		return NULL;
 	}
@@ -734,7 +737,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 {
 	__wsum csum_pseudo_hdr = 0;
 
-	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
+	if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT ||
+		     ipv6h->nexthdr == IPPROTO_HOPOPTS))
 		return -1;
 	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
@@ -767,7 +771,7 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
-		if (get_fixed_ipv6_csum(hw_checksum, skb, hdr))
+		if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr)))
 			return -1;
 #endif
 	return 0;
@@ -794,13 +798,15 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	u64 timestamp;
 	bool l2_tunnel;
 
-	if (!priv->port_up)
+	if (unlikely(!priv->port_up))
 		return 0;
 
-	if (budget <= 0)
+	if (unlikely(budget <= 0))
 		return polled;
 
-	xdp_prog = READ_ONCE(ring->xdp_prog);
+	/* Protect accesses to: ring->xdp_prog, priv->mac_hash list */
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(ring->xdp_prog);
 	doorbell_pending = 0;
 	tx_index = (priv->tx_ring_num - priv->xdp_ring_num) + cq->ring;
 
@@ -858,15 +864,11 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				/* Drop the packet, since HW loopback-ed it */
 				mac_hash = ethh->h_source[MLX4_EN_MAC_HASH_IDX];
 				bucket = &priv->mac_hash[mac_hash];
-				rcu_read_lock();
 				hlist_for_each_entry_rcu(entry, bucket, hlist) {
 					if (ether_addr_equal_64bits(entry->mac,
-								    ethh->h_source)) {
-						rcu_read_unlock();
+								    ethh->h_source))
 						goto next;
-					}
 				}
-				rcu_read_unlock();
 			}
 		}
 
@@ -902,16 +904,17 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			case XDP_PASS:
 				break;
 			case XDP_TX:
-				if (!mlx4_en_xmit_frame(frags, dev,
+				if (likely(!mlx4_en_xmit_frame(frags, dev,
 							length, tx_index,
-							&doorbell_pending))
+							&doorbell_pending)))
 					goto consumed;
-				break;
+				goto xdp_drop; /* Drop on xmit failure */
 			default:
 				bpf_warn_invalid_xdp_action(act);
 			case XDP_ABORTED:
 			case XDP_DROP:
-				if (mlx4_en_rx_recycle(ring, frags))
+xdp_drop:
+				if (likely(mlx4_en_rx_recycle(ring, frags)))
 					goto consumed;
 				goto next;
 			}
@@ -1015,12 +1018,12 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 		/* GRO not possible, complete processing here */
 		skb = mlx4_en_rx_skb(priv, rx_desc, frags, length);
-		if (!skb) {
+		if (unlikely(!skb)) {
 			ring->dropped++;
 			goto next;
 		}
 
-                if (unlikely(priv->validate_loopback)) {
+		if (unlikely(priv->validate_loopback)) {
 			validate_loopback(priv, skb);
 			goto next;
 		}
@@ -1077,6 +1080,7 @@ consumed:
 	}
 
 out:
+	rcu_read_unlock();
 	if (doorbell_pending)
 		mlx4_en_xmit_doorbell(priv->tx_ring[tx_index]);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d728704d0c7b..f9cbc67f1694 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -158,7 +158,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[31] = "Modifying loopback source checks using UPDATE_QP support",
 		[32] = "Loopback source checks support",
 		[33] = "RoCEv2 support",
-		[34] = "DMFS Sniffer support (UC & MC)"
+		[34] = "DMFS Sniffer support (UC & MC)",
+		[35] = "QinQ VST mode support",
 	};
 	int i;
 
