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

Pull networking fixes from David Miller:

 1) stmmac_drv_probe() can race with stmmac_open() because we register
    the netdevice too early. Fix from Florian Fainelli.

 2) UFO handling in __ip6_append_data() and ip6_finish_output() use
    different tests for deciding whether a frame will be fragmented or
    not, put them in sync. Fix from Zheng Li.

 3) The rtnetlink getstats handlers need to validate that the netlink
    request is large enough, fix from Mathias Krause.

 4) Use after free in mlx4 driver, from Jack Morgenstein.

 5) Fix setting of garbage UID value in sockets during setattr() calls,
    from Eric Biggers.

 6) Packet drop_monitor doesn't format the netlink messages properly
    such that nlmsg_next fails to work, fix from Reiter Wolfgang.

 7) Fix handling of wildcard addresses in l2tp lookups, from Guillaume
    Nault.

 8) __skb_flow_dissect() can crash on pptp packets, from Ian Kumlien.

 9) IGMP code doesn't reset group query timers properly, from Michal
    Tesar.

10) Fix overzealous MAIN/LOCAL route table combining in ipv4, from
    Alexander Duyck.

11) vxlan offload check needs to be more strict in be2net driver, from
    Sabrina Dubroca.

12) Moving l3mdev to packet hooks lost RX stat counters unintentionally,
    fix from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (52 commits)
  sh_eth: enable RX descriptor word 0 shift on SH7734
  sfc: don't report RX hash keys to ethtool when RSS wasn't enabled
  dpaa_eth: Initialize CGR structure before init
  dpaa_eth: cleanup after init_phy() failure
  net: systemport: Pad packet before inserting TSB
  net: systemport: Utilize skb_put_padto()
  LiquidIO VF: s/select/imply/ for PTP_1588_CLOCK
  libcxgb: fix error check for ip6_route_output()
  net: usb: asix_devices: add .reset_resume for USB PM
  net: vrf: Add missing Rx counters
  drop_monitor: consider inserted data in genlmsg_end
  benet: stricter vxlan offloading check in be_features_check
  ipv4: Do not allow MAIN to be alias for new LOCAL w/ custom rules
  net: macb: Updated resource allocation function calls to new version of API.
  net: stmmac: dwmac-oxnas: use generic pm implementation
  net: stmmac: dwmac-oxnas: fix fixed-link-phydev leaks
  net: stmmac: dwmac-oxnas: fix of-node leak
  Documentation/networking: fix typo in mpls-sysctl
  igmp: Make igmp group member RFC 3376 compliant
  flow_dissector: Update pptp handling to avoid null pointer deref.
  ...

9 files changed, 45 insertions, 88 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 7f6c225..f0b460f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -723,6 +723,9 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv)
 	int i;
 	struct ieee_ets ets;
 
+	if (!MLX5_CAP_GEN(priv->mdev, ets))
+		return;
+
 	memset(&ets, 0, sizeof(ets));
 	ets.ets_cap = mlx5_max_tc(priv->mdev) + 1;
 	for (i = 0; i < ets.ets_cap; i++) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 352462a..33a399a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -171,7 +171,6 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 		return NUM_SW_COUNTERS +
 		       MLX5E_NUM_Q_CNTRS(priv) +
 		       NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS +
-		       NUM_PCIE_COUNTERS +
 		       MLX5E_NUM_RQ_STATS(priv) +
 		       MLX5E_NUM_SQ_STATS(priv) +
 		       MLX5E_NUM_PFC_COUNTERS(priv) +
@@ -219,14 +218,6 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       pport_2819_stats_desc[i].format);
 
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_perf_stats_desc[i].format);
-
-	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pcie_tas_stats_desc[i].format);
-
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
@@ -339,14 +330,6 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
 						  pport_2819_stats_desc, i);
 
-	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
-						  pcie_perf_stats_desc, i);
-
-	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
-		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters,
-						  pcie_tas_stats_desc, i);
-
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 3691451..d088eff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -247,6 +247,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	}
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
+		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
 					     outer_headers_c, dmac_47_16),
 				fs->m_ext.h_dest);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cbfa38f..1236b27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -291,36 +291,12 @@ static void mlx5e_update_q_counter(struct mlx5e_priv *priv)
 				      &qcnt->rx_out_of_buffer);
 }
 
-static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv)
-{
-	struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int sz = MLX5_ST_SZ_BYTES(mpcnt_reg);
-	void *out;
-	u32 *in;
-
-	in = mlx5_vzalloc(sz);
-	if (!in)
-		return;
-
-	out = pcie_stats->pcie_perf_counters;
-	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
-
-	out = pcie_stats->pcie_tas_counters;
-	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
-
-	kvfree(in);
-}
-
 void mlx5e_update_stats(struct mlx5e_priv *priv)
 {
 	mlx5e_update_q_counter(priv);
 	mlx5e_update_vport_counters(priv);
 	mlx5e_update_pport_counters(priv);
 	mlx5e_update_sw_counters(priv);
-	mlx5e_update_pcie_counters(priv);
 }
 
 void mlx5e_update_stats_work(struct work_struct *work)
@@ -3805,14 +3781,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5_lag_add(mdev, netdev);
 
