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

Pull networking fixes from David Miller:

 1) All users of AF_PACKET's fanout feature want a symmetric packet
    header hash for load balancing purposes, so give it to them.

 2) Fix vlan state synchronization in e1000e, from Jarod Wilson.

 3) Use correct socket pointer in ip_skb_dst_mtu(), from Shmulik
    Ladkani.

 4) mlx5 bug fixes from Mohamad Haj Yahia, Daniel Jurgens, Matthew
    Finlay, Rana Shahout, and Shaker Daibes.  Mostly to do with
    operation timeouts and PCI error handling.

 5) Fix checksum handling in mirred packet action, from WANG Cong.

 6) Set skb->dev correctly when transmitting in !protect_frames case of
    macsec driver, from Daniel Borkmann.

 7) Fix MTU calculation in geneve driver, from Haishuang Yan.

 8) Missing netif_napi_del() in unregister path of qeth driver, from
    Ursula Braun.

 9) Handle malformed route netlink messages in decnet properly, from
    Vergard Nossum.

10) Memory leak of percpu data in ipv6 routing code, from Martin KaFai
    Lau.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  ipv6: Fix mem leak in rt6i_pcpu
  net: fix decnet rtnexthop parsing
  cxgb4: update latest firmware version supported
  net/mlx5: Avoid setting unused var when modifying vport node GUID
  bonding: fix enslavement slave link notifications
  r8152: fix runtime function for RTL8152
  qeth: delete napi struct when removing a qeth device
  Revert "fsl/fman: fix error handling"
  fsl/fman: fix error handling
  cdc_ncm: workaround for EM7455 "silent" data interface
  RDS: fix rds_tcp_init() error path
  geneve: fix max_mtu setting
  net: phy: dp83867: Fix initialization of PHYCR register
  enc28j60: Fix race condition in enc28j60 driver
  net: stmmac: Fix null-function call in ISR on stmmac1000
  tipc: fix nl compat regression for link statistics
  net: bcmsysport: Device stats are unsigned long
  macsec: set actual real device for xmit when !protect_frames
  net_sched: fix mirrored packets checksum
  packet: Use symmetric hash for PACKET_FANOUT_HASH.
  ...

43 files changed, 527 insertions, 212 deletions

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index ca81f46ea1aa..edc70ffad660 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -101,11 +101,14 @@ enum ad_link_speed_type {
 #define MAC_ADDRESS_EQUAL(A, B)	\
 	ether_addr_equal_64bits((const u8 *)A, (const u8 *)B)
 
-static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } };
+static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
+	0, 0, 0, 0, 0, 0
+};
 static u16 ad_ticks_per_sec;
 static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
 
-static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
+	MULTICAST_LACPDU_ADDR;
 
 /* ================= main 802.3ad protocol functions ================== */
 static int ad_lacpdu_send(struct port *port);
@@ -1739,7 +1742,7 @@ static void ad_clear_agg(struct aggregator *aggregator)
 		aggregator->is_individual = false;
 		aggregator->actor_admin_aggregator_key = 0;
 		aggregator->actor_oper_aggregator_key = 0;
-		aggregator->partner_system = null_mac_addr;
+		eth_zero_addr(aggregator->partner_system.mac_addr_value);
 		aggregator->partner_system_priority = 0;
 		aggregator->partner_oper_aggregator_key = 0;
 		aggregator->receive_state = 0;
@@ -1761,7 +1764,7 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 	if (aggregator) {
 		ad_clear_agg(aggregator);
 
-		aggregator->aggregator_mac_address = null_mac_addr;
+		eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value);
 		aggregator->aggregator_identifier = 0;
 		aggregator->slave = NULL;
 	}
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c5ac160a8ae9..551f0f8dead3 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -42,13 +42,10 @@
 
 
 
-#ifndef __long_aligned
-#define __long_aligned __attribute__((aligned((sizeof(long)))))
-#endif
-static const u8 mac_bcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff
 };
-static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
 	0x33, 0x33, 0x00, 0x00, 0x00, 0x01
 };
 static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 941ec99cd3b6..a2afa3be17a4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1584,6 +1584,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	}
 
 	/* check for initial state */
+	new_slave->link = BOND_LINK_NOCHANGE;
 	if (bond->params.miimon) {
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38105c9..bfa26a2590c9 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -392,7 +392,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		else
 			p = (char *)priv;
 		p += s->stat_offset;
-		data[i] = *(u32 *)p;
+		data[i] = *(unsigned long *)p;
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index c4b262ca7d43..2accab386323 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x0E
-#define T4FW_VERSION_MICRO 0x04
+#define T4FW_VERSION_MINOR 0x0F
+#define T4FW_VERSION_MICRO 0x25
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x0E
-#define T5FW_VERSION_MICRO 0x04
+#define T5FW_VERSION_MINOR 0x0F
+#define T5FW_VERSION_MICRO 0x25
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x0E
-#define T6FW_VERSION_MICRO 0x04
+#define T6FW_VERSION_MINOR 0x0F
+#define T6FW_VERSION_MICRO 0x25
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 73f745205a1c..2b2e2f8c6369 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -154,16 +154,6 @@ void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
 	writel(val, hw->hw_addr + reg);
 }
 
