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

Pull networking fixes from David Miller:

 1) Fix MAC address setting in mac80211 pmsr code, from Johannes Berg.

 2) Probe SFP modules after being attached, from Russell King.

 3) Byte ordering bug in SMC rx_curs_confirmed code, from Ursula Braun.

 4) Revert some r8169 changes that are causing regressions, from Heiner
    Kallweit.

 5) Fix spurious connection timeouts in netfilter nat code, from Florian
    Westphal.

 6) SKB leak in tipc, from Hoang Le.

 7) Short packet checkum issue in mlx4, similar to a previous mlx5
    change, from Saeed Mahameed. The issue is that whilst padding bytes
    are usually zero, it is not guarateed and the hardware doesn't take
    the padding bytes into consideration when generating the checksum.

 8) Fix various races in cls_tcindex, from Cong Wang.

 9) Need to set stream ext to NULL before freeing in SCTP code, from Xin
    Long.

10) Fix locking in phy_is_started, from Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (54 commits)
  net: ethernet: freescale: set FEC ethtool regs version
  net: hns: Fix object reference leaks in hns_dsaf_roce_reset()
  mm: page_alloc: fix ref bias in page_frag_alloc() for 1-byte allocs
  net: phy: fix potential race in the phylib state machine
  net: phy: don't use locking in phy_is_started
  selftests: fix timestamping Makefile
  net: dsa: bcm_sf2: potential array overflow in bcm_sf2_sw_suspend()
  net: fix possible overflow in __sk_mem_raise_allocated()
  dsa: mv88e6xxx: Ensure all pending interrupts are handled prior to exit
  net: phy: fix interrupt handling in non-started states
  sctp: set stream ext to NULL after freeing it in sctp_stream_outq_migrate
  sctp: call gso_reset_checksum when computing checksum in sctp_gso_segment
  net/mlx5e: XDP, fix redirect resources availability check
  net/mlx5: Fix a compilation warning in events.c
  net/mlx5: No command allowed when command interface is not ready
  net/mlx5e: Fix NULL pointer derefernce in set channels error flow
  netfilter: nft_compat: use-after-free when deleting targets
  team: avoid complex list operations in team_nl_cmd_options_set()
  net_sched: fix two more memory leaks in cls_tcindex
  net_sched: fix a memory leak in cls_tcindex
  ...

26 files changed, 188 insertions, 90 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index edb1c023a753..21bf8ac78380 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -197,9 +197,9 @@ config VXLAN
 
 config GENEVE
        tristate "Generic Network Virtualization Encapsulation"
-       depends on INET && NET_UDP_TUNNEL
+       depends on INET
        depends on IPV6 || !IPV6
-       select NET_IP_TUNNEL
+       select NET_UDP_TUNNEL
        select GRO_CELLS
        ---help---
 	  This allows one to create geneve virtual interfaces that provide
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 361fbde76654..17ec32b0a1cc 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds)
 	 * port, the other ones have already been disabled during
 	 * bcm_sf2_sw_setup
 	 */
-	for (port = 0; port < DSA_MAX_PORTS; port++) {
+	for (port = 0; port < ds->num_ports; port++) {
 		if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port))
 			bcm_sf2_port_disable(ds, port, NULL);
 	}
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 8dca2c949e73..12fd7ce3f1ff 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	unsigned int sub_irq;
 	unsigned int n;
 	u16 reg;
+	u16 ctl1;
 	int err;
 
 	mutex_lock(&chip->reg_lock);
@@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	if (err)
 		goto out;
 
-	for (n = 0; n < chip->g1_irq.nirqs; ++n) {
-		if (reg & (1 << n)) {
-			sub_irq = irq_find_mapping(chip->g1_irq.domain, n);
-			handle_nested_irq(sub_irq);
-			++nhandled;
+	do {
+		for (n = 0; n < chip->g1_irq.nirqs; ++n) {
+			if (reg & (1 << n)) {
+				sub_irq = irq_find_mapping(chip->g1_irq.domain,
+							   n);
+				handle_nested_irq(sub_irq);
+				++nhandled;
+			}
 		}
-	}
+
+		mutex_lock(&chip->reg_lock);
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1);
+		if (err)
+			goto unlock;
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg);
+unlock:
+		mutex_unlock(&chip->reg_lock);
+		if (err)
+			goto out;
+		ctl1 &= GENMASK(chip->g1_irq.nirqs, 0);
+	} while (reg & ctl1);
+
 out:
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a70bb1bb90e7..a6eacf2099c3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		goto err_device_destroy;
 	}
 