@@ -248,6 +249,72 @@ out:
 	return err;
 }
 
+static int mlx4_activate_vst_qinq(struct mlx4_priv *priv, int slave, int port)
+{
+	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_vport_state *vp_admin;
+	int err;
+
+	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+	vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
+
+	if (vp_admin->default_vlan != vp_oper->state.default_vlan) {
+		err = __mlx4_register_vlan(&priv->dev, port,
+					   vp_admin->default_vlan,
+					   &vp_oper->vlan_idx);
+		if (err) {
+			vp_oper->vlan_idx = NO_INDX;
+			mlx4_warn(&priv->dev,
+				  "No vlan resources slave %d, port %d\n",
+				  slave, port);
+			return err;
+		}
+		mlx4_dbg(&priv->dev, "alloc vlan %d idx  %d slave %d port %d\n",
+			 (int)(vp_oper->state.default_vlan),
+			 vp_oper->vlan_idx, slave, port);
+	}
+	vp_oper->state.vlan_proto   = vp_admin->vlan_proto;
+	vp_oper->state.default_vlan = vp_admin->default_vlan;
+	vp_oper->state.default_qos  = vp_admin->default_qos;
+
+	return 0;
+}
+
+static int mlx4_handle_vst_qinq(struct mlx4_priv *priv, int slave, int port)
+{
+	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_slave_state *slave_state;
+	struct mlx4_vport_state *vp_admin;
+	int err;
+
+	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+	vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
+	slave_state = &priv->mfunc.master.slave_state[slave];
+
+	if ((vp_admin->vlan_proto != htons(ETH_P_8021AD)) ||
+	    (!slave_state->active))
+		return 0;
+
+	if (vp_oper->state.vlan_proto == vp_admin->vlan_proto &&
+	    vp_oper->state.default_vlan == vp_admin->default_vlan &&
+	    vp_oper->state.default_qos == vp_admin->default_qos)
+		return 0;
+
+	if (!slave_state->vst_qinq_supported) {
+		/* Warn and revert the request to set vst QinQ mode */
+		vp_admin->vlan_proto   = vp_oper->state.vlan_proto;
+		vp_admin->default_vlan = vp_oper->state.default_vlan;
+		vp_admin->default_qos  = vp_oper->state.default_qos;
+
+		mlx4_warn(&priv->dev,
+			  "Slave %d does not support VST QinQ mode\n", slave);
+		return 0;
+	}
+
+	err = mlx4_activate_vst_qinq(priv, slave, port);
+	return err;
+}
+
 int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 				struct mlx4_vhcr *vhcr,
 				struct mlx4_cmd_mailbox *inbox,
@@ -311,14 +378,18 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_VF_ENABLE_QP0		0x08
 
 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
-#define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS (1 << 31)
 #define QUERY_FUNC_CAP_PHV_BIT			0x40
+#define QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE	0x20
+
+#define QUERY_FUNC_CAP_SUPPORTS_VST_QINQ	BIT(30)
+#define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS BIT(31)
 
 	if (vhcr->op_modifier == 1) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev, slave);
 		int converted_port = mlx4_slave_convert_port(
 				dev, slave, vhcr->in_modifier);
+		struct mlx4_vport_oper_state *vp_oper;
 
 		if (converted_port < 0)
 			return -EINVAL;
@@ -357,15 +428,24 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier],
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
 
-		if (dev->caps.phv_bit[port]) {
-			field = QUERY_FUNC_CAP_PHV_BIT;
-			MLX4_PUT(outbox->buf, field,
-				 QUERY_FUNC_CAP_FLAGS0_OFFSET);
-		}
+		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+		err = mlx4_handle_vst_qinq(priv, slave, port);
+		if (err)
+			return err;
+
+		field = 0;
+		if (dev->caps.phv_bit[port])
+			field |= QUERY_FUNC_CAP_PHV_BIT;
+		if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD))
+			field |= QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE;
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS0_OFFSET);
 
 	} else if (vhcr->op_modifier == 0) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev, slave);
+		struct mlx4_slave_state *slave_state =
+			&priv->mfunc.master.slave_state[slave];
+
 		/* enable rdma and ethernet interfaces, new quota locations,
 		 * and reserved lkey
 		 */
@@ -439,6 +519,10 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 
 		size = dev->caps.reserved_lkey + ((slave << 8) & 0xFF00);
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP_RESD_LKEY_OFFSET);
+
+		if (vhcr->in_modifier & QUERY_FUNC_CAP_SUPPORTS_VST_QINQ)
+			slave_state->vst_qinq_supported = true;
+
 	} else
 		err = -EINVAL;
 
@@ -454,10 +538,12 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 	u32			size, qkey;
 	int			err = 0, quotas = 0;
 	u32                     in_modifier;
+	u32			slave_caps;
 
 	op_modifier = !!gen_or_port; /* 0 = general, 1 = logical port */
-	in_modifier = op_modifier ? gen_or_port :
+	slave_caps = QUERY_FUNC_CAP_SUPPORTS_VST_QINQ |
 		QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS;
+	in_modifier = op_modifier ? gen_or_port : slave_caps;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -612,8 +698,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 		MLX4_GET(func_cap->phys_port_id, outbox,
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
 
-	MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
-	func_cap->flags |= (field & QUERY_FUNC_CAP_PHV_BIT);
+	MLX4_GET(func_cap->flags0, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
 