-static bool e1000e_vlan_used(struct e1000_adapter *adapter)
-{
-	u16 vid;
-
-	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
-		return true;
-
-	return false;
-}
-
 /**
  * e1000_regdump - register printout routine
  * @hw: pointer to the HW structure
@@ -3453,8 +3443,7 @@ static void e1000e_set_rx_mode(struct net_device *netdev)
 
 	ew32(RCTL, rctl);
 
-	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX ||
-	    e1000e_vlan_used(adapter))
+	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
 		e1000e_vlan_strip_enable(adapter);
 	else
 		e1000e_vlan_strip_disable(adapter);
@@ -6926,6 +6915,14 @@ static netdev_features_t e1000_fix_features(struct net_device *netdev,
 	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
 		features &= ~NETIF_F_RXFCS;
 
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
 	return features;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index 61a80da8b6f0..2819abc454c7 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -85,7 +85,7 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	if (!mbx->ops.read)
 		goto out;
@@ -111,7 +111,7 @@ out:
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops.write || !mbx->timeout)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a6d26d351dfc..d5d263bda333 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3458,6 +3458,8 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_irq:
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 0b4986268cc9..d6e2a1cae19a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -295,6 +295,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_FLOW_GROUP:
 	case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER:
+	case MLX5_CMD_OP_2ERR_QP:
+	case MLX5_CMD_OP_2RST_QP:
+	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
+	case MLX5_CMD_OP_MODIFY_FLOW_TABLE:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -321,8 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
-	case MLX5_CMD_OP_2ERR_QP:
-	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_QUERY_QP:
 	case MLX5_CMD_OP_SQD_RTS_QP:
 	case MLX5_CMD_OP_INIT2INIT_QP:
@@ -342,7 +346,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT:
-	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_ROCE_ADDRESS:
 	case MLX5_CMD_OP_SET_ROCE_ADDRESS:
 	case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
@@ -390,11 +393,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_RQT:
 	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
+
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE:
 	case MLX5_CMD_OP_CREATE_FLOW_GROUP:
 	case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
@@ -602,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev,
 		pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_cmd_work_ent *ent = container_of(dwork,
+						     struct mlx5_cmd_work_ent,
+						     cb_timeout_work);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+						 cmd);
+
+	ent->ret = -ETIMEDOUT;
+	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+		       mlx5_command_str(msg_to_opcode(ent->in)),
+		       msg_to_opcode(ent->in));
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
 	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
@@ -647,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work)
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
 
+	if (ent->callback)
+		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -691,13 +723,6 @@ static const char *deliv_status_to_str(u8 status)
 	}
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-	return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -706,13 +731,13 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 
 	if (cmd->mode == CMD_MODE_POLLING) {
 		wait_for_completion(&ent->done);
-		err = ent->ret;
-	} else {
-		if (!wait_for_completion_timeout(&ent->done, timeout))
-			err = -ETIMEDOUT;
-		else
-			err = 0;
+	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
+		ent->ret = -ETIMEDOUT;
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
 	}
+
+	err = ent->ret;
+
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
@@ -761,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (!callback)
 		init_completion(&ent->done);
 
+	INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
 	INIT_WORK(&ent->work, cmd_work_handler);
 	if (page_queue) {
 		cmd_work_handler(&ent->work);
@@ -770,28 +796,26 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 	}
 
-	if (!callback) {
-		err = wait_func(dev, ent);
-		if (err == -ETIMEDOUT)
-			goto out;
-
-		ds = ent->ts2 - ent->ts1;
-		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
-		if (op < ARRAY_SIZE(cmd->stats)) {
-			stats = &cmd->stats[op];
-			spin_lock_irq(&stats->lock);
-			stats->sum += ds;
-			++stats->n;
-			spin_unlock_irq(&stats->lock);
-		}
-		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
-				   "fw exec time for %s is %lld nsec\n",
-				   mlx5_command_str(op), ds);
-		*status = ent->status;
-		free_cmd(ent);
-	}
+	if (callback)
+		goto out;
 
-	return err;
+	err = wait_func(dev, ent);
+	if (err == -ETIMEDOUT)
+		goto out_free;
+
+	ds = ent->ts2 - ent->ts1;
+	op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock_irq(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock_irq(&stats->lock);
+	}
+	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
+			   "fw exec time for %s is %lld nsec\n",
+			   mlx5_command_str(op), ds);
+	*status = ent->status;
 
 out_free:
 	free_cmd(ent);
@@ -1181,41 +1205,30 @@ err_dbg:
 	return err;
 }
 
-void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		down(&cmd->sem);
-
 	down(&cmd->pages_sem);
 
