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
  ...

Documentation/networking/operstates.txt

@@ -22,8 +22,9 @@ and changeable from userspace under certain rules.
 2. Querying from userspace
 
 Both admin and operational state can be queried via the netlink
-operation RTM_GETLINK. It is also possible to subscribe to RTMGRP_LINK
-to be notified of updates. This is important for setting from userspace.
+operation RTM_GETLINK. It is also possible to subscribe to RTNLGRP_LINK
+to be notified of updates while the interface is admin up. This is
+important for setting from userspace.
 
 These values contain interface state:
 
@@ -101,8 +102,9 @@ because some driver controlled protocol establishment has to
 complete. Corresponding functions are netif_dormant_on() to set the
 flag, netif_dormant_off() to clear it and netif_dormant() to query.
 
-On device allocation, networking core sets the flags equivalent to
-netif_carrier_ok() and !netif_dormant().
+On device allocation, both flags __LINK_STATE_NOCARRIER and
+__LINK_STATE_DORMANT are cleared, so the effective state is equivalent
+to netif_carrier_ok() and !netif_dormant().
 
 
 Whenever the driver CHANGES one of these flags, a workqueue event is
@@ -133,11 +135,11 @@ netif_carrier_ok() && !netif_dormant() is set by the
 driver. Afterwards, the userspace application can set IFLA_OPERSTATE
 to IF_OPER_DORMANT or IF_OPER_UP as long as the driver does not set
 netif_carrier_off() or netif_dormant_on(). Changes made by userspace
-are multicasted on the netlink group RTMGRP_LINK.
+are multicasted on the netlink group RTNLGRP_LINK.
 
 So basically a 802.1X supplicant interacts with the kernel like this:
 
--subscribe to RTMGRP_LINK
+-subscribe to RTNLGRP_LINK
 -set IFLA_LINKMODE to 1 via RTM_SETLINK
 -query RTM_GETLINK once to get initial state
 -if initial flags are not (IFF_LOWER_UP && !IFF_DORMANT), wait until

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

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);
 	}

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);
 }

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",

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

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++) {

drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c

@@ -3081,13 +3081,15 @@ 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;
 	}
 
 	/* now, make sure we are running on compatible SoC */
 	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;
 	}
 

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -617,16 +617,29 @@ 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.
  */
 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 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		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)) &&

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -1583,6 +1583,24 @@ void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
 	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 */

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 {

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;

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) {

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);
 

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);
 }
 

drivers/net/ethernet/mellanox/mlx5/core/events.c

@@ -211,37 +211,38 @@ 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 &
 		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
 
 	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;
 }

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);

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);