-	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
-	/* Make sure we don't have a race with AENQ Links state handler */
-	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
-		netif_carrier_on(adapter->netdev);
-
 	rc = ena_enable_msix_and_set_admin_interrupts(adapter,
 						      adapter->num_queues);
 	if (rc) {
@@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter)
 	}
 
 	set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
+	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
+		netif_carrier_on(adapter->netdev);
+
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 	dev_err(&pdev->dev,
 		"Device reset completed successfully, Driver info: %s\n",
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index dc8b6173d8d8..63870072cbbd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -45,7 +45,7 @@
 
 #define DRV_MODULE_VER_MAJOR	2
 #define DRV_MODULE_VER_MINOR	0
-#define DRV_MODULE_VER_SUBMINOR 2
+#define DRV_MODULE_VER_SUBMINOR 3
 
 #define DRV_MODULE_NAME		"ena"
 #ifndef DRV_MODULE_VERSION
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2370dc204202..697c2427f2b7 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2098,6 +2098,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev)
 #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
 	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
 	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+static __u32 fec_enet_register_version = 2;
 static u32 fec_enet_register_offset[] = {
 	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
 	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
@@ -2128,6 +2129,7 @@ static u32 fec_enet_register_offset[] = {
 	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
 };
 #else
+static __u32 fec_enet_register_version = 1;
 static u32 fec_enet_register_offset[] = {
 	FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
 	FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
@@ -2149,6 +2151,8 @@ static void fec_enet_get_regs(struct net_device *ndev,
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
 
+	regs->version = fec_enet_register_version;
+
 	memset(buf, 0, regs->len);
 
 	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 3b9e74be5fbd..b8155f5e71b4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -3081,6 +3081,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	dsaf_dev = dev_get_drvdata(&pdev->dev);
 	if (!dsaf_dev) {
 		dev_err(&pdev->dev, "dsaf_dev is NULL\n");
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
@@ -3088,6 +3089,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
 		dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n",
 			dsaf_dev->ae_dev.name);
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 9a0881cb7f51..6c01314e87b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 /* We reach this function only after checking that any of
  * the (IPv4 | IPv6) bits are set in cqe->status.
  */
@@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
+	void *hdr;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to skip
+	 * checksum complete.
+	 */
+	if (short_frame(skb->len))
+		return -EINVAL;
 
-	void *hdr = (u8 *)va + sizeof(struct ethhdr);
-
+	hdr = (u8 *)va + sizeof(struct ethhdr);
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
 	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
@@ -819,6 +832,11 @@ xdp_drop_no_cnt:
 		skb_record_rx_queue(skb, cq_ring);
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			/* TODO: For IP non TCP/UDP packets when csum complete is
+			 * not an option (not supported or any other reason) we can
+			 * actually check cqe IPOK status bit and report
+			 * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE
+			 */
 			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						       MLX4_CQE_STATUS_UDP)) &&
 			    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3e0fa8a8077b..e267ff93e8a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1583,6 +1583,24 @@ no_trig:
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 }
 
+void mlx5_cmd_flush(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		while (down_trylock(&cmd->sem))
+			mlx5_cmd_trigger_completions(dev);
+
+	while (down_trylock(&cmd->pages_sem))
+		mlx5_cmd_trigger_completions(dev);
+
+	/* Unlock cmdif */
+	up(&cmd->pages_sem);
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
 static int status_to_err(u8 status)
 {
 	return status ? -1 : 0; /* TBD more meaningful codes */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8fa8fdd30b85..448a92561567 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -657,6 +657,7 @@ struct mlx5e_channel_stats {
 enum {
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
 };
 
 struct mlx5e_rqt {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3740177eed09..03b2a9f9c589 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_info xdpi;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 3a67cb3cd179..ee27a7c8cd87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	if (sq->doorbell_cseg) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3bbccead2f63..47233b9a4f81 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -354,9 +354,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
-	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		priv->channels.params = new_channels.params;
@@ -372,6 +369,10 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 	if (arfs_enabled)
 		mlx5e_arfs_disable(priv);
 