-	flush_workqueue(cmd->wq);
-
-	cmd->mode = CMD_MODE_EVENTS;
+	cmd->mode = mode;
 
 	up(&cmd->pages_sem);
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		up(&cmd->sem);
 }
 
-void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
-	int i;
-
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-
-	down(&cmd->pages_sem);
-
-	flush_workqueue(cmd->wq);
-	cmd->mode = CMD_MODE_POLLING;
+	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
+}
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+{
+	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1251,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+			if (ent->callback)
+				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
 				sem = &cmd->pages_sem;
 			else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index baa991a23475..943b1bd434bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -145,7 +145,6 @@ struct mlx5e_umr_wqe {
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
 struct mlx5e_params {
@@ -191,6 +190,7 @@ struct mlx5e_tstamp {
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_FLUSH_TIMEOUT,
 };
 
 struct mlx5e_cq {
@@ -220,6 +220,8 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
 typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
 				  u16 ix);
 
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
@@ -241,6 +243,7 @@ struct mlx5e_rq {
 	struct mlx5e_cq        cq;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
@@ -305,6 +308,7 @@ struct mlx5e_sq_dma {
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -538,6 +542,7 @@ struct mlx5e_priv {
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
+	struct work_struct         tx_timeout_work;
 	struct delayed_work        update_stats_work;
 
 	struct mlx5_core_dev      *mdev;
@@ -589,12 +594,16 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
 int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index b2db180ae2a5..c585349e05c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -96,7 +96,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC;
+			tc_tx_bw[i] = ets->tc_tx_bw[i];
 			break;
 		}
 	}
@@ -140,8 +140,12 @@ static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
 
 	/* Validate Bandwidth Sum */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			if (!ets->tc_tx_bw[i])
+				return -EINVAL;
+
 			bw_sum += ets->tc_tx_bw[i];
+		}
 	}
 
 	if (bw_sum != 0 && bw_sum != 100)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cb6defd71fc1..7a0dca29c642 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,13 @@
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5_EN_QP_FLUSH_TIMEOUT_MS	= 5000,
+	MLX5_EN_QP_FLUSH_MSLEEP_QUANT	= 20,
+	MLX5_EN_QP_FLUSH_MAX_ITER	= MLX5_EN_QP_FLUSH_TIMEOUT_MS /
+					  MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
+};
+
 struct mlx5e_rq_param {
 	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param       wq;
@@ -74,10 +81,13 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	port_state = mlx5_query_vport_state(mdev,
 		MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
 
-	if (port_state == VPORT_STATE_UP)
+	if (port_state == VPORT_STATE_UP) {
+		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
-	else
+	} else {
+		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
+	}
 }
 
 static void mlx5e_update_carrier_work(struct work_struct *work)
@@ -91,6 +101,26 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
+static void mlx5e_tx_timeout_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       tx_timeout_work);
+	int err;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+	mlx5e_close_locked(priv->netdev);
+	err = mlx5e_open_locked(priv->netdev);
+	if (err)
+		netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   err);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+}
+
 static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
@@ -305,6 +335,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
 		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
 		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
@@ -320,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
 		rq->wqe_sz = (priv->params.lro_en) ?
 				priv->params.lro_wqe_sz :
@@ -525,17 +557,25 @@ err_destroy_rq:
 
 static void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
+	int tout = 0;
+	int err;
+
 	clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
 
-	mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
-	while (!mlx5_wq_ll_is_empty(&rq->wq))
-		msleep(20);
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
+	while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
+	       tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+
+	if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
+		set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
 
 	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
 	napi_synchronize(&rq->channel->napi);
 
 	mlx5e_disable_rq(rq);
+	mlx5e_free_rx_descs(rq);
 	mlx5e_destroy_rq(rq);
 }
 
@@ -782,6 +822,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_close_sq(struct mlx5e_sq *sq)
 {
+	int tout = 0;
+	int err;
+
 	if (sq->txq) {
 		clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
 		/* prevent netif_tx_wake_queue */
@@ -792,15 +835,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+				      MLX5_SQC_STATE_ERR);
+		if (err)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
 	}
 
-	while (sq->cc != sq->pc) /* wait till sq is empty */
-		msleep(20);
+	/* wait till sq is empty, unless a TX timeout occurred on this SQ */
+	while (sq->cc != sq->pc &&
+	       !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+		if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+	}
 
 	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
 	napi_synchronize(&sq->channel->napi);
 