 	/* All other resources are allocated by the master, but we still report
 	 * 'num' and 'reserved' capabilities as follows:
@@ -690,6 +775,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET	0x52
 #define QUERY_DEV_CAP_MAX_SG_RQ_OFFSET		0x55
 #define QUERY_DEV_CAP_MAX_DESC_SZ_RQ_OFFSET	0x56
+#define QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET	0x5D
 #define QUERY_DEV_CAP_MAX_QP_MCG_OFFSET		0x61
 #define QUERY_DEV_CAP_RSVD_MCG_OFFSET		0x62
 #define QUERY_DEV_CAP_MAX_MCG_OFFSET		0x63
@@ -767,12 +853,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->max_eqs = 1 << (field & 0xf);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_MTT_OFFSET);
 	dev_cap->reserved_mtts = 1 << (field >> 4);
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MRW_SZ_OFFSET);
-	dev_cap->max_mrw_sz = 1 << field;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_MRW_OFFSET);
 	dev_cap->reserved_mrws = 1 << (field & 0xf);
-	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MTT_SEG_OFFSET);
-	dev_cap->max_mtt_seg = 1 << (field & 0x3f);
 	MLX4_GET(size, outbox, QUERY_DEV_CAP_NUM_SYS_EQ_OFFSET);
 	dev_cap->num_sys_eqs = size & 0xfff;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_REQ_QP_OFFSET);
@@ -857,6 +939,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	MLX4_GET(size, outbox, QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET);
 	dev_cap->max_sq_desc_sz = size;
 
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET);
+	if (field & 0x1)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_MCG_OFFSET);
 	dev_cap->max_qp_per_mcg = 1 << field;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_MCG_OFFSET);
@@ -2914,7 +2999,7 @@ int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv)
 	memset(&func_cap, 0, sizeof(func_cap));
 	err = mlx4_QUERY_FUNC_CAP(dev, port, &func_cap);
 	if (!err)
-		*phv = func_cap.flags & QUERY_FUNC_CAP_PHV_BIT;
+		*phv = func_cap.flags0 & QUERY_FUNC_CAP_PHV_BIT;
 	return err;
 }
 EXPORT_SYMBOL(get_phv_bit);
@@ -2938,6 +3023,22 @@ int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val)
 }
 EXPORT_SYMBOL(set_phv_bit);
 
+int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port,
+				      bool *vlan_offload_disabled)
+{
+	struct mlx4_func_cap func_cap;
+	int err;
+
+	memset(&func_cap, 0, sizeof(func_cap));
+	err = mlx4_QUERY_FUNC_CAP(dev, port, &func_cap);
+	if (!err)
+		*vlan_offload_disabled =
+			!!(func_cap.flags0 &
+			   QUERY_FUNC_CAP_VLAN_OFFLOAD_DISABLE);
+	return err;
+}
+EXPORT_SYMBOL(mlx4_get_is_vlan_offload_disabled);
+
 void mlx4_replace_zero_macs(struct mlx4_dev *dev)
 {
 	int i;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index cdbd76f10ced..5343a0599253 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -80,9 +80,7 @@ struct mlx4_dev_cap {
 	int max_eqs;
 	int num_sys_eqs;
 	int reserved_mtts;
-	int max_mrw_sz;
 	int reserved_mrws;
-	int max_mtt_seg;
 	int max_requester_per_qp;
 	int max_responder_per_qp;
 	int max_rdma_global;
@@ -152,7 +150,7 @@ struct mlx4_func_cap {
 	u32	qp1_proxy_qpn;
 	u32	reserved_lkey;
 	u8	physical_port;
-	u8	port_flags;
+	u8	flags0;
 	u8	flags1;
 	u64	phys_port_id;
 	u32	extra_flags;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index c9d7fc5159f2..e4878f31e45d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -46,6 +46,7 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <net/devlink.h>
+#include <linux/rwsem.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -482,6 +483,7 @@ struct mlx4_slave_state {
 	u8 init_port_mask;
 	bool active;
 	bool old_vlan_api;
+	bool vst_qinq_supported;
 	u8 function;
 	dma_addr_t vhcr_dma;
 	u16 mtu[MLX4_MAX_PORTS + 1];
@@ -507,6 +509,7 @@ struct mlx4_vport_state {
 	u64 mac;
 	u16 default_vlan;
 	u8  default_qos;
+	__be16 vlan_proto;
 	u32 tx_rate;
 	bool spoofchk;
 	u32 link_state;
@@ -627,6 +630,7 @@ struct mlx4_cmd {
 	struct mutex		slave_cmd_mutex;
 	struct semaphore	poll_sem;
 	struct semaphore	event_sem;
+	struct rw_semaphore	switch_sem;
 	int			max_cmds;
 	spinlock_t		context_lock;
 	int			free_head;
@@ -655,6 +659,7 @@ struct mlx4_vf_immed_vlan_work {
 	u8                      qos_vport;
 	u16			vlan_id;
 	u16			orig_vlan_id;
+	__be16			vlan_proto;
 };
 