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
+
 	/* Switch to new channels, set new parameters and close old ones */
 	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 01819e5c9975..93e50ccd44c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2938,6 +2938,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (mlx5e_is_vport_rep(priv))
@@ -2959,6 +2960,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index fbc42b7252a9..503035469d2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -211,11 +211,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 	enum port_module_event_status_type module_status;
 	enum port_module_event_error_type error_type;
 	struct mlx5_eqe_port_module *module_event_eqe;
-	const char *status_str, *error_str;
+	const char *status_str;
 	u8 module_num;
 
 	module_event_eqe = &eqe->data.port_module;
-	module_num = module_event_eqe->module;
 	module_status = module_event_eqe->module_status &
 			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
 	error_type = module_event_eqe->error_type &
@@ -223,25 +222,27 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 
 	if (module_status < MLX5_MODULE_STATUS_NUM)
 		events->pme_stats.status_counters[module_status]++;
-	status_str = mlx5_pme_status_to_string(module_status);
 
-	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+	if (module_status == MLX5_MODULE_STATUS_ERROR)
 		if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
 			events->pme_stats.error_counters[error_type]++;
-		error_str = mlx5_pme_error_to_string(error_type);
-	}
 
 	if (!printk_ratelimit())
 		return NOTIFY_OK;
 
-	if (module_status == MLX5_MODULE_STATUS_ERROR)
+	module_num = module_event_eqe->module;
+	status_str = mlx5_pme_status_to_string(module_status);
+	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		const char *error_str = mlx5_pme_error_to_string(error_type);
+
 		mlx5_core_err(events->dev,
 			      "Port module event[error]: module %u, %s, %s\n",
 			      module_num, status_str, error_str);
-	else
+	} else {
 		mlx5_core_info(events->dev,
 			       "Port module event: module %u, %s\n",
 			       module_num, status_str);
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 196c07383082..cb9fa3430c53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -103,7 +103,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mlx5_core_err(dev, "start\n");
 	if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		mlx5_cmd_trigger_completions(dev);
+		mlx5_cmd_flush(dev);
 	}
 
 	mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 5300b0b6d836..4fdac020b795 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -126,6 +126,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
 			     struct ptp_system_timestamp *sts);
 
 void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
+void mlx5_cmd_flush(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index abb94c543aa2..6e36b88ca7c9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1286,11 +1286,13 @@ static u16 rtl_get_events(struct rtl8169_private *tp)
 static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 {
 	RTL_W16(tp, IntrStatus, bits);
+	mmiowb();
 }
 
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
+	mmiowb();
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
@@ -6072,7 +6074,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
 	u32 opts[2], len;
-	bool stop_queue;
 	int frags;
 
 	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
@@ -6114,6 +6115,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
+	netdev_sent_queue(dev, skb->len);
+
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before releasing descriptor */
@@ -6126,14 +6129,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	tp->cur_tx += frags + 1;
 
-	stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS);
-	if (unlikely(stop_queue))
-		netif_stop_queue(dev);
+	RTL_W8(tp, TxPoll, NPQ);
 
-	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more))
-		RTL_W8(tp, TxPoll, NPQ);
+	mmiowb();
 
-	if (unlikely(stop_queue)) {
+	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
+		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
+		 * not miss a ring update when it notices a stopped queue.
+		 */
+		smp_wmb();
+		netif_stop_queue(dev);
 		/* Sync with rtl_tx:
 		 * - publish queue status and cur_tx ring index (write barrier)
 		 * - refresh dirty_tx ring index (read barrier).
@@ -6483,7 +6488,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
+
 		rtl_irq_enable(tp);
+		mmiowb();
 	}
 
 	return work_done;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 2f2bda68d861..c08034154a9a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -6115,7 +6115,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 static int efx_ef10_mtd_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
-	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT);
+	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };
 	struct efx_mcdi_mtd_partition *parts;
 	size_t outlen, n_parts_total, i, n_parts;
 	unsigned int type;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 189cd2048c3a..c5675df5fc6f 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -553,7 +553,7 @@ int phy_start_aneg(struct phy_device *phydev)
 	if (err < 0)
 		goto out_unlock;
 