+	mlx5e_free_tx_descs(sq);
 	mlx5e_disable_sq(sq);
 	mlx5e_destroy_sq(sq);
 }
@@ -1658,8 +1710,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 
 	netdev_set_num_tc(netdev, ntc);
 
+	/* Map netdev TCs to offset 0
+	 * We have our own UP to TXQ mapping for QoS
+	 */
 	for (tc = 0; tc < ntc; tc++)
-		netdev_set_tc_queue(netdev, tc, nch, tc * nch);
+		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
 int mlx5e_open_locked(struct net_device *netdev)
@@ -2590,6 +2645,29 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
+static void mlx5e_tx_timeout(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	bool sched_work = false;
+	int i;
+
+	netdev_err(dev, "TX timeout detected\n");
+
+	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
+		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
+			continue;
+		sched_work = true;
+		set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
+			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
+	}
+
+	if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state))
+		schedule_work(&priv->tx_timeout_work);
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -2607,6 +2685,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_sriov = {
@@ -2636,6 +2715,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2838,6 +2918,7 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
 	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 022acc2e8922..9f2a16a507e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -212,6 +212,20 @@ err_free_skb:
 	return -ENOMEM;
 }
 
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct sk_buff *skb = rq->skb[ix];
+
+	if (skb) {
+		rq->skb[ix] = NULL;
+		dma_unmap_single(rq->pdev,
+				 *((dma_addr_t *)skb->cb),
+				 rq->wqe_sz,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb(skb);
+	}
+}
+
 static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
 {
 	return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
@@ -574,6 +588,30 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 	return 0;
 }
 
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
+
+	wi->free_wqe(rq, wi);
+}
+
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_ix_be;
+	u16 wqe_ix;
+
+	while (!mlx5_wq_ll_is_empty(wq)) {
+		wqe_ix_be = *wq->tail_next;
+		wqe_ix    = be16_to_cpu(wqe_ix_be);
+		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+		rq->dealloc_wqe(rq, wqe_ix);
+		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+			       &wqe->next.next_wqe_index);
+	}
+}
+
 #define RQ_CANNOT_POST(rq) \
 		(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
 		 test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
@@ -878,6 +916,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done = 0;
 
+	if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+		return 0;
+
 	if (cq->decmprs_left)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 5a750b9cd006..5740b465ef84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -110,8 +110,20 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
-	int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ?
-		 skb->vlan_tci >> VLAN_PRIO_SHIFT : 0;
+	int up = 0;
+
+	if (!netdev_get_num_tc(dev))
+		return channel_ix;
+
+	if (skb_vlan_tag_present(skb))
+		up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+
+	/* channel_ix can be larger than num_channels since
+	 * dev->num_real_tx_queues = num_channels * num_tc
+	 */
+	if (channel_ix >= priv->params.num_channels)
+		channel_ix = reciprocal_scale(channel_ix,
+					      priv->params.num_channels);
 
 	return priv->channeltc_to_txq_map[channel_ix][up];
 }
@@ -123,7 +135,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 	 * headers and occur before the data gather.
 	 * Therefore these headers must be copied into the WQE
 	 */
-#define MLX5E_MIN_INLINE ETH_HLEN
+#define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 
 	if (bf) {
 		u16 ihs = skb_headlen(skb);
@@ -135,7 +147,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 			return skb_headlen(skb);
 	}
 
-	return MLX5E_MIN_INLINE;
+	return max(skb_network_offset(skb), MLX5E_MIN_INLINE);
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
@@ -341,6 +353,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb);
 }
 
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct sk_buff *skb;
+	u16 ci;
+	int i;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		skb = sq->skb[ci];
+		wi = &sq->wqe_info[ci];
+
+		if (!skb) { /* nop */
+			sq->cc++;
+			continue;
+		}
+
+		for (i = 0; i < wi->num_dma; i++) {
+			struct mlx5e_sq_dma *dma =
+				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+			mlx5e_tx_dma_unmap(sq->pdev, dma);
+		}
+
+		dev_kfree_skb_any(skb);
+		sq->cc += wi->num_wqebbs;
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq *sq;
@@ -352,6 +393,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
+	if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+		return false;
+
 	npkts = 0;
 	nbytes = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 42d16b9458e4..96a59463ae65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -108,15 +108,21 @@ static int in_fatal(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev)
 {
+	mutex_lock(&dev->intf_state_mutex);
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		return;
+		goto unlock;
 
 	mlx5_core_err(dev, "start\n");
-	if (pci_channel_offline(dev->pdev) || in_fatal(dev))
+	if (pci_channel_offline(dev->pdev) || in_fatal(dev)) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		trigger_cmd_completions(dev);
+	}
 