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9099dbd04951..a3528dd1e72e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -340,7 +340,7 @@ struct mlx4_en_rx_ring {
 	u8  fcs_del;
 	void *buf;
 	void *rx_info;
-	struct bpf_prog *xdp_prog;
+	struct bpf_prog __rcu *xdp_prog;
 	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 8b81114bdc72..84d7857ccc27 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -790,10 +790,22 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 				MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED |
 				MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED;
 		} else if (0 != vp_oper->state.default_vlan) {
-			qpc->pri_path.vlan_control |=
-				MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
-				MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
-				MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+			if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD)) {
+				/* vst QinQ should block untagged on TX,
+				 * but cvlan is in payload and phv is set so
+				 * hw see it as untagged. Block tagged instead.
+				 */
+				qpc->pri_path.vlan_control |=
+					MLX4_VLAN_CTRL_ETH_TX_BLOCK_PRIO_TAGGED |
+					MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+					MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
+					MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+			} else { /* vst 802.1Q */
+				qpc->pri_path.vlan_control |=
+					MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+					MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
+					MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+			}
 		} else { /* priority tagged */
 			qpc->pri_path.vlan_control |=
 				MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
@@ -802,7 +814,11 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 
 		qpc->pri_path.fvl_rx |= MLX4_FVL_RX_FORCE_ETH_VLAN;
 		qpc->pri_path.vlan_index = vp_oper->vlan_idx;
-		qpc->pri_path.fl |= MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN;
+		qpc->pri_path.fl |= MLX4_FL_ETH_HIDE_CQE_VLAN;
+		if (vp_oper->state.vlan_proto == htons(ETH_P_8021AD))
+			qpc->pri_path.fl |= MLX4_FL_SV;
+		else
+			qpc->pri_path.fl |= MLX4_FL_CV;
 		qpc->pri_path.feup |= MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN;
 		qpc->pri_path.sched_queue &= 0xC7;
 		qpc->pri_path.sched_queue |= (vp_oper->state.default_qos) << 3;
@@ -5238,6 +5254,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
 	u64 qp_path_mask = ((1ULL << MLX4_UPD_QP_PATH_MASK_VLAN_INDEX) |
 		       (1ULL << MLX4_UPD_QP_PATH_MASK_FVL) |
 		       (1ULL << MLX4_UPD_QP_PATH_MASK_CV) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_SV) |
 		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_HIDE_CQE_VLAN) |
 		       (1ULL << MLX4_UPD_QP_PATH_MASK_FEUP) |
 		       (1ULL << MLX4_UPD_QP_PATH_MASK_FVL_RX) |
@@ -5266,7 +5283,12 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
 	else if (!work->vlan_id)
 		vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
 			MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED;
-	else
+	else if (work->vlan_proto == htons(ETH_P_8021AD))
+		vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_PRIO_TAGGED |
+			MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+			MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
+			MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+	else  /* vst 802.1Q */
 		vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
 			MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
 			MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
@@ -5311,7 +5333,11 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
 				upd_context->qp_context.pri_path.fvl_rx =
 					qp->fvl_rx | MLX4_FVL_RX_FORCE_ETH_VLAN;
 				upd_context->qp_context.pri_path.fl =
-					qp->pri_path_fl | MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN;
+					qp->pri_path_fl | MLX4_FL_ETH_HIDE_CQE_VLAN;
+				if (work->vlan_proto == htons(ETH_P_8021AD))
+					upd_context->qp_context.pri_path.fl |= MLX4_FL_SV;
+				else
+					upd_context->qp_context.pri_path.fl |= MLX4_FL_CV;
 				upd_context->qp_context.pri_path.feup =
 					qp->feup | MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN;
 				upd_context->qp_context.pri_path.sched_queue =
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index 67146624eb58..f44d089e2ca6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -45,15 +45,12 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
 	struct mlx4_srq *srq;
 
-	spin_lock(&srq_table->lock);
-
+	rcu_read_lock();
 	srq = radix_tree_lookup(&srq_table->tree, srqn & (dev->caps.num_srqs - 1));
+	rcu_read_unlock();
 	if (srq)
 		atomic_inc(&srq->refcount);
-
-	spin_unlock(&srq_table->lock);
-
-	if (!srq) {
+	else {
 		mlx4_warn(dev, "Async event for bogus SRQ %08x\n", srqn);
 		return;
 	}
@@ -301,12 +298,11 @@ struct mlx4_srq *mlx4_srq_lookup(struct mlx4_dev *dev, u32 srqn)
 {
 	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
 	struct mlx4_srq *srq;
-	unsigned long flags;
 
-	spin_lock_irqsave(&srq_table->lock, flags);
+	rcu_read_lock();
 	srq = radix_tree_lookup(&srq_table->tree,
 				srqn & (dev->caps.num_srqs - 1));
-	spin_unlock_irqrestore(&srq_table->lock, flags);
+	rcu_read_unlock();
 
 	return srq;
 }