-	if (__phy_is_started(phydev)) {
+	if (phy_is_started(phydev)) {
 		if (phydev->autoneg == AUTONEG_ENABLE) {
 			err = phy_check_link_status(phydev);
 		} else {
@@ -709,7 +709,7 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (__phy_is_started(phydev))
+	if (phy_is_started(phydev))
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }
@@ -762,9 +762,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 {
 	struct phy_device *phydev = phy_dat;
 
-	if (!phy_is_started(phydev))
-		return IRQ_NONE;		/* It can't be ours.  */
-
 	if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev))
 		return IRQ_NONE;
 
@@ -842,15 +839,14 @@ EXPORT_SYMBOL(phy_stop_interrupts);
  */
 void phy_stop(struct phy_device *phydev)
 {
-	mutex_lock(&phydev->lock);
-
-	if (!__phy_is_started(phydev)) {
+	if (!phy_is_started(phydev)) {
 		WARN(1, "called from state %s\n",
 		     phy_state_to_str(phydev->state));
-		mutex_unlock(&phydev->lock);
 		return;
 	}
 
+	mutex_lock(&phydev->lock);
+
 	if (phy_interrupt_is_valid(phydev))
 		phy_disable_interrupts(phydev);
 
@@ -989,8 +985,10 @@ void phy_state_machine(struct work_struct *work)
 	 * state machine would be pointless and possibly error prone when
 	 * called from phy_disconnect() synchronously.
 	 */
+	mutex_lock(&phydev->lock);
 	if (phy_polling_mode(phydev) && phy_is_started(phydev))
 		phy_queue_state_machine(phydev, PHY_STATE_TIME);
+	mutex_unlock(&phydev->lock);
 }
 
 /**
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index e7becc7379d7..938803237d7f 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -474,6 +474,17 @@ static void phylink_run_resolve(struct phylink *pl)
 		queue_work(system_power_efficient_wq, &pl->resolve);
 }
 
+static void phylink_run_resolve_and_disable(struct phylink *pl, int bit)
+{
+	unsigned long state = pl->phylink_disable_state;
+
+	set_bit(bit, &pl->phylink_disable_state);
+	if (state == 0) {
+		queue_work(system_power_efficient_wq, &pl->resolve);
+		flush_work(&pl->resolve);
+	}
+}
+
 static void phylink_fixed_poll(struct timer_list *t)
 {
 	struct phylink *pl = container_of(t, struct phylink, link_poll);
@@ -924,9 +935,7 @@ void phylink_stop(struct phylink *pl)
 	if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio))
 		del_timer_sync(&pl->link_poll);
 
-	set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
-	queue_work(system_power_efficient_wq, &pl->resolve);
-	flush_work(&pl->resolve);
+	phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED);
 }
 EXPORT_SYMBOL_GPL(phylink_stop);
 
@@ -1632,9 +1641,7 @@ static void phylink_sfp_link_down(void *upstream)
 
 	ASSERT_RTNL();
 
-	set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state);
-	queue_work(system_power_efficient_wq, &pl->resolve);
-	flush_work(&pl->resolve);
+	phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_LINK);
 }
 
 static void phylink_sfp_link_up(void *upstream)
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index ad9db652874d..fef701bfad62 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus)
 				return ret;
 		}
 	}
+	bus->socket_ops->attach(bus->sfp);
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
 	bus->netdev->sfp_bus = bus;
@@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 	if (bus->registered) {
 		if (bus->started)
 			bus->socket_ops->stop(bus->sfp);
+		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index fd8bb998ae52..68c8fbf099f8 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -184,6 +184,7 @@ struct sfp {
 
 	struct gpio_desc *gpio[GPIO_MAX];
 
+	bool attached;
 	unsigned int state;
 	struct delayed_work poll;
 	struct delayed_work timeout;
@@ -1475,7 +1476,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	 */
 	switch (sfp->sm_mod_state) {
 	default:
-		if (event == SFP_E_INSERT) {
+		if (event == SFP_E_INSERT && sfp->attached) {
 			sfp_module_tx_disable(sfp);
 			sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT);
 		}
@@ -1607,6 +1608,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	mutex_unlock(&sfp->sm_mutex);
 }
 