 	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0);
 	mlx5_core_err(dev, "end\n");
+
+unlock:
+	mutex_unlock(&dev->intf_state_mutex);
 }
 
 static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
@@ -245,7 +251,6 @@ static void poll_health(unsigned long data)
 	u32 count;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		trigger_cmd_completions(dev);
 		mod_timer(&health->timer, get_next_poll_jiffies());
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c65f4a13e17e..6695893ddd2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1422,46 +1422,31 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 	mlx5_pci_err_detected(dev->pdev, 0);
 }
 
-/* wait for the device to show vital signs. For now we check
- * that we can read the device ID and that the health buffer
- * shows a non zero value which is different than 0xffffffff
+/* wait for the device to show vital signs by waiting
+ * for the health counter to start counting.
  */
-static void wait_vital(struct pci_dev *pdev)
+static int wait_vital(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	struct mlx5_core_health *health = &dev->priv.health;
 	const int niter = 100;
+	u32 last_count = 0;
 	u32 count;
-	u16 did;
 	int i;
 
-	/* Wait for firmware to be ready after reset */
-	msleep(1000);
-	for (i = 0; i < niter; i++) {
-		if (pci_read_config_word(pdev, 2, &did)) {
-			dev_warn(&pdev->dev, "failed reading config word\n");
-			break;
-		}
-		if (did == pdev->device) {
-			dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
-			break;
-		}
-		msleep(50);
-	}
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
-
 	for (i = 0; i < niter; i++) {
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
-			dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
-			break;
+			if (last_count && last_count != count) {
+				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				return 0;
+			}
+			last_count = count;
 		}
 		msleep(50);
 	}
 
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+	return -ETIMEDOUT;
 }
 
 static void mlx5_pci_resume(struct pci_dev *pdev)
@@ -1473,7 +1458,11 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
 	pci_save_state(pdev);
-	wait_vital(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		return;
+	}
 
 	err = mlx5_load_one(dev, priv);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 9eeee0545f1c..32dea3524cee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -345,7 +345,6 @@ retry:
 			       func_id, npages, err);
 		goto out_4k;
 	}
-	dev->priv.fw_pages += npages;
 
 	err = mlx5_cmd_status_to_err(&out.hdr);
 	if (err) {
@@ -373,6 +372,33 @@ out_free:
 	return err;
 }
 
+static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_manage_pages_inbox *in, int in_size,
+			     struct mlx5_manage_pages_outbox *out, int out_size)
+{
+	struct fw_page *fwp;
+	struct rb_node *p;
+	u32 npages;
+	u32 i = 0;
+
+	if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		return mlx5_cmd_exec_check_status(dev, (u32 *)in, in_size,
+						  (u32 *)out, out_size);
+
+	npages = be32_to_cpu(in->num_entries);
+
+	p = rb_first(&dev->priv.page_root);
+	while (p && i < npages) {
+		fwp = rb_entry(p, struct fw_page, rb_node);
+		out->pas[i] = cpu_to_be64(fwp->addr);
+		p = rb_next(p);
+		i++;
+	}
+
+	out->num_entries = cpu_to_be32(i);
+	return 0;
+}
+
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 			 int *nclaimed)
 {
@@ -398,15 +424,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	in.func_id = cpu_to_be16(func_id);
 	in.num_entries = cpu_to_be32(npages);
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
+	err = reclaim_pages_cmd(dev, &in, sizeof(in), out, outlen);
 	if (err) {
-		mlx5_core_err(dev, "failed reclaiming pages\n");
-		goto out_free;
-	}
-	dev->priv.fw_pages -= npages;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
+		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
 
@@ -417,13 +437,15 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 		err = -EINVAL;
 		goto out_free;
 	}
-	if (nclaimed)
-		*nclaimed = num_claimed;
 
 	for (i = 0; i < num_claimed; i++) {
 		addr = be64_to_cpu(out->pas[i]);
 		free_4k(dev, addr);
 	}
+
+	if (nclaimed)
+		*nclaimed = num_claimed;
+
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
@@ -514,14 +536,10 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		p = rb_first(&dev->priv.page_root);
 		if (p) {
 			fwp = rb_entry(p, struct fw_page, rb_node);
-			if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-				free_4k(dev, fwp->addr);
-				nclaimed = 1;
-			} else {
-				err = reclaim_pages(dev, fwp->func_id,
-						    optimal_reclaimed_pages(),
-						    &nclaimed);
-			}
+			err = reclaim_pages(dev, fwp->func_id,
+					    optimal_reclaimed_pages(),
+					    &nclaimed);
+
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
 					       err);
@@ -536,6 +554,13 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		}
 	} while (p);
 
+	WARN(dev->priv.fw_pages,
+	     "FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.fw_pages);
+	WARN(dev->priv.vfs_pages,
+	     "VFs FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.vfs_pages);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index daf44cd4c566..91846dfcbe9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -513,7 +513,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
-	u8 *guid;
 	void *in;
 	int err;
 