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
-
 	mlx5e_enable_async_events(priv);
-	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
 		mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
@@ -3822,6 +3791,18 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 		rep.netdev = netdev;
 		mlx5_eswitch_register_vport_rep(esw, 0, &rep);
 	}
+
+	if (netdev->reg_state != NETREG_REGISTERED)
+		return;
+
+	/* Device already registered: sync netdev system state */
+	if (mlx5e_vxlan_allowed(mdev)) {
+		rtnl_lock();
+		udp_tunnel_get_rx_info(netdev);
+		rtnl_unlock();
+	}
+
+	queue_work(priv->wq, &priv->set_rx_mode_work);
 }
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
@@ -3966,10 +3947,6 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	const struct mlx5e_profile *profile = priv->profile;
 
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
-	if (profile->disable)
-		profile->disable(priv);
-
-	flush_workqueue(priv->wq);
 
 	rtnl_lock();
 	if (netif_running(netdev))
@@ -3977,6 +3954,10 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	netif_device_detach(netdev);
 	rtnl_unlock();
 
+	if (profile->disable)
+		profile->disable(priv);
+	flush_workqueue(priv->wq);
+
 	mlx5e_destroy_q_counter(priv);
 	profile->cleanup_rx(priv);
 	mlx5e_close_drop_rq(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index f202f87..ba5db1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -39,7 +39,7 @@
 #define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \
 	(*(u32 *)((char *)ptr + dsc[i].offset))
 #define MLX5E_READ_CTR32_BE(ptr, dsc, i) \
-	be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
+	be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
 
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
@@ -276,32 +276,6 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
 	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
 };
 
-#define PCIE_PERF_OFF(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
-#define PCIE_PERF_GET(pcie_stats, c) \
-	MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \
-		 counter_set.pcie_perf_cntrs_grp_data_layout.c)
-#define PCIE_TAS_OFF(c) \
-	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c)
-#define PCIE_TAS_GET(pcie_stats, c) \
-	MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \
-		 counter_set.pcie_tas_cntrs_grp_data_layout.c)
-
-struct mlx5e_pcie_stats {
-	__be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
-	__be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
-};
-
-static const struct counter_desc pcie_perf_stats_desc[] = {
-	{ "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
-	{ "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
-};
-
-static const struct counter_desc pcie_tas_stats_desc[] = {
-	{ "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) },
-	{ "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) },
-};
-
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
@@ -386,8 +360,6 @@ static const struct counter_desc sq_stats_desc[] = {
 #define NUM_PPORT_802_3_COUNTERS	ARRAY_SIZE(pport_802_3_stats_desc)
 #define NUM_PPORT_2863_COUNTERS		ARRAY_SIZE(pport_2863_stats_desc)
 #define NUM_PPORT_2819_COUNTERS		ARRAY_SIZE(pport_2819_stats_desc)
-#define NUM_PCIE_PERF_COUNTERS		ARRAY_SIZE(pcie_perf_stats_desc)
-#define NUM_PCIE_TAS_COUNTERS		ARRAY_SIZE(pcie_tas_stats_desc)
 #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \
 	ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
 #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \
@@ -397,7 +369,6 @@ static const struct counter_desc sq_stats_desc[] = {
 					 NUM_PPORT_2819_COUNTERS  + \
 					 NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \
 					 NUM_PPORT_PRIO)
-#define NUM_PCIE_COUNTERS		(NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS)
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
 
@@ -406,7 +377,6 @@ struct mlx5e_stats {
 	struct mlx5e_qcounter_stats qcnt;
 	struct mlx5e_vport_stats vport;
 	struct mlx5e_pport_stats pport;
-	struct mlx5e_pcie_stats pcie;
 	struct rtnl_link_stats64 vf_vport;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d6807c3..f14d9c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
+	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	mutex_lock(&esw->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 466e161..03293ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -695,6 +695,12 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 		if (err)
 			goto err_reps;
 	}
+
+	/* disable PF RoCE so missed packets don't go through RoCE steering */
+	mlx5_dev_list_lock();
+	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	return 0;
 
 err_reps:
@@ -718,6 +724,11 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw)
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
+	/* enable back PF RoCE */
+	mlx5_dev_list_lock();
+	mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	mlx5_eswitch_disable_sriov(esw);
 	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a263d890..0ac7a2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1263,6 +1263,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
 	nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
 	handle = add_rule_fte(fte, fg, dest, dest_num, false);
 	if (IS_ERR(handle)) {
+		unlock_ref_node(&fte->node);
 		kfree(fte);
 		goto unlock_fg;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 54e5a78..6547f22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -503,6 +503,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
 		 to_fw_pkey_sz(dev, 128));
 
+	/* Check log_max_qp from HCA caps to set in current profile */
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
+			       profile[prof_sel].log_max_qp,
+			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
 			 prof->log_max_qp);
@@ -575,7 +582,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int numa_node           = priv->numa_node;
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
@@ -583,7 +589,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 		return -ENOMEM;
 	}
 
-	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
 	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
@@ -1189,6 +1195,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 {
 	int err = 0;
 
+	mlx5_drain_health_wq(dev);
+
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
 		dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
@@ -1351,10 +1359,9 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state and drain health wq */
+	/* In case of kernel call save the pci state */
 	if (state) {
 		pci_save_state(pdev);
-		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}