+static void sfp_attach(struct sfp *sfp)
+{
+	sfp->attached = true;
+	if (sfp->state & SFP_F_PRESENT)
+		sfp_sm_event(sfp, SFP_E_INSERT);
+}
+
+static void sfp_detach(struct sfp *sfp)
+{
+	sfp->attached = false;
+	sfp_sm_event(sfp, SFP_E_REMOVE);
+}
+
 static void sfp_start(struct sfp *sfp)
 {
 	sfp_sm_event(sfp, SFP_E_DEV_UP);
@@ -1667,6 +1681,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee,
 }
 
 static const struct sfp_socket_ops sfp_module_ops = {
+	.attach = sfp_attach,
+	.detach = sfp_detach,
 	.start = sfp_start,
 	.stop = sfp_stop,
 	.module_info = sfp_module_info,
@@ -1834,10 +1850,6 @@ static int sfp_probe(struct platform_device *pdev)
 	dev_info(sfp->dev, "Host maximum power %u.%uW\n",
 		 sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10);
 
-	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
-	if (!sfp->sfp_bus)
-		return -ENOMEM;
-
 	/* Get the initial state, and always signal TX disable,
 	 * since the network interface will not be up.
 	 */
@@ -1848,10 +1860,6 @@ static int sfp_probe(struct platform_device *pdev)
 		sfp->state |= SFP_F_RATE_SELECT;
 	sfp_set_state(sfp, sfp->state);
 	sfp_module_tx_disable(sfp);
-	rtnl_lock();
-	if (sfp->state & SFP_F_PRESENT)
-		sfp_sm_event(sfp, SFP_E_INSERT);
-	rtnl_unlock();
 
 	for (i = 0; i < GPIO_MAX; i++) {
 		if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i])
@@ -1884,6 +1892,10 @@ static int sfp_probe(struct platform_device *pdev)
 		dev_warn(sfp->dev,
 			 "No tx_disable pin: SFP modules will always be emitting.\n");
 
+	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
+	if (!sfp->sfp_bus)
+		return -ENOMEM;
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h
index 31b0acf337e2..64f54b0bbd8c 100644
--- a/drivers/net/phy/sfp.h
+++ b/drivers/net/phy/sfp.h
@@ -7,6 +7,8 @@
 struct sfp;
 
 struct sfp_socket_ops {
+	void (*attach)(struct sfp *sfp);
+	void (*detach)(struct sfp *sfp);
 	void (*start)(struct sfp *sfp);
 	void (*stop)(struct sfp *sfp);
 	int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo);
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index afd9d25d1992..958f1cf67282 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
-static bool __team_option_inst_tmp_find(const struct list_head *opts,
-					const struct team_option_inst *needle)
-{
-	struct team_option_inst *opt_inst;
-
-	list_for_each_entry(opt_inst, opts, tmp_list)
-		if (opt_inst == needle)
-			return true;
-	return false;
-}
-
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 	int err = 0;
 	int i;
 	struct nlattr *nl_option;
-	LIST_HEAD(opt_inst_list);
 
 	rtnl_lock();
 
@@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 		struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1];
 		struct nlattr *attr;
 		struct nlattr *attr_data;
+		LIST_HEAD(opt_inst_list);
 		enum team_option_type opt_type;
 		int opt_port_ifindex = 0; /* != 0 for per-port options */
 		u32 opt_array_index = 0;
@@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
-
-			/* dumb/evil user-space can send us duplicate opt,
-			 * keep only the last one
-			 */
-			if (__team_option_inst_tmp_find(&opt_inst_list,
-							opt_inst))
-				continue;
-
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
 			err = -ENOENT;
 			goto team_put;
 		}
-	}
 
-	err = team_nl_send_event_options_get(team, &opt_inst_list);
+		err = team_nl_send_event_options_get(team, &opt_inst_list);
+		if (err)
+			break;
+	}
 
 team_put:
 	team_nl_team_put(team);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5209ee9aac47..2aae11feff0c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2219,7 +2219,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev;
 	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
@@ -2239,9 +2239,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 #endif
 	}
 
+	rcu_read_lock();
+	dev = skb->dev;
+	if (unlikely(!(dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		goto drop;
+	}
+
 	if (dst_vxlan->cfg.flags & VXLAN_F_LEARN)
-		vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0,
-			    vni);
+		vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
@@ -2254,8 +2260,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
+drop:
 		dev->stats.rx_dropped++;
 	}
+	rcu_read_unlock();
 }
 
 static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,