@@ -535,8 +534,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
-	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
-			    node_guid);
 	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
 
 	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index 7066954c39d6..0a26b11ca8f6 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1151,7 +1151,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			enc28j60_phy_read(priv, PHIR);
 		}
 		/* TX complete handler */
-		if ((intflags & EIR_TXIF) != 0) {
+		if (((intflags & EIR_TXIF) != 0) &&
+		    ((intflags & EIR_TXERIF) == 0)) {
 			bool err = false;
 			loop++;
 			if (netif_msg_intr(priv))
@@ -1203,7 +1204,7 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 					enc28j60_tx_clear(ndev, true);
 			} else
 				enc28j60_tx_clear(ndev, true);
-			locked_reg_bfclr(priv, EIR, EIR_TXERIF);
+			locked_reg_bfclr(priv, EIR, EIR_TXERIF | EIR_TXIF);
 		}
 		/* RX Error handler */
 		if ((intflags & EIR_RXERIF) != 0) {
@@ -1238,6 +1239,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
  */
 static void enc28j60_hw_tx(struct enc28j60_net *priv)
 {
+	BUG_ON(!priv->tx_skb);
+
 	if (netif_msg_tx_queued(priv))
 		printk(KERN_DEBUG DRV_NAME
 			": Tx Packet Len:%d\n", priv->tx_skb->len);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 607bb7d4514d..87c642d3b075 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -772,6 +772,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	tx_ring->tx_stats.tx_bytes += skb->len;
 	tx_ring->tx_stats.xmit_called++;
 
+	/* Ensure writes are complete before HW fetches Tx descriptors */
+	wmb();
 	qlcnic_update_cmd_producer(tx_ring);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a473c182c91d..e4071265be76 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2804,7 +2804,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
 				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
 							priv->rx_tail_addr,
 							STMMAC_CHAN0);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cc39cefeae45..9b3dc3c61e00 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1072,12 +1072,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
+	struct geneve_dev *geneve = netdev_priv(dev);
 	/* The max_mtu calculation does not take account of GENEVE
 	 * options, to avoid excluding potentially valid
 	 * configurations.
 	 */
-	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
-		- dev->hard_header_len;
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
+
+	if (geneve->remote.sa.sa_family == AF_INET6)
+		max_mtu -= sizeof(struct ipv6hdr);
+	else
+		max_mtu -= sizeof(struct iphdr);
 
 	if (new_mtu < 68)
 		return -EINVAL;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 0e7eff7f1cd2..8bcd78f94966 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2640,6 +2640,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		u64_stats_update_begin(&secy_stats->syncp);
 		secy_stats->stats.OutPktsUntagged++;
 		u64_stats_update_end(&secy_stats->syncp);
+		skb->dev = macsec->real_dev;
 		len = skb->len;
 		ret = dev_queue_xmit(skb);
 		count_tx(dev, ret, len);
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 2afa61b51d41..91177a4a32ad 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -57,6 +57,7 @@
 
 /* PHY CTRL bits */
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
+#define DP83867_PHYCR_FIFO_DEPTH_MASK		(3 << 14)
 
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
@@ -133,8 +134,8 @@ static int dp83867_of_init(struct phy_device *phydev)
 static int dp83867_config_init(struct phy_device *phydev)
 {
 	struct dp83867_private *dp83867;
-	int ret;
-	u16 val, delay;
+	int ret, val;
+	u16 delay;
 
 	if (!phydev->priv) {
 		dp83867 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83867),
@@ -151,8 +152,12 @@ static int dp83867_config_init(struct phy_device *phydev)
 	}
 
 	if (phy_interface_is_rgmii(phydev)) {
-		ret = phy_write(phydev, MII_DP83867_PHYCTRL,
-			(dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT));
+		val = phy_read(phydev, MII_DP83867_PHYCTRL);
+		if (val < 0)
+			return val;
+		val &= ~DP83867_PHYCR_FIFO_DEPTH_MASK;
+		val |= (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT);
+		ret = phy_write(phydev, MII_DP83867_PHYCTRL, val);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 53759c315b97..877c9516e781 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -854,6 +854,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4e257b8d8f3e..0da72d39b4f9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"4"
+#define NET_VERSION		"5"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -624,6 +624,7 @@ struct r8152 {
 		int (*eee_get)(struct r8152 *, struct ethtool_eee *);
 		int (*eee_set)(struct r8152 *, struct ethtool_eee *);
 		bool (*in_nway)(struct r8152 *);
+		void (*autosuspend_en)(struct r8152 *tp, bool enable);
 	} rtl_ops;
 
 	int intr_interval;
@@ -2408,9 +2409,6 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 	if (enable) {
 		u32 ocp_data;
 
-		r8153_u1u2en(tp, false);
-		r8153_u2p3en(tp, false);
-
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2421,7 +2419,28 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
+		u32 ocp_data;
+
 		__rtl_set_wol(tp, tp->saved_wolopts);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
+
+		ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+		ocp_data &= ~LINK_OFF_WAKE_EN;
+		ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
+	}
+}
+
+static void rtl8153_runtime_enable(struct r8152 *tp, bool enable)
+{
+	rtl_runtime_suspend_enable(tp, enable);
+
+	if (enable) {
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+	} else {
 		r8153_u2p3en(tp, true);
 		r8153_u1u2en(tp, true);
 	}
@@ -3512,7 +3531,7 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 		napi_disable(&tp->napi);
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_stop_rx(tp);
-			rtl_runtime_suspend_enable(tp, true);
+			tp->rtl_ops.autosuspend_en(tp, true);
 		} else {
 			cancel_delayed_work_sync(&tp->schedule);
 			tp->rtl_ops.down(tp);
@@ -3538,7 +3557,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 
 	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
@@ -3557,7 +3576,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		if (tp->netdev->flags & IFF_UP)
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
 
@@ -4137,6 +4156,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8152_get_eee;
 		ops->eee_set		= r8152_set_eee;
 		ops->in_nway		= rtl8152_in_nway;
+		ops->autosuspend_en	= rtl_runtime_suspend_enable;
 		break;
 
 	case RTL_VER_03:
@@ -4152,6 +4172,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8153_get_eee;
 		ops->eee_set		= r8153_set_eee;
 		ops->in_nway		= rtl8153_in_nway;
+		ops->autosuspend_en	= rtl8153_runtime_enable;
 		break;
 
 	default:
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 61ba46404937..6086a0163249 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -395,8 +395,11 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu)
 	dev->hard_mtu = net->mtu + net->hard_header_len;
 	if (dev->rx_urb_size == old_hard_mtu) {
 		dev->rx_urb_size = dev->hard_mtu;
-		if (dev->rx_urb_size > old_rx_urb_size)
+		if (dev->rx_urb_size > old_rx_urb_size) {
+			usbnet_pause_rx(dev);
 			usbnet_unlink_rx_urbs(dev);
+			usbnet_resume_rx(dev);
+		}
 	}
 
 	/* max qlen depend on hard_mtu and rx_urb_size */
@@ -1508,8 +1511,9 @@ static void usbnet_bh (unsigned long param)
 	} else if (netif_running (dev->net) &&
 		   netif_device_present (dev->net) &&
 		   netif_carrier_ok(dev->net) &&
-		   !timer_pending (&dev->delay) &&
-		   !test_bit (EVENT_RX_HALT, &dev->flags)) {
+		   !timer_pending(&dev->delay) &&
+		   !test_bit(EVENT_RX_PAUSED, &dev->flags) &&
+		   !test_bit(EVENT_RX_HALT, &dev->flags)) {
 		int	temp = dev->rxq.qlen;
 
 		if (temp < RX_QLEN(dev)) {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 80b1979e8d95..df036b872b05 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1051,6 +1051,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ac544330daeb..709b52339ff9 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3226,6 +3226,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80776d0c52dc..fd72ecf0ce9f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -629,6 +629,7 @@ struct mlx5_cmd_work_ent {
 	void		       *uout;
 	int			uout_size;
 	mlx5_cmd_cbk_t		callback;
+	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
 	struct completion	done;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ee38a4127475..f39b37180c41 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
@@ -2870,6 +2871,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb,
 }
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
  *	@len: new length
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 791800ddd6d9..6360c259da6d 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -34,6 +34,9 @@
 
 #define BOND_DEFAULT_MIIMON	100
 
+#ifndef __long_aligned
+#define __long_aligned __attribute__((aligned((sizeof(long)))))
+#endif
 /*
  * Less bad way to call ioctl from within the kernel; this needs to be
  * done some other way to get the call out of interrupt context.
@@ -138,7 +141,9 @@ struct bond_params {
 	struct reciprocal_value reciprocal_packets_per_slave;
 	u16 ad_actor_sys_prio;
 	u16 ad_user_port_key;
-	u8 ad_actor_system[ETH_ALEN];
+
+	/* 2 bytes of padding : see ether_addr_equal_64bits() */
+	u8 ad_actor_system[ETH_ALEN + 2];
 };
 
 struct bond_parm_tbl {
diff --git a/include/net/ip.h b/include/net/ip.h
index 37165fba3741..08f36cd2b874 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	return min(dst->dev->mtu, IP_MAX_MTU);
 }
 
-static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
+static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
+					  const struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
-
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 2d25979273a6..77e7f69bf80d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -700,7 +700,7 @@ static int
 br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		  int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
-	unsigned int mtu = ip_skb_dst_mtu(skb);
+	unsigned int mtu = ip_skb_dst_mtu(sk, skb);
 	struct iphdr *iph = ip_hdr(skb);
 
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a669dea146c6..61ad43f61c5e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
+static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	__flow_hash_secret_init();
+
+	memset(&keys, 0, sizeof(keys));
+	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
+			   NULL, 0, 0, 0,
+			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	return __flow_hash_from_keys(&keys, hashrnd);
+}
+EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
+
 /**
  * __skb_get_hash: calculate a flow hash
  * @skb: sk_buff to calculate flow hash from
@@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	},
 };
 
+static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
 static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_dissector,
 				flow_keys_dissector_keys,
 				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_dissector_symmetric,
+				flow_keys_dissector_symmetric_keys,
+				ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
 	skb_flow_dissector_init(&flow_keys_buf_dissector,
 				flow_keys_buf_dissector_keys,
 				ARRAY_SIZE(flow_keys_buf_dissector_keys));
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f2b77e549c03..eb12d2161fb2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3016,24 +3016,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
- *	skb_push_rcsum - push skb and update receive checksum
- *	@skb: buffer to update
- *	@len: length of data pulled
- *
- *	This function performs an skb_push on the packet and updates
- *	the CHECKSUM_COMPLETE checksum.  It should be used on
- *	receive path processing instead of skb_push unless you know
- *	that the checksum difference is zero (e.g., a valid IP header)
- *	or you are setting ip_summed to CHECKSUM_NONE.
- */
-static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
-{
-	skb_push(skb, len);
-	skb_postpush_rcsum(skb, skb->data, len);
-	return skb->data;
-}
-
-/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index df4803437888..a796fc7cbc35 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -41,6 +41,7 @@
 #include <net/dn_fib.h>
 #include <net/dn_neigh.h>
 #include <net/dn_dev.h>
+#include <net/nexthop.h>
 
 #define RT_MIN_TABLE 1
 
@@ -150,14 +151,13 @@ static int dn_fib_count_nhs(const struct nlattr *attr)
 	struct rtnexthop *nhp = nla_data(attr);
 	int nhs = 0, nhlen = nla_len(attr);
 
-	while(nhlen >= (int)sizeof(struct rtnexthop)) {
-		if ((nhlen -= nhp->rtnh_len) < 0)
-			return 0;
+	while (rtnh_ok(nhp, nhlen)) {
 		nhs++;
-		nhp = RTNH_NEXT(nhp);
+		nhp = rtnh_next(nhp, &nhlen);
 	}
 
-	return nhs;
+	/* leftover implies invalid nexthop configuration, discard it */
+	return nhlen > 0 ? 0 : nhs;
 }
 
 static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
@@ -167,21 +167,24 @@ static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
 	int nhlen = nla_len(attr);
 
 	change_nexthops(fi) {
-		int attrlen = nhlen - sizeof(struct rtnexthop);
-		if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0)
+		int attrlen;
+
+		if (!rtnh_ok(nhp, nhlen))
 			return -EINVAL;
 
 		nh->nh_flags  = (r->rtm_flags&~0xFF) | nhp->rtnh_flags;
 		nh->nh_oif    = nhp->rtnh_ifindex;
 		nh->nh_weight = nhp->rtnh_hops + 1;
 
-		if (attrlen) {
+		attrlen = rtnh_attrlen(nhp);
+		if (attrlen > 0) {
 			struct nlattr *gw_attr;
 
 			gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY);
 			nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0;
 		}
-		nhp = RTNH_NEXT(nhp);
+
+		nhp = rtnh_next(nhp, &nhlen);
 	} endfor_nexthops(fi);
 
 	return 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 124bf0a66328..4bd4921639c3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 		return dst_output(net, sk, skb);
 	}
 #endif
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
@@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 	iph = ip_hdr(skb);
 
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
 		mtu = IPCB(skb)->frag_max_size;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1bcef2369d64..771be1fa4176 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		}
 	}
 
+	free_percpu(non_pcpu_rt->rt6i_pcpu);
 	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9bff6ef16fa7..9f0983fa4d52 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb_get_hash(skb), num);
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 74ee126a6fe6..c8a7b4c90190 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -616,7 +616,7 @@ static int rds_tcp_init(void)
 
 	ret = rds_tcp_recv_init();
 	if (ret)
-		goto out_slab;
+		goto out_pernet;
 
 	ret = rds_trans_register(&rds_tcp_transport);
 	if (ret)
@@ -628,8 +628,9 @@ static int rds_tcp_init(void)
 
 out_recv:
 	rds_tcp_recv_exit();
-out_slab:
+out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
+out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 128942bc9e42..1f5bd6ccbd2c 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb->mac_len);
+			skb_push_rcsum(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 3ad9fab1985f..1fd464764765 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -604,7 +604,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]),
+	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
 		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,